作者：汤少敏1, 刘桂雄1, 李小兵2
作者单位：1. 华南理工大学机械与汽车工程学院，广东 广州 510640;
2. 工业和信息化部第五研究所，广东 广州 510610
关键词：径向基神经网络;Bootstrap法;工业机器人伺服系统;可靠性
摘要：
针对高可靠性、长寿命产品可靠性试验数据样本较少难以进行有效可靠性评估问题，提出一种基于RBF神经网络的Bootstrap数据扩充方法，利用RBF神经网络获取原样本连续分布特性，邻域函数构建网络输入集。仿真表明，由该扩充方法获得的扩充样本分布特性更接近于其真实分布，并有效利用了原样本取值区间上、下限数据信息，拓展更宽的样本取值范围。将其应用于工业机器人伺服系统(IRSS)伪失效寿命分布可靠性评估中，扩充伪失效寿命数据，获得IRSS有效可靠性评估结果，表明方法的实际应用价值。
A Bootstrap data expansion method based on RBF neural network and its application on IRSS reliability evaluation
TANG Shaomin1, LIU Guixiong1, LI Xiaobing2
1. School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou 510640, China;
2. CEPREI, Guangzhou 510610, China
Abstract: For high reliability and long-life products, their reliability test data samples are too few to carry out effective reliability assessment. A Bootstrap data expansion method based on RBF neural network was proposed address to the issue. In the method, RBF neural network was applied to catch the continuous distribution characteristics of original samples, and neighborhood function was used to create the network input set. Simulation results show that the distribution of extended sample obtained by this method is closer to its real distribution, and the extended sample get a wider range of values as well. The proposed method is applied to the pseudo-failure life distribution reliability evaluation of industrial robot servo system (IRSS), and the effective reliability evaluation results of IRSS obtained, which indicated the practical application value of the proposed method.
Keywords: radial basis function neural network;Bootstrap method;industrial robot servo system;reliability evaluation
2022, 48(11):22-26,53 收稿日期: 2022-06-25;收到修改稿日期: 2022-08-20
基金项目: 广东省高端装备制造计划项目(2017B090914003)
作者简介: 汤少敏（1987-），女，广东珠海市人，博士研究生，研究方向为智能化检测与仪器研究
参考文献
[1] 高攀东, 沈雪瑾, 陈晓阳, 等. 基于自助法的小样本Weibull分布可靠性分析[J]. 机械设计与研究, 2015, 31(2): 164-167
[2] 杨茜茜, 耿丽松, 张宇. 光纤陀螺冗余可修复系统可靠性评估[J]. 中国测试, 2022, 48(3): 150-156
[3] EFRON B. Bootstrap methods: Another look at the jackknife[J]. The Annals of Statistics, 1979, 7(1): 1-26
[4] 刘贤军, 孙远航, 王永松, 等. 基于多场耦合建模与Bootstrap方法的滑环可靠性评估[J]. 北京航空航天大学学报, 2019, 45(11): 2301-2311
[5] 许凌天, 沈雪瑾, 蒋爽, 等. 退化量有缺失的无失效小样本轴承可靠性评估[J]. 航空动力学报, 2020, 35(9): 1977-1987
[6] JIANG Q H, ZHU L L, SHU C, et al. An efficient multilayer RBF neural network and its application to regression problems[J]. Neural Computing & Applications, 2022, 34(6): 4133-4150
[7] CHEN Z Y, KUO R J. Combining SOM and evolutionary computation algorithms for RBF neural network training[J]. Journal of Intelligent Manufacturing, 2019, 30(3): 1137-54
[8] 汤少敏, 刘桂雄, 林志宇, 等. 工业机器人伺服系统测试技术发展与趋势[J]. 中国测试, 2019, 45(8): 1-7
[9] 庄东辰, 茆诗松. 退化数据统计分析[M]. 北京: 中国统计出版社, 2013.
