Research On Capability Maturity Evaluation Of Intelligent Manufacturing Based On Firefly Algorithm And Sparrow Search Algorithm And BP Neural Network

With the deep integration of the new generation of information and communication technology and advanced manufacturing technology,intelligent manufacturing has become a new path of intelligent transformation and upgrading of manufacturing industry in the world.At present,the development of intelligent manufacturing is still at exploring stage.Different enterprises lack a unified understanding of intelligent manufacturing,and have a vague understanding of the positioning and development of their own intelligent manufacturing.There is an urgent need for effective methods to guide its distributed implementation and systematically promote the construction of intelligent manufacturing.Among them,it is a key problem to find a scientific evaluation method of intelligent manufacturing capability.In this thesis,based on the maturity theory,the influencing factors of intelligent manufacturing capability maturity are summarized.By using neural network and other intelligent algorithms,the capability maturity evaluation of intelligent manufacturing is studied.To help manufacturing enterprises identify the gap and determine the development goal of intelligent manufacturing.The main research work is as follows:(1)The capability maturity evaluation index system of intelligent manufacturing is constructed.Aiming at the problem of intelligent manufacturing capability maturity evaluation,the evaluation index is determined to lay the foundation for the evaluation model.Around the preliminary design of the evaluation index,Delphi method and correlation analysis are used to screen the index,establish the evaluation index system,and design a questionnaire survey based on the evaluation index to collect the evaluation sample data.(2)Sparrow search algorithm is improved.Aiming at the shortcoming that sparrow search algorithm is easy to fall into local extremum.The disturbance strategy of firefly algorithm is introduced to improve it.And an improved sparrow search algorithm(FASSA)is proposed.Low dimensional and high dimensional multimodal functions are selected to test the performance of the algorithm,the result shows that FASSA algorithm has higher convergence accuracy and speed,and better global search ability.(3)An evaluation model based on FASSA-BP algorithm is proposed.BP neural network is often used to evaluate problems.Aiming at the problem that BP neural network is sensitive to initial weights and thresholds,FASSA algorithm is used to optimize the initial weights and thresholds of BP neural network.The FASSA-BP algorithm is proposed and the evaluation model is constructed.Finally,the sample data is selected for model training and testing.The FASSA-BP model is compared with SSA-BP model,PSO-BP model and traditional BP model.The results show that the FASSA-BP evaluation model has higher accuracy and stability.(4)FASSA-BP evaluation model is applied.According to the evaluation demand of intelligent manufacturing capability maturity of domestic L battery enterprise,data were obtained through enterprise investigation and questionnaire.The proposed FASSA-BP model is used to evaluate the intelligent manufacturing capability maturity of L enterprise.According to the evaluation results to determine the level,help them identify the gap,and give suggestions for improvement.