Application Of Improved Grey Wolf Optimizer In Beer Packaging Workshop

With the development of science and technology and the fierce competition in the market,the differences in product taste between different breweries are gradually narrowing.Therefore,how to efficiently produce and distribute within the order period is particularly important.More and more enterprises pay attention to production scheduling.However,the production scheduling of beer enterprises in our country is mostly based on the order;through reading the literature,we can also find that the domestic and foreign research on the production scheduling of beer enterprises are mostly concentrated in the manufacturing industry and discrete industrial enterprises,and the research on the scheduling of beer enterprises is not very in-depth,most of them are simply the scheduling of production equipment,the scheduling of enterprises It is difficult to solve the actual scheduling problem.Therefore,how to use the scientific method to convert the process of product processing and variety conversion into the actual cost according to the order,and how to distribute the process reasonably has become the focus and difficulty of the research.Therefore,this paper studies the beer packaging scheduling problem,mainly doing the following work:(1)Introduces the research background of the beer packaging workshop scheduling problem,studies the actual scheduling problem,and analyzes the beer production process technology.(2)To solve the scheduling problem of beer packaging workshop,an improved gray wolf optimizer is proposed.In this algorithm,a series of improvements are made to solve the problems of poor population diversity,slow convergence speed and easy to fall into local optimum.First,the initial population is generated by using the reverse learning strategy and chaotic motion to increase the diversity of the population;then,the formula of the convergence factor parameter is changed to make the linear decreasing parameter a nonlinear,balance the search ability of the algorithm,and speed up the convergence speed in the later stage of the algorithm;then,the variation factor is added to the formula of the three individuals in the decision-making layer of the algorithm to increase the algorithm’s jumping out of the local maximum Finally,combined with the advantages of simulated annealing algorithm,the annealing process is added to the iterative process of Gray Wolf Optimizer,and the ability of jumping out of the local optimal value of the algorithm is strengthened again,which effectively improves the situation that gray wolf optimizer is prone to local optimal.(3)The improved gray wolf optimizer is used to experiment in the standard example,and the experimental results are compared with other algorithms.The results show that the improved gray wolf optimizer is better than the contrast algorithm in convergence speed and stability.(4)Through the practical research on the packaging workshop of a beer enterprise,the improved gray wolf optimizer is applied to the actual scheduling problem of the enterprise,and the development of the scheduling management system of a beer packaging workshop is realized.Compared with the scheduling results of other algorithms,it is proved that the improved gray wolf optimizer in this paper is most suitable for the production scheduling of the packaging workshop of this beer enterprise.Finally,the main research work of this paper is summarized,and the future research focus and direction are described.