A variety of data-driven methods have been proposed to predict remaining useful life (RUL) of key component for rolling bearings. The accuracy of data-driven RUL prediction model largely depends on the extraction method of performance degradation features. The individual heterogeneity and working condition difference of rolling bearings lead to the different performance degradation curves of rolling bearings, which result in the mismatch between the established RUL prediction model by the training rolling bearings and the test rolling bearings. If a feature is found, which can reflect the consistency of the performance degradation curve of each rolling bearings, and give the indicator to determine the node and predictable interval of the declining period, the accuracy of the RUL prediction model will be improved. To solve this problem, a new feature extraction method based on the data-driven method, namely, Fitting Curve Derivative Method of Maximum Power Spectrum Density (FDMPD), is proposed to extract the performance degradation features of the same or similar rolling bearings from the historical state monitoring data in this article. The FDMPD can make the performance degradation feature curves of life cycle, which takes on consistency trend for different rolling bearings, and the starting point of the rolling bearings to enter the degenerating period is defined and the working stage of rolling bearings is divided. Based on this, the kernel extreme learning machine (KELM) and weight application to failure times (WAFT) are combined with FDMPD to establish a new RUL prediction model of rolling bearings, which can effectively realize the RUL prediction of rolling bearings. The whole life cycle data of rolling bearings are used to verify the validity of the RUL prediction model. The experimental results show that the established RUL prediction model can accurately predict the RUL of rolling bearings. It has the advantages of rapidity, stability, and applicability.

Feature Extraction for Data-Driven Remaining Useful Life Prediction of Rolling Bearings

Bearing fault diagnosis based on EMD and improved Chebyshev distance in SDP image

A comprehensive review on blade tip timing-based health monitoring: status and future

As one of the key components in mechanical systems, rotatory machine plays a significant role in safe and stable operation. Accurate prediction of the Remaining Useful Life (RUL) of rotatory machine contributes to realization of intelligent operation and maintenance for mechanical manufacturing. In order to overcome the limitations of traditional machine learning algorithms in dealing with complex nonlinear signals, a novel prediction framework for RUL of rotatory machine based on deep learning is proposed in this paper. One-dimensional convolutional neural network is utilized to extract local features from the original signal sequence. In addition, the proposed framework analyzes sensor signals and predicts RUL by combining Long Short-Term Memory (LSTM) network with attention mechanism. Multi-layer LSTM is set up to extract useful temporal features layer by layer and improve the robustness of the model, while attention mechanism is able to effectively solve the problem of information loss in the long-distance signal transmission of LSTM. Through the feature extraction of multi-layer LSTM and the strong supervision ability of attention mechanism, the RUL of rotatory machine can be accurately predicted. The experimental results show that the proposed method for RUL estimation is efficient and has higher prediction accuracy than the traditional machine learning algorithms.

/pdf/attention-based-lstm-network-for-rotatory-machine-remaining-zqwgn1xo50.pdf

Attention-Based LSTM Network for Rotatory Machine Remaining Useful Life Prediction

Blade tip timing (BTT) is an effective noncontact measurement technology for rotating blade health monitoring. However, due to the mismatching between the high-speed rotation and the limited amount of probes, the signal collected from the BTT system is severely undersampled, which induces the difficulty in feature extraction. Multiple signal classification (MUSIC) has the potential to overcome the undersampled problem once the probes are properly placed. Whereas, if traditional MUSIC is directly used in BTT, the accuracy of frequency identification cannot be high enough and the identified number of frequency components is also severely restrained. To address these two problems, an improved MUSIC is proposed as an alternative methodology to extract the blade vibration frequency for BTT. Based on the orthogonality of the signal subspace and the noise subspace from undersampled signal, the presented method can effectively identify the vibration frequency components from the undersampled signal of BTT.

An Improved Multiple Signal Classification for Nonuniform Sampling in Blade Tip Timing

Rolling element bearings (REBs) are usually considered among the most critical elements of rotating machines. Therefore, accurate prediction of remaining useful life (RUL) of REBs is a fundamental challenge to improve reliability of the machines. Vibration condition monitoring is the most popular method used for diagnosis of REBs and this is a motivating fact to use recorded vibration data in RUL prediction too. However, it is necessary to extract appropriate features from vibration signal that represent actual damage progress in the REB. In this paper, wavelet packet transform is used to extract signal features and artificial neural network is applied to estimate RUL of the REB. To obtain more accurate results, a method is proposed to find appropriate mother wavelet, optimal level and optimal node for signal decomposition. The desired features were extracted from the decomposed wavelet coefficients. To reduce random fluctuations, which is essential in real-life tests, a preprocessing algorithm was applied on the raw data. A multilayer perceptron neural network was selected and trained by preprocessed input data as well as non-processed input data, and results are compared. A series of accelerated life tests were conducted on a group of radially loaded bearings and vibration signals were acquired in whole life cycle of the tested REBs. Comparison of the experimental results with the output of the trained neural network shows enhanced prediction capability of the proposed method.

Estimation of Remaining Useful Life of Rolling Element Bearings Using Wavelet Packet Decomposition and Artificial Neural Network

Identification of Asynchronous Blade Vibration Parameters by Linear Regression of Blade Tip Timing Data

Envelope analysis is widely used in fault diagnosis of rolling element bearings (REBs). In envelope analysis, it is necessary to select a frequency band which is related to the resonance of the bea...

Rolling element bearing diagnosis using spectral kurtosis based on optimized impulse response wavelet

Selecting appropriate features from the vibration condition monitoring data of ball-bearings is one of the main challenges in the application of data-driven methods for remaining useful life predic...

Abbas Rohani Bastami

Papers

Estimation of Remaining Useful Life of Rolling Element Bearings Using Wavelet Packet Decomposition and Artificial Neural Network

Identification of Asynchronous Blade Vibration Parameters by Linear Regression of Blade Tip Timing Data

Rolling element bearing diagnosis using spectral kurtosis based on optimized impulse response wavelet

Remaining useful life prediction of ball-bearings based on high-frequency vibration features:

A comprehensive evaluation of the effect of defect size in rolling element bearings on the statistical features of the vibration signal