A neural network based fuzzy learning controller and its experimental application to milling
In this paper a fuzzy learning controller for the milling process is developed based on the neural network. A BP neural network is used to construct the fuzzycontroller. To develop the fuzzy learning controller, a traditional fuzzy control table is used for the initial off-line training of the neural network. In the real-time control of the fuzzy learning controller, the difference between the real output and the desired output is used to adjust the weights of the neural network, i.e. the fuzzy control table is modified on-line by the neural network. The experiment results show that not only does the fuzzy learning control system have high robustness and stability, but also the machining efficiency of the milling system with the fuzzy learning controller is higher than with the traditional CNC milling system.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
Document Type: Research Article
Affiliations: School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, PR China
Publication date: September 1, 2000