Balance Algorithm Optimization And Simulation Verification Of Y Company's Laptop Computer Assembly Line

The 21 st century is the era of intelligent manufacturing.Intelligent manufacturing is a further form of manufacturing after automated manufacturing.Its core is digitization,networking,and intelligence.As a big country in the manufacturing,consumption and export of electronic products,my country's electronic manufacturing industry has developed rapidly,including the rapid growth of notebook computer production and export volume.This forces traditional notebook computer assembly companies to make changes,improve production efficiency,and use intelligent algorithms to move toward intelligence,in order to maintain their competitiveness in the fiercely competitive market and go longer.Y Company is a traditional notebook computer assembly company.In recent years,in the fierce market competition,its efficiency has been declining year by year,and there is a dilemma that traditional methods cannot improve.After the systematic analysis of this article,the company's lower assembly line production balance rate and higher smoothing index are the fundamental reasons.Therefore,this article uses intelligent algorithms to improve the balance of its notebook computer assembly line,increase assembly line productivity,and accelerate the company's entry into the smart manufacturing threshold.pace.This paper first summarizes the development and shortcomings of existing production line balancing algorithms,and finds that genetic algorithm is an excellent algorithm for solving production line balancing.However,genetic algorithms still have some shortcomings,including the number of iterations and the empirical selection of operating operators.Related theoretical guidance.But fundamentally speaking,the essence of genetic algorithm is to simulate the evolution process of organisms,so complex networks can be used to reveal the evolution process of genetic algorithms.Then this paper constructs a new kind of complex network entropy,which is used to measure the index and network topology structure characteristics in the complex network process of genetic algorithm.The test function is used to analyze the different iteration times in Pajek,and the crossover rate and mutation rate are compared to the complex network.The influence of the theory to guide the number of iterations and the choice of operation operators.After experiments,it is found that low iterations,high crossover rate and low mutation rate will generate more important nodes and paths in the network,which will have a positive impact on the stability of the network and the characteristics of the network topology,and it is also more conducive to genetic algorithms.The evolution process of genetic algorithm provides certain theoretical guidance for the selection of genetic algorithm iterations and operation operators,and also provides a new perspective for revealing the evolution process of genetic algorithm.Finally,this paper uses a genetic algorithm with low iterations,high crossover rate and low mutation rate to improve the assembly line of Y company in Matlab.Finally,the balance rate of the total assembly line rises from 73.58% to 90.58%,and the smoothing index drops from 10.02 to 2.99.The optimization effect is obvious,and the balance of Y company's production line has been significantly improved.