A Composite Failure Precursor for Condition Monitoring and Remaining Useful Life Prediction of Discrete Power Devices

Lubricating oil contains a lot of tribological information of the machine and plays an important role in machine health. Oil degrades with serving time and causes severe wear afterwards, which is a complex dynamic process, and difficult to be accurately described by a single property. Therefore, the main purpose of deterioration prediction is to estimate the remaining useful life that the oil can still fulfill its functions by analyzing oil condition monitoring data. With a large amount of oil condition monitoring data collected, a vector autoregressive model is applied to the original oil data to describe the dynamic deterioration process. Then dynamic principal component analysis, an effective dimensionality reduction method, is employed to obtain the principal components capturing the most information of the oil data. The proportional hazards model is then built to calculate the failure risk of the lubricating oil based on the condition monitoring information, where its baseline function represents the aging process assuming to follow the Weibull distribution and its positive link function represents the influence of covariates (the principal components) on the failure risk. Finally, the remaining useful life prediction of lubricating oil can be obtained by explicit formulas of the characteristics such as the conditional reliability function and the mean residual life function. This work provides an approach to assess the health of lubricating oil, and a guidance for oil maintenance strategy.

Download Full-text

Remaining useful life prediction methods for key structures of heavy-duty railway wagons based on condition monitoring data

10.22541/au.164041202.22151314/v1 ◽

2021 ◽

Author(s):

Chao Wang ◽

Tao Zhu ◽

Bing Yang ◽

Minxuan Yin ◽

Shoune Xiao ◽

...

Keyword(s):

Relative Error ◽

Condition Monitoring ◽

Delay Time ◽

Life Prediction ◽

Prediction Method ◽

Remaining Useful Life ◽

Monitoring Data ◽

Support Vector ◽

Heavy Duty ◽

Useful Life

To predict the remaining useful life for the key structures of heavy-duty railway wagons using condition monitoring data, methods for the coupler body with and without visible cracks were proposed. First, a method based on the delay time and hypothesis testing was proposed, considering the case without visible cracks in the coupler body. Then, for the case of visible cracks, methods based on a hypothetical distribution and support vector regression with the Kalman filter were proposed. Finally, by taking the coupler body monitoring data as an example, the prediction accuracies of the proposed methods were compared. The results indicated that the prediction method that only considers the common characteristics of the research objects had an average relative error of 57.56% for the coupler structure with a long lifespan. Considering the delay time of the current state of the structure and the assumed distribution prediction method, the relative error was reduced to 34.52%, and the remaining useful life prediction value fluctuated sharply with respect to the service mileage. On this basis, considering the performance degradation process of the structure, the change in the remaining useful life prediction value was smoother, and the relative error was 43.67%. The methods for predicting the remaining useful life of railway heavy-duty coupler bodies using condition monitoring data have important theoretical and practical value for improving vehicle safety, reducing maintenance costs, and accurately evaluating the remaining useful life.

Download Full-text