Research On Evaluation System Of Discrete Workshop Intelligent Manufacturing System Based On BP Neural Network

Discrete manufacturing plays an important role in China’s economic development and has a great impact on China’s comprehensive strength.As the traditional cost center of discrete manufacturing enterprises and the new profit center,the workshop plays a key role in the development of discrete manufacturing enterprises.In today’s increasingly fierce market competition,the importance of an intelligent manufacturing system that matches the production of workshops is not important.It goes without saying.At present,the evaluation of the discrete workshop intelligent manufacturing system is mainly from the aspects of production efficiency,manufacturing flexibility,etc.,from the perspective of the system,and the evaluation index system and evaluation method have certain limitations.In view of this,the dissertation constructs an evaluation model based on BP neural network algorithm,in order to provide a theoretical reference for the systematic evaluation of discrete workshop intelligent manufacturing system.First,the evaluation index system of the discrete workshop intelligent manufacturing system is constructed.On the basis of comprehensive analysis of the structure and general operation process of the discrete workshop intelligent manufacturing system,the evaluation index system is initially established from the three dimensions of basic resources,product manufacturing and system information,and the quantitative measurement methods and quantitative indicators of qualitative indicators in the evaluation system are analyzed one by one.The calculation formula,based on the existence of redundancy,uses the rough set attribute reduction method to optimize the evaluation index system.Secondly,an evaluation model of discrete shop intelligent manufacturing system based on BP neural network is established.Design the structure of the neural network model,use the trial and error method to determine the number of hidden layer nodes,select the transfer function of the hidden layer and the output layer according to the characteristics of the evaluation object,analyze the shortcomings of the traditional BP algorithm and select the appropriate optimization algorithm.MATLAB simulation engineering software selects the sample data scientifically in a front axle assembly workshop of a car,and performs data normalization processing on the BP evaluation model to analyze the output and verify the feasibility of the constructed BP evaluation model.Finally,the evaluation prototype system based on BP neural network algorithm is designed and implemented.Analyze and evaluate the prototype system requirements,design the system structure and database tables,and use the professional programming software such as Visual 2015 and SQL server 2014 to implement the designed prototype system using C# programming language.By adopting a combination of qualitative analysis and quantitative analysis to construct a scientific and comprehensive intelligent manufacturing system evaluation system and evaluation model,it can help enterprise managers to find the weak links of intelligent manufacturing systems and improve them,improve scientific management level,and enrich intelligence.The theoretical system for manufacturing system evaluation.