This Paper presents a methodology for solving the sensor failure detection, isolation and accommodation of aeroengine control systems using on line learning neural networks(NN), which has one main NN and a set of dec...This Paper presents a methodology for solving the sensor failure detection, isolation and accommodation of aeroengine control systems using on line learning neural networks(NN), which has one main NN and a set of decentralized NNs. Changes in the system dynamics are monitored by the on line learning NN. When a failure occurs in some sensor, the sensor failure detection can be accomplished with high precision, and the sensor failure accommodation can be achieved by replacing the value from the failed sensor with its estimate from the decentralized NN. By integrating the optimal estimation and failure logic, this method can detect soft failures. Simulation of one kind of turboshaft engine control system with this multiple neural network architecture shows that the ANN developed can detect and isolate hard and soft sensor failures timely and provide accurate accommodation.展开更多
A study is given on the application of BP neural network (BPNN) in sensorfailure detection in control systems, and on the networ architecture desgn, the redun-dancy,the quickness and the insensitivity to sensor noise ...A study is given on the application of BP neural network (BPNN) in sensorfailure detection in control systems, and on the networ architecture desgn, the redun-dancy,the quickness and the insensitivity to sensor noise of the BPNN based sensor detec-tion methed. Besules, an exploration is made into tbe factors accounting for the quality ofsignal recovery for failed sensor using BPNN. The results reveal clearly that BPNN can besuccessfully used in sensor failure detection and data recovery.展开更多
The method,which used an electroluminescent device to implement the clipped Hopfield neural network,is presented in detail.The electroluminescence devices are used to represent the neurons and the photodetectors are u...The method,which used an electroluminescent device to implement the clipped Hopfield neural network,is presented in detail.The electroluminescence devices are used to represent the neurons and the photodetectors are used to represent the connection matrix.The characteristics of the electroluminescence device and the photodetector are tested.And the characteristics of this system is discussed briefly.展开更多
The stability and the sequential dynamics of the sixteen-state Hamiltnn neural network model have been discussed with the energy function. The optical implementation scheme about Hamilton number vector-matrix multipli...The stability and the sequential dynamics of the sixteen-state Hamiltnn neural network model have been discussed with the energy function. The optical implementation scheme about Hamilton number vector-matrix multiplication is simply discussed.展开更多
Change detection identifies dynamic changes in surface cover and feature status by comparing remote sensing images at different points in time,which is of wide application value in the fields of disaster early warning...Change detection identifies dynamic changes in surface cover and feature status by comparing remote sensing images at different points in time,which is of wide application value in the fields of disaster early warning,urban management and ecological monitoring.Mainstream datasets are dominated by long-term datasets;to support short-term change detection,we collected a new dataset,HNU-CD,which contains some small and hard-to-identify change regions.A time correlation network(TCNet)is also proposed to address these challenges.First,foreground information is enhanced by interactively modelling foreground relations,while background noise is smoothed.Secondly,the temporal correlation between bit-time images is utilised to refine the feature representation and minimise false alarms due to irrelevant changes.Finally,a U-Net inspired architecture is adapted for dense upsampling to preserve details.TCNet demonstrates excellent performance on both the HNUCD(Hainan University change detection dataset)dataset and three widely used public datasets,indicating that its generalisation capabilities have been enhanced.The ablation experiments provide a good demonstration of the ability to reduce the impact caused by pseudo-variation through temporal correlation modelling.展开更多
The conventional Shear Stress Transport(SST)k–ωturbulence model often exhibits substantial inaccu-racies when applied to the prediction of flow behavior in complex regions within axial flow control valves.To enhance...The conventional Shear Stress Transport(SST)k–ωturbulence model often exhibits substantial inaccu-racies when applied to the prediction of flow behavior in complex regions within axial flow control valves.To enhance its predictive fidelity for internal flow fields,this study introduces a novel calibration framework that integrates an artificial neural network(ANN)surrogate model with a particle swarm optimization(PSO)algorithm.In particular,an optimal Latin hypercube sampling strategy was employed to generate representative sample points across the empirical parameter space.For each sample,numerical simulations using ANSYS Fluent were conducted to evaluate the flow characteristics,with empirical turbulence model parameters as inputs and flow rate as the target output.These data were used to construct the high-fidelity ANN surrogate model.The PSO algorithm was then applied to this surrogate to identify the optimal set of empirical parameters tailored specifically to axial flow control valve configurations.A revealed by the presented results,the calibrated SST k–ωmodel significantly improves prediction accuracy:deviations from large eddy simulation(LES)benchmarks at small valve openings were reduced from 7.6%to under 3%.Furthermore,the refined model maintains the computational efficiency characteristic of Reynolds-averaged Navier-Stokes(RANS)simulations while substantially enhancing the accuracy of both pressure and velocity field predictions.Overall,the proposed methodology effectively reconciles the trade-off between computational cost and predictive accuracy,offering a robust and scalable approach for turbulence model calibration in complex internal flow scenarios.展开更多
Nanofibrous membrane has great advantages in many fields,of which the microstructural analysis and optimization are the key to the industrial application.The U-Net multiclassifier based on network structure together w...Nanofibrous membrane has great advantages in many fields,of which the microstructural analysis and optimization are the key to the industrial application.The U-Net multiclassifier based on network structure together with the Jaccard-Lovasz extension loss function was proposed to classify the pixels of the nanofiber SEM image into three categories.A Conditional Random Field(CRF)network was utilized to post-process the segmentation results.Porosities of the filter membranes and the radii of the nanofibers were calculated based on the segmentation results.Experimental results show that the proposed U-Net multiclassifier can be used to deal with overlapped nanofibers and the corresponding segmentation results can retain important details of the SEM image.The technique is beneficial to the subsequent numerical simulation,which is of great academic and practical significance for the subsequent film performance improvement and application promotion.展开更多
Froth image features of coal flotation have been extracted and studied by neighboring grey level dependence matrix, spatial grey level dependence matrix and grey level histogram. In this paper, a basic algorithm of un...Froth image features of coal flotation have been extracted and studied by neighboring grey level dependence matrix, spatial grey level dependence matrix and grey level histogram. In this paper, a basic algorithm of unsupervised learning pattern classification is presented, and coal flotation froth images are classified by means of self organizing map (SOM). By extracting features from 51 flotation froth images with laboratory column, four types of froth images are classified. The correct rate of SOM cluster is satisfactory. And a good relationship of froth type with average ash content is also observed.展开更多
The paper presents the coupling of artificial intelligence-AI and Object-oriented methodology applied for the construction of the model-based decision support system MBDSS.The MBDSS is designed for support the strate...The paper presents the coupling of artificial intelligence-AI and Object-oriented methodology applied for the construction of the model-based decision support system MBDSS.The MBDSS is designed for support the strategic decision making lead to the achievemellt of optimal path towardsmarket economy from the central planning situation in China. To meet user's various requirements,a series of innovations in software development have been carried out, such as system formalization with OBFRAMEs in an object-oriented paradigm for problem solving automation and techniques of modules intelligent cooperation, hybrid system of reasoning, connectionist framework utilization,etc. Integration technology has been highly emphasized and discussed in this article and an outlook to future software engineering is given in the conclusion section.展开更多
Currently,the number of functions to improve user convenience in smartphone applications is increasing.In addition,more mobile applications are being loaded into mobile operating system memory for faster launches,thus...Currently,the number of functions to improve user convenience in smartphone applications is increasing.In addition,more mobile applications are being loaded into mobile operating system memory for faster launches,thus increasing the memory requirements for smartphones.The memory used by applications in mobile operating systems is managed using software;allocated memory is freed up by either considering the usage state of the application or terminating the least recently used(LRU)application.As LRU-based memory management schemes do not consider the application launch frequency in a low memory situation,currently used mobile operating systems can lead to the termination of a frequently executed application,thereby increasing its relaunch time.This study proposes a memory management system that can efficiently utilize the main memory space by analyzing the application usage information.The proposed system reduces the application launch time by leaving the most frequently used or likely to be run applications in the main memory for as long as possible.The performance evaluation conducted utilizing actual smartphone usage records showed that the proposed memory management system increases the number of times the applications resume from the main memory compared with the conventional memory management system,and that the average application execution time is reduced by approximately 17%.展开更多
The Dirac symbol is used to represent the discrete complex Hopfield neural network model.The signal-to-noise theory and the computer numerical solution are made to analyse the storage capacity of the model.The storage...The Dirac symbol is used to represent the discrete complex Hopfield neural network model.The signal-to-noise theory and the computer numerical solution are made to analyse the storage capacity of the model.The storage capacity ratio of the model equals to that of the Hopfield model.Finally,using the model to recognize the 4-level grey or color patterns is discussed.展开更多
A suitable fiberoptic sensing array embedded in the smart structure to monitor quasi-distributed forces on the structure is presented in this paper.Artificial nearal networks are used in processing of fiberoptic sensi...A suitable fiberoptic sensing array embedded in the smart structure to monitor quasi-distributed forces on the structure is presented in this paper.Artificial nearal networks are used in processing of fiberoptic sensing array signals.Fundamental experiments have been done and the results are also given.展开更多
Bionic optimisation is one of the most popular and efficient applications of bionic engineering. As there are many different approaches and terms being used, we try to come up with a structuring of the strategies and ...Bionic optimisation is one of the most popular and efficient applications of bionic engineering. As there are many different approaches and terms being used, we try to come up with a structuring of the strategies and compare the efficiency of the different methods. The methods mostly proposed in literature may be classified into evolutionary, particle swarm and artificial neural net optimisation. Some related classes have to be mentioned as the non-sexual fern optimisation and the response surfaces, which are close to the neuron nets. To come up with a measure of the efficiency that allows to take into account some of the published results the technical optimisation problems were derived from the ones given in literature. They deal with elastic studies of frame structures, as the computing time for each individual is very short. General proposals, which approach to use may not be given. It seems to be a good idea to learn about the applicability of the different methods at different problem classes and then do the optimisation according to these experiences. Furthermore in many cases there is some evidence that switching from one method to another improves the performance. Finally the identification of the exact position of the optimum by gradient methods is often more efficient than long random walks around local maxima.展开更多
Purpose–The purpose of this paper is to consider the concept of Fuzzy Radial Basis Function Neural Networks with Information Granulation(IG-FRBFNN)and their optimization realized by means of the Multiobjective Partic...Purpose–The purpose of this paper is to consider the concept of Fuzzy Radial Basis Function Neural Networks with Information Granulation(IG-FRBFNN)and their optimization realized by means of the Multiobjective Particle Swarm Optimization(MOPSO).Design/methodology/approach–In fuzzy modeling,complexity,interpretability(or simplicity)as well as accuracy of the obtained model are essential design criteria.Since the performance of the IG-RBFNN model is directly affected by some parameters,such as the fuzzification coefficient used in the FCM,the number of rules and the orders of the polynomials in the consequent parts of the rules,the authors carry out both structural as well as parametric optimization of the network.A multi-objective Particle Swarm Optimization using Crowding Distance(MOPSO-CD)as well as O/WLS learning-based optimization are exploited to carry out the structural and parametric optimization of the model,respectively,while the optimization is of multiobjective character as it is aimed at the simultaneous minimization of complexity and maximization of accuracy.Findings–The performance of the proposed model is illustrated with the aid of three examples.The proposed optimization method leads to an accurate and highly interpretable fuzzy model.Originality/value–A MOPSO-CD as well as O/WLS learning-based optimization are exploited,respectively,to carry out the structural and parametric optimization of the model.As a result,the proposed methodology is interesting for designing an accurate and highly interpretable fuzzy model.展开更多
Purpose–The purpose of this paper is to develop a methodology for the existence and global exponential stability of the unique equilibrium point of a class of impulsive Cohen-Grossberg neural networks.Design/methodol...Purpose–The purpose of this paper is to develop a methodology for the existence and global exponential stability of the unique equilibrium point of a class of impulsive Cohen-Grossberg neural networks.Design/methodology/approach–The authors perform M-matrix theory and homeomorphism mapping principle to investigate a class of impulsive Cohen-Grossberg networks with time-varying delays and distributed delays.The approach builds on new sufficient criterion without strict conditions imposed on self-regulation functions.Findings–The authors’approach results in new sufficient criteria easy to verify but without the usual assumption that the activation functions are bounded and the time-varying delays are differentiable.An example shows the effectiveness and superiority of the obtained results over some previously known results.Originality/value–The novelty of the proposed approach lies in removing the usual assumption that the activation functions are bounded and the time-varying delays are differentiable,and the use of M-matrix theory and homeomorphism mapping principle for the existence and global exponential stability of the unique equilibrium point of a class of impulsive Cohen-Grossberg neural networks.展开更多
Earthquakes,as one of the most disruptive natural hazards,have been a major research target for generations of scientists.Numerical simulation of earthquakes,as one of the few methods to verify and improve scientists...Earthquakes,as one of the most disruptive natural hazards,have been a major research target for generations of scientists.Numerical simulation of earthquakes,as one of the few methods to verify and improve scientists’understanding about the earthquake process,and a key tool in various earthquake engineering applications,has long been both an important and challenging application on supercomputers.In this paper,we discuss the major challenges for developing an accurate earthquake simulation tool on supercomputers.Based on the discussion,we then demonstrate our efforts on performing extreme-scale earthquake simulations on Sunway TaihuLight,a 125-Pflops machine with over 10 million heterogeneous cores.With systematic approaches to resolve the memory bandwidth constraint,we manage to achieve 8%to 16%efficiency for utilizing the entire machine to simulate Tangshan and Wenchuan Earthquakes with an unprecedented spatial resolution.展开更多
Driven by green energy advancements and system integration,the surge in retired lithium-ion batteries from electric vehicles has intensified battery recycling challenges.Traditional crushing methods suffer from low ma...Driven by green energy advancements and system integration,the surge in retired lithium-ion batteries from electric vehicles has intensified battery recycling challenges.Traditional crushing methods suffer from low material purity,limited economic value,and environmental pollution,necessitating advanced,eco-friendly recycling technologies.Fine disassembly,an emerging low-carbon approach,enhances resource recovery but faces stability and safety challenges due to the diversity of power batteries.This study innovatively applies deep learning to fine disassembly,employing the YOLOv8s model for precise cell localisation and counting,an LSTM-thermal infrared mechanism for fire risk prediction during cutting,and image segmentation for optimised electrode winding control.These methods address battery complexity,offering intelligent,safe solutions for disassembly,improving recycling efficiency,and advancing green energy systems and environmental sustainability.展开更多
Purpose–The purpose of this paper is to provide a shorter time cost,high-accuracy fault diagnosis method for water pumps.Water pumps are widely used in industrial equipment and their fault diagnosis is gaining increa...Purpose–The purpose of this paper is to provide a shorter time cost,high-accuracy fault diagnosis method for water pumps.Water pumps are widely used in industrial equipment and their fault diagnosis is gaining increasing attention.Considering the time-consuming empirical mode decomposition(EMD)method and the more efficient classification provided by the convolutional neural network(CNN)method,a novel classification method based on incomplete empirical mode decomposition(IEMD)and dual-input dual-channel convolutional neural network(DDCNN)composite data is proposed and applied to the fault diagnosis of water pumps.Design/methodology/approach–This paper proposes a data preprocessing method using IEMD combined with mel-frequency cepstrum coefficient(MFCC)and a neural network model of DDCNN.First,the sound signal is decomposed by IEMD to get numerous intrinsic mode functions(IMFs)and a residual(RES).Several IMFs and one RES are then extracted by MFCC features.Ultimately,the obtained features are split into two channels(IMFs one channel;RES one channel)and input into DDCNN.Findings–The Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection(MIMII dataset)is used to verify the practicability of the method.Experimental results show that decomposition into an IMF is optimal when taking into account the real-time and accuracy of the diagnosis.Compared with EMD,51.52% of data preprocessing time,67.25% of network training time and 63.7%of test time are saved and also improve accuracy.Research limitations/implications–This method can achieve higher accuracy in fault diagnosis with a shorter time cost.Therefore,the fault diagnosis of equipment based on the sound signal in the factory has certain feasibility and research importance.Originality/value–This method provides a feasible method for mechanical fault diagnosis based on sound signals in industrial applications.展开更多
Purpose–The purpose of this paper is to design a robust control scheme to achieve robust tracking of velocity and altitude commands for a general hypersonic vehicle(HSV)in the presence of parameter variations and ext...Purpose–The purpose of this paper is to design a robust control scheme to achieve robust tracking of velocity and altitude commands for a general hypersonic vehicle(HSV)in the presence of parameter variations and external disturbances.Design/methodology/approach–The robust control scheme is composed of nonsingular terminal sliding mode control(NTSMC),super twisting control algorithm(STC)and recurrent neural network(RNN).First,by combing a novel NTSMC and STC algorithm,a second order NTSMC approach for HSV is proposed to provide fast,continuous and high precision tracking control.Second to relax the requirements for the bounds of the lumped uncertainties in control design,a RNN disturbance observer is presented to increase the robustness of the control system.The weights of RNN are updated by adaptive laws based on Lyapunov theorem,thus the closed-loop stability can be guaranteed.Findings–Simulation results demonstrate that the proposed method is effective,leading to promising performance.Originality/value–The main contributions of this work are:first,both parameter variations and external disturbances are considered in control design for the longitudinal dynamic model of HSV;and second,the proposed controller can remove chattering and achieve more favorable tracking performances than conventional sliding mode control.展开更多
文摘This Paper presents a methodology for solving the sensor failure detection, isolation and accommodation of aeroengine control systems using on line learning neural networks(NN), which has one main NN and a set of decentralized NNs. Changes in the system dynamics are monitored by the on line learning NN. When a failure occurs in some sensor, the sensor failure detection can be accomplished with high precision, and the sensor failure accommodation can be achieved by replacing the value from the failed sensor with its estimate from the decentralized NN. By integrating the optimal estimation and failure logic, this method can detect soft failures. Simulation of one kind of turboshaft engine control system with this multiple neural network architecture shows that the ANN developed can detect and isolate hard and soft sensor failures timely and provide accurate accommodation.
文摘A study is given on the application of BP neural network (BPNN) in sensorfailure detection in control systems, and on the networ architecture desgn, the redun-dancy,the quickness and the insensitivity to sensor noise of the BPNN based sensor detec-tion methed. Besules, an exploration is made into tbe factors accounting for the quality ofsignal recovery for failed sensor using BPNN. The results reveal clearly that BPNN can besuccessfully used in sensor failure detection and data recovery.
文摘The method,which used an electroluminescent device to implement the clipped Hopfield neural network,is presented in detail.The electroluminescence devices are used to represent the neurons and the photodetectors are used to represent the connection matrix.The characteristics of the electroluminescence device and the photodetector are tested.And the characteristics of this system is discussed briefly.
文摘The stability and the sequential dynamics of the sixteen-state Hamiltnn neural network model have been discussed with the energy function. The optical implementation scheme about Hamilton number vector-matrix multiplication is simply discussed.
基金funded by the Hainan Province Science and Technology Special Fund(Grant ZDYF2025GXJS184)Haikou Science and Technology Plan Project(2022-007).
文摘Change detection identifies dynamic changes in surface cover and feature status by comparing remote sensing images at different points in time,which is of wide application value in the fields of disaster early warning,urban management and ecological monitoring.Mainstream datasets are dominated by long-term datasets;to support short-term change detection,we collected a new dataset,HNU-CD,which contains some small and hard-to-identify change regions.A time correlation network(TCNet)is also proposed to address these challenges.First,foreground information is enhanced by interactively modelling foreground relations,while background noise is smoothed.Secondly,the temporal correlation between bit-time images is utilised to refine the feature representation and minimise false alarms due to irrelevant changes.Finally,a U-Net inspired architecture is adapted for dense upsampling to preserve details.TCNet demonstrates excellent performance on both the HNUCD(Hainan University change detection dataset)dataset and three widely used public datasets,indicating that its generalisation capabilities have been enhanced.The ablation experiments provide a good demonstration of the ability to reduce the impact caused by pseudo-variation through temporal correlation modelling.
基金funded by Gansu Provincial Department of Education(Industrial Support Plan Project:2025CYZC-048).
文摘The conventional Shear Stress Transport(SST)k–ωturbulence model often exhibits substantial inaccu-racies when applied to the prediction of flow behavior in complex regions within axial flow control valves.To enhance its predictive fidelity for internal flow fields,this study introduces a novel calibration framework that integrates an artificial neural network(ANN)surrogate model with a particle swarm optimization(PSO)algorithm.In particular,an optimal Latin hypercube sampling strategy was employed to generate representative sample points across the empirical parameter space.For each sample,numerical simulations using ANSYS Fluent were conducted to evaluate the flow characteristics,with empirical turbulence model parameters as inputs and flow rate as the target output.These data were used to construct the high-fidelity ANN surrogate model.The PSO algorithm was then applied to this surrogate to identify the optimal set of empirical parameters tailored specifically to axial flow control valve configurations.A revealed by the presented results,the calibrated SST k–ωmodel significantly improves prediction accuracy:deviations from large eddy simulation(LES)benchmarks at small valve openings were reduced from 7.6%to under 3%.Furthermore,the refined model maintains the computational efficiency characteristic of Reynolds-averaged Navier-Stokes(RANS)simulations while substantially enhancing the accuracy of both pressure and velocity field predictions.Overall,the proposed methodology effectively reconciles the trade-off between computational cost and predictive accuracy,offering a robust and scalable approach for turbulence model calibration in complex internal flow scenarios.
基金supported by the National Natural Science Foundation of China (52275575)the Development and Reform Commission of Shenzhen Municipality (JSGG20220831094600002)Natural Science Foundation of Guangdong Province (2022A1515010923, 2022A1515010949)。
文摘Nanofibrous membrane has great advantages in many fields,of which the microstructural analysis and optimization are the key to the industrial application.The U-Net multiclassifier based on network structure together with the Jaccard-Lovasz extension loss function was proposed to classify the pixels of the nanofiber SEM image into three categories.A Conditional Random Field(CRF)network was utilized to post-process the segmentation results.Porosities of the filter membranes and the radii of the nanofibers were calculated based on the segmentation results.Experimental results show that the proposed U-Net multiclassifier can be used to deal with overlapped nanofibers and the corresponding segmentation results can retain important details of the SEM image.The technique is beneficial to the subsequent numerical simulation,which is of great academic and practical significance for the subsequent film performance improvement and application promotion.
基金National Natural Science Foundation of China( 5 99740 32 )
文摘Froth image features of coal flotation have been extracted and studied by neighboring grey level dependence matrix, spatial grey level dependence matrix and grey level histogram. In this paper, a basic algorithm of unsupervised learning pattern classification is presented, and coal flotation froth images are classified by means of self organizing map (SOM). By extracting features from 51 flotation froth images with laboratory column, four types of froth images are classified. The correct rate of SOM cluster is satisfactory. And a good relationship of froth type with average ash content is also observed.
文摘The paper presents the coupling of artificial intelligence-AI and Object-oriented methodology applied for the construction of the model-based decision support system MBDSS.The MBDSS is designed for support the strategic decision making lead to the achievemellt of optimal path towardsmarket economy from the central planning situation in China. To meet user's various requirements,a series of innovations in software development have been carried out, such as system formalization with OBFRAMEs in an object-oriented paradigm for problem solving automation and techniques of modules intelligent cooperation, hybrid system of reasoning, connectionist framework utilization,etc. Integration technology has been highly emphasized and discussed in this article and an outlook to future software engineering is given in the conclusion section.
基金This work was supported by the National Research Foundation of Korea(NRF)Grant funded by the Korea Government(MSIT)under Grant 2020R1A2C1005265.
文摘Currently,the number of functions to improve user convenience in smartphone applications is increasing.In addition,more mobile applications are being loaded into mobile operating system memory for faster launches,thus increasing the memory requirements for smartphones.The memory used by applications in mobile operating systems is managed using software;allocated memory is freed up by either considering the usage state of the application or terminating the least recently used(LRU)application.As LRU-based memory management schemes do not consider the application launch frequency in a low memory situation,currently used mobile operating systems can lead to the termination of a frequently executed application,thereby increasing its relaunch time.This study proposes a memory management system that can efficiently utilize the main memory space by analyzing the application usage information.The proposed system reduces the application launch time by leaving the most frequently used or likely to be run applications in the main memory for as long as possible.The performance evaluation conducted utilizing actual smartphone usage records showed that the proposed memory management system increases the number of times the applications resume from the main memory compared with the conventional memory management system,and that the average application execution time is reduced by approximately 17%.
文摘The Dirac symbol is used to represent the discrete complex Hopfield neural network model.The signal-to-noise theory and the computer numerical solution are made to analyse the storage capacity of the model.The storage capacity ratio of the model equals to that of the Hopfield model.Finally,using the model to recognize the 4-level grey or color patterns is discussed.
文摘A suitable fiberoptic sensing array embedded in the smart structure to monitor quasi-distributed forces on the structure is presented in this paper.Artificial nearal networks are used in processing of fiberoptic sensing array signals.Fundamental experiments have been done and the results are also given.
文摘Bionic optimisation is one of the most popular and efficient applications of bionic engineering. As there are many different approaches and terms being used, we try to come up with a structuring of the strategies and compare the efficiency of the different methods. The methods mostly proposed in literature may be classified into evolutionary, particle swarm and artificial neural net optimisation. Some related classes have to be mentioned as the non-sexual fern optimisation and the response surfaces, which are close to the neuron nets. To come up with a measure of the efficiency that allows to take into account some of the published results the technical optimisation problems were derived from the ones given in literature. They deal with elastic studies of frame structures, as the computing time for each individual is very short. General proposals, which approach to use may not be given. It seems to be a good idea to learn about the applicability of the different methods at different problem classes and then do the optimisation according to these experiences. Furthermore in many cases there is some evidence that switching from one method to another improves the performance. Finally the identification of the exact position of the optimum by gradient methods is often more efficient than long random walks around local maxima.
基金This work was supported by National Research Foundation of Korea Grant funded by the Korean Government(NRF-2010-D00065)the Grant of the Korean Ministry of Education,Science and Technology(The Regional Core Research Program/Center of Healthcare Technology Development)the GRRC program of Gyeonggi province[GRRC SUWON 2011-B2,Center for U-city Security&Surveillance Technology].
文摘Purpose–The purpose of this paper is to consider the concept of Fuzzy Radial Basis Function Neural Networks with Information Granulation(IG-FRBFNN)and their optimization realized by means of the Multiobjective Particle Swarm Optimization(MOPSO).Design/methodology/approach–In fuzzy modeling,complexity,interpretability(or simplicity)as well as accuracy of the obtained model are essential design criteria.Since the performance of the IG-RBFNN model is directly affected by some parameters,such as the fuzzification coefficient used in the FCM,the number of rules and the orders of the polynomials in the consequent parts of the rules,the authors carry out both structural as well as parametric optimization of the network.A multi-objective Particle Swarm Optimization using Crowding Distance(MOPSO-CD)as well as O/WLS learning-based optimization are exploited to carry out the structural and parametric optimization of the model,respectively,while the optimization is of multiobjective character as it is aimed at the simultaneous minimization of complexity and maximization of accuracy.Findings–The performance of the proposed model is illustrated with the aid of three examples.The proposed optimization method leads to an accurate and highly interpretable fuzzy model.Originality/value–A MOPSO-CD as well as O/WLS learning-based optimization are exploited,respectively,to carry out the structural and parametric optimization of the model.As a result,the proposed methodology is interesting for designing an accurate and highly interpretable fuzzy model.
基金supported by the National Natural Science Foundation of China under Grants 61074073,61034005,61273022,Program for New Century Excellent Talents in University of China(NCET-10-0306)the Fundamental Research Funds for the Central Universities under Grant N110504001.
文摘Purpose–The purpose of this paper is to develop a methodology for the existence and global exponential stability of the unique equilibrium point of a class of impulsive Cohen-Grossberg neural networks.Design/methodology/approach–The authors perform M-matrix theory and homeomorphism mapping principle to investigate a class of impulsive Cohen-Grossberg networks with time-varying delays and distributed delays.The approach builds on new sufficient criterion without strict conditions imposed on self-regulation functions.Findings–The authors’approach results in new sufficient criteria easy to verify but without the usual assumption that the activation functions are bounded and the time-varying delays are differentiable.An example shows the effectiveness and superiority of the obtained results over some previously known results.Originality/value–The novelty of the proposed approach lies in removing the usual assumption that the activation functions are bounded and the time-varying delays are differentiable,and the use of M-matrix theory and homeomorphism mapping principle for the existence and global exponential stability of the unique equilibrium point of a class of impulsive Cohen-Grossberg neural networks.
基金supported in part by the National Key R&D Program of China(Grant No.2017YFA0604500)the National Natural Science Foundation of China(Grant Nos.91530323,5171101179)+1 种基金the National Natural Science Foundation of China(Grant No.51761135015)Center for High Performance Computing and System Simulation,Pilot National Laboratory for Marine Science and Technology(Qingdao).
文摘Earthquakes,as one of the most disruptive natural hazards,have been a major research target for generations of scientists.Numerical simulation of earthquakes,as one of the few methods to verify and improve scientists’understanding about the earthquake process,and a key tool in various earthquake engineering applications,has long been both an important and challenging application on supercomputers.In this paper,we discuss the major challenges for developing an accurate earthquake simulation tool on supercomputers.Based on the discussion,we then demonstrate our efforts on performing extreme-scale earthquake simulations on Sunway TaihuLight,a 125-Pflops machine with over 10 million heterogeneous cores.With systematic approaches to resolve the memory bandwidth constraint,we manage to achieve 8%to 16%efficiency for utilizing the entire machine to simulate Tangshan and Wenchuan Earthquakes with an unprecedented spatial resolution.
基金supported by Natural Science Foundation,Grant/Award Number(62433013).
文摘Driven by green energy advancements and system integration,the surge in retired lithium-ion batteries from electric vehicles has intensified battery recycling challenges.Traditional crushing methods suffer from low material purity,limited economic value,and environmental pollution,necessitating advanced,eco-friendly recycling technologies.Fine disassembly,an emerging low-carbon approach,enhances resource recovery but faces stability and safety challenges due to the diversity of power batteries.This study innovatively applies deep learning to fine disassembly,employing the YOLOv8s model for precise cell localisation and counting,an LSTM-thermal infrared mechanism for fire risk prediction during cutting,and image segmentation for optimised electrode winding control.These methods address battery complexity,offering intelligent,safe solutions for disassembly,improving recycling efficiency,and advancing green energy systems and environmental sustainability.
基金At the same time,the authors also appreciate the support by the fund from the Network and Data Security Key Laboratory of Sichuan Province,UESTC(NO.NDS2021-7)Sichuan Province General Education Scientific Research(NO.2019514).
文摘Purpose–The purpose of this paper is to provide a shorter time cost,high-accuracy fault diagnosis method for water pumps.Water pumps are widely used in industrial equipment and their fault diagnosis is gaining increasing attention.Considering the time-consuming empirical mode decomposition(EMD)method and the more efficient classification provided by the convolutional neural network(CNN)method,a novel classification method based on incomplete empirical mode decomposition(IEMD)and dual-input dual-channel convolutional neural network(DDCNN)composite data is proposed and applied to the fault diagnosis of water pumps.Design/methodology/approach–This paper proposes a data preprocessing method using IEMD combined with mel-frequency cepstrum coefficient(MFCC)and a neural network model of DDCNN.First,the sound signal is decomposed by IEMD to get numerous intrinsic mode functions(IMFs)and a residual(RES).Several IMFs and one RES are then extracted by MFCC features.Ultimately,the obtained features are split into two channels(IMFs one channel;RES one channel)and input into DDCNN.Findings–The Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection(MIMII dataset)is used to verify the practicability of the method.Experimental results show that decomposition into an IMF is optimal when taking into account the real-time and accuracy of the diagnosis.Compared with EMD,51.52% of data preprocessing time,67.25% of network training time and 63.7%of test time are saved and also improve accuracy.Research limitations/implications–This method can achieve higher accuracy in fault diagnosis with a shorter time cost.Therefore,the fault diagnosis of equipment based on the sound signal in the factory has certain feasibility and research importance.Originality/value–This method provides a feasible method for mechanical fault diagnosis based on sound signals in industrial applications.
基金supported by the National Outstanding Youth Science Foundation(61125306)the National Natural Science Foundation of Major Research Plan(91016004).
文摘Purpose–The purpose of this paper is to design a robust control scheme to achieve robust tracking of velocity and altitude commands for a general hypersonic vehicle(HSV)in the presence of parameter variations and external disturbances.Design/methodology/approach–The robust control scheme is composed of nonsingular terminal sliding mode control(NTSMC),super twisting control algorithm(STC)and recurrent neural network(RNN).First,by combing a novel NTSMC and STC algorithm,a second order NTSMC approach for HSV is proposed to provide fast,continuous and high precision tracking control.Second to relax the requirements for the bounds of the lumped uncertainties in control design,a RNN disturbance observer is presented to increase the robustness of the control system.The weights of RNN are updated by adaptive laws based on Lyapunov theorem,thus the closed-loop stability can be guaranteed.Findings–Simulation results demonstrate that the proposed method is effective,leading to promising performance.Originality/value–The main contributions of this work are:first,both parameter variations and external disturbances are considered in control design for the longitudinal dynamic model of HSV;and second,the proposed controller can remove chattering and achieve more favorable tracking performances than conventional sliding mode control.
