Learning to Monitor Machine Health with Convolutional Bi-Directional LSTM Networks

By Rui Zhao, Ruqiang Yan, Jinjiang Wang, Kezhi Mao. Italian National Conference on Sensors, 2017

691 citations recorded by the source corpus.

In modern manufacturing systems and industries, more and more research efforts have been made in developing effective machine health monitoring systems. Among various machine health monitoring approaches, data-driven methods are gaining in popularity due to the development of advanced sensing and data analytic techniques. However, considering the noise, varying length and irregular sampling behind sensory data, this kind of sequential data cannot be fed into classification and regression models directly. Therefore, previous work focuses on feature extraction/fusion methods requiring expensive human labor and high quality expert knowledge. With the development of deep learning methods in the last few years, which redefine representation learning from raw data, a deep neural network structure named Convolutional Bi-directional Long Short-Term Memory networks (CBLSTM) has been designed here to address raw sensory data. CBLSTM firstly uses CNN to extract local features that are robust and informative from the sequential input. Then, bi-directional LSTM is introduced to encode temporal information. Long Short-Term Memory networks (LSTMs) are able to capture long-term dependencies and model sequential data, and the bi-directional structure enables the capture of past and future contexts. Stacked, fully-connected layers and the linear regression layer are built on top of bi-directional LSTMs to predict the target value. Here, a real-life tool wear test is introduced, and our proposed CBLSTM is able to predict the actual tool wear based on raw sensory data. The experimental results have shown that our model is able to outperform several state-of-the-art baseline methods.

Subfields: Artificial Intelligence, Control and Systems Engineering, Industrial and Manufacturing Engineering

View Paper: https://www.semanticscholar.org/paper/117fcfef38aa4641ae33e2605dc35013fc908719

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Control and Systems Engineering

In Industrial and Manufacturing Engineering

Citations in the corpus

Potential, challenges and future directions for deep learning in prognostics and health management applications (2020, methodology): “Recurrent neural networks (Hopfield, 1982; Rumelhart et al., 1988; Graves et al., 2013; Graves, 2013, especially LSTM (Gers, 1999; Graves and Schmidhuber, 2005) networks have been widely used for PHM applications (Yuan et al., 2016; Malhotra et al., 2016; Zhao et al., 2016, 2017; Wu et al., 2018).”
Machine Health Monitoring Using Local Feature-Based Gated Recurrent Unit Networks (2018, methodology): “Gated recurrent units were proposed to relief the problem of gradient exploding or vanishing in recurrent neural networks (RNN) with a controlled model complexity compared to another RNN variant: long-short term memory network [24]–[26].”
Fusing Physics-based and Deep Learning Models for Prognostics (2020, background): “A variety of supervised and semi-supervised deep learning models have shown promising performance in estimating the RUL from sensor data [5, 6, 7, 8, 9] for various prognostics benchmark problems [10, 11].”
A Bidirectional LSTM Prognostics Method Under Multiple Operational Conditions (2019, background): “be directly learned by means of the LSTM model without multidomain knowledge of feature extraction and selection [23].”
Predicting residential energy consumption using CNN-LSTM neural networks (2019, background): “designed the convolutional bi-directional long short-term memory network by mechanical health monitoring technique to predict tool wear [22].”