Forming Quality Forecasting for Inner Threads Copper Tubes Based on Neural Network

Abstract

Aims at the defects such as folding and gaps, this paper analyze the relationship between the main processing parameters and inner thread forming quality. Using the fitness function of genetic algorithm to calculate individual fitness value, then the initial weights and thresholds of the Neural Network are assigned, BP Neural Network prediction model based on genetic algorithm is established. The results show that the Neural Networks model has high convergence speed and forecast accuracy, can realize the inner thread forming prediction accurately and improve effectively the forming quality of inner thread.