单机带调整时间加权成套订单数问题遗传算法研究

通过大量的企业调研,提出了一类新的目标排序问题--单机带调整时间加权成套订单数排序问题:n个工件来自m个订单,分属B个不同类别,不同类之间的工件连续加工有调整时间,各工件有自己的交货期,一个订单中所有工件均按期完工则该订单成套完工,目标为加权成套延迟订单数最小.提出两类问题并且通过数学模型进行表述,设计相应的遗传算法,仿真结果表明该算法是可行而有效的.     

不确定环境下的单机成套订单鲁棒计划

讨论了不确定环境下订单数量可变的单机成套计划的优化问题,利用对偶变换给出了该问题的鲁棒整数规划模型,并设计了相应的遗传算法。算法对约束条件难点的处理采用了四种不同的方法即死亡惩罚、罚函数法、修补方法和解码方法,以检验算法的性能。最后进行了数值仿真实验,以比较不同算法的有效性。     

面向成套订单的生产与配送协调的排序研究

在工件体积和运输车辆容量的双重约束条件下,建立了以最大化成套订单数和最小化工件总配送时间的多目标规划模型,使用多目标排序寻找"约束解"的方法结合遗传算法求解此模型.最后通过算例分析,给出多目标规划模型及其综合算法在FLOW SHOP生产作业环境中的应用.计算结果表明,应用此模型和算法能够满足最大化成套订单数的要求,同时节省总的工件配送时间,有潜在的应用价值.     

关于导热反问题的一种遗传算法

导热反问题是一个不适定问题,它的求解往往是一项很复杂的计算任务．为了简化计算任务,缩短计算时间,文章提出一种解决导热反问题的遗传算法,该算法在遗传算法的基础上,针对导热反问题的不适定性特点,巧妙地优化遗传种群,较好地解决导热反问题。     

反相容工件系统的加权完工时间和的重新排序问题

重新排序问题是指在原始工件已经安排好的情形下,新到的工件集与原始工件集一起重新再排序,这是实际工作中常见一类优化问题。本文考虑了单机上当工件加工时间与权重反相容时,在最大错位量约束下的加权完工时间和最小化的重新排序问题。对于提出的四个问题,即在最大序列错位、最大时间错位、总序列错位和总时间错位约束下的加权完工时间和重新排序,基于问题的结构性质,运用动态规划方法分别给出了这些问题的多项式时间或拟多项式时间算法。     

改进遗传算法求解多时间约束的柔性作业车间调度问题

将加工时间、调整时间和移动时间分别作为独立时间因素考虑到柔性作业车间调度模型中,建立以最大完工时间最小、总调整时间最小、总移动时间最小为目标的考虑多时间约束的柔性作业车间调度模型,并提出改进的遗传算法求解该模型。通过测试标准数据集,并对比其他文献算法,验证了改进的遗传算法的可行性和有效性。     

带时间窗车辆路径问题的并行遗传算法

采用并行遗传算法研究了带时间窗限制的车辆路径问题.通过设计并行算法和交叉、变异等算子提高了算法的计算效率和性能.通过计算若干benchmark问题,验证了模型的有效性.     

低压成套开关设备型式试验的问题及改进方法

低压成套开关设备安全性能的良好与否与低压电器的正常运行息息相关,基于此,本文在对低压成套开关柜型式试验过程中可能发生的问题进行研究的基础上,分析了可能导致问题的各类原因,并对如何改进做出提出了一些方法并作出了一些设想。     

遗传算法求解TSP问题的改进

针对遗传算法解决TSP问题的特点,构造出遗传算法需要的初始种群.运用相同算法对改进前后的两种种群进行实验,得出改进方法具有增强遗传算法效率的作用.     

遗传算法加权中值滤波器的优化设计

当测试数据中随机干扰满足高斯分布时,可以采用线性滤波器进行信号处理得到所要求的有用信号.而当随机干扰为非高斯分布时,则必须采用非线性的信号处理方法才能获得所要求的有用信号.这里讨论一类非线性滤波器——加权中值滤波器的最优设计问题.取损失函数为绝对误差的数学期望值,采用实数值编码多子种群的标准遗传算法来极小化损失函数.由于遗传算法:是用点群进行寻优,而不是用一个单点进行寻优,具有隐含并行算法的特点;群体在每一代的进化过程中执行同样的复制、交叉、变异操作,仅使用问题本身所对应的适应度函数,而不需要任何其它先决条件或辅助信息;遗传算法使用随机转换规则,而不是确定性规则进行运算.遗传算法作为一类全局最优算法,它所得到的加权中值滤波器也是全局最优的.数值计算结果表明,采用遗传算法可以得到更小的绝对误差平均值,且优于LMA算法.     

Bi-objective mathematical model and improved algorithm for optimisation of welding shop scheduling problem

This paper addresses a bi-objective welding shop scheduling problem (BWSSP) aiming to minimise the total tardiness and the machine interaction effect. The BWSSP is a special flow-shop scheduling problem (FSP) which is characterised by the fact that more than one machine can process on one job at a certain stage. This study analyses the operation of a structural metal manufacturing plant, and includes various aspects such as job sequence, machine-number-dependent processing time, lifting up time, lifting down time and different delivery time. A novel mixed-integer programming model (MIPM) is established, which can be used to minimise the delayed delivery time and the total machine interaction effect. One machine interaction effect formula is given in this paper. In order to solve this BWSSP, an appropriate non-dominated sorting Genetic Algorithm III (NSGAIII), embedded with a restarted strategy (RNSGAIII), is proposed. The restarted strategy, which can increase the diversity of the solutions, will be triggered with a restart probability. Following the iterative process, an effective strategy is applied to reduce the interaction effect penalty, on the premise that the makespan will remain unchanged. Total five algorithms, namely NSGAII, NSGAIII, harmony search algorithm (HSA), strength Pareto evolutionary algorithm (SPEA2), and RNSGAIII are utilised to solve this engineering problem. Numerical simulations show that the improved RNSGAIII outperforms the other methods, and the Pareto solution distribution and diversity, in particular, are significantly improved.     

Stochastic customer order scheduling with setup times to minimize expected cycle time

Short cycle time of customer orders is crucial for companies to achieve mass customization and quick response. However, the complicated and stochastic environment, especially the exist of setup times, makes it extremely challenging to optimize the efficiency of a system. In this study, stochastic customer orders are scheduled to minimize their expect cycle time with the consideration of setup times. Customer orders arrive dynamically, and each order requires multiple product types with random workloads. These workloads will be assigned to a set of unrelated parallel machines to be processed. Particularly, for each machine, setup times are required whenever there is a product type changeover, and the lengthes are both machine- and product type-dependent. This paper intends to minimize the long-run expected order cycle time by proper policies including workload allocation and type sequencing. The impacts of product type sequence and workload variance are evaluated through theoretical study and several analytical properties are developed. With the help of these properties, three scheduling algorithms are proposed, and a lower bound is derived to evaluate the proposed algorithms. Computational experiment is conducted to demonstrate the effectiveness of the lower bound and the algorithms under various circumstances, and several important managerial insights are also provided.     

A Grafted Genetic Algorithm for the Job-Shop Scheduling Problem

The standard genetic algorithm has limitations of a low convergence rate and premature convergence in solving the job-shop scheduling problem. To overcome these limitations, this paper presents a new improved hybrid genetic algorithm on the basis of the idea of graft in botany. Through the introduction of a grafted population and crossover probability matrix, this algorithm accelerates the convergence rate greatly and also increases the ability to fight premature convergence. Finally, the approach is tested on a set of standard instances taken from the literature and compared with other approaches. The computation results validate the effectiveness of the proposed algorithm.     

基于遗传算法的指向性声源自适应有源消声系统优化

详细讨论了自由声场自适应有源噪声控制（ＡＡＮＣ）中，初级源为无限大刚性障板上的圆面活塞辐射器，采用一个和二个点源做次级声源时，使ＡＡＮＣ系统获得最大降噪效果的次级声源和误差传感器（以下统称为执行元件）的布放问题，并利用遗传算法（ＧＡ）确定次级源和远场误差传感器的最优位置。通过理论分析和计算机仿真结果的比较，证明了采用遗传算法可以准确地得到传统的梯度搜索优化算法难以得到的位置优化解。     

一类多资源调度问题的优化算法

若调度系统中的作业或任务需要一个或多个资源共同完成, 则这一类调度问题被称为多资源（或多处理机）调度问题。本文针对Jobshop中的这一调度问题,提出了基于遗传的优化调度算法,并用实例证实了该算法的有效性。     

混合流程型企业主生产计划的启发式算法

提出了一个新的启发式算法,该启发式算法称为多目标主生产计划算法(MOMPS),用于解决混合流水线车间的主生产计划安排,该启发式算法主要有以下目标:最小化拖期惩罚,最小化完工时间,最小化装设和库存成本等.该算法先对所有的定单进行排序,然后根据最小生产成本树及其该树的最大生产能力进行定单的分配,如果定单数量超出了最大生产能力,对生产网络进行调整,通过比较次优生产成本树和拖期以后的最小生产成本决定定单是否该拖期.最后通过和一般的线性规划进行比较,得出该算法在解决混合流程型企业的多目标主生产计划的制定中十分有效,有时得到的结果和线性规划模型解出的解是一致的.