Realization of neural network controller for electromotor frequency conversion speed-regulating based on LonWorks

In this paper, we present a study of neural network controller-based solution for electromotor frequency conversion speed-regulating. The neural network controller combines neural network model - M-P(McCulloch-Pitts) with motor speed closed-loop control. The LonWorks technology offers engineers a powerful solution for realization DCS (distributed control system) monitoring and control system. So, we use LonWorks field bus to establish a field measure and control network. The designs of the neural network controller including hardware design and software design are also based on the LonWorks technology. The algorithm for neural network controller and realization of the algorithm are expatiated. Finally, two tests are performed to test the neural network controller´s static performance and dynamic performance. Results of two tests are presented as two motor-speed response graphs which are plotted by workstation PC.