Abstract—With the wide application of power electronic devices, it is more and more important to realize their production control. In order to predict the production capacity of thyristor, the data set of production line is normalized based on principal component analysis, and the fuzzy multivariate linear equation of output rate is established. By combining mathematical programming model with fuzzy algorithm, the fuzzy c-means parameters of RBF algorithm are adjusted, and the output rate prediction model is established and optimized to predict the output of thyristor production line. Taking the data of a thyristor production line as the sample, the BP neural network and RBF network models are compared, and the prediction results under different hidden layer nodes are analyzed. The results show that compared with other models, the error of the improved FNN model is smaller, and the prediction accuracy can reach more than 95%, which has good generalization performance. At the same time, a large number of experiments verify that the best hidden layer node value is 30 when the model predicts the thyristor output rate.
 

Index Terms—thyristor, production capacity forecast, Fuzzy neural network, radial basis function neural network, production line

Cite: Zhi-Wen Xia, Yi-Fei Wang, Ke-Xin Yang, and Li-Jun Jin, "Production Capacity Prediction of Thyristor Based on Fuzzy Neural Network," Journal of Advances in Information Technology, Vol. 13, No. 1, pp. 100-105, February 2022. 

Copyright © 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.