We develop a novel deep learning framework to achieve highly-accurate machine fault diagnosis using transfer learning to enable and accelerate the training of deep neural network. Compared with existing methods, the proposed method is faster to train and more accurate. First, original sensor data are converted to images by conducting a Wavelet transformation to obtain time-frequency distributions. Next, a pre-trained network is used to extract lower level features. The labeled time-frequency images are then used to fine-tune the higher-levels of the neural network architecture. This paper creates a machine fault diagnosis pipeline and experiments are carried out to verify the effectiveness and generalization of the pipeline on three main mechanical datasets including induction motors, gearboxes, and bearings with sizes of 6,000, 9,000, and 5,000 time series samples, respectively. We achieve state-of-the-art results on each dataset, with most datasets showing test accuracy near 100%, and in the gearbox dataset, we achieve significant improvement from 94.8% to 99.64%. We created a repository including these datasets located at mlmechanics.ics.uci.edu.

In modern industries, machine health monitoring systems (MHMS) have been applied wildly with the goal of realizing predictive maintenance including failures tracking, downtime reduction, and assets preservation. In the era of big machinery data, data-driven MHMS have achieved remarkable results in the detection of faults after the occurrence of certain failures (diagnosis) and prediction of the future working conditions and the remaining useful life (prognosis). The numerical representation for raw sensory data is the key stone for various successful MHMS. Conventional methods are the labor-extensive as they usually depend on handcrafted features, which require expert knowledge. Inspired by the success of deep learning methods that redefine representation learning from raw data, we propose local feature-based gated recurrent unit (LFGRU) networks. It is a hybrid approach that combines handcrafted feature design with automatic feature learning for machine health monitoring. First, features from windows of input time series are extracted. Then, an enhanced bidirectional GRU network is designed and applied on the generated sequence of local features to learn the representation. A supervised learning layer is finally trained to predict machine condition. Experiments on three machine health monitoring tasks: tool wear prediction, gearbox fault diagnosis, and incipient bearing fault detection verify the effectiveness and generalization of the proposed LFGRU.

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.

For prognostics and health management (PHM) of mechanical systems, a core task is to predict machine remaining useful life (RUL). Currently, deep structures with automatic feature learning, such as long short-term memory (LSTM), have achieved great performances for RUL prediction. However, the conventional LSTM network only uses the learned features at last time step for regression or classification, which is not efficient. Besides, some handcrafted features with domain knowledge may convey additional information for the prediction of RUL. It is thus highly motivated to integrate both those handcrafted features and automatically learned features for RUL prediction. In this paper, we propose an attention based deep learning framework for machine RUL prediction. The LSTM network is employed to learn sequential features from raw sensory data. Meanwhile, the proposed attention mechanism is able to learn the importance of features and time steps, and assign larger weights to more important ones. Moreover, a feature fusion framework is developed to combine the handcrafted features with automatically learned features to boost the performance of RUL prediction. Extensive experiments have been conducted on two real datasets and experimental results demonstrate that our proposed approach outperforms the state-of-the-arts.

Convolutional neural network (CNN), with the ability of feature learning and nonlinear mapping, has demonstrated its effectiveness in prognostics and health management (PHM). However, an explanation on the physical meaning of a CNN architecture has rarely been studied. In this article, a novel wavelet-driven deep neural network, termed as WaveletKernelNet (WKN), is presented, where a continuous wavelet convolutional (CWConv) layer is designed to replace the first convolutional layer of the standard CNN. This enables the first CWConv layer to discover more meaningful kernels. Furthermore, only the scale parameter and translation parameter are directly learned from raw data at this CWConv layer. This provides a very effective way to obtain a customized kernel bank, specifically tuned for extracting defect-related impact component embedded in the vibration signal. In addition, three experimental studies using data from laboratory environment are carried out to verify the effectiveness of the proposed method for mechanical fault diagnosis. The experimental results show that the accuracy of the WKNs is higher than CNN by more than 10%, which indicate the importance of the designed CWConv layer. Besides, through theoretical analysis and feature map visualization, it is found that the WKNs are interpretable, have fewer parameters, and have the ability to converge faster within the same training epochs.