Mechanical Properties Prediction of Cold Rolled Ribbed Bars based on Full Sample Space and BP Neural Network

摘要

This paper proposes a method of mechanical performance prediction of cold rolled ribbed steel bars based on BP neural network with whole variable space. It builds a whole variable space model and studies the mechanical performance prediction of cold rolled ribbed steel bars based on the 5-in & 1-out BP network and the mechanical performance prediction of cold rolled ribbed steel bars based on the 5-in & 2-out BP network. The results show that this method can reliably predict the mechanical performance of cold rolled ribbed steel bars, and the predictive effect of the 5-in & 1-out BP network model based on whole variable space is superior to the 5-in & 2-out BP network model.