Intelligent Prediction System of Process Parameters in Complex Workshop Based on ABPNN

Abstract

With the improvement of workshop production process, the complexity of workshop production is also increasing, which intensifies the difficulty of workshop process parameter prediction. Aiming at the above problems, this paper proposes a workshop process parameter prediction model based on ABPNN algorithm. Aiming at the multi index data of complex workshop, the Pearson correlation coefficient is used to analyze the correlation of workshop process parameters, judge the correlation between the parameters to be predicted and various influencing factors according to the Pearson correlation coefficient, and realize the reduction of prediction parameters. On this basis, Adam algorithm is introduced to establish a learning rate adaptive optimization algorithm based on transfer learning to dynamically adjust the network structure, The reasonable model parameters are solved to improve the prediction accuracy of the model. Through the actual workshop production data as an example, the results show that compared with the traditional BP neural network, the model has certain advantages in prediction accuracy and running speed.