Transfer Learning with Deep Recurrent Neural Networks for Remaining Useful Life Estimation

Abstract

Prognostics, such as remaining useful life (RUL) prediction, is a crucial task in condition-based maintenance. A major challenge in data-driven prognostics is the difficulty of obtaining a sufficient number of samples of failure progression. However, for traditional machine learning methods and deep neural networks, enough training data is a prerequisite to train good prediction models. In this work, we proposed a transfer learning algorithm based on Bi-directional Long Short-Term Memory (BLSTM) recurrent neural networks for RUL estimation, in which the models can be first trained on different but related datasets and then fine-tuned by the target dataset. Extensive experimental results show that transfer learning can in general improve the prediction models on the dataset with a small number of samples. There is one exception that when transferring from multi-type operating conditions to single operating conditions, transfer learning led to a worse result.

Remaining Useful Strength (RUS) Prediction of SiCf-SiCm Composite Materials Using Deep Learning and Acoustic Emission

“…The number of publications between 1997 and 2011 amount to 576 while the total count of publications between 2012 and 2016 is 854. Along with their increasing popularity, there is also an anticipation of those machinery prognostics techniques in the industry [2,3]. Their expected impact is meant to particularly maximize the operational availability, reduce maintenance costs, and improve system reliability and safety [1,2].…”

“…Along with their increasing popularity, there is also an anticipation of those machinery prognostics techniques in the industry [2,3]. Their expected impact is meant to particularly maximize the operational availability, reduce maintenance costs, and improve system reliability and safety [1,2]. An important application of machinery prognostics is the remaining useful life (RUL) prediction: the goal is to predict the time left before observing a failure in a given machine or system [3].…”

Research on a Tool Wear Monitoring Algorithm Based on Residual Dense Network

“…As a result, these networks are more concise and fast. The deep learning method has shown promising results in related areas of the PHM, and has been applied to fault diagnosis, equipment life prediction, and tool wear detection [16][17][18][19]. In [16] a bearing fault diagnosis method is proposed based on a fully connected competitive self-encoder.…”

“…The experimental results show that the methods using a two-layer network can obtain higher diagnostic accuracy under normal conditions and can also demonstrate better robustness than methods with deeper and more complicated network models. Zhang et al propose a transferring learning and Long Short-Term Memory (LSTM) based model for predicting the remaining life of equipment [18]. This research addresses the problem of a small sample size, due to the difficulty in acquiring the faulty data.…”

A Review of the Use of Artificial Neural Network Models for Energy and Reliability Prediction. A Study of the Solar PV, Hydraulic and Wind Energy Sources

“…New developments in prediction tools based on AI could be employed or combined with ANN models as the quantity and quality of data variables increase. As an example, the following machine learning techniques are the most recommended to be employed [103][104][105][106][107][108][109]: Bi-directional Long Short-Term Memory (BLSTM), Deep Learning and Neural Network, Extreme Machine Learning, SVM, T-Basts, Random Forest and Boosting.…”