Ruqiang Yan

Wavelets for fault diagnosis of rotary machines: A review with applications

Over the last 20 years, particularly in last 10 years, great progress has been made in the theory and applications of wavelets and many publications have been seen in the field of fault diagnosis. This paper attempts to provide a review on recent applications of the wavelets with focus on rotary machine fault diagnosis. After brief introduction of the theoretical background on both classical wavelet transform and second generation wavelet transform, applications of wavelets in rotary machine fault diagnosis are summarized according to the following categories: continuous wavelet transform-based fault diagnosis, discrete wavelet transform-based fault diagnosis, wavelet packet transform-based fault diagnosis, and second generation wavelet transform-based fault diagnosis. In addition, some new research trends, including wavelet finite element method, dual-tree complex wavelet transform, wavelet function selection, new wavelet function design, and multi-wavelets that advance the development of wavelet-based fault diagnosis are also discussed.

Hilbert–Huang Transform-Based Vibration Signal Analysis for Machine Health Monitoring

This paper presents a signal analysis technique for machine health monitoring based on the Hilbert-Huang Transform (HHT). The HHT represents a time-dependent series in a two-dimensional (2-D) time-frequency domain by extracting instantaneous frequency components within the signal through an Empirical Mode Decomposition (EMD) process. The analytical background of the HHT is introduced, based on a synthetic analytic signal, and its effectiveness is experimentally evaluated using vibration signals measured on a test bearing. The results demonstrate that HHT is suited for capturing transient events in dynamic systems such as the propagation of structural defects in a rolling bearing, thus providing a viable signal processing tool for machine health monitoring

Energy-Aware Sensor Node Design With Its Application in Wireless Sensor Networks

Energy consumption remains as a major obstacle for full deployment and exploitation of wireless sensor network (WSN) technology nowadays. This paper presents the design and implementation of an energy-aware sensor node, which can help in constructing energy-efficient WSNs. An energy-efficient strategy, which aims at minimizing energy consumption from both the sensor node level and the network level in a WSN, is proposed. To minimize the communication energy consumption of the sensor node, the distance between the transmitter and the receiver is estimated before available transmission, and then, the lowest transmission power needed to transmit the measurement data is calculated and determined. The sensor nodes are also set to sleep mode between two consecutive measurements for energy saving in normal operating conditions. Furthermore, energy saving can be achieved by estimating the energy consumption within the whole network under different network configurations and then by choosing the most energy-efficient one.

Complexity as a measure for machine health evaluation

This paper presents a machine health evaluation technique using the Lempel-Ziv complexity as a numerical measure. Comparing to conventional techniques such as spectral and time-frequency analysis, the presented approach does not require a linear transfer function of the physical system to be evaluated, and is thus suited for the condition monitoring of machine systems under varying operation and loading conditions. Theoretical foundation of the technique is introduced, and its performance is investigated through experimental study of realistic vibration signals measured from a rolling bearing system. The results demonstrated that complexity provides an effective measure for machine health condition evaluation.

Energy-Based Feature Extraction for Defect Diagnosis in Rotary Machines

This paper presents an energy-based approach to defect diagnosis in rotary machines and machine components, which enhances the ability of the continuous wavelet transform in feature extraction from vibration signals. Specifically, the energy content of the wavelet coefficients of vibration signal measured on rolling bearings has been evaluated for selecting appropriate base wavelet and decomposition scale such that identification of defect-induced signal features is significantly improved. Through subsequent envelope spectral analysis of the extracted signal features, the location of structural defect in the bearing being monitored can be identified. An experimental study performed on two ball bearings has shown that the developed approach is more effective in diagnosing bearing defects than using the traditional techniques.

Prognosis of Defect Propagation Based on Recurrent Neural Networks

Incremental training is commonly applied to training recurrent neural networks (RNNs) for applications involving prognosis. As the number of prognostic time-step increases, the accuracy of prognosis generally decreases, as often seen in long-term prognosis. Revision of the training techniques is therefore necessary to improve the accuracy in long-term prognosis. This paper presents a competitive learning-based approach to long-term prognosis of machine health status. Specifically, vibration signals from a defect-seeded rolling bearing are preprocessed using continuous wavelet transform (CWT). Statistical parameters computed from both the raw data and the preprocessed data are then utilized as candidate inputs to an RNN. Based on the principle of competitive learning, input data were clustered for effective representation of similar stages of defect propagation of the bearing being monitored. Analysis has shown that the developed technique is more accurate in predicting bearing defect progression than the incremental training technique.

A Tour of the Tour of the Hilbert-Huang Transform: An Empirical Tool for Signal Analysis

The HHT provides an alternative tool for signal analysis. Case studies in applying the HHT technique for bearing degradation monitoring and machine tool breakage detection have demonstrated its effectiveness for revealing the non-stationary and non-linear features hidden in dynamic signals. In addition to the application illustrated in this article, the HHT technique has shown to be effective in other applications, such as biomedical engineering [8], [9], system identification [10], [11], environmental monitoring [12], or financial analysis [13]. Because of its empirical nature, rigorous mathematical proof of this technique has remained an active research topic. More interesting reports are to be expected on the application of this technique for solving various types of real-world problems.

BASE WAVELET SELECTION FOR BEARING VIBRATION SIGNAL ANALYSIS

A critical issue to ensuring the effectiveness of wavelet transform in machine condition monitoring and health diagnosis is the choice of the most suited base wavelet for signal decomposition and feature extraction. This paper addresses this issue by introducing a quantitative measure to select an appropriate base wavelet for analyzing vibration signals measured on rotary mechanical systems. Specifically, the measure based on energy-to-Shannon entropy ratio has been investigated. Both the simulated Gaussian-modulated sinusoidal signal and an actual ball bearing vibration signal have been used to evaluate the effectiveness of the developed measure on base wavelet selection. Experimental results demonstrate that the wavelet selected using the developed measure is better suited than other wavelets in diagnosing structural defects in the bearing. The method developed provides systematic guidance in wavelet selection.

Non-stationary signal processing for bearing health monitoring

Signals generated by transient vibrations in rolling bearings due to structural defects are non-stationary in nature, and reflect upon the operation condition of the bearing. Consequently, effective processing of non-stationary signals is critical to bearing health monitoring. This paper presents a comparative study of four representative time-frequency analysis techniques commonly employed for non-stationary signal processing. The analytical framework of the short-time Fourier transform, wavelet transform, wavelet packet transform, and Hilbert-Huang transform are first presented. The effectiveness of each technique in detecting transient features from a time-varying signal is then examined, using an analytically formulated test signal. Subsequently, the performance of each technique is experimentally evaluated, using realistic vibration signals measured from a bearing test system. The results demonstrate that selecting appropriate signal processing technique can significantly affect defect identification and consequently, improve the reliability of bearing health monitoring.

EOG artifact correction from EEG recording using stationary subspace analysis and empirical mode decomposition.

Ocular contamination of EEG data is an important and very common problem in the diagnosis of neurobiological events. An effective approach is proposed in this paper to remove ocular artifacts from the raw EEG recording. First, it conducts the blind source separation on the raw EEG recording by the stationary subspace analysis, which can concentrate artifacts in fewer components than the representative blind source separation methods. Next, to recover the neural information that has leaked into the artifactual components, the adaptive signal decomposition technique EMD is applied to denoise the components. Finally, the artifact-only components are projected back to be subtracted from EEG signals to get the clean EEG data. The experimental results on both the artificially contaminated EEG data and publicly available real EEG data have demonstrated the effectiveness of the proposed method, in particular for the cases where limited number of electrodes are used for the recording, as well as when the artifact contaminated signal is highly non-stationary and the underlying sources cannot be assumed to be independent or uncorrelated.