【作者】 李健；

【导师】 辜丽川； 侯传宇；

【作者基本信息】 安徽农业大学 ， 农业硕士（专业学位）， 2021， 硕士

【摘要】 随着科技的进步,生产技术得到了极大的发展,同时生产方式也随之变换,对于生产制造业来说,如何紧跟时代发展的脚步,满足人们对于商品各方面日益增长的需求,成为各个企业研究的重点,尤其是农产品生产加工企业,为了面对日益增长的订单数量以及小批量、多批次的订单模式,急需找到合适的车间生产加工方式来替代传统的生产加工模式。由于车间存在大量不确定的因素,以及小批量、多批次的订单模式极大的提高了排产方案的制定难度,此外,各个企业对于排产方案的制定也有各自不同的要求以及对于不同目标的优化,比如对于生产时间的优化、能量损耗的优化和设备利用率的优化等等。因此针对以上问题,本文依托于省科技重大专项《特色林果制品质量安全监控与追溯大数据云平台研发与应用》,针对XX公司的农产品干果类加工车间,展开了深入的研究,完成的主要研究工作和成果总结如下:1)本文采用多目标优化来对车间调度进行排产优化,所以重点研究了基于协同进化的多目标蚱蜢优化算法。本文提出了一种基于多种群协同进化框架的多目标蚱蜢优化算法,该框架能够在探索和开发之间实现良好的平衡。为了改善多目标优化解的收敛性和多样性、平衡群智能算法的探索和开发,设计了一种分组机制和协同进化机制,并将其集成到框架当中。采用分组机制提高搜索算子的多样性,提高搜索空间的覆盖率,通过搜索种群之间的相互作用,利用协同进化机制提高了算法的收敛速度。之后用几个标准测试函数测试,如CEC2009、ZDT和DTLZ对提出的算法进行了基准测试,利用IGD和GD性能指标对得到的多目标优化解与原始多目标蚱蜢算法解的收敛性和多样性进行了定量和定性比较,结果表明,所得到的解的多样性和收敛性得到了显著的改善,最后通过Wilcoxon秩和检验验证了结果的有效性。2)在对XX公司农产品干果类加工车间的生产流程、业务流程和生产目标需求分析的基础上,设定了相关约束条件和目标函数并进行了数值化处理,从而建立与实际生产需求结合的多目标柔性作业车间模型,同时利用基于协同进化的多目标蚱蜢优化算法对模型进行求解优化,针对加工的工序顺序,得到加工排产优化方案,最后设计并实现了干果类农产品加工车间排产优化系统。更多还原

【Abstract】 With the progress of science and technology,the production technology has been greatly developed,and the mode of production has also changed.For the production industry,how to keep up with the pace of the times and meet the growing demand of people for commodities has become the focus of research of various enterprises,especially the agricultural products production and processing enterprises,In order to face the growing number of orders and the small batch,multi batch order mode,it is urgent to find a suitable workshop production and processing mode to replace the traditional production and processing mode,in order to quickly and effectively develop the agricultural product workshop scheduling plan.Due to a large number of uncertain factors in the workshop and the small batch and multi batch order mode,it greatly improves the difficulty of making the scheduling scheme.In addition,each enterprise has its own different requirements and Optimization for different objectives,such as the optimization of production time,the optimization of energy consumption and the optimization of equipment utilization.Therefore,in view of the above problems,this paper will rely on the provincial major special project "research and development and application of big data cloud platform for quality and safety monitoring and traceability of characteristic forest and fruit products",and carry out in-depth research on the dry fruit processing workshop of XX company.1)In this thesis,we use multi-objective optimization to optimize the job shop scheduling,so we focus on the multi-objective grasshopper optimization algorithm based on co evolution.This paper proposes a multi-objective grasshopper optimization algorithm based on multi population co evolution framework,which can achieve a good balance between exploration and development.In order to improve the convergence and diversity of multi-objective optimization solutions,and to explore and develop the balanced swarm intelligence algorithm,a grouping mechanism and co evolution mechanism are designed and integrated into the framework.The grouping mechanism is used to improve the diversity of search operators and the coverage of search space.Through the interaction between search populations,the co evolution mechanism is used to improve the convergence speed of the algorithm.Then,several standard test functions,such as cec2009,ZDT and DTLZ,are used to benchmark the proposed algorithm.The convergence and diversity of the obtained multi-objective optimization solution and the original multi-objective grasshopper algorithm are quantitatively and qualitatively compared by using IGD and GD performance indicators.The results show that the diversity and convergence of the obtained solution are significantly improved,Finally,Wilcoxon rank sum test is used to verify the validity of the results.2)According to the on-the-spot investigation and information analysis of the dry fruit processing workshop of XX company,the constraint conditions and objective function are numerically processed,so as to establish a multi-objective flexible workshop model which is consistent with the actual situation.At the same time,the multi-objective grasshopper optimization algorithm based on co evolution is used to solve and optimize the model,and finally the production scheduling optimization scheme is obtained.Finally,the production scheduling optimization system of dry fruit agricultural products processing workshop is designed and implemented.更多还原