BP Evaluation Model of Discrete Workshop Intelligent Manufacturing System

• 1、School of Mechanical Engineering, Hefei University of Technology, Hefei 230009

Abstract：Aiming at the comprehensive evaluation problem of discrete shop intelligent manufacturing system with nonlinear mapping relationship between input and output, this paper constructs a system evaluation model based on BP neural network. Through the analysis of the structure and general operation process of the discrete workshop intelligent manufacturing system, the key elements are selected in the three dimensions of basic resources, product manufacturing and system information to establish an evaluation index system, and the evaluation indicators and system comprehensive evaluation values are taken as input and output respectively. The trial-and-error method is used to determine the number of hidden layer nodes, select the appropriate transfer function and training function, and construct a 3-layer BP neural network model. Taking the front axle assembly workshop of a car company as an example, the validity and feasibility of the model are verified.

Keywords： Discrete Workshop Intelligent Manufacturing System Evaluation System BP Neural Network