The Distribution Estimation Algorithm Based On Bayesian Network Solves The Green Scheduling Problem Of Complex Job Shop

With the rapid development of the global economy,many enterprises are improving the product "quantity" while improving their "quality".Energy saving has gradually became a clear consensus of the manufacturing industry,and shop green scheduling can reduce many unnecessary costs for the enterprise.The workshop scheduling problem is a hot topic in the field of manufacturing.Meanwhile,the problem of shop scheduling generally has the characteristics of NP-hard,nonlinearity,strong constraint,multi-objective and large-scale inevitable.It is one of the most difficult problems in theoretical research.Intelligent optimization algorithm is an effective method to solve the problem of shop floor scheduling.The use of such intelligent optimization algorithms has drawn wide attention of academia and industry.The distribution estimation algorithm(EDA)is a new evolutionary algorithm based on statistical probability model,and it has been successfully applied.Therefore,this paper studies bayesian-statistical-based estimation of distribution algorithm(BEDA)to solve three kinds of complex job shop green scheduling problems.The main work is as follows:(1)In this paper,a bayesian-statistical-based estimation of distribution algorithm is proposed to solve the multi-objective re-entrant job shop green scheduling problem with due date.The criteria are to minimize maximum tardiness(MT)and total electric consumption(TEC).In the aspect of global search,this algorithm uses the probabilistic model to learn the relationship between artifacts and enhances the global search ability of the algorithm.In the aspect of local search,a local search method with multiple strategies is designed to improve the local search ability of the algorithm.Simulation results show the effectiveness of the proposed algorithm.(2)In this paper,an improved bayesian distribution estimation algorithm(IBEDA)is proposed to solve the multi-objective flexible job shop green scheduling problem.The criteria are to minimize maximum completion time(makespan)and low carbon(LC).The algorithm uses the four-dimensional probability matrix to deduce the relationship between position and a pair of work piece,enhances the global search ability of the algorithm,and adds an improved insert-based local search method to improve the local search ability of the algorithm.Simulation results show the effectiveness of the proposed algorithm.(3)In this paper,an enhanced Bayesian distribution estimation algorithm(EBEDA)is proposed to solve the multi-objective reentrant flexible job shop green scheduling problem.The criteria are to minimize total energy consumption(TEC)and maximum completion time(makespan).Firstly,based on the former problem,the algorithm adds the improved method of adding distribution of equipment to flexible job shop problem.Secondly,by adding the suboptimal layer in the non-inferior solution set to form the double population,the al gorithm overcomes the premature convergence problem.Finally,an improved local search strategy is used to search the solutions.Simulation results show the effectiveness of the proposed algorithm.