Abstract
Aiming at predicting the remaining useful life of key components of engineering equipment, a remaining useful life prediction method based on an intelligent product limit estimator is developed. The proposed approach can overcome the shortcoming that current life prediction methods require a large number of life data values, as well as condition monitoring data and life cycle data. Besides, to solve the problem of “completely truncated data” in the prediction of key components, the life estimation value of the predicted object is obtained by using the fitting residuals, and the survival probability of the predicted object in a period in the future is obtained. A case study on the spindle bearing of a certain type of water pump shows the effectiveness of the proposed approach.
Highlights
Once the key components of typical products fail or degenerate, the system function may be reduced or lost, or even lead to catastrophic accidents
Benkedjouh et al [9] used support vector regression (SVR) to map health indicators to nonlinear regression, and fitted the regression to power model for mechanical Remaining useful life (RUL) prediction; Liu et al [10] developed an improved probabilistic support vector machine (SVM) to predict the degradation process of nuclear power plant components; Fumeo et al [11] developed an online support vector machine model for bearing RUL prediction by balancing the accuracy and computational efficiency; Wang et al [12] used similarity-based method combined with relevance vector machine (RVM) sparse learning to predict the RUL of the machine
The prediction accuracy of typical bearing residual service life based on the intelligent product limit estimator method is higher than 85 % and the confidence is higher than 90 %
Summary
Once the key components of typical products fail or degenerate, the system function may be reduced or lost, or even lead to catastrophic accidents. The major task of Remaining useful life (RUL) prediction is to forecast the time left before the machinery losses its operation ability based on the condition monitoring information. A REMAINING USEFUL LIFE PREDICTION METHOD FOR ENGINEERING COMPONENTS BASED ON INTELLIGENT PRODUCT LIMIT ESTIMATOR. A spindle bearing of a certain type of water pump has demonstrated the effectiveness of the proposed approach
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
