The problem of passive detection discussed in this paper involves searching and locating an aerial emitter by dualaircraft using passive radars. In order to improve the detection probability and accuracy, a fuzzy Q le...The problem of passive detection discussed in this paper involves searching and locating an aerial emitter by dualaircraft using passive radars. In order to improve the detection probability and accuracy, a fuzzy Q learning algorithrn for dual-aircraft flight path planning is proposed. The passive detection task model of the dual-aircraft is set up based on the partition of the target active radar＇s radiation area. The problem is formulated as a Markov decision process （MDP） by using the fuzzy theory to make a generalization of the state space and defining the transition functions, action space and reward function properly. Details of the path planning algorithm are presented. Simulation results indicate that the algorithm can provide adaptive strategies for dual-aircraft to control their flight paths to detect a non-maneuvering or maneu- vering target.展开更多
To get simpler operation in modified fuzzy adaptive learning control network （FALCON） in some engineering application, sigmoid nonlinear function is employed as a substitute of traditional Gaussian membership functi...To get simpler operation in modified fuzzy adaptive learning control network （FALCON） in some engineering application, sigmoid nonlinear function is employed as a substitute of traditional Gaussian membership function. For making the modified FALCON learning more efficient and stable, a simulated annealing （SA） learning coefficient is introduced into learning algorithm. At first, the basic concepts and main advantages of FALCON were briefly reviewed. Subsequently, the topological structure and nodes operation were illustrated; the gradient-descent learning algorithm with SA learning coefficient was derived; and the distinctions between the archetype and the modification were analyzed. Eventually, the significance and worthiness of the modified FALCON were validated by its application to probability prediction of anode effect in aluminium electrolysis cells.展开更多
It is a fairly challenging issue to make image repositories easy to be searched and browsed. This depends on a technique--image clustering. Kernel-based clustering algorithm has been one of the most promising clusteri...It is a fairly challenging issue to make image repositories easy to be searched and browsed. This depends on a technique--image clustering. Kernel-based clustering algorithm has been one of the most promising clustering methods in the last few years, beeanse it can handle data with high dimensional complex structure. In this paper, a kernel fuzzy learning （KFL） algorithm is proposed, which takes advantages of the distance kernel trick and the gradient-based fuzzy clustering method to execute the image clustering automatically. Experimental results show that KFL is a more efficient method for image clustering in comparison with recent renorted alternative methods.展开更多
This paper presents a new sensorless vector controlled induction motor drive robust against rotor resistance variation. Indeed, the speed and rotor resistance are estimated using extended Kalman filter （EKF）. Then, ...This paper presents a new sensorless vector controlled induction motor drive robust against rotor resistance variation. Indeed, the speed and rotor resistance are estimated using extended Kalman filter （EKF）. Then, we introduce a new fuzzy logic speed controller based on learning by minimizing cost function. This strategy is based on a topology control self-organized and an algorithm for modifying the knowledge base of fuzzy corrector. The learning mechanism addresses the con- sequences of corrector rules, which are modified according to the comparison between the current speed of machine and an output signal or a desired trajectory. Thus, fuzzy associative memory is constructed to meet the criteria imposed in problems either control or pursuit. The consequent algorithm updating consists of a regulator mechanism allowing a fast and robust learning without unnecessarily compromising the control signal and steady- state performance. The performance of this new strategy is satisfactory, even in the presence of noise or when there are variations in the parameters of induction motor drive.展开更多
The parameters of power system slowly change with time due to environmental effects or may change rapidly due to faults. It is preferable that the control technique in this system possesses robustness for various faul...The parameters of power system slowly change with time due to environmental effects or may change rapidly due to faults. It is preferable that the control technique in this system possesses robustness for various fault conditions and disturbances. The used flexible alternating current transmission system （FACTS） in this paper is an advanced super-conducting magnetic energy storage （ASMES）. Many control techniques that use ASMES to improve power system stability have been proposed. While fuzzy controller has proven its value in some applications, the researches applying fuzzy controller with ASMES have been actively reported. However, it is sometimes very difficult to specify the rule base for some plants, when the parameters change. To solve this problem, a fuzzy model reference learning controller （FMRLC） is proposed in this paper, which investigates multi-input multi-output FMRLC for time-variant nonlinear system. This control method provides the motivation for adaptive fuzzy control, where the focus is on the automatic online synthesis and tuning of fuzzy controller parameters （i.e., using online data to continually learn the fuzzy controller that will ensure that the performance objectives are met）. Simulation results show that the proposed robust controller is able to work with nonlinear and nonstationary power system （i.e., single machine-infinite bus （SMIB） system）, under various fault conditions and disturbances.展开更多
Railway point machine(RPM)condition monitoring has attracted engineers’attention for safe train operation and accident prevention.To realize the fast and accurate fault diagnosis of RPMs,this paper proposes a method ...Railway point machine(RPM)condition monitoring has attracted engineers’attention for safe train operation and accident prevention.To realize the fast and accurate fault diagnosis of RPMs,this paper proposes a method based on entropy measurement and broad learning system(BLS).Firstly,the modified multi-scale symbolic dynamic entropy(MMSDE)module extracts dynamic characteristics from the collected acoustic signals as entropy features.Then,the fuzzy BLS takes the above entropy features as input to complete model training.Fuzzy BLS introduces the Takagi-Sug eno fuzzy system into BLS,which improves the model’s classification performance while considering computational speed.Experimental results indicate that the proposed method significantly reduces the running time while maintaining high accuracy.展开更多
To address the issue of low denoising accuracy of unmanned aerial vehicle(UAV)sensor data in a nonlinear non-Gaussian system,an adaptive central error entropy(CEE)—strong tracking cubature Kalman filter(STCKF)algorit...To address the issue of low denoising accuracy of unmanned aerial vehicle(UAV)sensor data in a nonlinear non-Gaussian system,an adaptive central error entropy(CEE)—strong tracking cubature Kalman filter(STCKF)algorithm based on fuzzy broad learning system(fuzzy-BLS)is proposed in this paper.Although entropy algorithms are known to be effective for denoising in non-Gaussian systems,their application in nonlinear systems is still limited.To address this issue,this study combines the central error entropy criterion with the STCKF algorithm.This approach is boosted by the denoising capabilities of the STCKF algorithm for nonlinear systems,thereby compensating for the shortcomings of the CEE criterion for nonlinear systems and leveraging the advantages of CEE in non-Gaussian systems.Thus,the new algorithm has enhanced robustness and accuracy for nonlinear non-Gaussian systems.To further optimize this algorithm,a parameter update method based on fuzzyBLS is adopted to address the problem of excessive reliance on experience and lack of dependency in the selection of parameters,such as weight and kernel width,in the fusion of the CEE criterion.This method can dynamically adjust the optimal parameter template obtained from offline training online to minimize the root mean square error of the denoising results and provide adaptive denoising capability.Simulation and actual data denoising experiments confirmed that the proposed data denoising method accurately addresses the denoising problem of UAV sensor data in nonlinear non-Gaussian systems.展开更多
Accurate traffic state estimations(TSEs)within road networks are crucial for enhancing intelligent transportation systems and developing effective traffic management strategies.Traditional TSE methods often assume hom...Accurate traffic state estimations(TSEs)within road networks are crucial for enhancing intelligent transportation systems and developing effective traffic management strategies.Traditional TSE methods often assume homogeneous traffic,where all vehicles are considered identical,which does not accurately reflect the complexities of real traffic conditions that often exhibit heterogeneous characteristics.In this study,we address the limitations of conventional models by introducing a novel TSE model designed for precise estimations of heterogeneous traffic flows.We develop a comprehensive traffic feature index system tailored for heterogeneous traffic that includes four elements:basic traffic parameters,heterogeneous vehicle speeds,heterogeneous vehicle flows,and mixed flow rates.This system aids in capturing the unique traffic characteristics of different vehicle types.Our proposed high-dimensional fuzzy TSE model,termed HiF-TSE,integrates three main processes:feature selection,which eliminates redundant traffic features using Spearman correlation coefficients;dimension reduction,which utilizes the T-distributed stochastic neighbor embedding machine learning algorithm to reduce high-dimensional traffic feature data;and FCM clustering,which applies the fuzzy C-means algorithm to classify the simplified data into distinct clusters.The HiF-TSE model significantly reduces computational demands and enhances efficiency in TSE processing.We validate our model through a real-world case study,demonstrating its ability to adapt to variations in vehicle type compositions within heterogeneous traffic and accurately represent the actual traffic state.展开更多
基金supported by the National Natural Science Foundation of China(60874040)
文摘The problem of passive detection discussed in this paper involves searching and locating an aerial emitter by dualaircraft using passive radars. In order to improve the detection probability and accuracy, a fuzzy Q learning algorithrn for dual-aircraft flight path planning is proposed. The passive detection task model of the dual-aircraft is set up based on the partition of the target active radar＇s radiation area. The problem is formulated as a Markov decision process （MDP） by using the fuzzy theory to make a generalization of the state space and defining the transition functions, action space and reward function properly. Details of the path planning algorithm are presented. Simulation results indicate that the algorithm can provide adaptive strategies for dual-aircraft to control their flight paths to detect a non-maneuvering or maneu- vering target.
文摘To get simpler operation in modified fuzzy adaptive learning control network （FALCON） in some engineering application, sigmoid nonlinear function is employed as a substitute of traditional Gaussian membership function. For making the modified FALCON learning more efficient and stable, a simulated annealing （SA） learning coefficient is introduced into learning algorithm. At first, the basic concepts and main advantages of FALCON were briefly reviewed. Subsequently, the topological structure and nodes operation were illustrated; the gradient-descent learning algorithm with SA learning coefficient was derived; and the distinctions between the archetype and the modification were analyzed. Eventually, the significance and worthiness of the modified FALCON were validated by its application to probability prediction of anode effect in aluminium electrolysis cells.
基金Supported by the National Natural Science Foundation of China （No. 61101159, 60872123）, the China Postdoctoral Science Foundation （No. 20100480049） and the Fundamental Research Funds for the Central Universities （No. 201 IZM0033）
文摘It is a fairly challenging issue to make image repositories easy to be searched and browsed. This depends on a technique--image clustering. Kernel-based clustering algorithm has been one of the most promising clustering methods in the last few years, beeanse it can handle data with high dimensional complex structure. In this paper, a kernel fuzzy learning （KFL） algorithm is proposed, which takes advantages of the distance kernel trick and the gradient-based fuzzy clustering method to execute the image clustering automatically. Experimental results show that KFL is a more efficient method for image clustering in comparison with recent renorted alternative methods.
文摘This paper presents a new sensorless vector controlled induction motor drive robust against rotor resistance variation. Indeed, the speed and rotor resistance are estimated using extended Kalman filter （EKF）. Then, we introduce a new fuzzy logic speed controller based on learning by minimizing cost function. This strategy is based on a topology control self-organized and an algorithm for modifying the knowledge base of fuzzy corrector. The learning mechanism addresses the con- sequences of corrector rules, which are modified according to the comparison between the current speed of machine and an output signal or a desired trajectory. Thus, fuzzy associative memory is constructed to meet the criteria imposed in problems either control or pursuit. The consequent algorithm updating consists of a regulator mechanism allowing a fast and robust learning without unnecessarily compromising the control signal and steady- state performance. The performance of this new strategy is satisfactory, even in the presence of noise or when there are variations in the parameters of induction motor drive.
文摘The parameters of power system slowly change with time due to environmental effects or may change rapidly due to faults. It is preferable that the control technique in this system possesses robustness for various fault conditions and disturbances. The used flexible alternating current transmission system （FACTS） in this paper is an advanced super-conducting magnetic energy storage （ASMES）. Many control techniques that use ASMES to improve power system stability have been proposed. While fuzzy controller has proven its value in some applications, the researches applying fuzzy controller with ASMES have been actively reported. However, it is sometimes very difficult to specify the rule base for some plants, when the parameters change. To solve this problem, a fuzzy model reference learning controller （FMRLC） is proposed in this paper, which investigates multi-input multi-output FMRLC for time-variant nonlinear system. This control method provides the motivation for adaptive fuzzy control, where the focus is on the automatic online synthesis and tuning of fuzzy controller parameters （i.e., using online data to continually learn the fuzzy controller that will ensure that the performance objectives are met）. Simulation results show that the proposed robust controller is able to work with nonlinear and nonstationary power system （i.e., single machine-infinite bus （SMIB） system）, under various fault conditions and disturbances.
基金supported in part by the Fundamental Research Funds for the Central Universities(Grant No.2021RC271)NSFC(Grants No.62120106011,52172323 and U22A2046).
文摘Railway point machine(RPM)condition monitoring has attracted engineers’attention for safe train operation and accident prevention.To realize the fast and accurate fault diagnosis of RPMs,this paper proposes a method based on entropy measurement and broad learning system(BLS).Firstly,the modified multi-scale symbolic dynamic entropy(MMSDE)module extracts dynamic characteristics from the collected acoustic signals as entropy features.Then,the fuzzy BLS takes the above entropy features as input to complete model training.Fuzzy BLS introduces the Takagi-Sug eno fuzzy system into BLS,which improves the model’s classification performance while considering computational speed.Experimental results indicate that the proposed method significantly reduces the running time while maintaining high accuracy.
基金partially supported by the National Natural Science Foundation of China(Grant Nos.62033010,U23B2061)the Qing Lan Project of Jiangsu Province of China(Grant No.R2023Q07)the Joint Fund of Zhejiang Provincial Natural Science Foundation of China(Grant No.ZJMD25D050002)。
文摘To address the issue of low denoising accuracy of unmanned aerial vehicle(UAV)sensor data in a nonlinear non-Gaussian system,an adaptive central error entropy(CEE)—strong tracking cubature Kalman filter(STCKF)algorithm based on fuzzy broad learning system(fuzzy-BLS)is proposed in this paper.Although entropy algorithms are known to be effective for denoising in non-Gaussian systems,their application in nonlinear systems is still limited.To address this issue,this study combines the central error entropy criterion with the STCKF algorithm.This approach is boosted by the denoising capabilities of the STCKF algorithm for nonlinear systems,thereby compensating for the shortcomings of the CEE criterion for nonlinear systems and leveraging the advantages of CEE in non-Gaussian systems.Thus,the new algorithm has enhanced robustness and accuracy for nonlinear non-Gaussian systems.To further optimize this algorithm,a parameter update method based on fuzzyBLS is adopted to address the problem of excessive reliance on experience and lack of dependency in the selection of parameters,such as weight and kernel width,in the fusion of the CEE criterion.This method can dynamically adjust the optimal parameter template obtained from offline training online to minimize the root mean square error of the denoising results and provide adaptive denoising capability.Simulation and actual data denoising experiments confirmed that the proposed data denoising method accurately addresses the denoising problem of UAV sensor data in nonlinear non-Gaussian systems.
基金supported by the National Key R&D Program of China(Grant No.2023YFB4302702)the Fundamental Research Funds for the Central Universities(Grant No.2023JKF02ZK08).
文摘Accurate traffic state estimations(TSEs)within road networks are crucial for enhancing intelligent transportation systems and developing effective traffic management strategies.Traditional TSE methods often assume homogeneous traffic,where all vehicles are considered identical,which does not accurately reflect the complexities of real traffic conditions that often exhibit heterogeneous characteristics.In this study,we address the limitations of conventional models by introducing a novel TSE model designed for precise estimations of heterogeneous traffic flows.We develop a comprehensive traffic feature index system tailored for heterogeneous traffic that includes four elements:basic traffic parameters,heterogeneous vehicle speeds,heterogeneous vehicle flows,and mixed flow rates.This system aids in capturing the unique traffic characteristics of different vehicle types.Our proposed high-dimensional fuzzy TSE model,termed HiF-TSE,integrates three main processes:feature selection,which eliminates redundant traffic features using Spearman correlation coefficients;dimension reduction,which utilizes the T-distributed stochastic neighbor embedding machine learning algorithm to reduce high-dimensional traffic feature data;and FCM clustering,which applies the fuzzy C-means algorithm to classify the simplified data into distinct clusters.The HiF-TSE model significantly reduces computational demands and enhances efficiency in TSE processing.We validate our model through a real-world case study,demonstrating its ability to adapt to variations in vehicle type compositions within heterogeneous traffic and accurately represent the actual traffic state.
