基于相关向量机模型的设备运行可靠性预测

Operational reliability prediction of equipment based on relevance vector machine

针对机械设备失效数据少、传统基于统计的可靠性评估方法不能有效评估设备可靠性的问题,引入运行可靠度的概念来描述设备运行状态,并提出了一种基于相关向量机的设备运行可靠性预测方法。该方法首先采用运行可靠性计算模型,建立特定特征指标与运行可靠性的关系;然后采用相关向量机预测不同时刻下特征指标的值及其概率密度函数,并将其输入到运行可靠性模型,计算获得其所对应的运行可靠度。将该方法应用到航空发动机转子轴承运行可靠性分析中,预测的轴承失效时间与实际失效时间误差<5%,证明该方法的有效性和合理性。

Due to lack of failure d a t a, traditional statistics-based reliability evaluation m e t h o d s cannot effectively evaluate the reliability of mechanical e q u i p m e n t. T h e operational reliability c oncept w a s introduced in this w o r k to describe the running condition of the equipment, a n d a prediction m e t h o d for the operational reliability b a s e d o n relevance vector machine （RVM ） was p r o p osed. In the m ethod, the operational reliability calculation m o d e l w a s a d o p t e d firstly to establish the relationship between status indicators of the e q u i p m e n t a n d the operational reliability, a n d then the relevance vector machine was introduced to predict the trend a n d the corresponding probability distribution function （ PDF ） of the status indicators. Finally, the predicted values a n d PDF of status indicators w e r e inputted into the operational reliability calculation model and the predicted operational reliability of the equipment was then obtained. The method was applied to the operational reliability evaluation of aero engine b e a rings, the result s h o w that the error between the predicted failure time and the actual failure time was within 5 % , which proves the rationality a n d effectiveness of the method.