公差设计多目标模型及其粒子群优化算法研究

为解决成本一公差设计模型中忽视产品质量的问题，以新型的田口质量观和Pareto最优解集概念为基础，提出了一种公差设计多目标模型。该模型将加工成本和质量损失分别作为设计目标，并以统计法公差装配成功率为约束条件，获得了比极值公差法更加宽松的公差限。改进了传统的粒子群优化算法，利用Pareto最优性重新定义粒子，然后采用快速非支配排序技术进行粒子的适应度排序，使其能够有效地对多目标模型进行求解。该算法对具体工程实例求解时，一次运行就可求得令人满意的Pareto最优解集，设计者可以根据生产实际和市场需求从中进行选取。通过对求得的Pareto进行最优前沿的分析，可得到该类零件公差设计的特性，其结果验证了公差诒计的一船规徨．

Multi-objective model of tolerance design and its solution with particle swarm optimization algorithm

To solve the problem of ignored product quality in cost-tolerance model,a multi-objective model of tolerance design was presented,which was based on Taguchi's quality view and the conception of Pareto optimum set.Manufacturing cost and quality loss were both taken as design objectives,which were subject to assembly success rate of statistical tolerance,and the obtained tolerance zone was looser than the worst tolerance's.The traditional particle swarm optimization was improved,the particle was redefined according to the conception of Pareto optimum,and then the fast non-dominant sorting technology was adopted to sequence the particles by their fitness values,so multi-objective model of tolerance design could be solved by the improved algorithm.Used to engineering example,only through one operation good Pareto optimum set was obtained.Solutions could be selected according to manufacturing reality and market demand.Based on analysis of Pareto front,the tolerance design characteristics of this kind of part could be got,and the general laws of tolerance design were also validated by results.