Study on a Kind of Thyristor Driven Induction Motor System Based on Neural Network Control

The complex principles of induction motor often bring difficulties to electrical driven system. Due to its nonlinearity, strong coupling and uncertainties, the input and output characteristics are only considered in conventional applications. Thyristors still occupy part of the driven fields where precise speed regulation is not needed, and some solid state controllers have been put into practice. However, from the view point of the system, the performance analysis and modeling of thyristor driven induction motor system still completely depend on circuit calculation. This paper has proposed a method of combining circuit calculation with RBF neural network approximating, and has designed a controller with NN. Comparison of simulation results, actual waveform and experiment data, the validity of the design has been verified. It has provided theoretic support to conventional applications.