http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Modified Recurrent Fuzzy Neural Network Sliding Mode Control for Nonlinear Systems
Yundi Chu,Ming Yang,Jienan Han,Qianwen Xie 제어로봇시스템학회 2021 제어로봇시스템학회 국제학술대회 논문집 Vol.2021 No.10
In this study, a modified fuzzy neural network sliding mode control for a class of nonlinear systems is designed. Firstly, the considered nonlinear system is given and a global sliding mode control is proposed. Then, a modified fuzzy neural network (FNN) is constructed and utilized for estimating the uncertain function. Compared with the conventional FNN, the designed FNN can obtain a better generalization capability with two feedback loops. Moreover, the stability analysis in the Lyapunov framework is implemented to ensure the zero-error-convergence performance. To validate the control performance of the proposed scheme, active power filter is selected as the controlled plant. The simulation results demonstrate that the designed control method can achieve superior control capability.
Continuous Terminal Sliding Mode Control for Active Power Filter
Shixi Hou,Yuqing Fan,Yundi Chu 제어로봇시스템학회 2019 제어로봇시스템학회 국제학술대회 논문집 Vol.2019 No.10
In this paper, a continuous terminal sliding mode control methods (CTSMC) are proposed for three-phase shunt active power filter as current controller. First, the dynamic model of active power filter with parameter perturbation and unknown external disturbance is introduced. Second, a continuous terminal sliding mode control applied to current control loop is designed to guarantee the fast and finite-time convergence. Moreover, compensation control term is designed to ensure the elimination of chattering phenomenon caused by the switching term. Compared to the conventional sliding mode control method, the proposed continuous terminal sliding control method obtains a faster convergence and better tracking performance. Simulation results demonstrate that the proposed control methods offer superior properties in both steady state and transient operation, reducing the THD of source current to less than 5% and improving the power quality in order to meet the recommendations of the IEEE 519 standard.
Indirect Adaptive Fuzzy Control for Active Power Filter Using Global Sliding Mode Control
Shixi Hou,Juntao Fei,Yundi Chu,Chen Chen 제어로봇시스템학회 2019 제어로봇시스템학회 국제학술대회 논문집 Vol.2019 No.10
In this paper, an indirect adaptive fuzzy global sliding mode control methods (AFGSMC) are proposed for single-phase shunt active power filter as current controller. Firstly a global sliding mode control applied to current control loop is designed to guarantee the global robustness. Then a fuzzy system is used to approximate the unknown dynamics in order to eliminate the dependence on the prior knowledge, and another fuzzy system is used to replace the switching control term to reduce the chattering phenomenon. Moreover, compensation control term is designed based on the fuzzy approximation error estimation, which ensures the tracking performance of the closed loop system. Experimental results demonstrate that the proposed control methods offer a good behavior in both steady state and transient operation, reducing the THD of source current to less than 5% and improving the power quality in order to meet the recommendations of the IEEE 519 standard.
Tool Monitoring System Using Vibration and Current Signals
Zhennan Wei,Zhenyu Qiu,Qian Huang,Yundi Chu 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11
The on-line monitoring of tool wear condition plays an important role in reducing production cost and improving production efficiency. Firstly, this paper introduces the wear mechanism of cutting tools, the detection method of tool wear, and the commonly used signal processing technology. Secondly, through the experiments of various cutting parameters, various characteristic information in different grinding processes is obtained, and the correlation analysis is carried out, and the characteristic values related to the grinding process are obtained. Then, the corresponding BP neural network model is established. Finally, according to the characteristics of the CNC machine monitoring system, Cortex_A15 is selected as the core of the monitoring system, and the neural network algorithm is applied to the hardware board which is more economical than the PC to save the production cost.