Under the condition that the object model is definite, unvaried, and linear and that the operation condition and environment is ascertained, it is efficient to adopt traditional control scheme. But for the situation o...
详细信息
ISBN:
(纸本)0780374797
Under the condition that the object model is definite, unvaried, and linear and that the operation condition and environment is ascertained, it is efficient to adopt traditional control scheme. But for the situation of high precision and fine feed, the timing and variable factors such as the variation of structure and parameters of the object, the effects of all kinds of nonlinear factors, the changes of operation environment and environmental interferes must be considered to obtain satisfying control effect. Nowadays modern control schemes are taken seriously in the study of LPMSM In this paper, we propose a control scheme for the speed servo control of LPMSM with modelreferenceadaptive and neuralnetwork techniques. modelreferenceadaptiveneuralnetworkcontrol is a new technique which is the combination of the modelreferenceadaptivecontrol and the neuralnetworkcontrol. This kind of control method has double advantages of the two methods. To improve the robustness of the system, we use on-line identification technique to compensate the variation of the parameters and modify the calculation of the neuralnetworks teacher value. The result of simulation shows that the system has good speed servo performance, especially in overcoming the end effect of LPMSM..
暂无评论