Bearing is one of the most critical components in most electrical and power drives. Effective bearing fault diagnosis is important for keeping the electrical and power drives safe and operating normally. In the age of Internet of Things and Industrial 4.0, massive real-time data are collected from bearing health monitoring systems. Mechanical big data have the characteristics of large volume, diversity, and high velocity. There are two major problems in using the existing methods for bearing fault diagnosis with big data. The features are manually extracted relying on much prior knowledge about signal processing techniques and diagnostic expertise, and the used models have shallow architectures, limiting their capability in fault diagnosis. Effectively mining features from big data and accurately identifying the bearing health conditions with new advanced methods have become new issues. This paper presents a deep learning-based approach for bearing fault diagnosis. The presented approach preprocesses sensor signals using short-time Fourier transform (STFT). Based on a simple spectrum matrix obtained by STFT, an optimized deep learning structure, large memory storage retrieval (LAMSTAR) neural network, is built to diagnose the bearing faults. Acoustic emission signals acquired from a bearing test rig are used to validate the presented method. The validation results show the accurate classification performance on various bearing faults under different working conditions. The performance of the presented method is also compared with other effective bearing fault diagnosis methods reported in the literature. The comparison results have shown that the presented method gives much better diagnostic performance, even at relatively low rotating speeds.

In the age of Internet of Things and Industrial 4.0, prognostic and health management (PHM) systems are used to collect massive real-time data from mechanical equipment. PHM big data has the characteristics of large-volume, diversity, and high-velocity. Effectively mining features from such data and accurately predicting the remaining useful life (RUL) of the rotating components with new advanced methods become issues in PHM. Traditional data driven prognostics is based on shallow learning architectures, requires establishing explicit model equations and much prior knowledge about signal processing techniques and prognostic expertise, and therefore is limited in the age of big data. This paper presents a deep learning-based approach for RUL prediction of rotating components with big data. The presented approach is tested and validated using data collected from a gear test rig and bearing run-to-failure tests and compared with existing PHM methods. The test results show the promising RUL prediction performance of the deep learning-based approach.

Accurate and timely prediction of remaining useful life (RUL) of a machine enables us to make appropriate maintenance and logistic decisions. Data-driven RUL prediction methods are more attractive to researchers because they can be deployed more quickly and cheaply compared to other approaches. The existing deep neural network (DNN) models for RUL prediction are mostly based on single-path and top-down propagation. In order to improve the prognostic performance of the network, this paper proposes a directed acyclic graph (DAG) network that combines long short term memory (LSTM) and convolutional neural network (CNN) for RUL prediction. The existing prediction models use CNN to extract features and supply these features to LSTM for RUL prediction. Moreover, when a single time stamp is used as an input, padding the signals in the same training batch would affect the predictive ability of the developed model. To overcome this drawback, the method proposed in this paper combines CNN and LSTM for simultaneous feature extraction and RUL prediction. It generates a short-term sequence by sliding the time window (TW) with one step size. In addition, based on the degradation mechanism, the piece-wise RUL function is used instead of the traditional linear function. To validate the proposed RUL prediction model, the turbofan engine degradation simulation dataset provided by NASA is used. By comparing the existing methods using the same dataset, it can be concluded that the prediction model proposed in this paper gives a better RUL prediction performance.

In recent years, acoustic emission (AE) sensors and AE-based techniques have been developed and tested for gearbox fault diagnosis. In general, AE-based techniques require much higher sampling rates than vibration analysis-based techniques for gearbox fault diagnosis. Therefore, it is questionable whether an AE-based technique would give a better or at least the same performance as the vibration analysis-based techniques using the same sampling rate. To answer the question, this paper presents a comparative study for gearbox tooth damage level diagnostics using AE and vibration measurements, the first known attempt to compare the gearbox fault diagnostic performance of AE- and vibration analysis-based approaches using the same sampling rate. Partial tooth cut faults are seeded in a gearbox test rig and experimentally tested in a laboratory. Results have shown that the AE-based approach has the potential to differentiate gear tooth damage levels in comparison with the vibration-based approach. While vibration signals are easily affected by mechanical resonance, the AE signals show more stable performance.