A Bayesian Optimization AdaBN-DCNN Method With Self-Optimized Structure and Hyperparameters for Domain Adaptation Remaining Useful Life Prediction

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. INDEX TERMS Remaining useful life prediction, Bayesian optimization, adaptive batch normalization, domain adaptation.

A probabilistic Bayesian recurrent neural network for remaining useful life prognostics considering epistemic and aleatory uncertainties

“…In particular, four deep learning-based models are selected for performance benchmarking: a multi-objective deep belief networks ensemble (MODBNE) model uses multiple object evolutionary algorithm (MOEA) to train simultaneously many deep belief networks 46 ; a deep convolutional neural network (DCNN) developed uses many layers of CNNs to process the data and extract more complex features 49 ; a deep LSTM (DLSTM) model uses many stacks of LSTM to train a deep learning model 50 ; and a domain adaptive CNN (AdaBN-CNN) uses batch normalization to adapt the domain of the prediction allowing the network to use one dataset and test on another by the application of two different CNNs. 51 Table 8 summarizes the results retrieved from the four above-mentioned models as well as the results from the proposed probabilistic Bayesian RNN: probabilistic Bayesian LSTM for FD001, probabilistic Bayesian VRNN for FD002, probabilistic Bayesian GRU for FD003, and probabilistic Bayesian VRNN for FD004. The best result with the lowest RMSE value for each dataset is highlighted in bold.…”

Using Data From Similar Systems for Data-Driven Condition Diagnosis and Prognosis of Engineering Systems: A Review and an Outline of Future Research Challenges

“…Specifically, a network is first trained using the labeled source data and then transferred to the target domain by adjusting the BN statistics. There are applications of AdaBN in PHM, e.g., on condition diagnosis of bearings and gearboxes [50], [268] and on RUL prognosis of aircraft engines [295].…”

A Systematic Literature Review on Transfer Learning for Predictive Maintenance in Industry 4.0

“…12, only a few studies have been devoted to a deeper understanding of the above-mentioned TLRM scenario, and its related issues, via TL. For instance, with the aim of identifying the health conditions of Scenario References TIM [146], [148], [112], [28], [182], [29], [30], [31], [149], [147], [32], [150], [33], [84], [34], [183], [36], [37], [38], [196], [155], [40], [35], [157], [41], [25], [42], [159], [85], [43], [60], [46], [48], [49], [65], [190], [86], [87], [89], [50], [51], [52], [56], [81], [92], [58], [162],…”