基于鲁棒最小二乘支持向量机的齿轮磨损预测  

Gear Wear Prediction Based on Robust Least Squares Support Vector Machine

作　　者：衷路生[1] 陈立勇[1] 杨辉[1] 龚锦红[1] 张永贤[1] 祝振敏[1] 

机构地区：[1]华东交通大学电气与电子工程学院,南昌330013

出　　处：《北京工业大学学报》2014年第7期1028-1034,1047,共8页Journal of Beijing University of Technology

基　　金：国家自然科学基金资助项目(61263010);江西省教育厅资助项目(GJJ12316)

摘　　要：为了降低包含噪声的现场齿轮磨损数据对最小二乘支持向量机(least squares support vector machine,LSSVM)模型稳健性的影响,采用迭代鲁棒最小二乘支持向量机(iteratively robust least squares support vector machine,IRLSSVM)对齿轮磨损数据进行建模和预报.首先,增加权函数迭代次数以保证建模过程的鲁棒性;然后,将具有全局搜索的耦合模拟退火(coupled simulated annealing,CSA)与局部优化的单纯形法(simplex method,SM)相结合的方法用于优化IRLSSVM模型超参数,进而采用鲁棒交叉验证作为CSA-SM算法拟合目标函数,提高IRLSSVM模型超参数优化过程的鲁棒性;最后,利用K727840ZW变速箱现场齿轮磨损数据进行了数值实验,结果验证了所提出方法的有效性.To reduce the influence of the gear wear data that contains noise on the robustness of least squares support vector machine （LSSVM） model, the data was modeled and forecasted by iteratively robust least squares support vector machine （IRLSSVM）. First, model process robustness was assured by increasing weight function iteration times; Second, the IRLSSVM hyper-parameter was optimized based on the method combined global optimization method CSA with local optimum method SM; Third, the robust cross validation was used as CSA-SM algorithm objective function to improve IRLSSVM model robustness of parameter optimization process; Finally, numerical experiment was carried out by using K727840ZW gearbox data. result shows that the proposed method is effective.

关 键 词：最小二乘支持向量机(LSSVM) 鲁棒 交叉验证 参数寻优 齿轮磨损 

分 类 号：TH117[机械工程—机械设计及理论] TP393[自动化与计算机技术—计算机应用技术]