Industrial robot dynamics lay the foundation for high-precision and high-speed control, and accurate identification of dynamic parameters is essential for precise dynamic calculations. The choice of friction models is...Industrial robot dynamics lay the foundation for high-precision and high-speed control, and accurate identification of dynamic parameters is essential for precise dynamic calculations. The choice of friction models is a critical component in the identification of industrial robot dynamics. Traditional static friction models struggle to capture the hysteresis effects caused by robot joint elasticity and clearances, leading to large torque prediction errors when the joint velocity crosses zero. Due to the presence of hysteresis effects, the joint velocity crosses zero in the forward direction, and the reverse direction will have different friction patterns. Although the hysteresis effects can be modeled as an ordinary differential equation(ODE), it is difficult to determine the ODE structure that achieves both generalization and accuracy to describe the hysteresis effects of the friction model. To address this issue, we propose the neural hysteresis friction(NHF), which uses neural ODE to model the hysteresis effects in a data-driven manner, thereby mitigating the current inadequacies in the study of dynamic friction characteristics. The experiments on a real 6-axis industrial robot demonstrate that our proposed method can accurately model the friction dynamics during directional switching and outperform other modeling methods. Velocity tracking control experiments show that NHF can effectively reduce tracking errors when the velocity crosses zero.展开更多
The spatial distribution of discontinuities and the size of rock blocks are the key indicators for rock mass quality evaluation and rockfall risk assessment.Traditional manual measurement is often dangerous or unreach...The spatial distribution of discontinuities and the size of rock blocks are the key indicators for rock mass quality evaluation and rockfall risk assessment.Traditional manual measurement is often dangerous or unreachable at some high-steep rock slopes.In contrast,unmanned aerial vehicle(UAV)photogrammetry is not limited by terrain conditions,and can efficiently collect high-precision three-dimensional(3D)point clouds of rock masses through all-round and multiangle photography for rock mass characterization.In this paper,a new method based on a 3D point cloud is proposed for discontinuity identification and refined rock block modeling.The method is based on four steps:(1)Establish a point cloud spatial topology,and calculate the point cloud normal vector and average point spacing based on several machine learning algorithms;(2)Extract discontinuities using the density-based spatial clustering of applications with noise(DBSCAN)algorithm and fit the discontinuity plane by combining principal component analysis(PCA)with the natural breaks(NB)method;(3)Propose a method of inserting points in the line segment to generate an embedded discontinuity point cloud;and(4)Adopt a Poisson reconstruction method for refined rock block modeling.The proposed method was applied to an outcrop of an ultrahigh steep rock slope and compared with the results of previous studies and manual surveys.The results show that the method can eliminate the influence of discontinuity undulations on the orientation measurement and describe the local concave-convex characteristics on the modeling of rock blocks.The calculation results are accurate and reliable,which can meet the practical requirements of engineering.展开更多
In current neural network algorithms for nuclide identification in high-background,poor-resolution detectors,traditional network paradigms including back-propagation networks,convolutional neural networks,recurrent ne...In current neural network algorithms for nuclide identification in high-background,poor-resolution detectors,traditional network paradigms including back-propagation networks,convolutional neural networks,recurrent neural networks,etc.,have been limited in research on γ spectrum analysis because of their inherent mathematical mechanisms.It is difficult to make progress in terms of training data requirements and prediction accuracy.In contrast to traditional network paradigms,network models based on the transformer structure have the characteristics of parallel computing,position encoding,and deep stacking,which have enabled good performance in natural language processing tasks in recent years.Therefore,in this paper,a transformer-based neural network (TBNN) model is proposed to achieve nuclide identification for the first time.First,the Geant4 program was used to generate the basic single-nuclide energy spectrum through Monte Carlo simulations.A multi-nuclide energy spectrum database was established for neural network training using random matrices of γ-ray energy,activity,and noise.Based on the encoder–decoder structure,a network topology based on the transformer was built,transforming the 1024-channel energy spectrum data into a 32×32 energy spectrum sequence as the model input.Through experiments and adjustments of model parameters,including the learning rate of the TBNN model,number of attention heads,and number of network stacking layers,the overall recognition rate reached 98.7%.Additionally,this database was used for training AI models such as back-propagation networks,convolutional neural networks,residual networks,and long shortterm memory neural networks,with overall recognition rates of 92.8%,95.3%,96.3%,and 96.6%,respectively.This indicates that the TBNN model exhibited better nuclide identification among these AI models,providing an important reference and theoretical basis for the practical application of transformers in the qualitative and quantitative analysis of the γ spectrum.展开更多
In complex systems,there is a kind of parameters having only a minor impact on the outputs in most cases,but their accurate values are still critical for the operation of systems.In this paper,the authors focus on the...In complex systems,there is a kind of parameters having only a minor impact on the outputs in most cases,but their accurate values are still critical for the operation of systems.In this paper,the authors focus on the identification of these weak influence parameters in the complex systems and propose a identification model based on the parameter recursion.As an application,three parameters of the steam generator are identified,that is,the valve opening,the valve CV value,and the reference water level,in which the valve opening and the reference water level are weak influence parameters under most operating conditions.Numerical simulation results show that,in comparison with the multi-layer perceptron(MLP),the identification error rate is decreased.Actually,the average identification error rate for the valve opening decreases by 0.96%,for the valve CV decreases by 0.002%,and for the reference water level decreases by 12%after one recursion.After two recursions,the average identification error rate for the valve opening decreases by 11.07%,for the valve CV decreases by 2.601%,and for the reference water level decreases by 95.79%.This method can help to improve the control of the steam generator.展开更多
Dear Editor,This letter presents a novel approach to the data-driven control of unknown nonlinear systems.By leveraging online sparse identification based on the Koopman operator,a high-dimensional linear system model...Dear Editor,This letter presents a novel approach to the data-driven control of unknown nonlinear systems.By leveraging online sparse identification based on the Koopman operator,a high-dimensional linear system model approximating the actual system is obtained online.The upper bound of the discrepancy between the identified model and the actual system is estimated using real-time prediction error,which is then utilized in the design of a tube-based robust model predictive controller.The effectiveness of the proposed approach is validated by numerical simulation.展开更多
A state-of-the-art review is presented of mathematical manoeuvring models for surface ships and parameter estimation methods that have been used to build mathematical manoeuvring models for surface ships. In the first...A state-of-the-art review is presented of mathematical manoeuvring models for surface ships and parameter estimation methods that have been used to build mathematical manoeuvring models for surface ships. In the first part, the classical manoeuvring models, such as the Abkowitz model, MMG, Nomoto and their revised versions, are revisited and the model structure with the hydrodynamic coefficients is also presented.Then, manoeuvring tests, including both the scaled model tests and sea trials, are introduced with the fact that the test data is critically important to obtain reliable results using parameter estimation methods. In the last part, selected papers published in journals and international conferences are reviewed and the statistical analysis of the manoeuvring models, test data, system identification methods and environmental disturbances used in the paper is presented.展开更多
The complex geometrical features of mechanical components significantly influence contact interactions and system dynamics.However,directly modeling contact forces on surfaces with intricate geometries presents consid...The complex geometrical features of mechanical components significantly influence contact interactions and system dynamics.However,directly modeling contact forces on surfaces with intricate geometries presents considerable challenges.This study focuses on the helically twisted wire rope-sheave contact and proposes a contact force model that incorporates complex geometric features through a parameter identification approach.The model's impact on contact forces and system dynamics is thoroughly investigated.Leveraging a point contact model and an elliptic integral approximation,a loss function is formulated using the finite element(FE)contact model results as the reference data.Geometric parameters are subsequently determined by optimizing this loss function via a genetic algorithm(GA).The findings reveal that the contact stiffness increases with the wire rope pitch length,the radius of principal curvature,and the elliptic eccentricity of the contact zone.The proposed contact force model is integrated into a rigid-flexible coupled dynamics model,developed by the absolute node coordinate formulation,to examine the effects of contact geometry on system dynamics.The results demonstrate that the variations in wire rope geometry alter the contact stiffness,which in turn affects dynamic rope tension through frictional energy dissipation.The enhanced model's predictions exhibit superior alignment with the experimental data,thereby validating the methodology.This approach provides new insights for deducing the contact geometry from kinetic parameters and monitoring the performance degradation of mechanical components.展开更多
Accurate and reliable photovoltaic(PV)modeling is crucial for the performance evaluation,control,and optimization of PV systems.However,existing methods for PV parameter identification often suffer from limitations in...Accurate and reliable photovoltaic(PV)modeling is crucial for the performance evaluation,control,and optimization of PV systems.However,existing methods for PV parameter identification often suffer from limitations in accuracy and efficiency.To address these challenges,we propose an adaptive multi-learning cooperation search algorithm(AMLCSA)for efficient identification of unknown parameters in PV models.AMLCSA is a novel algorithm inspired by teamwork behaviors in modern enterprises.It enhances the original cooperation search algorithm in two key aspects:(i)an adaptive multi-learning strategy that dynamically adjusts search ranges using adaptive weights,allowing better individuals to focus on local exploitation while guiding poorer individuals toward global exploration;and(ii)a chaotic grouping reflection strategy that introduces chaotic sequences to enhance population diversity and improve search performance.The effectiveness of AMLCSA is demonstrated on single-diode,double-diode,and three PV-module models.Simulation results show that AMLCSA offers significant advantages in convergence,accuracy,and stability compared to existing state-of-the-art algorithms.展开更多
An efficient determination of the geological characteristics and soil-rock type ahead of a tunnel face is critical for adjusting construction parameters during shield tunnelling.In general,operational engineers rely o...An efficient determination of the geological characteristics and soil-rock type ahead of a tunnel face is critical for adjusting construction parameters during shield tunnelling.In general,operational engineers rely on visual observations of mucky soil types from belt conveyors.This results in shield halting and involves both time and cost implications.This paper proposes a deep learning approach designed to identify mucky soil by monitoring a video installed on the strut of a belt conveyer.The proposed approach comprises four steps:(1)image acquisition,(2)enhanced you-only-look-once(YOLO)modelling,(3)model performance evaluation,and(4)soil identification based on an optimal analysis.The enhanced YOLO model is a deep image detection algorithm.It was introduced by integrating two innovative strategies:data augmentation and imbalance learning.This enhancement accelerates the speed of image identification and improves the overall classification performance.A case study of shield tunnelling in the soil-rock mixed strata of the GuangzhoueFoshan intercity railway line was conducted to validate the proposed approach.The results indicate that the enhanced YOLO model achieves a classification performance comparable to that of the highly optimised AlexNet and GoogleNet.Additionally,the proposed approach more effectively detects the muck soil content than manual observation.This demonstrates its potential for real-time applications in shield tunnelling operations.展开更多
In order to improve the traditional teaching model of traditional Chinese medicine identification course for graduate students of pharmacy,this paper described the research on constructing and practicing the blended t...In order to improve the traditional teaching model of traditional Chinese medicine identification course for graduate students of pharmacy,this paper described the research on constructing and practicing the blended teaching model of"online+offline"based on the teaching concept of TfU by taking the course of"Authentic Medicinal Materials and Quality of Traditional Chinese Medicine"as an example.In the preparatory phase,through resource integration and course content decomposition,it identifies"generative topics"to engage students in pre-class online discussions.During the instructional phase,"comprehension-oriented objectives"are established based on learning analytics,followed by the implementation of"understanding-focused activities"for guided inquiry in offline classrooms.The post-class phase employs online extended materials to conduct"sustained assessment"through evaluations and summaries,thereby continuously optimizing subsequent teaching practices.This pedagogical framework not only effectively cultivates investigative research thinking among graduate students but also enhances standardized management and scientific development of the teaching team.The practical research outcomes and experiences derived from this model can provide valuable references for analogous course reforms.展开更多
Current experimental and computational methods have limitations in accurately and efficiently classifying ion channels within vast protein spaces.Here we have developed a deep learning algorithm,GPT2 Ion Channel Class...Current experimental and computational methods have limitations in accurately and efficiently classifying ion channels within vast protein spaces.Here we have developed a deep learning algorithm,GPT2 Ion Channel Classifier(GPT2-ICC),which effectively distinguishing ion channels from a test set containing approximately 239 times more non-ion-channel proteins.GPT2-ICC integrates representation learning with a large language model(LLM)-based classifier,enabling highly accurate identification of potential ion channels.Several potential ion channels were predicated from the unannotated human proteome,further demonstrating GPT2-ICC’s generalization ability.This study marks a significant advancement in artificial-intelligence-driven ion channel research,highlighting the adaptability and effectiveness of combining representation learning with LLMs to address the challenges of imbalanced protein sequence data.Moreover,it provides a valuable computational tool for uncovering previously uncharacterized ion channels.展开更多
To ensure the safe operation of batteries,accurately obtaining key internal state parameters is essential.However,traditional parameter measurement methods either require opening the battery or long-term measurements,...To ensure the safe operation of batteries,accurately obtaining key internal state parameters is essential.However,traditional parameter measurement methods either require opening the battery or long-term measurements,which are impractical.Therefore,the fixed values are commonly used for these parameters in electrochemical models and have significant limitations.To overcome these limitations,this paper proposes a deep neural network(DNN)based data-driven evaluation method to determine model parameters.By coupling an improved one-dimensional isothermal pseudo-twodimensional(P2D)model with DNN,this study identified concentration-dependent parameters through detailed discharge curve analysis.The results show that the data-driven method can effectively obtain the change trend of concentration-dependent parameters through the charge and discharge curve,and the method can be extended to different battery systems in different discharge rates and aging applications.This work is expected to provide new parameter selection insights for data-driven battery prediction and monitoring models.展开更多
The efficiency of tunnel excavation,rock strength,stability of surrounding rock,and underground engineering disasters are closely related to lithology.Accurately identifying lithology is a necessary prerequisite for i...The efficiency of tunnel excavation,rock strength,stability of surrounding rock,and underground engineering disasters are closely related to lithology.Accurately identifying lithology is a necessary prerequisite for intelligent,safe,and efficient tunnel construction.The design of conventional recognition models heavily relies on experience and extensive calculations.To develop a model suitable for deployment on construction sites and capable of accurate lithology identification,a fast search method for lithology identification models is proposed.This method integrates geological knowledge,apparent feature extraction techniques,and search algorithms.An efficient feature extraction super network using multi-scale geological features of rock surface is constructed,a model evaluation method that comprehensively considers accuracy and latency is developed,and differential evolution algorithm is used to search for the optimal model parameters.Experiments demonstrate that the proposed method enables the model to evolve faster and more accurately,and eventually a model(LithoNet)suitable for lithological classification is found.It only takes 2.10 ms to infer an image of 224×224,which is 57.25%faster than MobileNet v3 and 62.83%faster than ShuffleNet V2.The F1-score of LithoNet is 0.9874,surpassing classical models such as EfficientNetV2-S.LithoNet can be easily deployed on portable devices,effectively promoting the intelligence and accuracy of lithology identification at engineering sites.展开更多
To enhance the recognition accuracy of current network models for apple leaf diseases,a lightweight model that leverages an enhanced MobileNetV3-Small architecture is introduced in this study.The improved model utiliz...To enhance the recognition accuracy of current network models for apple leaf diseases,a lightweight model that leverages an enhanced MobileNetV3-Small architecture is introduced in this study.The improved model utilizes MobileNetV3-Small,a lightweight architecture with fewer parameters,serving as the primary network for feature extraction.It integrates a weighted bi-directional feature pyramid network that fuses multi-scale features,thereby enhancing the model's capacity to detect disease characteristics across various scales.Additionally,an efficient multi-scale attention mechanism is integrated to mitigate the influence of complex background noise in natural environments,further improving disease recognition accuracy.The experiment utilizes the AppleLeaf9 public dataset to classify healthy apple leaves and eight distinct disease types.The results indicate that,when using the augmented dataset,the improved model achieves a recognition accuracy of 95.98%,with only 1.72 M parameters,123.16 M FLOPs,and an inference time of just 14.10 ms.Compared with eight other lightweight neural network models,including MobileNetV2,ShuffleNet_v2_1.5×,ResNet50,MobileNetV3-Large,EfficientNet-B0,MobileNetV3-Small,MobileNetV4-Conv-Small,and MobileNetV4-Conv-Medium,the improved model demonstrates superior accuracy.In particular,the proposed model achieves a recognition accuracy improvement of 0.93 percentage points compared with the baseline MobileNetV3-Small model.The optimized model introduced in this study effectively improves the accuracy in identifying diseases in apple leaves,while maintaining a low parameter count and fast inference speed,thus offering a novel approach for deploying disease recognition models on agricultural electronic devices.展开更多
The identification of rock mass discontinuities is critical for rock mass characterization.While high-resolution digital outcrop models(DOMs)are widely used,current digital methods struggle to generalize across divers...The identification of rock mass discontinuities is critical for rock mass characterization.While high-resolution digital outcrop models(DOMs)are widely used,current digital methods struggle to generalize across diverse geological settings.Large-scale models(LSMs),with vast parameter spaces and extensive training datasets,excel in solving complex visual problems.This study explores the potential of using one such LSM,Segment anything model(SAM),to identify facet-type discontinuities across several outcrops via interactive prompting.The findings demonstrate that SAM effectively segments two-dimensional(2D)discontinuities,with its generalization capability validated on a dataset of 2426 identified discontinuities across 170 outcrops.The model achieves 0.78 mean IoU and 0.86 average precision using 11-point prompts.To extend to three dimensions(3D),a framework integrating SAM with Structure-from-Motion(SfM)was proposed.By utilizing the inherent but often overlooked relationship between image pixels and point clouds in SfM,the identification process was simplified and generalized across photogrammetric devices.Benchmark studies showed that the framework achieved 0.91 average precision,identifying 87 discontinuities in Dataset-3D.The results confirm its high precision and efficiency,making it a valuable tool for data annotation.The proposed method offers a practical solution for geological investigations.展开更多
To solve the problems of redundant feature information,the insignificant difference in feature representation,and low recognition accuracy of the fine-grained image,based on the ResNeXt50 model,an MSFResNet network mo...To solve the problems of redundant feature information,the insignificant difference in feature representation,and low recognition accuracy of the fine-grained image,based on the ResNeXt50 model,an MSFResNet network model is proposed by fusing multi-scale feature information.Firstly,a multi-scale feature extraction module is designed to obtain multi-scale information on feature images by using different scales of convolution kernels.Meanwhile,the channel attention mechanism is used to increase the global information acquisition of the network.Secondly,the feature images processed by the multi-scale feature extraction module are fused with the deep feature images through short links to guide the full learning of the network,thus reducing the loss of texture details of the deep network feature images,and improving network generalization ability and recognition accuracy.Finally,the validity of the MSFResNet model is verified using public datasets and applied to wild mushroom identification.Experimental results show that compared with ResNeXt50 network model,the accuracy of the MSFResNet model is improved by 6.01%on the FGVC-Aircraft common dataset.It achieves 99.13%classification accuracy on the wild mushroom dataset,which is 0.47%higher than ResNeXt50.Furthermore,the experimental results of the thermal map show that the MSFResNet model significantly reduces the interference of background information,making the network focus on the location of the main body of wild mushroom,which can effectively improve the accuracy of wild mushroom identification.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
Under the condition of frequent replacement of wind tunnel models,multiple types of wind tunnel models are fixed by a slender support sting with low stiffness damping.When excited by wind load,various models produce r...Under the condition of frequent replacement of wind tunnel models,multiple types of wind tunnel models are fixed by a slender support sting with low stiffness damping.When excited by wind load,various models produce random multi-dimensional vibration with different characteristics,which makes it impossible to obtain accurate and efficient aerodynamic data.Therefore,in order to ensure the reliable and efficient conduction of wind tunnel test,a wind-tunnel-modeladaptive vibration control method is proposed in this paper.First,the split type adaptive vibration suppression structure is designed.Second,the multi-dimensional vibration characteristic characterization method is derived and the vibration characteristic identification method of the system is designed.Then,a vibration state estimation model is established according to the identification results of vibration characteristics,and a multi-actuator cooperative control method based on vibration state estimation is constructed.Finally,a model-adaptive vibration control system is built,and vibration characteristics identification and hammer experiments are carried out for two types of typical models.The results show that the proposed model-adaptive vibration control method increases the equivalent damping ratio of pitch and yaw dimensions of the high-aspect-ratio class model by 8.19 times and 48.81 times,respectively.The equivalent damping ratio of pitch and yaw dimensions of the highslenderness-ratio class model is increased by 16.44 and 5.43 times,respectively.It provides a strong guarantee for the reliable and efficient development of multi-type wind tunnel test tasks.展开更多
Photovoltaic(PV)systems are electrical systems designed to convert solar energy into electrical energy.As a crucial component of PV systems,harsh weather conditions,photovoltaic panel temperature and solar irradiance ...Photovoltaic(PV)systems are electrical systems designed to convert solar energy into electrical energy.As a crucial component of PV systems,harsh weather conditions,photovoltaic panel temperature and solar irradiance influence the power output of photovoltaic cells.Therefore,accurately identifying the parameters of PV models is essential for simulating,controlling and evaluating PV systems.In this study,we propose an enhanced weighted-mean-of-vectors optimisation(EINFO)for efficiently determining the unknown parameters in PV systems.EINFO introduces a Lambert W-based explicit objective function for the PV model,enhancing the computational accuracy of the algorithm's population fitness.This addresses the challenge of improving the metaheuristic algorithms'identification accuracy for unknown parameter identification in PV models.We experimentally apply EINFO to three types of PV models(single-diode,double-diode and PV-module models)to validate its accuracy and stability in parameter identification.The results demonstrate that EINFO achieves root mean square errors(RMSEs)of 7.7301E-04,6.8553E-04 and 2.0608E-03 for the single-diode model,double-diode model and PV-module model,respectively,surpassing those obtained by using INFO algorithm as well as other methods in terms of convergence speed,accuracy and stability.Furthermore,comprehensive experimental findings on three commercial PV modules(ST40,SM55 and KC200GT)indicate that EINFO consistently maintains high accuracy across varying temperatures and irradiation levels.In conclusion,EINFO emerges as a highly competitive and practical approach for parameter identification in diverse types of PV models.展开更多
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
基金supported by the National Natural Science Foundation of China (Grant No.52188102)。
文摘Industrial robot dynamics lay the foundation for high-precision and high-speed control, and accurate identification of dynamic parameters is essential for precise dynamic calculations. The choice of friction models is a critical component in the identification of industrial robot dynamics. Traditional static friction models struggle to capture the hysteresis effects caused by robot joint elasticity and clearances, leading to large torque prediction errors when the joint velocity crosses zero. Due to the presence of hysteresis effects, the joint velocity crosses zero in the forward direction, and the reverse direction will have different friction patterns. Although the hysteresis effects can be modeled as an ordinary differential equation(ODE), it is difficult to determine the ODE structure that achieves both generalization and accuracy to describe the hysteresis effects of the friction model. To address this issue, we propose the neural hysteresis friction(NHF), which uses neural ODE to model the hysteresis effects in a data-driven manner, thereby mitigating the current inadequacies in the study of dynamic friction characteristics. The experiments on a real 6-axis industrial robot demonstrate that our proposed method can accurately model the friction dynamics during directional switching and outperform other modeling methods. Velocity tracking control experiments show that NHF can effectively reduce tracking errors when the velocity crosses zero.
基金supported by the National Natural Science Foundation of China(Grant Nos.41941017 and 42177139)Graduate Innovation Fund of Jilin University(Grant No.2024CX099)。
文摘The spatial distribution of discontinuities and the size of rock blocks are the key indicators for rock mass quality evaluation and rockfall risk assessment.Traditional manual measurement is often dangerous or unreachable at some high-steep rock slopes.In contrast,unmanned aerial vehicle(UAV)photogrammetry is not limited by terrain conditions,and can efficiently collect high-precision three-dimensional(3D)point clouds of rock masses through all-round and multiangle photography for rock mass characterization.In this paper,a new method based on a 3D point cloud is proposed for discontinuity identification and refined rock block modeling.The method is based on four steps:(1)Establish a point cloud spatial topology,and calculate the point cloud normal vector and average point spacing based on several machine learning algorithms;(2)Extract discontinuities using the density-based spatial clustering of applications with noise(DBSCAN)algorithm and fit the discontinuity plane by combining principal component analysis(PCA)with the natural breaks(NB)method;(3)Propose a method of inserting points in the line segment to generate an embedded discontinuity point cloud;and(4)Adopt a Poisson reconstruction method for refined rock block modeling.The proposed method was applied to an outcrop of an ultrahigh steep rock slope and compared with the results of previous studies and manual surveys.The results show that the method can eliminate the influence of discontinuity undulations on the orientation measurement and describe the local concave-convex characteristics on the modeling of rock blocks.The calculation results are accurate and reliable,which can meet the practical requirements of engineering.
基金supported by the National Natural Science Foundation of China(No.42127807)Natural Science Foundation of Sichuan Province(Nos.2024NSFSC0422,23NSFSCC0116)Nuclear Energy Development Project(No.[2021]-88).
文摘In current neural network algorithms for nuclide identification in high-background,poor-resolution detectors,traditional network paradigms including back-propagation networks,convolutional neural networks,recurrent neural networks,etc.,have been limited in research on γ spectrum analysis because of their inherent mathematical mechanisms.It is difficult to make progress in terms of training data requirements and prediction accuracy.In contrast to traditional network paradigms,network models based on the transformer structure have the characteristics of parallel computing,position encoding,and deep stacking,which have enabled good performance in natural language processing tasks in recent years.Therefore,in this paper,a transformer-based neural network (TBNN) model is proposed to achieve nuclide identification for the first time.First,the Geant4 program was used to generate the basic single-nuclide energy spectrum through Monte Carlo simulations.A multi-nuclide energy spectrum database was established for neural network training using random matrices of γ-ray energy,activity,and noise.Based on the encoder–decoder structure,a network topology based on the transformer was built,transforming the 1024-channel energy spectrum data into a 32×32 energy spectrum sequence as the model input.Through experiments and adjustments of model parameters,including the learning rate of the TBNN model,number of attention heads,and number of network stacking layers,the overall recognition rate reached 98.7%.Additionally,this database was used for training AI models such as back-propagation networks,convolutional neural networks,residual networks,and long shortterm memory neural networks,with overall recognition rates of 92.8%,95.3%,96.3%,and 96.6%,respectively.This indicates that the TBNN model exhibited better nuclide identification among these AI models,providing an important reference and theoretical basis for the practical application of transformers in the qualitative and quantitative analysis of the γ spectrum.
文摘In complex systems,there is a kind of parameters having only a minor impact on the outputs in most cases,but their accurate values are still critical for the operation of systems.In this paper,the authors focus on the identification of these weak influence parameters in the complex systems and propose a identification model based on the parameter recursion.As an application,three parameters of the steam generator are identified,that is,the valve opening,the valve CV value,and the reference water level,in which the valve opening and the reference water level are weak influence parameters under most operating conditions.Numerical simulation results show that,in comparison with the multi-layer perceptron(MLP),the identification error rate is decreased.Actually,the average identification error rate for the valve opening decreases by 0.96%,for the valve CV decreases by 0.002%,and for the reference water level decreases by 12%after one recursion.After two recursions,the average identification error rate for the valve opening decreases by 11.07%,for the valve CV decreases by 2.601%,and for the reference water level decreases by 95.79%.This method can help to improve the control of the steam generator.
基金supported by the National Natural Science Foundation of China(62473020).
文摘Dear Editor,This letter presents a novel approach to the data-driven control of unknown nonlinear systems.By leveraging online sparse identification based on the Koopman operator,a high-dimensional linear system model approximating the actual system is obtained online.The upper bound of the discrepancy between the identified model and the actual system is estimated using real-time prediction error,which is then utilized in the design of a tube-based robust model predictive controller.The effectiveness of the proposed approach is validated by numerical simulation.
基金the Strategic Research Plan of the Centre for Marine Technology and Ocean Engineeringfinanced by the Portuguese Foundation for Science and Technology (Fundacao para a Ciência e Tecnologia-FCT) under contract UIDB/UIDP/00134/2020。
文摘A state-of-the-art review is presented of mathematical manoeuvring models for surface ships and parameter estimation methods that have been used to build mathematical manoeuvring models for surface ships. In the first part, the classical manoeuvring models, such as the Abkowitz model, MMG, Nomoto and their revised versions, are revisited and the model structure with the hydrodynamic coefficients is also presented.Then, manoeuvring tests, including both the scaled model tests and sea trials, are introduced with the fact that the test data is critically important to obtain reliable results using parameter estimation methods. In the last part, selected papers published in journals and international conferences are reviewed and the statistical analysis of the manoeuvring models, test data, system identification methods and environmental disturbances used in the paper is presented.
基金supported by the National Key Research and Development Program of China(No.2023YFC3010400)。
文摘The complex geometrical features of mechanical components significantly influence contact interactions and system dynamics.However,directly modeling contact forces on surfaces with intricate geometries presents considerable challenges.This study focuses on the helically twisted wire rope-sheave contact and proposes a contact force model that incorporates complex geometric features through a parameter identification approach.The model's impact on contact forces and system dynamics is thoroughly investigated.Leveraging a point contact model and an elliptic integral approximation,a loss function is formulated using the finite element(FE)contact model results as the reference data.Geometric parameters are subsequently determined by optimizing this loss function via a genetic algorithm(GA).The findings reveal that the contact stiffness increases with the wire rope pitch length,the radius of principal curvature,and the elliptic eccentricity of the contact zone.The proposed contact force model is integrated into a rigid-flexible coupled dynamics model,developed by the absolute node coordinate formulation,to examine the effects of contact geometry on system dynamics.The results demonstrate that the variations in wire rope geometry alter the contact stiffness,which in turn affects dynamic rope tension through frictional energy dissipation.The enhanced model's predictions exhibit superior alignment with the experimental data,thereby validating the methodology.This approach provides new insights for deducing the contact geometry from kinetic parameters and monitoring the performance degradation of mechanical components.
基金supported by the National Natural Science Foundation of China(Grant Nos.62303197,62273214)the Natural Science Foundation of Shandong Province(ZR2024MFO18).
文摘Accurate and reliable photovoltaic(PV)modeling is crucial for the performance evaluation,control,and optimization of PV systems.However,existing methods for PV parameter identification often suffer from limitations in accuracy and efficiency.To address these challenges,we propose an adaptive multi-learning cooperation search algorithm(AMLCSA)for efficient identification of unknown parameters in PV models.AMLCSA is a novel algorithm inspired by teamwork behaviors in modern enterprises.It enhances the original cooperation search algorithm in two key aspects:(i)an adaptive multi-learning strategy that dynamically adjusts search ranges using adaptive weights,allowing better individuals to focus on local exploitation while guiding poorer individuals toward global exploration;and(ii)a chaotic grouping reflection strategy that introduces chaotic sequences to enhance population diversity and improve search performance.The effectiveness of AMLCSA is demonstrated on single-diode,double-diode,and three PV-module models.Simulation results show that AMLCSA offers significant advantages in convergence,accuracy,and stability compared to existing state-of-the-art algorithms.
基金funded by Guangdong Province Scientific Research Project for Young Innovation Talent(Grant No.2022KQNCX239)The Pearl River Talent Recruitment Program(Grant No.2019CX01G338),Guangdong Province.
文摘An efficient determination of the geological characteristics and soil-rock type ahead of a tunnel face is critical for adjusting construction parameters during shield tunnelling.In general,operational engineers rely on visual observations of mucky soil types from belt conveyors.This results in shield halting and involves both time and cost implications.This paper proposes a deep learning approach designed to identify mucky soil by monitoring a video installed on the strut of a belt conveyer.The proposed approach comprises four steps:(1)image acquisition,(2)enhanced you-only-look-once(YOLO)modelling,(3)model performance evaluation,and(4)soil identification based on an optimal analysis.The enhanced YOLO model is a deep image detection algorithm.It was introduced by integrating two innovative strategies:data augmentation and imbalance learning.This enhancement accelerates the speed of image identification and improves the overall classification performance.A case study of shield tunnelling in the soil-rock mixed strata of the GuangzhoueFoshan intercity railway line was conducted to validate the proposed approach.The results indicate that the enhanced YOLO model achieves a classification performance comparable to that of the highly optimised AlexNet and GoogleNet.Additionally,the proposed approach more effectively detects the muck soil content than manual observation.This demonstrates its potential for real-time applications in shield tunnelling operations.
基金Supported by Guangxi Degree and Postgraduate Education Reform Project(JGY2023213,JGY2023211).
文摘In order to improve the traditional teaching model of traditional Chinese medicine identification course for graduate students of pharmacy,this paper described the research on constructing and practicing the blended teaching model of"online+offline"based on the teaching concept of TfU by taking the course of"Authentic Medicinal Materials and Quality of Traditional Chinese Medicine"as an example.In the preparatory phase,through resource integration and course content decomposition,it identifies"generative topics"to engage students in pre-class online discussions.During the instructional phase,"comprehension-oriented objectives"are established based on learning analytics,followed by the implementation of"understanding-focused activities"for guided inquiry in offline classrooms.The post-class phase employs online extended materials to conduct"sustained assessment"through evaluations and summaries,thereby continuously optimizing subsequent teaching practices.This pedagogical framework not only effectively cultivates investigative research thinking among graduate students but also enhances standardized management and scientific development of the teaching team.The practical research outcomes and experiences derived from this model can provide valuable references for analogous course reforms.
基金funded by grants from the National Key Research and Development Program of China(Grant Nos.:2022YFE0205600 and 2022YFC3400504)the National Natural Science Foundation of China(Grant Nos.:82373792 and 82273857)the Fundamental Research Funds for the Central Universities,China,and the East China Normal University Medicine and Health Joint Fund,China(Grant No.:2022JKXYD07001).
文摘Current experimental and computational methods have limitations in accurately and efficiently classifying ion channels within vast protein spaces.Here we have developed a deep learning algorithm,GPT2 Ion Channel Classifier(GPT2-ICC),which effectively distinguishing ion channels from a test set containing approximately 239 times more non-ion-channel proteins.GPT2-ICC integrates representation learning with a large language model(LLM)-based classifier,enabling highly accurate identification of potential ion channels.Several potential ion channels were predicated from the unannotated human proteome,further demonstrating GPT2-ICC’s generalization ability.This study marks a significant advancement in artificial-intelligence-driven ion channel research,highlighting the adaptability and effectiveness of combining representation learning with LLMs to address the challenges of imbalanced protein sequence data.Moreover,it provides a valuable computational tool for uncovering previously uncharacterized ion channels.
基金supported by National Natural Science Foundation of China(22478239)Science and Technology Commission of Shanghai Municipality(19DZ2271100)National Natural Science Foundation of China(22208208)。
文摘To ensure the safe operation of batteries,accurately obtaining key internal state parameters is essential.However,traditional parameter measurement methods either require opening the battery or long-term measurements,which are impractical.Therefore,the fixed values are commonly used for these parameters in electrochemical models and have significant limitations.To overcome these limitations,this paper proposes a deep neural network(DNN)based data-driven evaluation method to determine model parameters.By coupling an improved one-dimensional isothermal pseudo-twodimensional(P2D)model with DNN,this study identified concentration-dependent parameters through detailed discharge curve analysis.The results show that the data-driven method can effectively obtain the change trend of concentration-dependent parameters through the charge and discharge curve,and the method can be extended to different battery systems in different discharge rates and aging applications.This work is expected to provide new parameter selection insights for data-driven battery prediction and monitoring models.
基金financial support from the National Natural Science Foundation of China(Grant Nos.52279103 and 52379103)the Natural Science Foundation of Shandong Province(Grant No.ZR2023YQ049).
文摘The efficiency of tunnel excavation,rock strength,stability of surrounding rock,and underground engineering disasters are closely related to lithology.Accurately identifying lithology is a necessary prerequisite for intelligent,safe,and efficient tunnel construction.The design of conventional recognition models heavily relies on experience and extensive calculations.To develop a model suitable for deployment on construction sites and capable of accurate lithology identification,a fast search method for lithology identification models is proposed.This method integrates geological knowledge,apparent feature extraction techniques,and search algorithms.An efficient feature extraction super network using multi-scale geological features of rock surface is constructed,a model evaluation method that comprehensively considers accuracy and latency is developed,and differential evolution algorithm is used to search for the optimal model parameters.Experiments demonstrate that the proposed method enables the model to evolve faster and more accurately,and eventually a model(LithoNet)suitable for lithological classification is found.It only takes 2.10 ms to infer an image of 224×224,which is 57.25%faster than MobileNet v3 and 62.83%faster than ShuffleNet V2.The F1-score of LithoNet is 0.9874,surpassing classical models such as EfficientNetV2-S.LithoNet can be easily deployed on portable devices,effectively promoting the intelligence and accuracy of lithology identification at engineering sites.
基金Sponsored by China National Key R&D Program during the 13th Five-year Plan Period(Grant No.2019YFD0901605)。
文摘To enhance the recognition accuracy of current network models for apple leaf diseases,a lightweight model that leverages an enhanced MobileNetV3-Small architecture is introduced in this study.The improved model utilizes MobileNetV3-Small,a lightweight architecture with fewer parameters,serving as the primary network for feature extraction.It integrates a weighted bi-directional feature pyramid network that fuses multi-scale features,thereby enhancing the model's capacity to detect disease characteristics across various scales.Additionally,an efficient multi-scale attention mechanism is integrated to mitigate the influence of complex background noise in natural environments,further improving disease recognition accuracy.The experiment utilizes the AppleLeaf9 public dataset to classify healthy apple leaves and eight distinct disease types.The results indicate that,when using the augmented dataset,the improved model achieves a recognition accuracy of 95.98%,with only 1.72 M parameters,123.16 M FLOPs,and an inference time of just 14.10 ms.Compared with eight other lightweight neural network models,including MobileNetV2,ShuffleNet_v2_1.5×,ResNet50,MobileNetV3-Large,EfficientNet-B0,MobileNetV3-Small,MobileNetV4-Conv-Small,and MobileNetV4-Conv-Medium,the improved model demonstrates superior accuracy.In particular,the proposed model achieves a recognition accuracy improvement of 0.93 percentage points compared with the baseline MobileNetV3-Small model.The optimized model introduced in this study effectively improves the accuracy in identifying diseases in apple leaves,while maintaining a low parameter count and fast inference speed,thus offering a novel approach for deploying disease recognition models on agricultural electronic devices.
基金support in dataset preparation.This study was funded by National Natural Science Foundation of China(Nos.42422704 and 52379109)Opening the fund of State Key Laboratory of Geohazard Prevention and Geoenvironment Protection(Chengdu University of Technology)(No.SKLGP2024K028)Science and Technology Research and Design Projects of China State Construction Engineering Corporation Ltd.(No.CSCEC-2024-Q-68).
文摘The identification of rock mass discontinuities is critical for rock mass characterization.While high-resolution digital outcrop models(DOMs)are widely used,current digital methods struggle to generalize across diverse geological settings.Large-scale models(LSMs),with vast parameter spaces and extensive training datasets,excel in solving complex visual problems.This study explores the potential of using one such LSM,Segment anything model(SAM),to identify facet-type discontinuities across several outcrops via interactive prompting.The findings demonstrate that SAM effectively segments two-dimensional(2D)discontinuities,with its generalization capability validated on a dataset of 2426 identified discontinuities across 170 outcrops.The model achieves 0.78 mean IoU and 0.86 average precision using 11-point prompts.To extend to three dimensions(3D),a framework integrating SAM with Structure-from-Motion(SfM)was proposed.By utilizing the inherent but often overlooked relationship between image pixels and point clouds in SfM,the identification process was simplified and generalized across photogrammetric devices.Benchmark studies showed that the framework achieved 0.91 average precision,identifying 87 discontinuities in Dataset-3D.The results confirm its high precision and efficiency,making it a valuable tool for data annotation.The proposed method offers a practical solution for geological investigations.
基金supported by National Natural Science Foundation of China(No.61862037)Lanzhou Jiaotong University Tianyou Innovation Team Project(No.TY202002)。
文摘To solve the problems of redundant feature information,the insignificant difference in feature representation,and low recognition accuracy of the fine-grained image,based on the ResNeXt50 model,an MSFResNet network model is proposed by fusing multi-scale feature information.Firstly,a multi-scale feature extraction module is designed to obtain multi-scale information on feature images by using different scales of convolution kernels.Meanwhile,the channel attention mechanism is used to increase the global information acquisition of the network.Secondly,the feature images processed by the multi-scale feature extraction module are fused with the deep feature images through short links to guide the full learning of the network,thus reducing the loss of texture details of the deep network feature images,and improving network generalization ability and recognition accuracy.Finally,the validity of the MSFResNet model is verified using public datasets and applied to wild mushroom identification.Experimental results show that compared with ResNeXt50 network model,the accuracy of the MSFResNet model is improved by 6.01%on the FGVC-Aircraft common dataset.It achieves 99.13%classification accuracy on the wild mushroom dataset,which is 0.47%higher than ResNeXt50.Furthermore,the experimental results of the thermal map show that the MSFResNet model significantly reduces the interference of background information,making the network focus on the location of the main body of wild mushroom,which can effectively improve the accuracy of wild mushroom identification.
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 in part by the National Natural Science Foundation of China(Nos.52475550,52305095)in part by the Key R&D Project of Liaoning Province,China(No.2023JH2/101800026)。
文摘Under the condition of frequent replacement of wind tunnel models,multiple types of wind tunnel models are fixed by a slender support sting with low stiffness damping.When excited by wind load,various models produce random multi-dimensional vibration with different characteristics,which makes it impossible to obtain accurate and efficient aerodynamic data.Therefore,in order to ensure the reliable and efficient conduction of wind tunnel test,a wind-tunnel-modeladaptive vibration control method is proposed in this paper.First,the split type adaptive vibration suppression structure is designed.Second,the multi-dimensional vibration characteristic characterization method is derived and the vibration characteristic identification method of the system is designed.Then,a vibration state estimation model is established according to the identification results of vibration characteristics,and a multi-actuator cooperative control method based on vibration state estimation is constructed.Finally,a model-adaptive vibration control system is built,and vibration characteristics identification and hammer experiments are carried out for two types of typical models.The results show that the proposed model-adaptive vibration control method increases the equivalent damping ratio of pitch and yaw dimensions of the high-aspect-ratio class model by 8.19 times and 48.81 times,respectively.The equivalent damping ratio of pitch and yaw dimensions of the highslenderness-ratio class model is increased by 16.44 and 5.43 times,respectively.It provides a strong guarantee for the reliable and efficient development of multi-type wind tunnel test tasks.
基金partially supported by MRC(MC_PC_17171)Royal Society(RP202G0230)+8 种基金BHF(AA/18/3/34220)Hope Foundation for Cancer Research(RM60G0680)GCRF(P202PF11)Sino-UK Industrial Fund(RP202G0289)Sino-UK Education Fund(OP202006)LIAS(P202ED10,P202RE969)Data Science Enhancement Fund(P202RE237)Fight for Sight(24NN201)BBSRC(RM32G0178B8).
文摘Photovoltaic(PV)systems are electrical systems designed to convert solar energy into electrical energy.As a crucial component of PV systems,harsh weather conditions,photovoltaic panel temperature and solar irradiance influence the power output of photovoltaic cells.Therefore,accurately identifying the parameters of PV models is essential for simulating,controlling and evaluating PV systems.In this study,we propose an enhanced weighted-mean-of-vectors optimisation(EINFO)for efficiently determining the unknown parameters in PV systems.EINFO introduces a Lambert W-based explicit objective function for the PV model,enhancing the computational accuracy of the algorithm's population fitness.This addresses the challenge of improving the metaheuristic algorithms'identification accuracy for unknown parameter identification in PV models.We experimentally apply EINFO to three types of PV models(single-diode,double-diode and PV-module models)to validate its accuracy and stability in parameter identification.The results demonstrate that EINFO achieves root mean square errors(RMSEs)of 7.7301E-04,6.8553E-04 and 2.0608E-03 for the single-diode model,double-diode model and PV-module model,respectively,surpassing those obtained by using INFO algorithm as well as other methods in terms of convergence speed,accuracy and stability.Furthermore,comprehensive experimental findings on three commercial PV modules(ST40,SM55 and KC200GT)indicate that EINFO consistently maintains high accuracy across varying temperatures and irradiation levels.In conclusion,EINFO emerges as a highly competitive and practical approach for parameter identification in diverse types of PV models.
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.
