无失效转向架侧架贝叶斯可靠性评估方法  

Reliability Evaluation of Zero Failure Bogie Side Frame Based on Bayesian Method

作　　者：王洪昆 操琴 蒋增强[2] WANG Hongkun;CAO Qin;JIANG Zengqiang(Shenhua Railway Freight Transport Co.LTD,Beijing 100044,China;不详)

机构地区：[1]神华铁路货车运输有限责任公司,北京100011 [2]北京交通大学机械与电子控制工程学院,北京100044

出　　处：《武汉理工大学学报（信息与管理工程版）》2021年第4期346-351,共6页Journal of Wuhan University of Technology：Information & Management Engineering

基　　金：中央高校基本科研业务费专项资金项目(2020JBM051).

摘　　要：针对高可靠性零部件,在无失效数据情况下,以C80货车K6型转向架侧架为研究对象进行可靠性评估。在期望贝叶斯估计法与参数Bootstrap法的框架下,结合加权最小二乘法、蒙特卡洛仿真等技术,深入讨论期望贝叶斯模型中超参数选取与分布形式、参数Bootstrap重抽样样本量等对评估结果的影响。通过实例研究对比了所提出模型与传统的置信限法和固定超参数取值的期望贝叶斯估计模型的区别,分析了超参数选取对可靠性评估的影响,丰富了无失效数据情况下的可靠性评估方法。This paper focuses on the reliability evaluation issue of high-reliability components,such as the K6 bogie side frame of the C80 freight car,under zero failure scenario.Based on the framework of expected Bayesian estimation method and parametric Bootstrap method,this paper discussed the influence of hyperparameter selection,distribution form,parameter Bootstrap resample sample size on the evaluation results.During this process,weighted least squares method,Monte Carlo simulation and other technologies are employed.A case study is conducted to analyze the differences among the proposed model,the traditional confidence limit method,and the expected Bayesian estimation model with fixed hyperparameter values.This paper analyzes the influence of hyperparameter selection on reliability evaluation,enriches the reliability evaluation methods under the condition of no failure data.

关 键 词：可靠性评估 无失效数据 期望贝叶斯估计法 侧架 参数Bootstrap方法 

分 类 号：U270.35[机械工程—车辆工程]