In this paper,a stable and adaptive sliding mode control(SMC)method for induction motors is introduced.Determining the parameters of this system has been one of the existing challenges.To solve this challenge,a new se...In this paper,a stable and adaptive sliding mode control(SMC)method for induction motors is introduced.Determining the parameters of this system has been one of the existing challenges.To solve this challenge,a new self-tuning type-2 fuzzy neural network calculates and updates the control system parameters with a fast mechanism.According to the dynamic changes of the system,in addition to the parameters of the SMC,the parameters of the type-2 fuzzy neural network are also updated online.The conditions for guaranteeing the convergence and stability of the control system are provided.In the simulation part,in order to test the proposed method,several uncertain models and load torque have been applied.Also,the results have been compared to the SMC based on the type-1 fuzzy system,the traditional SMC,and the PI controller.The average RMSE in different scenarios,for type-2 fuzzy SMC,is 0.0311,for type-1 fuzzy SMC is 0.0497,for traditional SMC is 0.0778,and finally for PI controller is 0.0997.展开更多
In many problems,to analyze the process/metabolism behavior,a mod-el of the system is identified.The main gap is the weakness of current methods vs.noisy environments.The primary objective of this study is to present a...In many problems,to analyze the process/metabolism behavior,a mod-el of the system is identified.The main gap is the weakness of current methods vs.noisy environments.The primary objective of this study is to present a more robust method against uncertainties.This paper proposes a new deep learning scheme for modeling and identification applications.The suggested approach is based on non-singleton type-3 fuzzy logic systems(NT3-FLSs)that can support measurement errors and high-level uncertainties.Besides the rule optimization,the antecedent parameters and the level of secondary memberships are also adjusted by the suggested square root cubature Kalmanfilter(SCKF).In the learn-ing algorithm,the presented NT3-FLSs are deeply learned,and their nonlinear structure is preserved.The designed scheme is applied for modeling carbon cap-ture and sequestration problem using real-world data sets.Through various ana-lyses and comparisons,the better efficiency of the proposed fuzzy modeling scheme is verified.The main advantages of the suggested approach include better resistance against uncertainties,deep learning,and good convergence.展开更多
基金This research is financially supported by the Ministry of Science and Technology of China(Grant No.2019YFE0112400)the Department of Science and Technology of Shandong Province(Grant No.2021CXGC011204).
文摘In this paper,a stable and adaptive sliding mode control(SMC)method for induction motors is introduced.Determining the parameters of this system has been one of the existing challenges.To solve this challenge,a new self-tuning type-2 fuzzy neural network calculates and updates the control system parameters with a fast mechanism.According to the dynamic changes of the system,in addition to the parameters of the SMC,the parameters of the type-2 fuzzy neural network are also updated online.The conditions for guaranteeing the convergence and stability of the control system are provided.In the simulation part,in order to test the proposed method,several uncertain models and load torque have been applied.Also,the results have been compared to the SMC based on the type-1 fuzzy system,the traditional SMC,and the PI controller.The average RMSE in different scenarios,for type-2 fuzzy SMC,is 0.0311,for type-1 fuzzy SMC is 0.0497,for traditional SMC is 0.0778,and finally for PI controller is 0.0997.
基金supported by the project of the National Social Science Fundation(21BJL052,20BJY020,20BJL127,19BJY090)the 2018 Fujian Social Science Planning Project(FJ2018B067)The Planning Fund Project of Humanities and Social Sciences Research of the Ministry of Education in 2019(19YJA790102),The grant has been received by Aoqi Xu.
文摘In many problems,to analyze the process/metabolism behavior,a mod-el of the system is identified.The main gap is the weakness of current methods vs.noisy environments.The primary objective of this study is to present a more robust method against uncertainties.This paper proposes a new deep learning scheme for modeling and identification applications.The suggested approach is based on non-singleton type-3 fuzzy logic systems(NT3-FLSs)that can support measurement errors and high-level uncertainties.Besides the rule optimization,the antecedent parameters and the level of secondary memberships are also adjusted by the suggested square root cubature Kalmanfilter(SCKF).In the learn-ing algorithm,the presented NT3-FLSs are deeply learned,and their nonlinear structure is preserved.The designed scheme is applied for modeling carbon cap-ture and sequestration problem using real-world data sets.Through various ana-lyses and comparisons,the better efficiency of the proposed fuzzy modeling scheme is verified.The main advantages of the suggested approach include better resistance against uncertainties,deep learning,and good convergence.