基于差分进化的粒子群算法的鼓式制动器多目标优化设计_韩永印.pdfVIP

网络出版时间：2014-12-29 09:11 网络出版地址：/kcms/detail/51.1196.TP0911.059.html 优先出版 计 算 机 应 用 研 究 第32 卷 基于差分进化的粒子群算法的鼓式制动器多目标优化设计 韩永印1, 2 (1 武汉大学 计算机学院，武汉 430072 ；2 徐州工业职业技术学院，江苏 徐州 221140) 摘 要：为了提高鼓式制动器的设计水平，建立了一种以制动鼓体积最小和制动器温升最低为目标的鼓式制动器多目标 优化模型，并使用一种基于差分进化的粒子群算法进行优化设计。为了进一步增加算法多样性，该算法将差分进化策略 引入到多目标粒子群算法中；为了避免粒子飞行速度过快，陷入局部最优解，加入一种速度控制策略。通过无约束的 ZDT 系列和3 个有约束的基准测试函数进行测试，并与其他4 种算法对比实验，证明该算法在收敛性和多样性方面都 占优，在工程实例求解结果表明了算法的工程可行性。 关键词：鼓式制动器模型；多目标优化；差分进化；速度控制策略；粒子群优化 中图分类号：TP 文献标志码：A Multi-objective optimization design of drum brake based on differential evolution of particle swarm optimization HAN Yong-yin1, 2 (1. College of Computer, Wuhan University, Wuhan 430072, China; 2. Xuzhou College of Industrial Technology, Xuzhou 221140, China) Abstract: In order to improve the quality of drum brakes, a brake drum multi-objective optimization model aiming at minimizing the size of the brake drum and brake temperature rise was established and a PSO based evolutionary optimization was proposed for optimization design. To enhance the diversity of the algorithm, the new introduced differential evolution strategy into PSO. In order to avoid flying too fast into local optimal solution, adding a speed control strategy. The results indicate that the improved algorithm outperforms the four compared algorithms concerning the convergence and diversity in solving multi-objective optimization problems with unconstraint of ZDT family and th