In wireless sensor networks,ensuring communication security via specific emitter identification(SEI)is crucial.However,existing SEI methods are limited to closed-set scenarios and lack the ability to detect unknown de...In wireless sensor networks,ensuring communication security via specific emitter identification(SEI)is crucial.However,existing SEI methods are limited to closed-set scenarios and lack the ability to detect unknown devices and perform classincremental training.This study proposes a class-incremental open-set SEI approach.The open-set SEI model calculates radiofrequency fingerprints(RFFs)prototypes for known signals and employs a self-attention mechanism to enhance their discriminability.Detection thresholds are set through Gaussian fitting for each class.For class-incremental learning,the algorithm freezes the parameters of the previously trained model to initialize the new model.It designs specific losses:the RFFs extraction distribution difference loss and the prototype transformation distribution difference loss,which force the new model to retain old knowledge while learning new knowledge.The training loss enables learning of new class RFFs.Experimental results demonstrate that the open-set SEI model achieves state-of-theart performance and strong noise robustness.Moreover,the class-incremental learning algorithm effectively enables the model to retain old device RFFs knowledge,acquire new device RFFs knowledge,and detect unknown devices simultaneously.展开更多
Electrochemical models,characterized by high fidelity and physical interpretability,have been applied in var-ious fields such as fast charging,battery state estimation,and battery material design.Currently,widely util...Electrochemical models,characterized by high fidelity and physical interpretability,have been applied in var-ious fields such as fast charging,battery state estimation,and battery material design.Currently,widely utilized single particle-based model exhibits high computational efficiency but suffers from low simulation accuracy under high-rate charge/discharge conditions.In this work,an electrochemical model for lithium-ion batteries based on multi-particle hypothesis is developed.Two particles are employed to represent the electrode char-acteristics of the positive and negative electrodes,respectively.Through theoretical derivation,mathematical equations are established to describe various processes within the battery,including solid-phase diffusion,li-quidphase diffusion,reaction polarization,and ohmic polarization.In addition,a method for obtaining model parameters is proposed.Finally,the model is experimentally validated by using lithium iron phosphate and nickel-cobalt-manganese lithium-ion batteries under constant current conditions.The identified battery elec-trochemical model parameters are within reasonable accuracy as evidenced by the experimental validation results.展开更多
The formation and development of natural fractures in tight sandstone reservoirs are governed by a combination of stratigraphic structure,lithological properties,and stress conditions.These fractures often exhibit irr...The formation and development of natural fractures in tight sandstone reservoirs are governed by a combination of stratigraphic structure,lithological properties,and stress conditions.These fractures often exhibit irregular geometries,signicant variations in height,and complex lling materials,leading to intricate conventional logging responses with pronounced multi-solution ambiguities that complicate accurate identication.To address this challenge,this study proposes a multi-model selective coupling identication method.This approach incorporated data cleaning,augmentation,and resampling techniques during the preprocessing phase.Subsequently,multi-dimensional feature extraction and cascade-based feature selection were performed,followed by optimizing model parameters using random search,Bayesian optimization,and grid search algorithms.High-performing models were selected via an evaluation framework.These models were then coupled through voting mechanisms to construct a robust identication model capable of deeply exploring the nonlinear relationship between fractures and logging data.The proposed method achieved an 85.19%fracture identication accuracy in blind tests involving 27 fracture segments across three wells,demonstrating strong identication capability.This methodology provides a valuable reference for fracture identication in hydrocarbon reservoirs within the Hongde area.展开更多
The reliable operation of power grid secondary equipment is an important guarantee for the safety and stability of the power system.However,various defects could be produced in the secondary equipment during longtermo...The reliable operation of power grid secondary equipment is an important guarantee for the safety and stability of the power system.However,various defects could be produced in the secondary equipment during longtermoperation.The complex relationship between the defect phenomenon andmulti-layer causes and the probabilistic influence of secondary equipment cannot be described through knowledge extraction and fusion technology by existing methods,which limits the real-time and accuracy of defect identification.Therefore,a defect recognition method based on the Bayesian network and knowledge graph fusion is proposed.The defect data of secondary equipment is transformed into the structured knowledge graph through knowledge extraction and fusion technology.The knowledge graph of power grid secondary equipment is mapped to the Bayesian network framework,combined with historical defect data,and introduced Noisy-OR nodes.The prior and conditional probabilities of the Bayesian network are then reasonably assigned to build a model that reflects the probability dependence between defect phenomena and potential causes in power grid secondary equipment.Defect identification of power grid secondary equipment is achieved by defect subgraph search based on the knowledge graph,and defect inference based on the Bayesian network.Practical application cases prove this method’s effectiveness in identifying secondary equipment defect causes,improving identification accuracy and efficiency.展开更多
Selectivity remains a significant challenge for gas sensors. In contrast to conventional gas sensors that depend solely on conductivity to detect gases, we exploited a single NiO-doped SnO_(2) sensor to simultaneously...Selectivity remains a significant challenge for gas sensors. In contrast to conventional gas sensors that depend solely on conductivity to detect gases, we exploited a single NiO-doped SnO_(2) sensor to simultaneously monitor transient changes in both sensor conductivity and temperature. The distinct response profiles of H_(2) and NH_(3) gases were attributed to differences in their redox rates and enthalpy changes during chemical reactions, which provided an opportunity for gas identification using machine learning(ML) algorithms. The test results indicate that preprocessing the extracted calorimetric and chemi-resistive parameters using the principal component analysis(PCA), followed by the application of ML classifiers for identification,enables a 100% accuracy for both target analytes. This work presents a facile gas identification method that enhances chiplevel sensor applications while minimizing the need for complex sensor arrays.展开更多
In the fast-paced living environment, changes in dietary patterns have led to a continuous increase in the incidence and mortality rates of colorectal cancer (CRC), making it a prevalent malignant tumor of the digesti...In the fast-paced living environment, changes in dietary patterns have led to a continuous increase in the incidence and mortality rates of colorectal cancer (CRC), making it a prevalent malignant tumor of the digestive system worldwide. Currently, CRC clinical diagnosis and treatment face challenges such as high costs and persistently high recurrence rates. Traditional quantification of tumor-infiltrating lymphocytes (TILs) relies on manual analysis and judgment, resulting in low diagnostic efficiency and susceptibility to subjective factors, leading to missed or misdiagnosed cases. To enhance the efficiency and quality of CRC clinical diagnosis and treatment, this study explores domestic and international research on the automatic identification of CRC cells using machine learning strategies. It analyzes the morphological heterogeneity and prognostic value in the application of this strategy, aiming to deepen the understanding of intelligent tool applications in precise diagnosis, treatment, and prognostic evaluation of colorectal cancer, comprehend the current research status and development trends, and provide references for addressing and addressing the gaps in related research.展开更多
High-throughput single nucleotide polymorphism(SNP) arrays have emerged as essential genotyping tools,significantly accelerating breeding programs and advancing basic research.In this study,a high-throughput 10K SNP g...High-throughput single nucleotide polymorphism(SNP) arrays have emerged as essential genotyping tools,significantly accelerating breeding programs and advancing basic research.In this study,a high-throughput 10K SNP genotyping array for wax gourd was developed using genotyping by target sequencing(GBTS),featuring 10,722 SNPs evenly distributed across all 12 chromosomes,including 278 functional loci associated with key economic traits.To demonstrate its utility,genetic distances among 19 elite inbred lines were calculated from SNP data and correlated with heterosis for single fruit weight.The results revealed that greater genetic distance was associated with higher middle parent heterosis(MPH) for single fruit weight.Furthermore,56 commercial wax gourd cultivars collected from eight regions were selected and genotyped.Population structure analysis,phylogenetic analysis,and principal component analysis(PCA) collectively indicated that these cultivars fall into two major groups.Group I,comprising black or dark green skinned wax gourds,exhibited lower genetic diversity than Group II,which includes green or light green skinned varieties,reflecting shorter genetic distances within Group I.Finally,60 polymorphic SNPs were used to construct DNA fingerprints for distinguishing the 56 cultivars.As the first high-throughput genotyping platform for wax gourd,this SNP array provides an effective and powerful tool for genetic analysis.展开更多
Underground engineering projects such as deep tunnel excavation often encounter rockburst disasters accompanied by numerous microseismic events.Rapid interpretation of microseismic signals is crucial for the timely id...Underground engineering projects such as deep tunnel excavation often encounter rockburst disasters accompanied by numerous microseismic events.Rapid interpretation of microseismic signals is crucial for the timely identification of rockbursts.However,conventional processing encompasses multi-step workflows,including classification,denoising,picking,locating,and computational analysis,coupled with manual intervention,which collectively compromise the reliability of early warnings.To address these challenges,this study innovatively proposes the“microseismic stethoscope"-a multi-task machine learning and deep learning model designed for the automated processing of massive microseismic signals.This model efficiently extracts three key parameters that are necessary for recognizing rockburst disasters:rupture location,microseismic energy,and moment magnitude.Specifically,the model extracts raw waveform features from three dedicated sub-networks:a classifier for source zone classification,and two regressors for microseismic energy and moment magnitude estimation.This model demonstrates superior efficiency compared to traditional processing and semi-automated processing,reducing per-event processing time from 0.71 s to 0.49 s to merely 0.036 s.It concurrently achieves 98%accuracy in source zone classification,with microseismic energy and moment magnitude estimation errors of 0.13 and 0.05,respectively.This model has been well applied and validated in the Daxiagu Tunnel case in Sichuan,China.The application results indicate that the model is as accurate as traditional methods in determining source parameters,and thus can be used to identify potential geomechanical processes of rockburst disasters.By enhancing the signal processing reliability of microseismic events,the proposed model in this study presents a significant advancement in the identification of rockburst disasters.展开更多
The growing use of lithium-ion batteries in electric transportation and grid-scale storage systems has intensified the need for accurate and highly generalizable state-of-health(SOH)estimation.Conventional approaches ...The growing use of lithium-ion batteries in electric transportation and grid-scale storage systems has intensified the need for accurate and highly generalizable state-of-health(SOH)estimation.Conventional approaches often suffer from reduced accuracy under dynamically uncertain state-of-charge(SOC)operating ranges and heterogeneous aging stresses.This study presents a unified SOH estimation framework that integrates physics-informed modeling,subspace identification,and Transformer-based learning.A reduced-order model is derived from simplified electrochemical dynamics,providing an interpretable and computationally efficient representation of battery behavior.Subspace identification across a wide SOC and SOH range yields degradation-sensitive features,which the Transformer uses to capture long-range aging dynamics via multi-head self-attention.Experiments on LiFePO4 cells under joint-cell training show consistently accurate SOH estimation,with a maximum error of 1.39%,demonstrating the framework’s effectiveness in decoupling SOC and SOH effects.In cross-cell validation,where training and validation are performed on different cells,the model maintains a maximum error of 2.06%,confirming strong generalization to unseen aging trajectories.Comparative experiments on LiFePO_(4)and public LiCoO_(2)datasets confirm the framework’s cross-chemistry applicability.By extracting low-dimensional,physically interpretable features via subspace identification,the framework significantly reduces training cost while maintaining high SOH estimation accuracy,outperforming conventional data-driven models lacking physical guidance.展开更多
Background:The medicinal material known as Os Draconis(Longgu)originates from fossilized remains of ancient mammals and is widely used in treating emotional and mental conditions.However,fossil resources are nonrenewa...Background:The medicinal material known as Os Draconis(Longgu)originates from fossilized remains of ancient mammals and is widely used in treating emotional and mental conditions.However,fossil resources are nonrenewable,and clinical demand is increasingly difficult to meet,leading to a proliferation of counterfeit products.During prolonged geological burial,static pressure from the surrounding strata severely compromises the microstructural integrity of osteons in Os Draconis,but Os Draconis still largely retains the structural features of mammalian bone.Methods:Using verified authentic Os Draconis samples over 10,000 years old as a baseline,this study summarizes the ultrastructural characteristics of genuine Os Draconis.Employing electron probe microanalysis and optical polarized light microscopy,we examined 28 batches of authentic Os Draconis and 31 batches of counterfeits to identify their ultrastructural differences.Key points for ultrastructural identification of Os Draconis were compiled,and a new identification approach was proposed based on these differences.Results:Authentic Os Draconis exhibited distinct ultrastructural markers:irregularly shaped osteons with traversing fissures,deformed/displaced Haversian canals,and secondary mineral infill(predominantly calcium carbonate).Counterfeits showed regular osteon arrangements,absent traversal fissures,and homogeneous hydroxyapatite composition.Lab-simulated samples lacked structural degradation features.EPMA confirmed calcium carbonate infill in fossilized Haversian canals,while elemental profiles differentiated lacunae types(void vs.mineral-packed).Conclusion:The study established ultrastructural criteria for authentic Os Draconis identification:osteon deformation,geological fissures penetrating bone units,and heterogenous mineral deposition.These features,unattainable in counterfeits or modern processed bones,provide a cost-effective,accurate identification method.This approach bridges gaps in TCM material standardization and supports quality control for clinical applications.展开更多
This paper proposes a robust control-oriented identification method for errors-in-variables(EIV)systems in output feedbacks using frequency-response(FR)experimental data.An important relation between such a closed-loo...This paper proposes a robust control-oriented identification method for errors-in-variables(EIV)systems in output feedbacks using frequency-response(FR)experimental data.An important relation between such a closed-loop EIV system and its coprime factor(CF)uncertainty description is first derived,based on which the FR measurements suitable for plant CF identification are able to be generated.Different factorizations of a given controller in the closed-loop system can be made best use to adjust right coprime factors(RCFs)of the plant so as to realize an improvement on the signal-to-noise ratio of identification experimental data.Subsequently,a nominal RCF model is estimated by linear matrix inequalities from the applicable FR measurements and its associated worst-case errors are quantified from a priori and a posteriori information on the underlying system.A resulting RCF perturbation model set can then be described by the nominal RCF model and its worst-case error bounds.Such a model set capable of being stabilized by the given controller is ready for its robust stabilizing controller redesign and robust performance analysis.Finally,a numerical simulation is given to show the efficacy of the proposed identification method.展开更多
The technology of locating magnetic anomaly targets via geomagnetic eld measurements has been increasingly widely applied,with multiple magnetic anomaly target localization emerging as a critical research direction.Ho...The technology of locating magnetic anomaly targets via geomagnetic eld measurements has been increasingly widely applied,with multiple magnetic anomaly target localization emerging as a critical research direction.However,when two magnetic anomaly targets are horizontally close but vertically separated,traditional clustering-based localization methods tend to omit the deeper target.To address this issue,we propose an improved clustering-based localization method for multiple magnetic anomaly targets,which integrates two core innovations:the introduction of a reference target to establish a benchmark for normal magnetic moment distribution,and the utilization of spatial distribution characteristics of magnetic moment estimates to judge the presence of omitted targets.Simulation results demonstrate that the proposed method not only achieves accurate localization of conventional targets but also eectively identies the omission of deeper targets,providing a reliable basis for determining whether supplementary localization steps are required.展开更多
In this paper,we consider a multiple-input single-output(MISO)Hammerstein system whose inputs and output are disturbed by unknown Gaussian white measurement noises.The parameter estimation of such a system is a typica...In this paper,we consider a multiple-input single-output(MISO)Hammerstein system whose inputs and output are disturbed by unknown Gaussian white measurement noises.The parameter estimation of such a system is a typical errors-in-variables(EIV)nonlinear system identification problem.This paper proposes a bias-correction least squares(BCLS)identification methods to compute a consistent estimate of EIV MISO Hammerstein systems from noisy data.To obtain the unbiased parameter estimates of EIV MISO Hammerstein system,the analytical expression of estimated bias for the standard least squares(LS)algorithm is derived first,which is a function about the variances of noises.And then a recursive algorithm is proposed to estimate the unknown term of noises variances from noisy data.Finally,based on bias estimation scheme,the bias caused by the correlation between the input–output signals exciting the true system and the corresponding measurement noise,resulting in unbiased parameter estimates of the EIV MISO Hammerstein system.The performance of the proposed method is demonstrated through a simulation example and a chemical continuously stirred tank reactor(CSTR)system.展开更多
Simultaneous identification and quantitative detection of phenylenediamine(PDA)isomers,including o-phenylenediamine(OPD),m-phenylenediamine(MPD),and p-phenylenediamine(PPD),are essential for environmental risk assessm...Simultaneous identification and quantitative detection of phenylenediamine(PDA)isomers,including o-phenylenediamine(OPD),m-phenylenediamine(MPD),and p-phenylenediamine(PPD),are essential for environmental risk assessment and human health protection.However,current visual detection methods can only distinguish individual PDA isomers and failed to identify binary or ternary mixtures.Herein,a highly active and ultrastable peroxidase(POD)-like CoPt graphitic nanozyme was used for naked-eye identification and colorimetric/fluorescent(FL)dual-mode quantitative detection of PDA isomers.The CoPt@G nanozyme effectively catalyzed the oxidation of OPD,MPD,PPD,OPD+PPD,OPD+MPD,MPD+PPD and OPD+MPD+PPD into yellow,colorless,lilac,yellow,yellow,wine red and reddish-brown products,respectively,in the presence of H_(2)O_(2).Thus,the MPD,PPD,MPD+PPD and OPD+MPD+PPD were easily identified based on the distinct color of their oxidation products,and the OPD,OPD+PPD,OPD+MPD could be further identified by the additional addition of MPD or PPD.Subsequently,CoPt@G/H_(2)O_(2)-,a 3,3′,5,5′-tetramethylbenzidine(TMB)/CoPt@G/H_(2)O_(2)-,and MPD/CoPt@G/H_(2)O_(2)-enabled colorimetric/FL dual-mode platforms for the quantitative detection of OPD,MPD and PPD were proposed.The experimental results illustrated that the constructed sensing platforms exhibit satisfactory sensitivity,comparable to that reported in previous studies.Finally,the evaluation of PDAs in water samples was realized,yielding satisfactory recoveries.This work expanded the application prospects of nanozymes in assessing environmental risks and protection of human security.展开更多
With the continuous advancement of social technology and the increasing awareness of health management,biomass-based triboelectric nanogenerator(TENG)displayed significant potential as flexible wearable electronics fo...With the continuous advancement of social technology and the increasing awareness of health management,biomass-based triboelectric nanogenerator(TENG)displayed significant potential as flexible wearable electronics for continuous foot gait monitoring.Nevertheless,existing biomass-based TENG often faces challenges of insufficient mechanical robustness and durability in practical applications,where they are prone to surface abrasion and structural fracture under continuous compression and friction,severely limiting their long-term performances.In order to address these challenges,this work proposed a multiscale crosslinking strategy,which strengthened the noncovalent interactions within the polymer by constructing multiple reinforcement networks,successfully fabricating a dual-network C-lignin-based triboelectric material(CLTM)with excellent durability and crack resistance.Among them,the optimal CLTM(PSGCL-0.2)exhibited high mechanical strength(strain 445%,tensile strength 41.56 MPa,Young's modulus 41.25 MPa,toughness 159.67 MJ/m^(3))and excellent cyclic stability(300 cycles)with versatile functionalities,including antibacterial,antioxidant,and UV-shielding properties,water stabilization(255.51 g/m^(2)/d),efficient photothermal conversion,and full recyclability.Furthermore,biomass-based TENG device assembled from PSGCL-0.2 achieved stable triboelectric output properties(102.5 V,2.9μA,and 61.3 nC),and sustainable for 2000 cycles,fast response time(68 ms),and excellent power density(325.9 mW/m^(2)),effectively converting mechanical energy into electrical energy.Especially,PSGCL 0.2 was also integrated into the wireless self-powered smart insole,successfully enabling real-time visual monitoring of plantar pressure distribution and dynamic gait.Meanwhile,combined with the machine learning algorithm,the self-powered smart insole achieved precise recognition and classification of eight different motion states with an accuracy of 98%.This study provides the feasible strategy for developing extremely stable and durable biomass-based TENG,aimed at advancing sustainable intelligent healthcare systems.展开更多
Root rot is a prevalent soil-borne fungal disease in citrus.Citron C-05(Citrus medica)stands out as a germplasm within Citrus spp.due to its complete resistance to citrus canker and favorable characteristics such as s...Root rot is a prevalent soil-borne fungal disease in citrus.Citron C-05(Citrus medica)stands out as a germplasm within Citrus spp.due to its complete resistance to citrus canker and favorable characteristics such as single embryo and easy rooting.However,Citron C-05 was found to be highly susceptible to root rot during cultivation,with the specific pathogens previously unknown.In this study,four candidate fungal species were isolated from Citron C-05 roots.Sequence analysis of ITS,EF-1a,RPB1,and RPB2 identified two Fusarium solani strains,Rr-2 and Rr-4,as the candidates causing root rot in Citron C-05.Resistance tests showed these two pathogens increased root damage rate from 10.30%to 35.69%in Citron C-05,sour orange(Citrus aurantium),sweet orange(Citrus sinensis)and pummelo(Citrus grandis).F.solani exhibited the weak pathogenicity towards trifoliate orange(Poncirus trifoliata).DAB staining revealed none of reddish-brown precipitation in the four susceptible citrus germplasm after infection with F.solani,while trifoliate orange exhibited significant H2O2 accumulation.Trypan blue staining indicated increased cell death in the four susceptible citrus germplasm following infection with these two pathogens but not in trifoliate orange.These findings provide a comprehensive understanding of citrus root rot and support future research on the mechanisms of root rot resistance in citrus.展开更多
Many spore-forming Bacillus species can cause serious human diseases,because of accidental Bacillusspore infection.Thus,developing an identification strategy with both high sensitivity and specificity is greatly in de...Many spore-forming Bacillus species can cause serious human diseases,because of accidental Bacillusspore infection.Thus,developing an identification strategy with both high sensitivity and specificity is greatly in demand.In this work,we proposed a novel approach named multi-head self-attention mechanism-guided neural network Raman platform to identify living Bacillus spores within a single-cell resolution.The multi-head self-attention mechanism-guided neural network Raman platform was created by combining single-cell Raman spectroscopy,convolutional neural network(CNN),and multi-head self-attention mechanism.To address the limited size of the original spectra dataset,Gaussian noise-based spectra augmentation was employed to increase the number of single-cell Raman spectra datasets for CNN training.Owing to the assistance of both spectra augmentation and multi-head self-attention mechanism,the obtained prediction accuracy of five Bacillus spore species was further improved from 92.29±0.82%to 99.43±0.15%.To figure out the spectra differences covered by the multi-head self-attention mechanism-guided CNN,the relative classification weight from typical Raman bands was visualized via multi-head self-attention mechanism curve.In the process of spectra augmentation from 0 to 1000,the distribution of relative classification weight varied from a discrete state to a more concentrated phase.More importantly,these highlighted four Raman bands(1017,1449,1576,and 1660 cm^(-1))were assigned large weights,showing that the spectra differences in the Raman bands produced the largest contribution to prediction accuracy.It can be foreseen that,our proposed sorting platform has great potential in accurately identifying Bacillus and its related genera species at a single-cell level.展开更多
Accurate identification of water sources is crucial for effective water management and safety in mining operations.However,imbalanced water sample datasets often lead to suboptimal classification accuracy.To address t...Accurate identification of water sources is crucial for effective water management and safety in mining operations.However,imbalanced water sample datasets often lead to suboptimal classification accuracy.To address this challenge,this study proposes a novel water source identification method integrating Synthetic Minority Over-Sampling Technique(SMOTE),Zebra Optimization Algorithm(ZOA),and Light Gradient Boosting Machine(LightGBM).Initially,SMOTE is utilized to synthesize samples for the minority class within the imbalanced dataset,thereby generating a balanced water sample dataset and mitigating class distribution disparities.Subsequently,an efficient water source identification model is constructed by combining ZOA with LightGBM,leveraging the strengths of both algorithms.The model’s performance is validated using a test set and compared with other common classification models.Results demonstrate that SMOTE significantly alleviates class imbalance and enhances the classification accuracy of LightGBM for minority class water samples.ZOA parameter tuning accelerates model convergence and further improves classification accuracy,optimizing the model’s overall performance.In experimental validation,the proposed SMOTE-ZOA-LightGBM model achieved an accuracy of 88.41%and a F1 score of 88.24%,outperforming six other classification models.The method proposed in this paper can accurately identify water source types,effectively addressing the issue of low classification accuracy caused by imbalanced water sample data.It provides reliable technical support and scientific basis for identifying and preventing water inrush sources in mines.展开更多
The integration of a high proportion of renewable energy introduces significant challenges for the adaptability of traditional fault nature identification methods.To address these challenges,this paper presents a nove...The integration of a high proportion of renewable energy introduces significant challenges for the adaptability of traditional fault nature identification methods.To address these challenges,this paper presents a novel fault nature identification method for renewable energy grid-connected interconnection lines,leveraging wavelet packet decomposition and voltage waveform time-frequency morphology comparison algorithms.First,the paper investigates the harmonic injection mechanism during non-full-phase operation following fault isolation in photovoltaic renewable energy systems,and examines the voltage characteristics of faulted phases in renewable energy scenarios.The analysis reveals that substantial differences exist in both the time and frequency domains of phase voltages before and after the extinction of transient faults,whereas permanent faults do not exhibit such variations.Building on this observation,the paper proposes a voltage time-frequency feature extraction method based on wavelet packet decomposition,wherein low-frequency waveform components are selected to characterize fault features.Subsequently,a fault nature identification method is introduced,based on a voltage waveform time-frequency morphology comparison.By employing a windowing technique to quantify waveform differences before and after arc extinction,this method effectively distinguishes between permanent and transient faults and accurately determines the arc extinction time.Finally,a 220 kV renewable energy grid connection line model is developed using PSCAD for verification.The results demonstrate that the proposed method is highly adaptable across various fault locations,transition resistances,and renewable energy control strategies,and can reliably identify fault nature in renewable energy grid connection scenarios.展开更多
Agile lithology identification can assist mining by providing important information in the exploration and production of mineral resources.This study proposes a new lithology recognition procedure using video-logging ...Agile lithology identification can assist mining by providing important information in the exploration and production of mineral resources.This study proposes a new lithology recognition procedure using video-logging of boreholes with an endoscope,applied to six production blocks in a limestone quarry.Images are automatically extracted from the videos and the lithology is classified into three classes based on clay content,i.e.massive limestone,brecciated limestone,and high amount of clay.The image quality is evaluated with a gray pixel intensity threshold and three no-reference image quality metrics,i.e.perception-based image quality evaluator,natural image quality evaluator,and blind/referenceless image spatial quality evaluator.After removing low-quality images,7583 images are retained and used for developing lithology classification models using six optimized classification techniques.The contrast-limited adaptive histogram equalization(CLAHE)technique is used to improve image quality.Ten color characteristics involving three percentiles of red,green and blue pixel intensities,together with color counting and five texture characteristics-correlation,entropy,homogeneity,contrast and energy-are used as inputs.Bayesian optimized light gradient boosting machine model performs best,with an overall accuracy of 88.04%,and a precision on the classes of massive limestone,brecciated limestone and high amount of clay of 90.72%,83.52%and 85.29%,respectively,for the testing set.The feature importance scores show that the color counting is the most significant parameter for the development of the classification model.Compared with previous image-based methodologies,this study provides a more flexible and cheaper procedure to identify lithology.展开更多
基金supported by the National Natural Science Foundation of China(62371465)Taishan Scholar Project of Shandong Province(ts201511020)。
文摘In wireless sensor networks,ensuring communication security via specific emitter identification(SEI)is crucial.However,existing SEI methods are limited to closed-set scenarios and lack the ability to detect unknown devices and perform classincremental training.This study proposes a class-incremental open-set SEI approach.The open-set SEI model calculates radiofrequency fingerprints(RFFs)prototypes for known signals and employs a self-attention mechanism to enhance their discriminability.Detection thresholds are set through Gaussian fitting for each class.For class-incremental learning,the algorithm freezes the parameters of the previously trained model to initialize the new model.It designs specific losses:the RFFs extraction distribution difference loss and the prototype transformation distribution difference loss,which force the new model to retain old knowledge while learning new knowledge.The training loss enables learning of new class RFFs.Experimental results demonstrate that the open-set SEI model achieves state-of-theart performance and strong noise robustness.Moreover,the class-incremental learning algorithm effectively enables the model to retain old device RFFs knowledge,acquire new device RFFs knowledge,and detect unknown devices simultaneously.
基金Supported by the National Natural Science Foundation of China(Grant Nos.52407238,52177210)the Youth Foundation of Shandong Provincial Natural Science Foundation(Grant No.ZR2023QE036).
文摘Electrochemical models,characterized by high fidelity and physical interpretability,have been applied in var-ious fields such as fast charging,battery state estimation,and battery material design.Currently,widely utilized single particle-based model exhibits high computational efficiency but suffers from low simulation accuracy under high-rate charge/discharge conditions.In this work,an electrochemical model for lithium-ion batteries based on multi-particle hypothesis is developed.Two particles are employed to represent the electrode char-acteristics of the positive and negative electrodes,respectively.Through theoretical derivation,mathematical equations are established to describe various processes within the battery,including solid-phase diffusion,li-quidphase diffusion,reaction polarization,and ohmic polarization.In addition,a method for obtaining model parameters is proposed.Finally,the model is experimentally validated by using lithium iron phosphate and nickel-cobalt-manganese lithium-ion batteries under constant current conditions.The identified battery elec-trochemical model parameters are within reasonable accuracy as evidenced by the experimental validation results.
基金supported by the"Tianchi Talents"Program of the Xinjiang Uygur Autonomous Region(Project No.51052300560)National Natural Science Foundation of China(Project No.42464006)the Open Fund Project of Key Laboratory of Oil and Gas Resources Research of the Gansu Province(Project No.SZDKFJJ2023007).
文摘The formation and development of natural fractures in tight sandstone reservoirs are governed by a combination of stratigraphic structure,lithological properties,and stress conditions.These fractures often exhibit irregular geometries,signicant variations in height,and complex lling materials,leading to intricate conventional logging responses with pronounced multi-solution ambiguities that complicate accurate identication.To address this challenge,this study proposes a multi-model selective coupling identication method.This approach incorporated data cleaning,augmentation,and resampling techniques during the preprocessing phase.Subsequently,multi-dimensional feature extraction and cascade-based feature selection were performed,followed by optimizing model parameters using random search,Bayesian optimization,and grid search algorithms.High-performing models were selected via an evaluation framework.These models were then coupled through voting mechanisms to construct a robust identication model capable of deeply exploring the nonlinear relationship between fractures and logging data.The proposed method achieved an 85.19%fracture identication accuracy in blind tests involving 27 fracture segments across three wells,demonstrating strong identication capability.This methodology provides a valuable reference for fracture identication in hydrocarbon reservoirs within the Hongde area.
基金supported by the State Grid Southwest Branch Project“Research on Defect Diagnosis and Early Warning Technology of Relay Protection and Safety Automation Devices Based on Multi-Source Heterogeneous Defect Data”.
文摘The reliable operation of power grid secondary equipment is an important guarantee for the safety and stability of the power system.However,various defects could be produced in the secondary equipment during longtermoperation.The complex relationship between the defect phenomenon andmulti-layer causes and the probabilistic influence of secondary equipment cannot be described through knowledge extraction and fusion technology by existing methods,which limits the real-time and accuracy of defect identification.Therefore,a defect recognition method based on the Bayesian network and knowledge graph fusion is proposed.The defect data of secondary equipment is transformed into the structured knowledge graph through knowledge extraction and fusion technology.The knowledge graph of power grid secondary equipment is mapped to the Bayesian network framework,combined with historical defect data,and introduced Noisy-OR nodes.The prior and conditional probabilities of the Bayesian network are then reasonably assigned to build a model that reflects the probability dependence between defect phenomena and potential causes in power grid secondary equipment.Defect identification of power grid secondary equipment is achieved by defect subgraph search based on the knowledge graph,and defect inference based on the Bayesian network.Practical application cases prove this method’s effectiveness in identifying secondary equipment defect causes,improving identification accuracy and efficiency.
基金supported in part by the National Natural Science Foundation of China (62431018)in part by the Guangzhou Municipal Science and Technology Bureau (SL2023A04J00435)in part by the One Hundred Youth Project of Guangdong University of Technology (263113873)。
文摘Selectivity remains a significant challenge for gas sensors. In contrast to conventional gas sensors that depend solely on conductivity to detect gases, we exploited a single NiO-doped SnO_(2) sensor to simultaneously monitor transient changes in both sensor conductivity and temperature. The distinct response profiles of H_(2) and NH_(3) gases were attributed to differences in their redox rates and enthalpy changes during chemical reactions, which provided an opportunity for gas identification using machine learning(ML) algorithms. The test results indicate that preprocessing the extracted calorimetric and chemi-resistive parameters using the principal component analysis(PCA), followed by the application of ML classifiers for identification,enables a 100% accuracy for both target analytes. This work presents a facile gas identification method that enhances chiplevel sensor applications while minimizing the need for complex sensor arrays.
文摘In the fast-paced living environment, changes in dietary patterns have led to a continuous increase in the incidence and mortality rates of colorectal cancer (CRC), making it a prevalent malignant tumor of the digestive system worldwide. Currently, CRC clinical diagnosis and treatment face challenges such as high costs and persistently high recurrence rates. Traditional quantification of tumor-infiltrating lymphocytes (TILs) relies on manual analysis and judgment, resulting in low diagnostic efficiency and susceptibility to subjective factors, leading to missed or misdiagnosed cases. To enhance the efficiency and quality of CRC clinical diagnosis and treatment, this study explores domestic and international research on the automatic identification of CRC cells using machine learning strategies. It analyzes the morphological heterogeneity and prognostic value in the application of this strategy, aiming to deepen the understanding of intelligent tool applications in precise diagnosis, treatment, and prognostic evaluation of colorectal cancer, comprehend the current research status and development trends, and provide references for addressing and addressing the gaps in related research.
基金supported by the Science and Technology Talent Support Project of Hunan Province,China (2022TJ-N15)the Hunan Agricultural Science and Technology Innovation Fund,China (2024CX90 and 2024CX65)the Science and Technology Innovation Program of Hunan Province,China (2021NK1006)。
文摘High-throughput single nucleotide polymorphism(SNP) arrays have emerged as essential genotyping tools,significantly accelerating breeding programs and advancing basic research.In this study,a high-throughput 10K SNP genotyping array for wax gourd was developed using genotyping by target sequencing(GBTS),featuring 10,722 SNPs evenly distributed across all 12 chromosomes,including 278 functional loci associated with key economic traits.To demonstrate its utility,genetic distances among 19 elite inbred lines were calculated from SNP data and correlated with heterosis for single fruit weight.The results revealed that greater genetic distance was associated with higher middle parent heterosis(MPH) for single fruit weight.Furthermore,56 commercial wax gourd cultivars collected from eight regions were selected and genotyped.Population structure analysis,phylogenetic analysis,and principal component analysis(PCA) collectively indicated that these cultivars fall into two major groups.Group I,comprising black or dark green skinned wax gourds,exhibited lower genetic diversity than Group II,which includes green or light green skinned varieties,reflecting shorter genetic distances within Group I.Finally,60 polymorphic SNPs were used to construct DNA fingerprints for distinguishing the 56 cultivars.As the first high-throughput genotyping platform for wax gourd,this SNP array provides an effective and powerful tool for genetic analysis.
基金supported by the National Natural Science Foundation of China(Grant Nos.42130719 and 42177173)the Doctoral Direct Train Project of Chongqing Natural Science Foundation(Grant No.CSTB2023NSCQ-BSX0029).
文摘Underground engineering projects such as deep tunnel excavation often encounter rockburst disasters accompanied by numerous microseismic events.Rapid interpretation of microseismic signals is crucial for the timely identification of rockbursts.However,conventional processing encompasses multi-step workflows,including classification,denoising,picking,locating,and computational analysis,coupled with manual intervention,which collectively compromise the reliability of early warnings.To address these challenges,this study innovatively proposes the“microseismic stethoscope"-a multi-task machine learning and deep learning model designed for the automated processing of massive microseismic signals.This model efficiently extracts three key parameters that are necessary for recognizing rockburst disasters:rupture location,microseismic energy,and moment magnitude.Specifically,the model extracts raw waveform features from three dedicated sub-networks:a classifier for source zone classification,and two regressors for microseismic energy and moment magnitude estimation.This model demonstrates superior efficiency compared to traditional processing and semi-automated processing,reducing per-event processing time from 0.71 s to 0.49 s to merely 0.036 s.It concurrently achieves 98%accuracy in source zone classification,with microseismic energy and moment magnitude estimation errors of 0.13 and 0.05,respectively.This model has been well applied and validated in the Daxiagu Tunnel case in Sichuan,China.The application results indicate that the model is as accurate as traditional methods in determining source parameters,and thus can be used to identify potential geomechanical processes of rockburst disasters.By enhancing the signal processing reliability of microseismic events,the proposed model in this study presents a significant advancement in the identification of rockburst disasters.
基金supported by the National Natural Science Foundation of China(No.52207228)the Beijing Natural Science Foundation,China(No.3224070)the National Natural Science Foundation of China(No.52077208).
文摘The growing use of lithium-ion batteries in electric transportation and grid-scale storage systems has intensified the need for accurate and highly generalizable state-of-health(SOH)estimation.Conventional approaches often suffer from reduced accuracy under dynamically uncertain state-of-charge(SOC)operating ranges and heterogeneous aging stresses.This study presents a unified SOH estimation framework that integrates physics-informed modeling,subspace identification,and Transformer-based learning.A reduced-order model is derived from simplified electrochemical dynamics,providing an interpretable and computationally efficient representation of battery behavior.Subspace identification across a wide SOC and SOH range yields degradation-sensitive features,which the Transformer uses to capture long-range aging dynamics via multi-head self-attention.Experiments on LiFePO4 cells under joint-cell training show consistently accurate SOH estimation,with a maximum error of 1.39%,demonstrating the framework’s effectiveness in decoupling SOC and SOH effects.In cross-cell validation,where training and validation are performed on different cells,the model maintains a maximum error of 2.06%,confirming strong generalization to unseen aging trajectories.Comparative experiments on LiFePO_(4)and public LiCoO_(2)datasets confirm the framework’s cross-chemistry applicability.By extracting low-dimensional,physically interpretable features via subspace identification,the framework significantly reduces training cost while maintaining high SOH estimation accuracy,outperforming conventional data-driven models lacking physical guidance.
基金supported by the Scientific and Technological Innovation Project of the China Academy of Chinese Medical Sciences(CI2021A04013)the National Natural Science Foundation of China(82204610)+1 种基金the Qihang Talent Program(L2022046)the Fundamental Research Funds for the Central Public Welfare Research Institutes(ZZ15-YQ-041 and L2021029).
文摘Background:The medicinal material known as Os Draconis(Longgu)originates from fossilized remains of ancient mammals and is widely used in treating emotional and mental conditions.However,fossil resources are nonrenewable,and clinical demand is increasingly difficult to meet,leading to a proliferation of counterfeit products.During prolonged geological burial,static pressure from the surrounding strata severely compromises the microstructural integrity of osteons in Os Draconis,but Os Draconis still largely retains the structural features of mammalian bone.Methods:Using verified authentic Os Draconis samples over 10,000 years old as a baseline,this study summarizes the ultrastructural characteristics of genuine Os Draconis.Employing electron probe microanalysis and optical polarized light microscopy,we examined 28 batches of authentic Os Draconis and 31 batches of counterfeits to identify their ultrastructural differences.Key points for ultrastructural identification of Os Draconis were compiled,and a new identification approach was proposed based on these differences.Results:Authentic Os Draconis exhibited distinct ultrastructural markers:irregularly shaped osteons with traversing fissures,deformed/displaced Haversian canals,and secondary mineral infill(predominantly calcium carbonate).Counterfeits showed regular osteon arrangements,absent traversal fissures,and homogeneous hydroxyapatite composition.Lab-simulated samples lacked structural degradation features.EPMA confirmed calcium carbonate infill in fossilized Haversian canals,while elemental profiles differentiated lacunae types(void vs.mineral-packed).Conclusion:The study established ultrastructural criteria for authentic Os Draconis identification:osteon deformation,geological fissures penetrating bone units,and heterogenous mineral deposition.These features,unattainable in counterfeits or modern processed bones,provide a cost-effective,accurate identification method.This approach bridges gaps in TCM material standardization and supports quality control for clinical applications.
文摘This paper proposes a robust control-oriented identification method for errors-in-variables(EIV)systems in output feedbacks using frequency-response(FR)experimental data.An important relation between such a closed-loop EIV system and its coprime factor(CF)uncertainty description is first derived,based on which the FR measurements suitable for plant CF identification are able to be generated.Different factorizations of a given controller in the closed-loop system can be made best use to adjust right coprime factors(RCFs)of the plant so as to realize an improvement on the signal-to-noise ratio of identification experimental data.Subsequently,a nominal RCF model is estimated by linear matrix inequalities from the applicable FR measurements and its associated worst-case errors are quantified from a priori and a posteriori information on the underlying system.A resulting RCF perturbation model set can then be described by the nominal RCF model and its worst-case error bounds.Such a model set capable of being stabilized by the given controller is ready for its robust stabilizing controller redesign and robust performance analysis.Finally,a numerical simulation is given to show the efficacy of the proposed identification method.
基金funded by the Youth Project of Basic Research Plan for Natural Sciences in Shaanxi Province,grant number 2024JC-YBQN-0253.
文摘The technology of locating magnetic anomaly targets via geomagnetic eld measurements has been increasingly widely applied,with multiple magnetic anomaly target localization emerging as a critical research direction.However,when two magnetic anomaly targets are horizontally close but vertically separated,traditional clustering-based localization methods tend to omit the deeper target.To address this issue,we propose an improved clustering-based localization method for multiple magnetic anomaly targets,which integrates two core innovations:the introduction of a reference target to establish a benchmark for normal magnetic moment distribution,and the utilization of spatial distribution characteristics of magnetic moment estimates to judge the presence of omitted targets.Simulation results demonstrate that the proposed method not only achieves accurate localization of conventional targets but also eectively identies the omission of deeper targets,providing a reliable basis for determining whether supplementary localization steps are required.
基金supported in part by the National Natural Science Foundation of China(62373070 and 52272388)in part by the Chongqing Natural Science Foundation(CSTB2024NSCQ-QCXMX0054,CSTB2022NSCQ-MSX1225 and CSTC2024YCJH-BGZXM0042)in part by the Key Research and Development Project of Anhui Province(202304a05020060).
文摘In this paper,we consider a multiple-input single-output(MISO)Hammerstein system whose inputs and output are disturbed by unknown Gaussian white measurement noises.The parameter estimation of such a system is a typical errors-in-variables(EIV)nonlinear system identification problem.This paper proposes a bias-correction least squares(BCLS)identification methods to compute a consistent estimate of EIV MISO Hammerstein systems from noisy data.To obtain the unbiased parameter estimates of EIV MISO Hammerstein system,the analytical expression of estimated bias for the standard least squares(LS)algorithm is derived first,which is a function about the variances of noises.And then a recursive algorithm is proposed to estimate the unknown term of noises variances from noisy data.Finally,based on bias estimation scheme,the bias caused by the correlation between the input–output signals exciting the true system and the corresponding measurement noise,resulting in unbiased parameter estimates of the EIV MISO Hammerstein system.The performance of the proposed method is demonstrated through a simulation example and a chemical continuously stirred tank reactor(CSTR)system.
基金supported by the National Key Research and Development Program of China(No.2022YFC2403500)the National Natural Science Foundation of China(No.22225401)+1 种基金the Science and Technology Innovation Program of Hunan Province(No.2020RC4017)the Guizhou Provincial Science and Technology Projects(No.ZK[2023]293).
文摘Simultaneous identification and quantitative detection of phenylenediamine(PDA)isomers,including o-phenylenediamine(OPD),m-phenylenediamine(MPD),and p-phenylenediamine(PPD),are essential for environmental risk assessment and human health protection.However,current visual detection methods can only distinguish individual PDA isomers and failed to identify binary or ternary mixtures.Herein,a highly active and ultrastable peroxidase(POD)-like CoPt graphitic nanozyme was used for naked-eye identification and colorimetric/fluorescent(FL)dual-mode quantitative detection of PDA isomers.The CoPt@G nanozyme effectively catalyzed the oxidation of OPD,MPD,PPD,OPD+PPD,OPD+MPD,MPD+PPD and OPD+MPD+PPD into yellow,colorless,lilac,yellow,yellow,wine red and reddish-brown products,respectively,in the presence of H_(2)O_(2).Thus,the MPD,PPD,MPD+PPD and OPD+MPD+PPD were easily identified based on the distinct color of their oxidation products,and the OPD,OPD+PPD,OPD+MPD could be further identified by the additional addition of MPD or PPD.Subsequently,CoPt@G/H_(2)O_(2)-,a 3,3′,5,5′-tetramethylbenzidine(TMB)/CoPt@G/H_(2)O_(2)-,and MPD/CoPt@G/H_(2)O_(2)-enabled colorimetric/FL dual-mode platforms for the quantitative detection of OPD,MPD and PPD were proposed.The experimental results illustrated that the constructed sensing platforms exhibit satisfactory sensitivity,comparable to that reported in previous studies.Finally,the evaluation of PDAs in water samples was realized,yielding satisfactory recoveries.This work expanded the application prospects of nanozymes in assessing environmental risks and protection of human security.
基金supported by the grants from National Natural Science Foundation of China(Nos.22278091,22278046)Young Elite Sci-entists Sponsorship Program by CAST(No.2024QNRC0387)+2 种基金the Guangxi Natural Science Foundation of China(Nos.2025GXNSFBA069146,2023GXNSFGA026001,GKAD25069076)the Foundation(No.202403)of Tianjin Key Laboratory of Pulp&Paper(Tianjin University of Science&Technology)P.R.China,and the Foundation of Guangxi Key Laboratory of Clean Pulp&Papermaking and Pollution Control,College of Light Industry and Food Engineering,Guangxi University(No.2021KF01).
文摘With the continuous advancement of social technology and the increasing awareness of health management,biomass-based triboelectric nanogenerator(TENG)displayed significant potential as flexible wearable electronics for continuous foot gait monitoring.Nevertheless,existing biomass-based TENG often faces challenges of insufficient mechanical robustness and durability in practical applications,where they are prone to surface abrasion and structural fracture under continuous compression and friction,severely limiting their long-term performances.In order to address these challenges,this work proposed a multiscale crosslinking strategy,which strengthened the noncovalent interactions within the polymer by constructing multiple reinforcement networks,successfully fabricating a dual-network C-lignin-based triboelectric material(CLTM)with excellent durability and crack resistance.Among them,the optimal CLTM(PSGCL-0.2)exhibited high mechanical strength(strain 445%,tensile strength 41.56 MPa,Young's modulus 41.25 MPa,toughness 159.67 MJ/m^(3))and excellent cyclic stability(300 cycles)with versatile functionalities,including antibacterial,antioxidant,and UV-shielding properties,water stabilization(255.51 g/m^(2)/d),efficient photothermal conversion,and full recyclability.Furthermore,biomass-based TENG device assembled from PSGCL-0.2 achieved stable triboelectric output properties(102.5 V,2.9μA,and 61.3 nC),and sustainable for 2000 cycles,fast response time(68 ms),and excellent power density(325.9 mW/m^(2)),effectively converting mechanical energy into electrical energy.Especially,PSGCL 0.2 was also integrated into the wireless self-powered smart insole,successfully enabling real-time visual monitoring of plantar pressure distribution and dynamic gait.Meanwhile,combined with the machine learning algorithm,the self-powered smart insole achieved precise recognition and classification of eight different motion states with an accuracy of 98%.This study provides the feasible strategy for developing extremely stable and durable biomass-based TENG,aimed at advancing sustainable intelligent healthcare systems.
基金supported by Joint Funds of the National Natural Science Foundation of China(Grant No.U21A20228).
文摘Root rot is a prevalent soil-borne fungal disease in citrus.Citron C-05(Citrus medica)stands out as a germplasm within Citrus spp.due to its complete resistance to citrus canker and favorable characteristics such as single embryo and easy rooting.However,Citron C-05 was found to be highly susceptible to root rot during cultivation,with the specific pathogens previously unknown.In this study,four candidate fungal species were isolated from Citron C-05 roots.Sequence analysis of ITS,EF-1a,RPB1,and RPB2 identified two Fusarium solani strains,Rr-2 and Rr-4,as the candidates causing root rot in Citron C-05.Resistance tests showed these two pathogens increased root damage rate from 10.30%to 35.69%in Citron C-05,sour orange(Citrus aurantium),sweet orange(Citrus sinensis)and pummelo(Citrus grandis).F.solani exhibited the weak pathogenicity towards trifoliate orange(Poncirus trifoliata).DAB staining revealed none of reddish-brown precipitation in the four susceptible citrus germplasm after infection with F.solani,while trifoliate orange exhibited significant H2O2 accumulation.Trypan blue staining indicated increased cell death in the four susceptible citrus germplasm following infection with these two pathogens but not in trifoliate orange.These findings provide a comprehensive understanding of citrus root rot and support future research on the mechanisms of root rot resistance in citrus.
基金partially supported by the National Natural Science Foundation of China(62075137)the Guangdong Basic and Applied Basic Research Foundation(2023A1515140161)+3 种基金the Guangxi Natural Science Foundation of China(2021JJB 110003)the Dongguan Science and Technology of Social Development Program(20231800936312)the high-level talent program of Dongguan University of Technology(No.221110080)the Sanming Project of Medicine in Shenzhen(No.SZSM202103014).
文摘Many spore-forming Bacillus species can cause serious human diseases,because of accidental Bacillusspore infection.Thus,developing an identification strategy with both high sensitivity and specificity is greatly in demand.In this work,we proposed a novel approach named multi-head self-attention mechanism-guided neural network Raman platform to identify living Bacillus spores within a single-cell resolution.The multi-head self-attention mechanism-guided neural network Raman platform was created by combining single-cell Raman spectroscopy,convolutional neural network(CNN),and multi-head self-attention mechanism.To address the limited size of the original spectra dataset,Gaussian noise-based spectra augmentation was employed to increase the number of single-cell Raman spectra datasets for CNN training.Owing to the assistance of both spectra augmentation and multi-head self-attention mechanism,the obtained prediction accuracy of five Bacillus spore species was further improved from 92.29±0.82%to 99.43±0.15%.To figure out the spectra differences covered by the multi-head self-attention mechanism-guided CNN,the relative classification weight from typical Raman bands was visualized via multi-head self-attention mechanism curve.In the process of spectra augmentation from 0 to 1000,the distribution of relative classification weight varied from a discrete state to a more concentrated phase.More importantly,these highlighted four Raman bands(1017,1449,1576,and 1660 cm^(-1))were assigned large weights,showing that the spectra differences in the Raman bands produced the largest contribution to prediction accuracy.It can be foreseen that,our proposed sorting platform has great potential in accurately identifying Bacillus and its related genera species at a single-cell level.
基金funding from the Natural Science Foundation of Henan Province(252300421852)the State Key Laboratory of Development and Comprehensive Utilization of Coking Coal Resources(41040220201308)+4 种基金the National Natural Science Foundation of China(41972254)the China Postdoctoral Science Foundation(2019M662494)Supported by the Key Scientific Research Projects of Higher Education Institutions of Henan Province(19A170005)the Fundamental Research Funds for the Universities of Henan Province(NSFRF200337,NSFRF200103)Key Research and Development Project of Henan Province(251111322300).
文摘Accurate identification of water sources is crucial for effective water management and safety in mining operations.However,imbalanced water sample datasets often lead to suboptimal classification accuracy.To address this challenge,this study proposes a novel water source identification method integrating Synthetic Minority Over-Sampling Technique(SMOTE),Zebra Optimization Algorithm(ZOA),and Light Gradient Boosting Machine(LightGBM).Initially,SMOTE is utilized to synthesize samples for the minority class within the imbalanced dataset,thereby generating a balanced water sample dataset and mitigating class distribution disparities.Subsequently,an efficient water source identification model is constructed by combining ZOA with LightGBM,leveraging the strengths of both algorithms.The model’s performance is validated using a test set and compared with other common classification models.Results demonstrate that SMOTE significantly alleviates class imbalance and enhances the classification accuracy of LightGBM for minority class water samples.ZOA parameter tuning accelerates model convergence and further improves classification accuracy,optimizing the model’s overall performance.In experimental validation,the proposed SMOTE-ZOA-LightGBM model achieved an accuracy of 88.41%and a F1 score of 88.24%,outperforming six other classification models.The method proposed in this paper can accurately identify water source types,effectively addressing the issue of low classification accuracy caused by imbalanced water sample data.It provides reliable technical support and scientific basis for identifying and preventing water inrush sources in mines.
基金supported by State Grid Sichuan Electric Power Company science and technology project“Research on Key Technologies for Reclosing of High-Ratio New Energy Grid Connection Lines.”(Program No:52199723002Q).
文摘The integration of a high proportion of renewable energy introduces significant challenges for the adaptability of traditional fault nature identification methods.To address these challenges,this paper presents a novel fault nature identification method for renewable energy grid-connected interconnection lines,leveraging wavelet packet decomposition and voltage waveform time-frequency morphology comparison algorithms.First,the paper investigates the harmonic injection mechanism during non-full-phase operation following fault isolation in photovoltaic renewable energy systems,and examines the voltage characteristics of faulted phases in renewable energy scenarios.The analysis reveals that substantial differences exist in both the time and frequency domains of phase voltages before and after the extinction of transient faults,whereas permanent faults do not exhibit such variations.Building on this observation,the paper proposes a voltage time-frequency feature extraction method based on wavelet packet decomposition,wherein low-frequency waveform components are selected to characterize fault features.Subsequently,a fault nature identification method is introduced,based on a voltage waveform time-frequency morphology comparison.By employing a windowing technique to quantify waveform differences before and after arc extinction,this method effectively distinguishes between permanent and transient faults and accurately determines the arc extinction time.Finally,a 220 kV renewable energy grid connection line model is developed using PSCAD for verification.The results demonstrate that the proposed method is highly adaptable across various fault locations,transition resistances,and renewable energy control strategies,and can reliably identify fault nature in renewable energy grid connection scenarios.
基金the DigiEcoQuarry project,funded by the European Union's Horizon 2020 research and innovation program under Grant Agreement No.101003750supported by the China Scholarship Council(Grant No.202006370006).
文摘Agile lithology identification can assist mining by providing important information in the exploration and production of mineral resources.This study proposes a new lithology recognition procedure using video-logging of boreholes with an endoscope,applied to six production blocks in a limestone quarry.Images are automatically extracted from the videos and the lithology is classified into three classes based on clay content,i.e.massive limestone,brecciated limestone,and high amount of clay.The image quality is evaluated with a gray pixel intensity threshold and three no-reference image quality metrics,i.e.perception-based image quality evaluator,natural image quality evaluator,and blind/referenceless image spatial quality evaluator.After removing low-quality images,7583 images are retained and used for developing lithology classification models using six optimized classification techniques.The contrast-limited adaptive histogram equalization(CLAHE)technique is used to improve image quality.Ten color characteristics involving three percentiles of red,green and blue pixel intensities,together with color counting and five texture characteristics-correlation,entropy,homogeneity,contrast and energy-are used as inputs.Bayesian optimized light gradient boosting machine model performs best,with an overall accuracy of 88.04%,and a precision on the classes of massive limestone,brecciated limestone and high amount of clay of 90.72%,83.52%and 85.29%,respectively,for the testing set.The feature importance scores show that the color counting is the most significant parameter for the development of the classification model.Compared with previous image-based methodologies,this study provides a more flexible and cheaper procedure to identify lithology.
