Artificial neural network has unique advantages for massively parallel processing, distributed storage capacity and self-learning ability. The paper mainly constructs neural network identifier and neural network contr...Artificial neural network has unique advantages for massively parallel processing, distributed storage capacity and self-learning ability. The paper mainly constructs neural network identifier and neural network controller for system identification and control on temperature and hmnidity of heating and drying system of materials. And the paper introduces the structure and principles of neural network, and focuses on analyzing learning algorithm, training algorithm and limitation of the most widely applied multi-layer feed-forward neural network （ BP network） , based on which the paper proposes introducing momentum to improve BP network.展开更多
Based on the structure of Elman and Jordan neural networks, a new dynamic neural network is constructed. The network can remember the past state of the hidden layer and adjust the effect of the past signal to the curr...Based on the structure of Elman and Jordan neural networks, a new dynamic neural network is constructed. The network can remember the past state of the hidden layer and adjust the effect of the past signal to the current value in real-time. And in order to enhance the signal processing capabilities, the feedback of output layer nodes is increased. A hybrid learning algorithm based on genetic algorithm （GA） and error back propagation algorithm （BP） is used to adjust the weight values of the network, which can accelerate the rate of convergence and avoid getting into local optimum. Finally, the improved neural network is utilized to identify underwater vehicle （UV） ＇ s hydrodynamic model, and the simulation results show that the neural network based on hybrid learning algorithm can improve the learning rate of convergence and identification nrecision.展开更多
A dynamic velocity feed-forward compensation （RBF-NN） dynamic model identification was presented for control （DVFCC） approach with RBF neural network the adaptive trajectory tracking of industrial robots. The prop...A dynamic velocity feed-forward compensation （RBF-NN） dynamic model identification was presented for control （DVFCC） approach with RBF neural network the adaptive trajectory tracking of industrial robots. The proposed control approach combined the advantages of traditional feedback closed-loop position control and computed torque control based on inverse dynamic model. The feed-forward compensator used a nominal robot dynamics as accurate dynamic model and on-line identification with RBF-NN as uncertain part to improve dynamic modeling accu- racy. The proposed compensation was applied as velocity feed-forward by an inverse velocity controller that can con- vert torque signal into velocity in the standard industrial controller. Then, the need for a torque control interface was avoided in the real-time dynamic control of industrial robot. The simulations and experiments were carried out on a gas cutting manipulator. The results show that the proposed control approach can reduce steady-state error, suppress overshoot and enhance tracking accuracy and efficiency in joint space and Cartesian space, especially under high- speed condition.展开更多
Gait recognition is the key question of functional electrical stimulation (FES) system control for paraplegic walking. A new risk-tendency-graph (RTG) method was proposed to recognize the stability information in FES-...Gait recognition is the key question of functional electrical stimulation (FES) system control for paraplegic walking. A new risk-tendency-graph (RTG) method was proposed to recognize the stability information in FES-assisted walking gait. The main instrument was a specialized walker dynamometer system based on a multi-channel strain-gauge bridge network fixed on the walker frame. During walking process, this system collected the reaction forces between patient's upper extremities and walker and converted them into RTG morphologic curves of dynamic gait stability in temporal and spatial domains. To demonstrate the potential usefulness of RTG, preliminary clinical trials were done with paraplegic patients. The gait stability levels of two walking cases with 4- and 12-week FES training from one subject were quantified (0.43 and 0.19) from the results of temporal and spatial RTG. Relevant instable phases in gait cycle and dangerous inclinations of patient's body during walking process were also brought forward. In conclusion, the new RTG method is practical for distinguishing more useful gait stability information for FES system control.展开更多
Fuzzy control is an important branch of intelligent control, and this paper describes the application of fuzzy pattern study in intelligent control, begins with a brief overview introduction for development of intelli...Fuzzy control is an important branch of intelligent control, and this paper describes the application of fuzzy pattern study in intelligent control, begins with a brief overview introduction for development of intelligent control, and then describes the main components of the fuzzy model and its characteristics and fuzzy pattern control system.Fuzzy pattern applications in the intersection signal intelligent control showed fuzzy mode control can effectively reduce the single intersection average vehicle delay time, making the intersection more unobstructed to pass.展开更多
文摘Artificial neural network has unique advantages for massively parallel processing, distributed storage capacity and self-learning ability. The paper mainly constructs neural network identifier and neural network controller for system identification and control on temperature and hmnidity of heating and drying system of materials. And the paper introduces the structure and principles of neural network, and focuses on analyzing learning algorithm, training algorithm and limitation of the most widely applied multi-layer feed-forward neural network （ BP network） , based on which the paper proposes introducing momentum to improve BP network.
基金Supported by the Postdoctoral Science Foundation of China（ No. 20100480964 ） , the Basic Research Foundation of Central University （ No. HEUCF100104） and the National Natural Science Foundation of China （No. 50909025/E091002）.
文摘Based on the structure of Elman and Jordan neural networks, a new dynamic neural network is constructed. The network can remember the past state of the hidden layer and adjust the effect of the past signal to the current value in real-time. And in order to enhance the signal processing capabilities, the feedback of output layer nodes is increased. A hybrid learning algorithm based on genetic algorithm （GA） and error back propagation algorithm （BP） is used to adjust the weight values of the network, which can accelerate the rate of convergence and avoid getting into local optimum. Finally, the improved neural network is utilized to identify underwater vehicle （UV） ＇ s hydrodynamic model, and the simulation results show that the neural network based on hybrid learning algorithm can improve the learning rate of convergence and identification nrecision.
文摘A dynamic velocity feed-forward compensation （RBF-NN） dynamic model identification was presented for control （DVFCC） approach with RBF neural network the adaptive trajectory tracking of industrial robots. The proposed control approach combined the advantages of traditional feedback closed-loop position control and computed torque control based on inverse dynamic model. The feed-forward compensator used a nominal robot dynamics as accurate dynamic model and on-line identification with RBF-NN as uncertain part to improve dynamic modeling accu- racy. The proposed compensation was applied as velocity feed-forward by an inverse velocity controller that can con- vert torque signal into velocity in the standard industrial controller. Then, the need for a torque control interface was avoided in the real-time dynamic control of industrial robot. The simulations and experiments were carried out on a gas cutting manipulator. The results show that the proposed control approach can reduce steady-state error, suppress overshoot and enhance tracking accuracy and efficiency in joint space and Cartesian space, especially under high- speed condition.
基金Supported by National Natural Science Foundation of China (No.60501005)Key Programof Tianjin Science Technology Support Plan(No.2007-68)
文摘Gait recognition is the key question of functional electrical stimulation (FES) system control for paraplegic walking. A new risk-tendency-graph (RTG) method was proposed to recognize the stability information in FES-assisted walking gait. The main instrument was a specialized walker dynamometer system based on a multi-channel strain-gauge bridge network fixed on the walker frame. During walking process, this system collected the reaction forces between patient's upper extremities and walker and converted them into RTG morphologic curves of dynamic gait stability in temporal and spatial domains. To demonstrate the potential usefulness of RTG, preliminary clinical trials were done with paraplegic patients. The gait stability levels of two walking cases with 4- and 12-week FES training from one subject were quantified (0.43 and 0.19) from the results of temporal and spatial RTG. Relevant instable phases in gait cycle and dangerous inclinations of patient's body during walking process were also brought forward. In conclusion, the new RTG method is practical for distinguishing more useful gait stability information for FES system control.
文摘Fuzzy control is an important branch of intelligent control, and this paper describes the application of fuzzy pattern study in intelligent control, begins with a brief overview introduction for development of intelligent control, and then describes the main components of the fuzzy model and its characteristics and fuzzy pattern control system.Fuzzy pattern applications in the intersection signal intelligent control showed fuzzy mode control can effectively reduce the single intersection average vehicle delay time, making the intersection more unobstructed to pass.
