scholarly journals Rolling Element Bearing Fault Time Series Prediction Using Optimized MCKD-LSTM Model

2021 ◽  
Author(s):  
Leilei Ma ◽  
Hong Jiang ◽  
Tongwei Ma ◽  
Xiangfeng Zhang ◽  
Lei Xia ◽  
...  
Keyword(s):  
Time Series ◽  
Short Term Memory ◽  
Time Series Prediction ◽  
Vibration Signal ◽  
Cuckoo Search ◽  
Rolling Element Bearing ◽  
Bearing Fault ◽  
Rolling Element ◽  
Element Bearing ◽  
Original Time

This paper realizes early bearing fault warning through bearing fault time series prediction, and proposes a bearing fault time series prediction model based on optimized maximum correlation kurtosis deconvolution (MCKD) and long short-term memory (LSTM) recurrent neural network to ensure bearings operation reliability. The model is based on lifecycle vibration signal of the bearing, to begin, the cuckoo search (CS) is utilized to optimize the parameter filter length L and deconvolution period T of MCKD, taking into account the influence and periodicity of the bearing time series, the fault impact component of the optimized MCKD deconvolution time series is improved. Then select the LSTM learning rate α depending on deconvolution time series. Finally, the dataset obtained through various preprocessing approaches are used to train and predict the LSTM model. The average prediction accuracy of the optimized MCKD-LSTM model is 26 percent higher than that of the original time series, proving the efficiency of this method, and the prediction results track the real fault data well, according to the XI'AN JIAOTONG University XJTU-SY bearing dataset.

Cyclic Spectrum Analysis on Rolling-Element Bearing with Inner-Race Point Defect

2011 ◽  
Vol 291-294 ◽  
pp. 1469-1473
Author(s):  
Wei Ke ◽  
Yong Xiang Zhang ◽  
Lin Li
Keyword(s):  
Point Defect ◽  
Signal To Noise Ratio ◽  
Vibration Signal ◽  
Rolling Element Bearing ◽  
Bearing Fault ◽  
Rolling Element ◽  
Element Bearing ◽  
Simulation Signal ◽  
Inner Race ◽  
Cyclic Spectrum

Vibration signal of rolling-element bearing is random cyclostationarity when a fault develops, the proper analysis of which can be used for condition monitor. Cyclic spectrum is a common cyclostationary analysis method and has a great many algorithms which have distinct efficiency in different application circumstance, two common algorithms (SSCA and FAM) are compared in the paper. The FAM is recommended to be used in diagnosing rolling-element bearing fault via calculation of simulation signal in different signal to noise ratio. The cyclic spectrum of practice signal of rolling-element bearing with inner-race point defect is analyzed and a new characteristic extraction method is put forward. The preferable result is acquired verify the correctness of the analysis and indicate that the cyclic spectrum is a robust method in diagnosing rolling-element bearing fault.

scholarly journals Rolling Element Bearing Fault Detection using Statistical Features and Ensemble Classifiers

2020 ◽  
Vol 9 (3) ◽  
pp. 350-358
Keyword(s):  
Machine Learning ◽  
Fault Diagnosis ◽  
Vibration Signal ◽  
Rolling Element Bearing ◽  
Machine Learning Techniques ◽  
Ensemble Classifiers ◽  
Statistical Features ◽  
Bearing Fault ◽  
Rolling Element ◽  
Element Bearing

Rolling element bearing health condition is monitored by analysing its vibration signature. Raw vibration signal picked up through suitably placed accelerometers is difficult to analyse hence many signal processing techniques have been proposed and developed by researchers to process the data for suitably extracting an effective signal feature set. Various machine learning techniques have been used for interpretation and accurate fault diagnosis using this extracted feature set. In this study “Empirical mode decomposition” is used for pre-processing the raw vibration data. Six “Statistical features” are extracted from the best Intrinsic mode function obtained through EMD and “Ensemble machine learning classifiers” are used for bearing fault diagnosis. A stacked ensemble of five classifiers is proposed for accurate fault diagnosis and results are compared with conventional ensemble classifiers to prove its effectiveness

scholarly journals A Novel Method for Adaptive Multiresonance Bands Detection Based on VMD and Using MTEO to Enhance Rolling Element Bearing Fault Diagnosis

2016 ◽  
Vol 2016 ◽  
pp. 1-20 ◽  
Author(s):  
Xingxing Jiang ◽  
Shunming Li ◽  
Chun Cheng
Keyword(s):  
Fault Diagnosis ◽  
Energy Operator ◽  
Vibration Signal ◽  
Rolling Element Bearing ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis ◽  
Teager Energy Operator ◽  
Rolling Element ◽  
Element Bearing ◽  
Teager Energy

Vibration signals of the defect rolling element bearings are usually immersed in strong background noise, which make it difficult to detect the incipient bearing defect. In our paper, the adaptive detection of the multiresonance bands in vibration signal is firstly considered based on variational mode decomposition (VMD). As a consequence, the novel method for enhancing rolling element bearing fault diagnosis is proposed. Specifically, the method is conducted by the following three steps. First, the VMD is introduced to decompose the raw vibration signal. Second, the one or more modes with the information of fault-related impulses are selected through the kurtosis index. Third, Multiresolution Teager Energy Operator (MTEO) is employed to extract the fault-related impulses hidden in the vibration signal and avoid the negative value phenomenon of Teager Energy Operator (TEO). Meanwhile, the physical meaning of MTEO is also discovered in this paper. In addition, an idea of combining the multiresonance bands is constructed to further enhance the fault-related impulses. The simulation studies and experimental verifications confirm that the proposed method is effective for identifying the multiresonance bands and enhancing rolling element bearing fault diagnosis by comparing with Hilbert transform, EMD-based demodulation, and fast Kurtogram analysis.

Rolling Element Bearing Fault Detection Using Redundant Second Generation Wavelet Packet Transform

2011 ◽  
Vol 199-200 ◽  
pp. 931-935 ◽  
Author(s):  
Ning Li ◽  
Rui Zhou
Keyword(s):  
Wavelet Transform ◽  
Fault Detection ◽  
Second Generation ◽  
Wavelet Packet ◽  
Vibration Signal ◽  
Rolling Element Bearing ◽  
Bearing Fault ◽  
Rolling Element ◽  
Element Bearing ◽  
Second Generation Wavelet

Wavelet transform has been widely used for the vibration signal based rolling element bearing fault detection. However, the problem of aliasing inhering in discrete wavelet transform restricts its further application in this field. To overcome this deficiency, a novel fault detection method for roll element bearing using redundant second generation wavelet packet transform (RSGWPT) is proposed. Because of the absence of the downsampling and upsampling operations in the redundant wavelet transform, the aliasing in each subband signal is alleviated. Consequently, the signal in each subband can be characterized by the extracted features more effectively. The proposed method is applied to analyze the vibration signal measured from a faulty bearing. Testing results confirm that the proposed method is effective in extracting weak fault feature from a complex background.

A new fault diagnosis model of rolling element bearing based on a recurrent neural network

2021 ◽  
pp. 095440892110644
Author(s):  
Xudong Song ◽  
Dajie Zhu ◽  
Shaocong Sun
Keyword(s):  
Fault Diagnosis ◽  
Short Term Memory ◽  
Rolling Element Bearing ◽  
Short Term ◽  
Term Memory ◽  
Bearing Fault ◽  
Rolling Element ◽  
Element Bearing ◽  
Long Short Term Memory ◽  
Gated Recurrent Unit

The rolling element bearing is an important part of mechanical equipment, it has various kinds of malfunctions, the location of the fault may occur in the inner ring, outer ring, or rolling element of the bearing. Therefore, traditional methods of classification are difficult to classify and identify effectively. To improve the accuracy of bearing fault diagnosis, the deep learning method is used to diagnose the fault of the rolling element bearing. In this paper, the long short-term memory and gated recurrent unit are combined to build a bearing fault diagnosis model. On the other hand, this paper adjusts the hidden layer structure and optimizes the network parameters to establish a better long short-term memory–gated recurrent unit–long short-term memory diagnostic model and classify the fault types of bearings with Softmax. The model proposed in this paper can effectively diagnose the bearing fault under the bearing data set of Case Western Reserve University and the University of Cincinnati. Compared with the traditional long short-term memory and the gated recurrent unit, the model proposed in this paper has high accuracy in fault diagnosis as well as certain reliability and generalization ability.

scholarly journals NEW APPROACH OF CLASSIFICATION OF ROLLING ELEMENT BEARING FAULT USING ARTIFICIAL NEURAL NETWORK

1970 ◽  
Vol 40 (2) ◽  
pp. 119-130 ◽  
Author(s):  
V. Hariharan ◽  
PSS. Srinivasan
Keyword(s):  
Neural Network ◽  
Time Domain ◽  
Vibration Signal ◽  
Rolling Element Bearing ◽  
Data Set ◽  
New Approach ◽  
Bearing Fault ◽  
Rolling Element ◽  
Element Bearing

The paper presents a new approach to the classification of rolling element bearing faults by implementing Artificial Neural Network. Diagnostics of rolling element bearing faults actually represents the problem of pattern classification and recognition, where the key step is feature extraction from the vibration signal. Characterization of each recorded vibration signal is performed by a combination of signal's time-varying statistical parameters and characteristic rolling element bearing fault frequency components obtained through the frequency spectrum analysis method. The experimental data is collected for four bearings at three different speeds. The sensor is located at three different positions for each bearing. Both time domain and frequency domain signals were measured. Thus the data was three time spectrums and three frequency spectrums for each speed for a bearing. The entire data set comprised of 72 (6 x 3 x 4) data. The time domain signal was comprised of 8192 samples and extracting these features from a huge data set was difficult. To overcome this difficulty the 8192 samples were split into 32 bins each containing 256 samples. Two Network RBFN and PNN are used to classify the bearing defects. The entire process of splitting and evaluating the seven features was coded in MATLAB.  From these seven features the most suitable features are for explaining the intensity of the defect is discussed.Key Words: Feature Extraction; Fault Frequencies; Roller Bearing; Bearing fault; Crest Factor; Variant;Radial Basis Function Network (RBFN); Probabilistic Neural Network (PNN)DOI: 10.3329/jme.v40i2.5353Journal of Mechanical Engineering, Vol. ME 40, No. 2, December 2009 119-130

Sign in / Sign up

Export Citation Format

Share Document