基于禁忌制造特征动态调整的STEP-NC工艺路线蚁群优化方法

针对STEP-NC制造特征的加工工艺路线生成与优化问题,提出了一种以机床、夹具及刀具更换率最低为目标函数的禁忌制造特征动态更新的工艺路线蚁群优化方法。首先,根据加工工艺对制造特征进行分解,将工艺路线优化问题转化为对制造特征的排序;然后根据制造特征在加工过程中存在的加工遮挡关系以及刚性工艺性约束,提出禁忌制造特征动态更新的工艺路线生成方法;最后将禁忌制造特征动态更新方法与Ant-Cycle模型的蚁群算法相结合,求解制造特征工艺路线的优化问题。实例应用表明,提出的方法能较好解决加工工艺路线优化过程中的刚性约束处理问题。     

基于遗传算法与约束矩阵的工艺路线优化方法研究

提出了一种基于遗传算法和约束矩阵的工艺路线优化方法.该方法利用约束矩阵来描述加工元间的优先关系,由系统自动生成约束矩阵,开发了保证加工元序列满足工艺约束关系的加工元序列有效性检验与调整算法.以总变换成本最小为优化目标,采用改进的遗传算法进行工艺路线的优化,以实现工艺过程的全局优化.     

采用差分进化算法的复杂轴零件工艺路线优化

针对某复杂轴工艺路线编制不合理导致加工效率低的问题,从现有工艺路线优化方案出发,将加工特征以加工精度为加工元节点进行详细划分,构架合理加工元编码,以生产实际中装夹为依据,对工艺约束关系分组分析,获得更优的约束矩阵表达。利用差分进化算法,以机床、刀具及装夹更换最少为目标函数,合理设计差分变异、交叉及序列有效性校验与调整算法。通过对比表明,优化方案相较于优化前方案以及工艺约束不分组方案,刀具、装夹更换次数均有减少。     

基于直觉模糊数与多目标优化算法的工艺路线优化

为解决工艺规划中的工艺路线决策问题,提出基于直觉模糊数与元胞自动机—第二代强度Pareto进化算法的工艺路线多目标优化方法。分析了零件的加工特征并将其分解为可用知识化表达的加工元,为有效处理加工元之间的模糊性顺序约束关系,利用直觉模糊数设计结构矩阵来建立加工元之间的约束关系。在此基础上,构建了以加工设备变换成本、装夹变换成本、刀具变换成本为优化目标的工艺路线多目标优化模型。为提高求解多目标工艺路线的求解效率,利用元胞自动机和第二代强度Pareto进化算法对工艺路线优化模型进行求解,得到由多个可行的工艺路线组成的Pareto前沿,进而通过模糊熵对其评价后筛选出最佳工艺路线。以某设备的传动箱箱体为例,验证了所提方法的可行性与有效性。     

基于成组技术与遗传算法的两阶段制造伙伴选择

文章分析了制造伙伴选择的研究现状及其不足之处,提出了两阶段制造伙伴选择:即基于成组技术的制造资源预配置、基于遗传算法的可执行加工路线优化.制造资源预配置根据制造能力进行制造伙伴的初选,可执行加工路线优化综合考虑备选制造伙伴的信誉度、加工时间、运输时间、加工成本、运输成本、质量等因素,优选出整体最优的可执行加工路线.     

基于遗传算法的加工工艺决策与排序优化

针对箱体类零件的工艺路线排序问题,以总生产时间最短为优化目标,建立了加工中心零件的工步排序数学模型。考虑加工中心多次装夹下零件特征有多种加工方案的情形,通过引入特征约束矩阵和加工优先级系数,保证了工艺规划中约束的合理性。设计了相应的初始种群生成、染色体的选择、交叉和变异策略,利用遗传算法对加工方案进行选择与排序。最后通过多个实例分析验证了该方法可以有效提高工艺规划中加工工艺的排序优化能力。     

知识化制造系统产品工艺路线的自重构

为满足动态多变的产品需求,研究了知识化制造产品工艺路线自重构问题.以最小化平均在制品水平和最小化重构后各工序在机器上的分配变动数目为目标,在满足生产率、工序优先顺序、工件加工完整性、机器加工可行性约束的前提下,对产品工艺路线重构问题进行数学建模.提出了改进的混沌非支配排序遗传算法,利用带随机参数的Skew Tent映射对种群个体进行扰动,避免搜索陷入局部最优.设计了基于工序优先约束矩阵和候选机器集的解码方法,可获得产品可行的加工工序序列及加工机器序列.通过实例研究验证了模型和算法的有效性,为决策者提供了多种可选工艺路线重构方案.     

基于遗传算法的发动机箱体工艺路线优化

针对发动机箱体,提出了基于遗传算法和约束矩阵的工艺路线优化方法。通过对箱体特征的定义和分类,确定了特征加工的优先关系,自动生成了工艺规划的约束矩阵。在计算机辅助工艺过程设计（CAPP）平台中,定义了缸孔、瓦孔和通水孔等关键部件的加工工艺。按照提出的工艺路线优化方法,进一步优化了发动机箱体的工艺路线。     

面向低碳的工艺规划与车间调度集成优化

为更好地减少制造过程中的碳排放,弥补将工艺规划与车间调度分开碳排放优化时忽略了工艺规划方案中加工方法和工艺路线对调度阶段各工序加工机床分配方案、搬运距离以及工件加工顺序的影响,提出一个集成优化工件各特征加工方法、工艺路线、工件加工顺序以及各工序的机床分配,以实现制造过程碳排放和最大完工时间最小的多目标集成优化模型;针对集成优化模型中优化参数较多且相互影响的特性,提出一种前后相关联的四段式编码方法,采用NSGA-II算法求解,通过将所得的集成优化结果与先进行面向低碳的单目标工艺规划优化,再进行面向低碳的多目标车间调度分开优化结果进行对比,说明提出的集成优化模型可以得到更低的制造过程碳排放和完工时间,从而验证了集成优化模型的有效性。     

面向制造特征的STEP-NC非线性工艺路线激励生成方法

为解决STEP-NC非线性工艺路线生成中处理加工约束困难的问题,根据STEP-NC面向制造特征的特点,提出一种对制造特征进行激励选择排序的非线性工艺路线规划方法。利用加工方案选择原则确定制造特征的加工方案,根据已确定的制造特征加工方案,对具有多个加工操作的制造特征进行特征分解。针对制造特征相交可能存在的加工遮挡问题,提出基于制造特征划分的刚性优先约束判断方法。利用制造特征集合划分方法表达刚性优先约束以及装夹与刀具的柔性约束,并通过对不同制造特征集中制造特征的激励、选择、可行制造特征动态更新等操作,实现非线性工艺路线的生成。结合实例验证了所提非线性工艺路线激励生成方法的可行性与有效性,并表明该方法较好地解决了工艺约束及其知识的表示问题。     

Research on selection strategy of machining equipment in cloud manufacturing

Cloud manufacturing (CM) is a new type of networked manufacturing model, which is proposed in 2010. Optimization technology is one of the key techniques for CM operation, which are used for the efficient integration of manufacturing resources. In all kinds of manufacturing resources, the machining equipment is one of the most important resources. Using optimization techniques to achieve optimal selection of machining equipment is rarely studied in the CM. In order to handle the optimization selection of machining equipment in CM, comparing with the existing resources optimal configuration, an optimal selection strategy is introduced for the machining equipment in CM. In the selection strategy, first, a multiple objective and binary integer programming model is proposed to describe the optimal selection of machining equipment in CM. Second, after analyzing the mathematical model and the real-world problem of the machining equipment selection in CM, the priority method is adopted to convert the multiple-objective problem into a single-objective problem. Third, an improved particle swarm optimization (IPSO) algorithm based on a novel encoding scheme and fitness function is presented to solve the single-objective mathematical model. Finally, the simulation experiments verify the effectiveness of the IPSO algorithm and show that the selection strategy is more objective and effective to help the client select the machining equipment in the CM than current resources optimization model. This research provides a theoretical support for the development of CM.     

基于遗传算法的工步优化排序方法

针对数控加工中心上零件加工工步的排序问题,以辅助加工时间最短为优化目标,使用遗传算法对零件在一次装夹情况下的加工工步进行优化排序。提出了使用特征关系图和特征高度描述待加工特征之间加工的优先顺序、采用工步优先关系矩阵校验工步序列合理性的方法。论述了初始群体的生成、遗传算子以及工步优化排序的过程和算法。实际应用表明,该方法可有效提高工艺规划系统中工步的优化排序能力。     

An effective hybrid graph and genetic algorithm approach to process planning optimization for prismatic parts

Computer-aided process planning is an important interface between computer-aided design and computer-aided manufacturing in computer-integrated manufacturing environments. In this paper, the complicated process planning is modeled as a combinatorial optimization problem with constraints, and a hybrid graph and genetic algorithm (GA) approach has been developed. The approach deals with process planning problems in a concurrent manner by simultaneously considering activities such as sequencing operations, selecting manufacturing resources, and determining setup plans to achieve the global optimal objective. Graph theory accompanied with matrix theory, as the basic mathematical tool for operation sequencing, is embedded into the main frame of GA. The precedence constraints between operations are formulated in an operation precedence graph (OPG). The initial population composed of all feasible solutions is generated by an elaborately designed topologic sort algorithm to the OPG. A modified crossover operator guaranteeing only feasible offspring generated is used, two types of mutation strategies are adopted, and a heuristic algorithm is applied to adjust the infeasible plan generated by the mutation operator to the feasible domain. A case study has been carried out to demonstrate the feasibility and efficiency of the proposed approach.     

一种设计和工序公差计算机辅助并行设计方法的研究

提出一种计算机辅助设计公差和工序公差并行设计的数学模型，以成本公差函数作为目标函数，以装配功能要求、加工方法、加工余量、工序制造公差范围作为约束条件，并用蒙特卡洛法模拟尺寸装配、模拟退火算法用于优化求解，实现了设计公差和工序公差并行设计，缩短了设计周期。     

基于自适应蚁群算法的协同制造项目资源优化配置

为探索更高效的协同制造资源优化配置算法,提出了基于自适应蚁群算法的求解方法。针对零件的特定工艺线路,建立了以时间、成本和质量为目标的制造资源优化配置模型,设计了模型求解的自适应蚁群算法,并给出具体算例,验证了算法的可行性和有效性。     

Manufacturing- and machining-based topology optimization

Topology optimization is used in the initial stage of the product manufacturing process. However, the non-manufacturable or non-machineable results of topology optimization have become an obstacle to process manufacturing. This paper proposes a modified topology optimization method by adding manufacturing and machining constraints to the topology optimization formulation. A hybrid topology optimization algorithm (combining the method of moving asymptotes and wavelets) is applied to solve this optimization problem. With this approach, the design space can be reduced and an engineering-accepted and manufacturable topology result can be guaranteed.     

Using flower pollinating with artificial bees (FPAB) technique to determine machinable volumes in process planning for prismatic parts

Process planning (PP) has an important role in manufacturing systems design and operations. Volume decomposition and machinable volumes (MVs) or machining features determination is the core activity in process planning. This process requires extraction of elementary volumes (EVs), merging or clustering EVs to construct feasible MVs and finally selecting an optimal combination of MVs. Development of MVs is an important activity, so that better solution is obtained by better developed MVs. Generation of limited number of MVs or machining features, which is often performed by experts may miss the optimal solution. Also, using exact methods such as combinatorial optimization not only generate infeasible MVs, but also require an excessive amount of computational time. In this research, the meta-heuristic procedure of flower pollinating by artificial bees (FPAB) is used in manufacturing context to generate and assess the feasibility of MVs. Furthermore, a set-covering method is used to select the optimal solution. The performance of the proposed model is assessed through some numerical examples. The encouraging results of the numerical examples demonstrate good performance of the proposed method in machining feature or machinable volumes determination problem (MVDP).