基于PSO算法和SVR模型的加工中心可靠性模型参数估计

发布时间：2018-09-05 13:55

【摘要】：针对加工中心可靠性模型,提出了一种基于支持向量回归模型的参数估计方法,并利用改进的局部最优粒子群优化算法对支持向量回归模型的参数进行优化,以提高其对可靠性模型参数的估计精度。与标准的局部最优粒子群优化算法比较,改进的局部最优粒子群优化算法引入了变异操作和自适应调节惯性因子,提高了算法的全局最优解搜索能力。将提出的方法与最小二乘法、最大似然估计法、局部最优粒子群优化算法优化的支持向量回归模型和遗传算法优化的支持向量回归模型进行了对比试验。试验结果表明:该方法的参数估计精度高于最小二乘法、最大似然估计法、局部最优粒子群优化算法优化的支持向量回归模型和遗传算法优化的支持向量回归模型。最后,将该方法用于估计实际加工中心可靠性模型的参数,得出了相应的平均故障间隔时间的评估数值。
[Abstract]:For the reliability model of machining center, a parameter estimation method based on support vector regression model is proposed, and the parameters of support vector regression model are optimized by using an improved local optimal particle swarm optimization algorithm. In order to improve the estimation accuracy of reliability model parameters. Compared with the standard local optimal particle swarm optimization algorithm, the improved local optimal particle swarm optimization algorithm introduces mutation operation and adaptively adjusts inertia factor, and improves the ability of searching the global optimal solution of the algorithm. The proposed method is compared with the least squares method, the maximum likelihood estimation method, the support vector regression model optimized by the local optimal particle swarm optimization algorithm and the support vector regression model optimized by the genetic algorithm. The experimental results show that the accuracy of this method is higher than that of the least square method, the maximum likelihood estimation method, the support vector regression model of local optimal particle swarm optimization algorithm and the support vector regression model of genetic algorithm optimization. Finally, the method is used to estimate the parameters of the reliability model of the actual machining center, and the corresponding evaluation value of the average fault interval time is obtained.
【作者单位】：吉林大学机械科学与工程学院;吉林大学机械工业数控装备可靠性技术重点实验室;空军航空大学飞行器与动力系;
【基金】：吉林省科技发展计划项目(20130302009GX) 吉林大学研究生创新基金项目(2014053)
【分类号】：TG659

【参考文献】