Autism spectrum disorder(ASD)is a multifaceted neurological developmental condition that manifests in several ways.Nearly all autistic children remain undiagnosed before the age of three.Developmental problems affecti...Autism spectrum disorder(ASD)is a multifaceted neurological developmental condition that manifests in several ways.Nearly all autistic children remain undiagnosed before the age of three.Developmental problems affecting face features are often associated with fundamental brain disorders.The facial evolution of newborns with ASD is quite different from that of typically developing children.Early recognition is very significant to aid families and parents in superstition and denial.Distinguishing facial features from typically developing children is an evident manner to detect children analyzed with ASD.Presently,artificial intelligence(AI)significantly contributes to the emerging computer-aided diagnosis(CAD)of autism and to the evolving interactivemethods that aid in the treatment and reintegration of autistic patients.This study introduces an Ensemble of deep learning models based on the autism spectrum disorder detection in facial images(EDLM-ASDDFI)model.The overarching goal of the EDLM-ASDDFI model is to recognize the difference between facial images of individuals with ASD and normal controls.In the EDLM-ASDDFI method,the primary level of data pre-processing is involved by Gabor filtering(GF).Besides,the EDLM-ASDDFI technique applies the MobileNetV2 model to learn complex features from the pre-processed data.For the ASD detection process,the EDLM-ASDDFI method uses ensemble techniques for classification procedure that encompasses long short-term memory(LSTM),deep belief network(DBN),and hybrid kernel extreme learning machine(HKELM).Finally,the hyperparameter selection of the three deep learning(DL)models can be implemented by the design of the crested porcupine optimizer(CPO)technique.An extensive experiment was conducted to emphasize the improved ASD detection performance of the EDLM-ASDDFI method.The simulation outcomes indicated that the EDLM-ASDDFI technique highlighted betterment over other existing models in terms of numerous performance measures.展开更多
The direct torque control of the dual star induction motor(DTC-DSIM) using conventional PI controllers is characterized by unsatisfactory performance, such as high ripples of torque and flux, and sensitivity to parame...The direct torque control of the dual star induction motor(DTC-DSIM) using conventional PI controllers is characterized by unsatisfactory performance, such as high ripples of torque and flux, and sensitivity to parametric variations. Among the most evoked control strategies adopted in this field to overcome these drawbacks presented in classical drive, it is worth mentioning the use of the second order sliding mode control(SOSMC) based on the super twisting algorithm(STA) combined with the fuzzy logic control(FSOSMC). In order to realize the optimal control performance, the FSOSMC parameters are adjusted using an optimization algorithm based on the genetic algorithm(GA). The performances of the envisaged control scheme, called G-FSOSMC, are investigated against G-SOSMC, G-PI and BBO-FSOSMC algorithms. The proposed controller scheme is efficient in reducing the torque and flux ripples, and successfully suppresses chattering. The effects of parametric uncertainties do not affect system performance.展开更多
To improve the spectral characteristics of the high-order weighted compact nonlinear scheme(WCNS),optimized flux difference schemes are proposed.The disadvantages in previous optimization routines,i.e.,reducing formal...To improve the spectral characteristics of the high-order weighted compact nonlinear scheme(WCNS),optimized flux difference schemes are proposed.The disadvantages in previous optimization routines,i.e.,reducing formal orders,or extending stencil widths,are avoided in the new optimized schemes by utilizing fluxes from both cell-edges and cell-nodes.Optimizations are implemented with Fourier analysis for linear schemes and the approximate dispersion relation(ADR)for nonlinear schemes.Classical difference schemes are restored near discontinuities to suppress numerical oscillations with use of a shock sensor based on smoothness indicators.The results of several benchmark numerical tests indicate that the new optimized difference schemes outperform the classical schemes,in terms of accuracy and resolution for smooth wave and vortex,especially for long-time simulations.Using optimized schemes increases the total CPU time by less than 4%.展开更多
Due to the lack of accurate data and complex parameterization,the prediction of groundwater depth is a chal-lenge for numerical models.Machine learning can effectively solve this issue and has been proven useful in th...Due to the lack of accurate data and complex parameterization,the prediction of groundwater depth is a chal-lenge for numerical models.Machine learning can effectively solve this issue and has been proven useful in the prediction of groundwater depth in many areas.In this study,two new models are applied to the prediction of groundwater depth in the Ningxia area,China.The two models combine the improved dung beetle optimizer(DBO)algorithm with two deep learning models:The Multi-head Attention-Convolution Neural Network-Long Short Term Memory networks(MH-CNN-LSTM)and the Multi-head Attention-Convolution Neural Network-Gated Recurrent Unit(MH-CNN-GRU).The models with DBO show better prediction performance,with larger R(correlation coefficient),RPD(residual prediction deviation),and lower RMSE(root-mean-square error).Com-pared with the models with the original DBO,the R and RPD of models with the improved DBO increase by over 1.5%,and the RMSE decreases by over 1.8%,indicating better prediction results.In addition,compared with the multiple linear regression model,a traditional statistical model,deep learning models have better prediction performance.展开更多
Dear Editor,In this letter,a constrained networked predictive control strategy is proposed for the optimal control problem of complex nonlinear highorder fully actuated(HOFA)systems with noises.The method can effectiv...Dear Editor,In this letter,a constrained networked predictive control strategy is proposed for the optimal control problem of complex nonlinear highorder fully actuated(HOFA)systems with noises.The method can effectively deal with nonlinearities,constraints,and noises in the system,optimize the performance metric,and present an upper bound on the stable output of the system.展开更多
GNSS time series analysis provides an effective method for research on the earth's surface deformation,and it can be divided into two parts,deterministic models and stochastic models.The former part can be achieve...GNSS time series analysis provides an effective method for research on the earth's surface deformation,and it can be divided into two parts,deterministic models and stochastic models.The former part can be achieved by several parameters,such as polynomial terms,periodic terms,offsets,and post-seismic models.The latter contains some stochastic noises,which can be affected by detecting the former parameters.If there are not enough parameters assumed,modeling errors will occur and adversely affect the analysis results.In this study,we propose a processing strategy in which the commonly-used 1-order of the polynomial term can be replaced with different orders for better fitting GNSS time series of the Crustal Movement Network of China(CMONOC)stations.Initially,we use the Bayesian Information Criterion(BIC)to identify the best order within the range of 1-4 during the fitting process using the white noise plus power-law noise(WN+PL)model.Then,we compare the 1-order and the optimal order on the effect of deterministic models in GNSS time series,including the velocity and its uncertainty,amplitudes,and initial phases of the annual signals.The results indicate that the first-order polynomial in the GNSS time series is not the primary factor.The root mean square(RMS)reduction rates of almost all station components are positive,which means the new fitting of optimal-order polynomial helps to reduce the RMS of residual series.Most stations maintain the velocity difference(VD)within ±1 mm/yr,with percentages of 85.6%,81.9%and 63.4%in the North,East,and Up components,respectively.As for annual signals,the numbers of amplitude difference(AD)remained at ±0.2 mm are 242,239,and 200 in three components,accounting for 99.6%,98.4%,and 82.3%,respectively.This finding reminds us that the detection of the optimal-order polynomial is necessary when we aim to acquire an accurate understanding of the crustal movement features.展开更多
The synchrotron radiation beamline BL17B of the National Facility for Protein Science(NFPS)in Shanghai,situated at the Shanghai Synchrotron Radiation Facility(SSRF),was originally designed for diffraction experiments ...The synchrotron radiation beamline BL17B of the National Facility for Protein Science(NFPS)in Shanghai,situated at the Shanghai Synchrotron Radiation Facility(SSRF),was originally designed for diffraction experiments and accommodates techniques including single-crystal diffraction,powder diffraction,and grazing-incidence wide-angle X-ray scattering(GIWAXS)to enable the characterization of long-range ordered atomic structures.The academic community associated with BL17B engages in research domains encompassing biology,environment,energy,and materials,and a pronounced demand for characterizing short-range ordered structures exists.To address these requirements,BL17B established an advanced X-ray absorption fine structure(XAFS)experimental platform that enabled it to address a wide range of systems,from crystalline to amorphous and from long-range order to short-range order.The XAFS platform allows simultaneous XAFS data acquisition for both the transmission and fluorescence modes within an energy range of 5-23 keV,encompassing the K-edges of titanium to ruthenium and the L3-edges of cesium to bismuth.The platform exemplifies high levels of automation achieved through automated sample assessment and data collection based on large-capacity sample wheels that facilitate remote sample loading.When integrated with a highly integrated control system that simplifies experimental preparation and data collection,the XAFS platform significantly bolsters experimental efficiency and enhances user experience.Notably,the platform boasts an impressively low extended X-ray absorption fine structure(EXAFS)detection limit of 0.04 wt%for dilute copper phthalocyanine(CuPc)samples and an even more remarkable X-ray absorption near edge structure(XANES)detection threshold of 0.01 wt%.These results demonstrate the methodology?s reliability in low-concentration sample analysis,confirming its capability to generate high-quality XAFS data.展开更多
This paper introduces the Surrogate-assisted Multi-objective Grey Wolf Optimizer(SMOGWO)as a novel methodology for addressing the complex problem of empty-heavy train allocation,with a focus on line utilization balanc...This paper introduces the Surrogate-assisted Multi-objective Grey Wolf Optimizer(SMOGWO)as a novel methodology for addressing the complex problem of empty-heavy train allocation,with a focus on line utilization balance.By integrating surrogate models to approximate the objective functions,SMOGWO significantly improves the efficiency and accuracy of the optimization process.The effectiveness of this approach is evaluated using the CEC2009 multi-objective test function suite,where SMOGWO achieves a superiority rate of 76.67%compared to other leading multi-objective algorithms.Furthermore,the practical applicability of SMOGWO is demonstrated through a case study on empty and heavy train allocation,which validates its ability to balance line capacity,minimize transportation costs,and optimize the technical combination of heavy trains.The research highlights SMOGWO's potential as a robust solution for optimization challenges in railway transportation,offering valuable contributions toward enhancing operational efficiency and promoting sustainable development in the sector.展开更多
The stable nanobubbles adhered to mineral surfaces may facilitate their efficient separation via flotation in the mining industry.However,the state of nanobubbles on mineral solid surfaces is still elusive.In this stu...The stable nanobubbles adhered to mineral surfaces may facilitate their efficient separation via flotation in the mining industry.However,the state of nanobubbles on mineral solid surfaces is still elusive.In this study,molecular dynamics(MD)simulations are employed to examine mineral-like model surfaces with varying degrees of hydrophobicity,modulated by surface charges,to elucidate the adsorption behavior of nanobubbles at the interface.Our findings not only contribute to the fundamental understanding of nanobubbles but also have potential applications in the mining industry.We observed that as the surface charge increases,the contact angle of the nanobubbles increases accordingly with shape transformation from a pancake-like gas film to a cap-like shape,and ultimately forming a stable nanobubble upon an ordered water monolayer.When the solid–water interactions are weak with a small partial charge,the hydrophobic gas(N_(2))molecules accumulate near the solid surfaces.However,we have found,for the first time,that gas molecules assemble a nanobubble on the water monolayer adjacent to the solid surfaces with large partial charges.Such phenomena are attributed to the formation of a hydrophobic water monolayer with a hydrogen bond network structure near the surface.展开更多
With the development of renewable energy technologies such as photovoltaics and wind power,it has become a research hotspot to improve the consumption rate of new energy and reduce energy costs through algorithm impro...With the development of renewable energy technologies such as photovoltaics and wind power,it has become a research hotspot to improve the consumption rate of new energy and reduce energy costs through algorithm improvement.To reduce the operational costs of micro-grid systems and the energy abandonment rate of renewable energy,while simultaneously enhancing user satisfaction on the demand side,this paper introduces an improvedmultiobjective Grey Wolf Optimizer based on Cauchy variation.The proposed approach incorporates a Cauchy variation strategy during the optimizer’s search phase to expand its exploration range and minimize the likelihood of becoming trapped in local optima.At the same time,adoptingmultiple energy storage methods to improve the consumption rate of renewable energy.Subsequently,under different energy balance orders,themulti-objective particle swarmalgorithm,multi-objective grey wolf optimizer,and Cauchy’s variant of the improvedmulti-objective grey wolf optimizer are used for example simulation,solving the Pareto solution set of the model and comparing.The analysis of the results reveals that,compared to the original optimizer,the improved optimizer decreases the daily cost by approximately 100 yuan,and reduces the energy abandonment rate to zero.Meanwhile,it enhances user satisfaction and ensures the stable operation of the micro-grid.展开更多
To enhance the prediction accuracy of unsteady wakes behind wind turbines,a novel reduced-order model is proposed by integrating a multifunctional recurrent fuzzy neural network(MFRFNN)and proper orthogonal decom-posi...To enhance the prediction accuracy of unsteady wakes behind wind turbines,a novel reduced-order model is proposed by integrating a multifunctional recurrent fuzzy neural network(MFRFNN)and proper orthogonal decom-position(POD).First,POD is employed to reduce the di-mensionality of the wind field data,extracting spatiotempo-rally correlated modal coefficients and modes.These reduced-order variables can effectively capture the essential features of unsteady wake behaviors.Next,MFRFNN is utilized to predict the time series of modal coefficients.Fi-nally,by combining the predicted modal coefficients with their corresponding modes,a flow field is reconstructed,al-lowing accurate prediction of unsteady wake dynamics.The predicted wake data exhibit high consistency with large eddy simulation results in both the near-and far-wake re-gions and outperform existing data-driven methods.This ap-proach offers significant potential for optimizing wind farm design and provides a new solution for the precise prediction of wind turbine wake behavior.展开更多
Bayesian-optimized lithology identification has important basic geological research significance and engineering application value,and this paper proposes a Bayesian-optimized lithology identification method based on ...Bayesian-optimized lithology identification has important basic geological research significance and engineering application value,and this paper proposes a Bayesian-optimized lithology identification method based on machine learning of rock visible and near-infrared spectral data.First,the rock spectral data are preprocessed using Savitzky-Golay(SG)smoothing to remove the noise of the spectral data;then,the preprocessed rock spectral data are downscaled using Principal Component Analysis(PCA)to reduce the redundancy of the data,optimize the effective discriminative information,and obtain the rock spectral features;finally,a Bayesian-optimized lithology identification model is established based on rock spectral features,optimize the model hyperparameters using Bayesian optimization(BO)algorithm to avoid the combination of hyperparameters falling into the local optimal solution,and output the predicted type of rock,so as to realize the Bayesian-optimized lithology identification.In addition,this paper conducts comparative analysis on models based on Artificial Neural Network(ANN)/Random Forest(RF),dimensionality reduction/full band,and optimization algorithms.It uses the confusion matrix,accuracy,Precison(P),Recall(R)and F_(1)values(F_(1))as the evaluation indexes of model accuracy.The results indicate that the lithology identification model optimized by the BO-ANN after dimensionality reduction achieves an accuracy of up to 99.80%,up to 99.79%and up to 99.79%.Compared with the BO-RF model,it has higher identification accuracy and better stability for each type of rock identification.The experiments and reliability analysis show that the Bayesian-optimized lithology identification method proposed in this paper has good robustness and generalization performance,which is of great significance for realizing fast,accurate and Bayesian-optimized lithology identification in tunnel site.展开更多
In this manuscript,we propose an analytical equivalent linear viscoelastic constitutive model for fiber-reinforced composites,bypassing general computational homogenization.The method is based on the reduced-order hom...In this manuscript,we propose an analytical equivalent linear viscoelastic constitutive model for fiber-reinforced composites,bypassing general computational homogenization.The method is based on the reduced-order homogenization(ROH)approach.The ROH method typically involves solving multiple finite element problems under periodic conditions to evaluate elastic strain and eigenstrain influence functions in an‘off-line’stage,which offers substantial cost savings compared to direct computational homogenization methods.Due to the unique structure of the fibrous unit cell,“off-line”stage calculation can be eliminated by influence functions obtained analytically.Introducing the standard solid model to the ROH method enables the creation of a comprehensive analytical homogeneous viscoelastic constitutive model.This method treats fibrous composite materials as homogeneous,anisotropic viscoelastic materials,significantly reducing computational time due to its analytical nature.This approach also enables precise determination of a homogenized anisotropic relaxation modulus and accurate capture of various viscoelastic responses under different loading conditions.Three sets of numerical examples,including unit cell tests,three-point beam bending tests,and torsion tests,are given to demonstrate the predictive performance of the homogenized viscoelastic model.Furthermore,the model is validated against experimental measurements,confirming its accuracy and reliability.展开更多
In this paper,we delve into a generalized higher order Camassa-Holm type equation,(or,an ghmCH equation for short).We establish local well-posedness for this equation under the condition that the initial data uo belon...In this paper,we delve into a generalized higher order Camassa-Holm type equation,(or,an ghmCH equation for short).We establish local well-posedness for this equation under the condition that the initial data uo belongs to the Sobolev space H'(R)for some s>2.In addition,we obtain the weak formulation of this equation and prove the existence of both single peakon solution and a multi-peakon dynamic system.展开更多
Stereoscopic agriculture,as an advanced method of agricultural production,poses new challenges for multi-task trajectory planning of unmanned aerial vehicles(UAVs).To address the need for UAVs to perform multi-task tr...Stereoscopic agriculture,as an advanced method of agricultural production,poses new challenges for multi-task trajectory planning of unmanned aerial vehicles(UAVs).To address the need for UAVs to perform multi-task trajectory planning in stereoscopic agriculture,a multi-task trajectory planning model and algorithm(IEP-AO)that synthesizes flight safety and flight efficiency is proposed.Based on the requirements of stereoscopic agricultural geomorphological features and operational characteristics,the multi-task trajectory planning model is ensured by constructing targeted constraints at five aspects,including the path,slope,altitude,corner,energy and obstacle threat,to improve the effectiveness of the trajectory planning model.And combined with the path optimization algorithm,an Aquila optimizer(IEP-AO)based on the interference-enhanced combination model is proposed,which can help UAVs to improve the trajectory search capability in complex operation space and large-scale operation tasks,and jump out of the locally optimal trajectory path region timely,to generate the optimal trajectory planning plan that can adapt to the diversity of the tasks and the flight efficiency.Meanwhile,four simulated flights with different operation scales and different scene constraints were conducted under the constructed real 3Dimension scene,and the experimental results can show that the proposedmulti-task trajectory planning method canmeet themulti-task requirements in stereoscopic agriculture and improve the mission execution efficiency and agricultural production effect of UAV.展开更多
This paper deals with extensions of higher-order optimality conditions for scalar optimization to multiobjective optimization.A type of directional derivatives for a multiobjective function is proposed,and with this n...This paper deals with extensions of higher-order optimality conditions for scalar optimization to multiobjective optimization.A type of directional derivatives for a multiobjective function is proposed,and with this notion characterizations of strict local minima of order k for a multiobjective optimization problem with a nonempty set constraint are established,generalizing the corresponding scalar case obtained by Studniarski[3].Also necessary not sufficient and sufficient not necessary optimality conditions for this minima are derived based on our directional derivatives,which are generalizations of some existing scalar results and equivalent to some existing multiobjective ones.Many examples are given to illustrate them there.展开更多
Teacher–student relationships play a vital role in improving college students’academic performance and the quality of higher education.However,empirical studies with substantial data-driven insights remain limited.T...Teacher–student relationships play a vital role in improving college students’academic performance and the quality of higher education.However,empirical studies with substantial data-driven insights remain limited.To address this gap,this study collected 3278 questionnaires from seven universities across four provinces in China to analyze the key factors affecting college students’academic performance.A machine learning framework,CQFOA-KELM,was developed by enhancing the Fruit Fly Optimization Algorithm(FOA)with Covariance Matrix Adaptation Evolution Strategy(CMAES)and Quadratic Approximation(QA).CQFOA significantly improved population diversity and was validated on the IEEE CEC2017 benchmark functions.The CQFOA-KELM model achieved an accuracy of 98.15%and a sensitivity of 98.53%in predicting college students’academic performance.Additionally,it effectively identified the key factors influencing academic performance through the feature selection process.展开更多
In this paper,we give a complete characterization of all self-adjoint domains of odd order differential operators on two intervals.These two intervals with all four endpoints are singular(one endpoint of each interval...In this paper,we give a complete characterization of all self-adjoint domains of odd order differential operators on two intervals.These two intervals with all four endpoints are singular(one endpoint of each interval is singular or all four endpoints are regulars are the special cases).And these extensions yield"new"self-adjoint operators,which involve interactions between the two intervals.展开更多
Alloying transition metals with Pt is an effective strategy for optimizing Pt-based catalysts toward the oxygen reduction reaction(ORR).Atomic ordered intermetallic compounds(IMC)provide unique electronic and geometri...Alloying transition metals with Pt is an effective strategy for optimizing Pt-based catalysts toward the oxygen reduction reaction(ORR).Atomic ordered intermetallic compounds(IMC)provide unique electronic and geometrical effects as well as stronger intermetallic interactions due to the ordered arrangement of metal atoms,thus exhibiting superior electrocata-lytic activity and durability.However,quantitatively analyzing the ordering degree of IMC and exploring the correlation between the ordering degree and ORR activity remains extremely challenging.Herein,a series of ternary Pt_(2)NiCo interme-tallic catalysts(o-Pt_(2)NiCo)with different ordering degree were synthesized by annealing temperature modulation.Among them,the o-Pt_(2)NiCo which annealed at 800℃for two hours exhibits the highest ordering degree and the optimal ORR ac-tivity,which the mass activity of o-Pt_(2)NiCo is 1.8 times and 2.8 times higher than that of disordered Pt_(2)NiCo alloy and Pt/C.Furthermore,the o-Pt_(2)NiCo still maintains 70.8%mass activity after 30,000 potential cycles.Additionally,the ORR activity test results for Pt_(2)NiCo IMC with different ordering degree also provide a positive correlation between the ordering degree and ORR activity.This work provides a prospective design direction for ternary Pt-based electrocatalysts.展开更多
Prediction of stability in SG(Smart Grid)is essential in maintaining consistency and reliability of power supply in grid infrastructure.Analyzing the fluctuations in power generation and consumption patterns of smart ...Prediction of stability in SG(Smart Grid)is essential in maintaining consistency and reliability of power supply in grid infrastructure.Analyzing the fluctuations in power generation and consumption patterns of smart cities assists in effectively managing continuous power supply in the grid.It also possesses a better impact on averting overloading and permitting effective energy storage.Even though many traditional techniques have predicted the consumption rate for preserving stability,enhancement is required in prediction measures with minimized loss.To overcome the complications in existing studies,this paper intends to predict stability from the smart grid stability prediction dataset using machine learning algorithms.To accomplish this,pre-processing is performed initially to handle missing values since it develops biased models when missing values are mishandled and performs feature scaling to normalize independent data features.Then,the pre-processed data are taken for training and testing.Following that,the regression process is performed using Modified PSO(Particle Swarm Optimization)optimized XGBoost Technique with dynamic inertia weight update,which analyses variables like gamma(G),reaction time(tau1–tau4),and power balance(p1–p4)for providing effective future stability in SG.Since PSO attains optimal solution by adjusting position through dynamic inertial weights,it is integrated with XGBoost due to its scalability and faster computational speed characteristics.The hyperparameters of XGBoost are fine-tuned in the training process for achieving promising outcomes on prediction.Regression results are measured through evaluation metrics such as MSE(Mean Square Error)of 0.011312781,MAE(Mean Absolute Error)of 0.008596322,and RMSE(Root Mean Square Error)of 0.010636156 and MAPE(Mean Absolute Percentage Error)value of 0.0052 which determine the efficacy of the system.展开更多
基金Researchers supporting Project number(RSPD2025R1107),King Saud University,Riyadh,Saudi Arabia.
文摘Autism spectrum disorder(ASD)is a multifaceted neurological developmental condition that manifests in several ways.Nearly all autistic children remain undiagnosed before the age of three.Developmental problems affecting face features are often associated with fundamental brain disorders.The facial evolution of newborns with ASD is quite different from that of typically developing children.Early recognition is very significant to aid families and parents in superstition and denial.Distinguishing facial features from typically developing children is an evident manner to detect children analyzed with ASD.Presently,artificial intelligence(AI)significantly contributes to the emerging computer-aided diagnosis(CAD)of autism and to the evolving interactivemethods that aid in the treatment and reintegration of autistic patients.This study introduces an Ensemble of deep learning models based on the autism spectrum disorder detection in facial images(EDLM-ASDDFI)model.The overarching goal of the EDLM-ASDDFI model is to recognize the difference between facial images of individuals with ASD and normal controls.In the EDLM-ASDDFI method,the primary level of data pre-processing is involved by Gabor filtering(GF).Besides,the EDLM-ASDDFI technique applies the MobileNetV2 model to learn complex features from the pre-processed data.For the ASD detection process,the EDLM-ASDDFI method uses ensemble techniques for classification procedure that encompasses long short-term memory(LSTM),deep belief network(DBN),and hybrid kernel extreme learning machine(HKELM).Finally,the hyperparameter selection of the three deep learning(DL)models can be implemented by the design of the crested porcupine optimizer(CPO)technique.An extensive experiment was conducted to emphasize the improved ASD detection performance of the EDLM-ASDDFI method.The simulation outcomes indicated that the EDLM-ASDDFI technique highlighted betterment over other existing models in terms of numerous performance measures.
基金Project supported by the LEB Research LaboratoryDepartment of Electrical Engineering,University of Batna 2, Algeria。
文摘The direct torque control of the dual star induction motor(DTC-DSIM) using conventional PI controllers is characterized by unsatisfactory performance, such as high ripples of torque and flux, and sensitivity to parametric variations. Among the most evoked control strategies adopted in this field to overcome these drawbacks presented in classical drive, it is worth mentioning the use of the second order sliding mode control(SOSMC) based on the super twisting algorithm(STA) combined with the fuzzy logic control(FSOSMC). In order to realize the optimal control performance, the FSOSMC parameters are adjusted using an optimization algorithm based on the genetic algorithm(GA). The performances of the envisaged control scheme, called G-FSOSMC, are investigated against G-SOSMC, G-PI and BBO-FSOSMC algorithms. The proposed controller scheme is efficient in reducing the torque and flux ripples, and successfully suppresses chattering. The effects of parametric uncertainties do not affect system performance.
基金Project supported by the National Key Project(No.GJXM92579)the Defense Industrial Technology Development Program(No.C1520110002)the State Administration of Science,Technology and Industry for National Defence,China。
文摘To improve the spectral characteristics of the high-order weighted compact nonlinear scheme(WCNS),optimized flux difference schemes are proposed.The disadvantages in previous optimization routines,i.e.,reducing formal orders,or extending stencil widths,are avoided in the new optimized schemes by utilizing fluxes from both cell-edges and cell-nodes.Optimizations are implemented with Fourier analysis for linear schemes and the approximate dispersion relation(ADR)for nonlinear schemes.Classical difference schemes are restored near discontinuities to suppress numerical oscillations with use of a shock sensor based on smoothness indicators.The results of several benchmark numerical tests indicate that the new optimized difference schemes outperform the classical schemes,in terms of accuracy and resolution for smooth wave and vortex,especially for long-time simulations.Using optimized schemes increases the total CPU time by less than 4%.
基金supported by the National Natural Science Foundation of China [grant numbers 42088101 and 42375048]。
文摘Due to the lack of accurate data and complex parameterization,the prediction of groundwater depth is a chal-lenge for numerical models.Machine learning can effectively solve this issue and has been proven useful in the prediction of groundwater depth in many areas.In this study,two new models are applied to the prediction of groundwater depth in the Ningxia area,China.The two models combine the improved dung beetle optimizer(DBO)algorithm with two deep learning models:The Multi-head Attention-Convolution Neural Network-Long Short Term Memory networks(MH-CNN-LSTM)and the Multi-head Attention-Convolution Neural Network-Gated Recurrent Unit(MH-CNN-GRU).The models with DBO show better prediction performance,with larger R(correlation coefficient),RPD(residual prediction deviation),and lower RMSE(root-mean-square error).Com-pared with the models with the original DBO,the R and RPD of models with the improved DBO increase by over 1.5%,and the RMSE decreases by over 1.8%,indicating better prediction results.In addition,compared with the multiple linear regression model,a traditional statistical model,deep learning models have better prediction performance.
基金supported in part by the National Natural Science Foundation of China(62173255,62188101)Shenzhen Key Laboratory of Control Theory and Intelligent Systems(ZDSYS20220330161800001)
文摘Dear Editor,In this letter,a constrained networked predictive control strategy is proposed for the optimal control problem of complex nonlinear highorder fully actuated(HOFA)systems with noises.The method can effectively deal with nonlinearities,constraints,and noises in the system,optimize the performance metric,and present an upper bound on the stable output of the system.
基金supported by the National Natural Science Foundation of China(Grant Nos.42404017,42122025 and 42174030).
文摘GNSS time series analysis provides an effective method for research on the earth's surface deformation,and it can be divided into two parts,deterministic models and stochastic models.The former part can be achieved by several parameters,such as polynomial terms,periodic terms,offsets,and post-seismic models.The latter contains some stochastic noises,which can be affected by detecting the former parameters.If there are not enough parameters assumed,modeling errors will occur and adversely affect the analysis results.In this study,we propose a processing strategy in which the commonly-used 1-order of the polynomial term can be replaced with different orders for better fitting GNSS time series of the Crustal Movement Network of China(CMONOC)stations.Initially,we use the Bayesian Information Criterion(BIC)to identify the best order within the range of 1-4 during the fitting process using the white noise plus power-law noise(WN+PL)model.Then,we compare the 1-order and the optimal order on the effect of deterministic models in GNSS time series,including the velocity and its uncertainty,amplitudes,and initial phases of the annual signals.The results indicate that the first-order polynomial in the GNSS time series is not the primary factor.The root mean square(RMS)reduction rates of almost all station components are positive,which means the new fitting of optimal-order polynomial helps to reduce the RMS of residual series.Most stations maintain the velocity difference(VD)within ±1 mm/yr,with percentages of 85.6%,81.9%and 63.4%in the North,East,and Up components,respectively.As for annual signals,the numbers of amplitude difference(AD)remained at ±0.2 mm are 242,239,and 200 in three components,accounting for 99.6%,98.4%,and 82.3%,respectively.This finding reminds us that the detection of the optimal-order polynomial is necessary when we aim to acquire an accurate understanding of the crustal movement features.
基金supported by the Chinese Academy of Science(CAS)Key Technology Talent Program(No.2021000022)。
文摘The synchrotron radiation beamline BL17B of the National Facility for Protein Science(NFPS)in Shanghai,situated at the Shanghai Synchrotron Radiation Facility(SSRF),was originally designed for diffraction experiments and accommodates techniques including single-crystal diffraction,powder diffraction,and grazing-incidence wide-angle X-ray scattering(GIWAXS)to enable the characterization of long-range ordered atomic structures.The academic community associated with BL17B engages in research domains encompassing biology,environment,energy,and materials,and a pronounced demand for characterizing short-range ordered structures exists.To address these requirements,BL17B established an advanced X-ray absorption fine structure(XAFS)experimental platform that enabled it to address a wide range of systems,from crystalline to amorphous and from long-range order to short-range order.The XAFS platform allows simultaneous XAFS data acquisition for both the transmission and fluorescence modes within an energy range of 5-23 keV,encompassing the K-edges of titanium to ruthenium and the L3-edges of cesium to bismuth.The platform exemplifies high levels of automation achieved through automated sample assessment and data collection based on large-capacity sample wheels that facilitate remote sample loading.When integrated with a highly integrated control system that simplifies experimental preparation and data collection,the XAFS platform significantly bolsters experimental efficiency and enhances user experience.Notably,the platform boasts an impressively low extended X-ray absorption fine structure(EXAFS)detection limit of 0.04 wt%for dilute copper phthalocyanine(CuPc)samples and an even more remarkable X-ray absorption near edge structure(XANES)detection threshold of 0.01 wt%.These results demonstrate the methodology?s reliability in low-concentration sample analysis,confirming its capability to generate high-quality XAFS data.
基金supported by the National Natural Science Foundation of China(Project No.5217232152102391)+2 种基金Sichuan Province Science and Technology Innovation Talent Project(2024JDRC0020)China Shenhua Energy Company Limited Technology Project(GJNY-22-7/2300-K1220053)Key science and technology projects in the transportation industry of the Ministry of Transport(2022-ZD7-132).
文摘This paper introduces the Surrogate-assisted Multi-objective Grey Wolf Optimizer(SMOGWO)as a novel methodology for addressing the complex problem of empty-heavy train allocation,with a focus on line utilization balance.By integrating surrogate models to approximate the objective functions,SMOGWO significantly improves the efficiency and accuracy of the optimization process.The effectiveness of this approach is evaluated using the CEC2009 multi-objective test function suite,where SMOGWO achieves a superiority rate of 76.67%compared to other leading multi-objective algorithms.Furthermore,the practical applicability of SMOGWO is demonstrated through a case study on empty and heavy train allocation,which validates its ability to balance line capacity,minimize transportation costs,and optimize the technical combination of heavy trains.The research highlights SMOGWO's potential as a robust solution for optimization challenges in railway transportation,offering valuable contributions toward enhancing operational efficiency and promoting sustainable development in the sector.
基金supported by the National Natural Science Foundation of China(Grant Nos.12022508,12074394,and 22125604)Shanghai Supercomputer Center of ChinaShanghai Snowlake Technology Co.Ltd.
文摘The stable nanobubbles adhered to mineral surfaces may facilitate their efficient separation via flotation in the mining industry.However,the state of nanobubbles on mineral solid surfaces is still elusive.In this study,molecular dynamics(MD)simulations are employed to examine mineral-like model surfaces with varying degrees of hydrophobicity,modulated by surface charges,to elucidate the adsorption behavior of nanobubbles at the interface.Our findings not only contribute to the fundamental understanding of nanobubbles but also have potential applications in the mining industry.We observed that as the surface charge increases,the contact angle of the nanobubbles increases accordingly with shape transformation from a pancake-like gas film to a cap-like shape,and ultimately forming a stable nanobubble upon an ordered water monolayer.When the solid–water interactions are weak with a small partial charge,the hydrophobic gas(N_(2))molecules accumulate near the solid surfaces.However,we have found,for the first time,that gas molecules assemble a nanobubble on the water monolayer adjacent to the solid surfaces with large partial charges.Such phenomena are attributed to the formation of a hydrophobic water monolayer with a hydrogen bond network structure near the surface.
基金supported by the Open Fund of Guangxi Key Laboratory of Building New Energy and Energy Conservation(Project Number:Guike Energy 17-J-21-3).
文摘With the development of renewable energy technologies such as photovoltaics and wind power,it has become a research hotspot to improve the consumption rate of new energy and reduce energy costs through algorithm improvement.To reduce the operational costs of micro-grid systems and the energy abandonment rate of renewable energy,while simultaneously enhancing user satisfaction on the demand side,this paper introduces an improvedmultiobjective Grey Wolf Optimizer based on Cauchy variation.The proposed approach incorporates a Cauchy variation strategy during the optimizer’s search phase to expand its exploration range and minimize the likelihood of becoming trapped in local optima.At the same time,adoptingmultiple energy storage methods to improve the consumption rate of renewable energy.Subsequently,under different energy balance orders,themulti-objective particle swarmalgorithm,multi-objective grey wolf optimizer,and Cauchy’s variant of the improvedmulti-objective grey wolf optimizer are used for example simulation,solving the Pareto solution set of the model and comparing.The analysis of the results reveals that,compared to the original optimizer,the improved optimizer decreases the daily cost by approximately 100 yuan,and reduces the energy abandonment rate to zero.Meanwhile,it enhances user satisfaction and ensures the stable operation of the micro-grid.
基金The National Natural Science Foundation of China (No. 51908107)。
文摘To enhance the prediction accuracy of unsteady wakes behind wind turbines,a novel reduced-order model is proposed by integrating a multifunctional recurrent fuzzy neural network(MFRFNN)and proper orthogonal decom-position(POD).First,POD is employed to reduce the di-mensionality of the wind field data,extracting spatiotempo-rally correlated modal coefficients and modes.These reduced-order variables can effectively capture the essential features of unsteady wake behaviors.Next,MFRFNN is utilized to predict the time series of modal coefficients.Fi-nally,by combining the predicted modal coefficients with their corresponding modes,a flow field is reconstructed,al-lowing accurate prediction of unsteady wake dynamics.The predicted wake data exhibit high consistency with large eddy simulation results in both the near-and far-wake re-gions and outperform existing data-driven methods.This ap-proach offers significant potential for optimizing wind farm design and provides a new solution for the precise prediction of wind turbine wake behavior.
基金support from the National Natural Science Foundation of China(Grant Nos:52379103 and 52279103)the Natural Science Foundation of Shandong Province(Grant No:ZR2023YQ049).
文摘Bayesian-optimized lithology identification has important basic geological research significance and engineering application value,and this paper proposes a Bayesian-optimized lithology identification method based on machine learning of rock visible and near-infrared spectral data.First,the rock spectral data are preprocessed using Savitzky-Golay(SG)smoothing to remove the noise of the spectral data;then,the preprocessed rock spectral data are downscaled using Principal Component Analysis(PCA)to reduce the redundancy of the data,optimize the effective discriminative information,and obtain the rock spectral features;finally,a Bayesian-optimized lithology identification model is established based on rock spectral features,optimize the model hyperparameters using Bayesian optimization(BO)algorithm to avoid the combination of hyperparameters falling into the local optimal solution,and output the predicted type of rock,so as to realize the Bayesian-optimized lithology identification.In addition,this paper conducts comparative analysis on models based on Artificial Neural Network(ANN)/Random Forest(RF),dimensionality reduction/full band,and optimization algorithms.It uses the confusion matrix,accuracy,Precison(P),Recall(R)and F_(1)values(F_(1))as the evaluation indexes of model accuracy.The results indicate that the lithology identification model optimized by the BO-ANN after dimensionality reduction achieves an accuracy of up to 99.80%,up to 99.79%and up to 99.79%.Compared with the BO-RF model,it has higher identification accuracy and better stability for each type of rock identification.The experiments and reliability analysis show that the Bayesian-optimized lithology identification method proposed in this paper has good robustness and generalization performance,which is of great significance for realizing fast,accurate and Bayesian-optimized lithology identification in tunnel site.
基金support by the National Key R&D Program of China(Grant No.2023YFA1008901)the National Natural Science Foundation of China(Grant Nos.11988102,12172009)is gratefully acknowledged.
文摘In this manuscript,we propose an analytical equivalent linear viscoelastic constitutive model for fiber-reinforced composites,bypassing general computational homogenization.The method is based on the reduced-order homogenization(ROH)approach.The ROH method typically involves solving multiple finite element problems under periodic conditions to evaluate elastic strain and eigenstrain influence functions in an‘off-line’stage,which offers substantial cost savings compared to direct computational homogenization methods.Due to the unique structure of the fibrous unit cell,“off-line”stage calculation can be eliminated by influence functions obtained analytically.Introducing the standard solid model to the ROH method enables the creation of a comprehensive analytical homogeneous viscoelastic constitutive model.This method treats fibrous composite materials as homogeneous,anisotropic viscoelastic materials,significantly reducing computational time due to its analytical nature.This approach also enables precise determination of a homogenized anisotropic relaxation modulus and accurate capture of various viscoelastic responses under different loading conditions.Three sets of numerical examples,including unit cell tests,three-point beam bending tests,and torsion tests,are given to demonstrate the predictive performance of the homogenized viscoelastic model.Furthermore,the model is validated against experimental measurements,confirming its accuracy and reliability.
文摘In this paper,we delve into a generalized higher order Camassa-Holm type equation,(or,an ghmCH equation for short).We establish local well-posedness for this equation under the condition that the initial data uo belongs to the Sobolev space H'(R)for some s>2.In addition,we obtain the weak formulation of this equation and prove the existence of both single peakon solution and a multi-peakon dynamic system.
基金funded by the Jiangxi Provincial Social Science Planning Project(21GL12)Jiangxi Provincial Higher Education Humanities and Social Sciences Planning Project(GL22232)Jiangxi Province College Students’Innovation and Entrepreneurship Training Program Project(S20241041027).
文摘Stereoscopic agriculture,as an advanced method of agricultural production,poses new challenges for multi-task trajectory planning of unmanned aerial vehicles(UAVs).To address the need for UAVs to perform multi-task trajectory planning in stereoscopic agriculture,a multi-task trajectory planning model and algorithm(IEP-AO)that synthesizes flight safety and flight efficiency is proposed.Based on the requirements of stereoscopic agricultural geomorphological features and operational characteristics,the multi-task trajectory planning model is ensured by constructing targeted constraints at five aspects,including the path,slope,altitude,corner,energy and obstacle threat,to improve the effectiveness of the trajectory planning model.And combined with the path optimization algorithm,an Aquila optimizer(IEP-AO)based on the interference-enhanced combination model is proposed,which can help UAVs to improve the trajectory search capability in complex operation space and large-scale operation tasks,and jump out of the locally optimal trajectory path region timely,to generate the optimal trajectory planning plan that can adapt to the diversity of the tasks and the flight efficiency.Meanwhile,four simulated flights with different operation scales and different scene constraints were conducted under the constructed real 3Dimension scene,and the experimental results can show that the proposedmulti-task trajectory planning method canmeet themulti-task requirements in stereoscopic agriculture and improve the mission execution efficiency and agricultural production effect of UAV.
文摘This paper deals with extensions of higher-order optimality conditions for scalar optimization to multiobjective optimization.A type of directional derivatives for a multiobjective function is proposed,and with this notion characterizations of strict local minima of order k for a multiobjective optimization problem with a nonempty set constraint are established,generalizing the corresponding scalar case obtained by Studniarski[3].Also necessary not sufficient and sufficient not necessary optimality conditions for this minima are derived based on our directional derivatives,which are generalizations of some existing scalar results and equivalent to some existing multiobjective ones.Many examples are given to illustrate them there.
文摘Teacher–student relationships play a vital role in improving college students’academic performance and the quality of higher education.However,empirical studies with substantial data-driven insights remain limited.To address this gap,this study collected 3278 questionnaires from seven universities across four provinces in China to analyze the key factors affecting college students’academic performance.A machine learning framework,CQFOA-KELM,was developed by enhancing the Fruit Fly Optimization Algorithm(FOA)with Covariance Matrix Adaptation Evolution Strategy(CMAES)and Quadratic Approximation(QA).CQFOA significantly improved population diversity and was validated on the IEEE CEC2017 benchmark functions.The CQFOA-KELM model achieved an accuracy of 98.15%and a sensitivity of 98.53%in predicting college students’academic performance.Additionally,it effectively identified the key factors influencing academic performance through the feature selection process.
基金Supported by NSFC (No.12361027)NSF of Inner Mongolia (No.2018MS01021)+1 种基金NSF of Shandong Province (No.ZR2020QA009)Science and Technology Innovation Program for Higher Education Institutions of Shanxi Province (No.2024L533)。
文摘In this paper,we give a complete characterization of all self-adjoint domains of odd order differential operators on two intervals.These two intervals with all four endpoints are singular(one endpoint of each interval is singular or all four endpoints are regulars are the special cases).And these extensions yield"new"self-adjoint operators,which involve interactions between the two intervals.
基金supported by the National Natural Science Foundation(22279036)the Innovation and Talent Recruitment Base of New Energy Chemistry and Device(B21003).
文摘Alloying transition metals with Pt is an effective strategy for optimizing Pt-based catalysts toward the oxygen reduction reaction(ORR).Atomic ordered intermetallic compounds(IMC)provide unique electronic and geometrical effects as well as stronger intermetallic interactions due to the ordered arrangement of metal atoms,thus exhibiting superior electrocata-lytic activity and durability.However,quantitatively analyzing the ordering degree of IMC and exploring the correlation between the ordering degree and ORR activity remains extremely challenging.Herein,a series of ternary Pt_(2)NiCo interme-tallic catalysts(o-Pt_(2)NiCo)with different ordering degree were synthesized by annealing temperature modulation.Among them,the o-Pt_(2)NiCo which annealed at 800℃for two hours exhibits the highest ordering degree and the optimal ORR ac-tivity,which the mass activity of o-Pt_(2)NiCo is 1.8 times and 2.8 times higher than that of disordered Pt_(2)NiCo alloy and Pt/C.Furthermore,the o-Pt_(2)NiCo still maintains 70.8%mass activity after 30,000 potential cycles.Additionally,the ORR activity test results for Pt_(2)NiCo IMC with different ordering degree also provide a positive correlation between the ordering degree and ORR activity.This work provides a prospective design direction for ternary Pt-based electrocatalysts.
基金Prince Sattam bin Abdulaziz University project number(PSAU/2023/R/1445)。
文摘Prediction of stability in SG(Smart Grid)is essential in maintaining consistency and reliability of power supply in grid infrastructure.Analyzing the fluctuations in power generation and consumption patterns of smart cities assists in effectively managing continuous power supply in the grid.It also possesses a better impact on averting overloading and permitting effective energy storage.Even though many traditional techniques have predicted the consumption rate for preserving stability,enhancement is required in prediction measures with minimized loss.To overcome the complications in existing studies,this paper intends to predict stability from the smart grid stability prediction dataset using machine learning algorithms.To accomplish this,pre-processing is performed initially to handle missing values since it develops biased models when missing values are mishandled and performs feature scaling to normalize independent data features.Then,the pre-processed data are taken for training and testing.Following that,the regression process is performed using Modified PSO(Particle Swarm Optimization)optimized XGBoost Technique with dynamic inertia weight update,which analyses variables like gamma(G),reaction time(tau1–tau4),and power balance(p1–p4)for providing effective future stability in SG.Since PSO attains optimal solution by adjusting position through dynamic inertial weights,it is integrated with XGBoost due to its scalability and faster computational speed characteristics.The hyperparameters of XGBoost are fine-tuned in the training process for achieving promising outcomes on prediction.Regression results are measured through evaluation metrics such as MSE(Mean Square Error)of 0.011312781,MAE(Mean Absolute Error)of 0.008596322,and RMSE(Root Mean Square Error)of 0.010636156 and MAPE(Mean Absolute Percentage Error)value of 0.0052 which determine the efficacy of the system.
