Impact Statement:The damage of rolling bearing will bring great influence to industrial production process. However, the existing remaining useful life prediction methods for rolling bear...Show More
Abstract:
Remaining useful life (RUL) prediction for condition-based maintenance decision making plays a key role in prognostics and health management (PHM). Accurately predicting ...Show MoreMetadata
Impact Statement:
The damage of rolling bearing will bring great influence to industrial production process. However, the existing remaining useful life prediction methods for rolling bearing have a prediction error superposition problem that can affect the future prediction in multi-step prediction. The adversarial learning prognostics model proposed in this paper can overcome the problem. The proposed method uses long short-term memory network as generator to predict remaining useful life for rolling bearing, and uses auto-encoder as discriminator to estimate the prediction accuracy. The method will improve the multi-step prediction accuracy of remaining useful life for rolling bearing, and provides reliable and scientific strategy in prognostics and health management of mechatronics equipment.
Abstract:
Remaining useful life (RUL) prediction for condition-based maintenance decision making plays a key role in prognostics and health management (PHM). Accurately predicting RUL of the rotating components of complex machines becomes a challenging task for PHM. For many existing methods, the current prediction error of RUL prediction may be accumulated into the future predictions, and thus can lead to a prediction error superposition problem. In this article, the formation mechanism of prediction error superposition is analyzed, and for the first time a deep adversarial long short-term memory (LSTM) prognostic framework is proposed to overcome the major issue related to prediction error superposition. In the proposed framework, a generative adversarial network (GAN) architecture combining the LSTM network and autoencoder (AE) is investigated for bearing RUL monitoring. In the proposed deep adversarial learning prediction framework, due to the potential involvement of long-term and complex t...
Published in: IEEE Transactions on Artificial Intelligence ( Volume: 2, Issue: 4, August 2021)