GAN-LSTM Predictor for Failure Prognostics of Rolling Element Bearings

Abstract

Failure prognostics is the process of predicting the remaining useful life (RUL) of machine components, which is vital for the predictive maintenance of industrial machinery. This paper presents a new deep learning approach for failure prognostics of rolling element bearings based on a Long Short-Term Memory (LSTM) predictor trained simultaneously within a Generative Adversarial Network (GAN) architecture. The LSTM predictor takes the current and past observations of a well-defined health index as an input, uses those to forecast the future degradation trajectory, and then derives the RUL. Our proposed approach has three unique features: (1) Defining the bearing failure threshold by adopting an International Organization of Standardization (ISO) standard, making the approach industryrelevant; (2) Employing a GAN-based data augmentation technique to improve the accuracy and robustness of RUL prediction in cases where the deep learning model has access to only a small amount of training data; (3) Integrating the training process of the LSTM predictor within the GAN architecture. A joint training approach is utilized to ensure that the LSTM predictor model learns both the original and artificially generated data to capture the degradation trajectories. We utilize a publicly available accelerated run-to-failure dataset of rolling element bearings to assess the performance of the proposed approach. Results of a five-fold cross-validation study show that the integration of the LSTM predictor with GAN helps to decrease the average RUL prediction error by 29% over a simple LSTM model without GAN implementation.

Scalability, Explainability and Performance of Data-Driven Algorithms in Predicting the Remaining Useful Life: A Comprehensive Review

“…Several hybrid methods use different DL methods within the generator or discriminator of a GAN. Examples include using AEs [207], Adversarial AEs [105], AE-based DBN [136], Deep Convolutional GANs [227] or its conditional variant [108], LSTM [107], or BiLSTM and AEs [96,104] within a GAN.…”

“…[26,27,38,55,58,59,65,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128] …”

Scalability, Explainability and Performance of Data-Driven Algorithms in Predicting the Remaining Useful Life: A Comprehensive Review

“…Several hybrid methods use different DL methods within the generator or discriminator of a GAN. Examples include using AEs [223], Adversarial AEs [120], AE-based DBN [151], Deep Convolutional GANs [246] or its conditional variant [123], LSTM [122], or BiLSTM and AEs [111,119] within a GAN.…”

Improving Tool Wear Prediction with Synthetic Features from Conditional Generative Adversarial Networks

“…In the end, the authors demonstrated models trained with a mixture of real and realistic synthetic data exhibiting stronger prediction power in RUL estimation tasks for turbofan engines and lithium-ion battery systems. Recently, Lu et al proposed a jointly trainable GAN-LSTM predictor that significantly reduced RUL estimation errors for rolling element bearings [33].…”