Abstract
The prediction of remaining useful life (RUL) of mechanical equipment provides a timely understanding of the equipment degradation and is critical for predictive maintenance of the equipment. In recent years, the applications of deep learning (DL) methods to predict equipment RUL have attracted much attention. There are two major challenges when applying the DL methods for RUL prediction: (1) It is difficult to select the prediction model structure and hyperparameters such as network depth, learning rate, batch size, and etc. (2) The developed prediction model is domain dependent, i.e., it can only give good prediction performance in one data domain (one particular type of working conditions and fault modes). In order to meet the challenges, a novel RUL prediction method developed using a deep convolutional neural network (DCNN) combined with Bayesian optimization and adaptive batch normalization (AdaBN) is presented in this paper. The proposed RUL prediction model is validated by the turbofan engine degradation simulation dataset provided by NASA. The prediction results show that the proposed prediction model provides better prediction results than model structures obtained by random search and grid search. The results also show that the domain adaptation capability of the prediction model has been improved.
Highlights
In recent years, mechanical equipment has become more and more complicated with the development of new sciences and technologies
To address the two issues encountered in developing Deep learning (DL) based prediction methods mentioned above, this paper proposes a remaining useful life (RUL) prediction method based on deep convolutional neural network (DCNN) combined with Bayesian optimization [25] and adaptive batch normalization (AdaBN) algorithm
3) PREDICTION RESULTS IN DIFFERENT DATA DOMAINS The application of data-driven prediction methods does not require a deep understanding of the mechanical equipment, relying solely on data to develop a prediction model
Summary
Mechanical equipment has become more and more complicated with the development of new sciences and technologies. Among the DL based methods for mechanical equipment RUL prediction mentioned above, two important aspects related to model development need to be addressed: (1) selection of the model structure and hyperparameters (e.g. learning rate, batchsize, momentum etc.), and (2) domain adaptability of the developed model. When Gaussian priors are performed on n observation points, it is known D1:n = {x1:n,f (x1:n)}, and the function values f (x1:n) are obey to a multivariate normal distribution, i.e., f (x1:n) ∼ N (m(x1:n), K ). The optimization is achieved by continuously increasing the observation points and performing repeating the Gaussian process prior until the prediction model is close to the real function f (x). Where (·) is the cumulative distribution function of the standard normal, x+ is the point with the minimum f value among all observation points, and ξ is a trade-off parameter slightly greater than 0. The Gaussian process with 9 observation points selected by PI method can find the best point
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.
