scholarly journals Iterative variational mode decomposition and extreme learning machine for gearbox diagnosis based on vibration signals

2019 ◽  
Vol 13 (1) ◽  
pp. 4477-4492
Author(s):  
M. Firdaus Isham ◽  
M. Salman Leong ◽  
L. M. Hee ◽  
Z. A. B. Ahmad
Keyword(s):  
Signal Processing ◽  
Fault Diagnosis ◽  
Extreme Learning Machine ◽  
Processing Method ◽  
Mode Number ◽  
Variational Mode Decomposition ◽  
Vibration Signals ◽  
Signal Processing Method ◽  
Mode Decomposition ◽  
Learning Machine

Vibration-based monitoring and diagnosis provide an excellent and reliable monitoring strategies for maintaining and sustaining a million dollars of industrial assets. The signal processing method is one of the key elements in gearbox fault diagnosis for extracting most useful information from raw vibration signals. Variational mode decomposition (VMD) is one of the recent signal processing methods that helps to solve many limitations in traditional signal processing method. However, pre-determine the input parameters especially the mode number become a challenging task for using this method. Then, this study aims to propose an iterative approach for selecting the mode number for the VMD method by using the normalized mean value (NMV) plot. The NMV value is calculates based on the ratio of a summation of VMD modes and the input signals. The result shows that the proposed iterative VMD approach can select an accurate mode number for the VMD method. Then, the vibration signals decomposed into different VMD modes and used for gearbox fault diagnosis. Statistical features have been extracted from the selected VMD modes and pass into extreme learning machine (ELM) for fault classification. Iterative VMD-ELM provide significance improvement of about 20% higher accuracy in classification result as compared with EMD-ELM. Hence, this research study offers a new mean for gearbox diagnosis strategy.  

scholarly journals A Hydraulic Pump Fault Diagnosis Method Based on the Modified Ensemble Empirical Mode Decomposition and Wavelet Kernel Extreme Learning Machine Methods

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2599
Author(s):  
Zhenbao Li ◽  
Wanlu Jiang ◽  
Sheng Zhang ◽  
Yu Sun ◽  
Shuqing Zhang
Keyword(s):  
Fault Diagnosis ◽  
Extreme Learning Machine ◽  
Recognition Accuracy ◽  
Ensemble Empirical Mode Decomposition ◽  
Hydraulic Pump ◽  
Vibration Signals ◽  
Mode Decomposition ◽  
Diagnosis Method ◽  
Kernel Extreme Learning Machine ◽  
Learning Machine

To address the problem that the faults in axial piston pumps are complex and difficult to effectively diagnose, an integrated hydraulic pump fault diagnosis method based on the modified ensemble empirical mode decomposition (MEEMD), autoregressive (AR) spectrum energy, and wavelet kernel extreme learning machine (WKELM) methods is presented in this paper. First, the non-linear and non-stationary hydraulic pump vibration signals are decomposed into several intrinsic mode function (IMF) components by the MEEMD method. Next, AR spectrum analysis is performed for each IMF component, in order to extract the AR spectrum energy of each component as fault characteristics. Then, a hydraulic pump fault diagnosis model based on WKELM is built, in order to extract the features and diagnose faults of hydraulic pump vibration signals, for which the recognition accuracy reached 100%. Finally, the fault diagnosis effect of the hydraulic pump fault diagnosis method proposed in this paper is compared with BP neural network, support vector machine (SVM), and extreme learning machine (ELM) methods. The hydraulic pump fault diagnosis method presented in this paper can diagnose faults of single slipper wear, single slipper loosing and center spring wear type with 100% accuracy, and the fault diagnosis time is only 0.002 s. The results demonstrate that the integrated hydraulic pump fault diagnosis method based on MEEMD, AR spectrum, and WKELM methods has higher fault recognition accuracy and faster speed than existing alternatives.

scholarly journals Research on Multi-Domain Fault Diagnosis of Gearbox of Wind Turbine Based on Adaptive Variational Mode Decomposition and Extreme Learning Machine Algorithms

Energies ◽  
2020 ◽  
Vol 13 (6) ◽  
pp. 1375 ◽  
Author(s):  
Hui Li ◽  
Bangji Fan ◽  
Rong Jia ◽  
Fang Zhai ◽  
Liang Bai ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Extreme Learning Machine ◽  
Grey Wolf Optimizer ◽  
Mechanical Equipment ◽  
Variational Mode Decomposition ◽  
Time Frequency ◽  
Mode Decomposition ◽  
Fault Features ◽  
Frequency Domains ◽  
Learning Machine

Since variational mode decomposition (VMD) was proposed, it has been widely used in condition monitoring and fault diagnosis of mechanical equipment. However, the parameters K and α in the VMD algorithm need to be set before decomposition, which causes VMD to be unable to decompose adaptively and obtain the best result for signal decomposition. Therefore, this paper optimizes the VMD algorithm. On this basis, this paper also proposes a method of multi-domain feature extraction of signals and combines an extreme learning machine (ELM) to realize comprehensive and accurate fault diagnosis. First, VMD is optimized according to the improved grey wolf optimizer; second, the feature vectors of the time, frequency, and time-frequency domains are calculated, which are synthesized after dimensionality reduction; ultimately, the synthesized vectors are input into the ELM for training and classification. The experimental results show that the proposed method can decompose the signal adaptively, which produces the best decomposition parameters and results. Moreover, this method can extract the fault features of the signal more completely to realize accurate fault identification.

Rotor Complex Fault Vibration Analysis Based on Frequency Heterodyne EMD Method

2011 ◽  
Vol 199-200 ◽  
pp. 845-849 ◽  
Author(s):  
Hong Ying Hu ◽  
Er Bao ◽  
Jing Kang
Keyword(s):  
Signal Processing ◽  
Processing Method ◽  
Frequency Resolution ◽  
Vibration Signals ◽  
Signal Processing Method ◽  
Mode Decomposition ◽  
Complex Fault ◽  
Non Stationary Signal ◽  
Signal Processing Methods ◽  
Emd Method

Rotor Complex Fault Vibration signals are very hard to analysis since there are many frequencies lies in them. It needs new signal processing methods to deal with these problems. Empirical Mode Decomposition (EMD) is a non-stationary signal processing method developed recently. The frequency heterodyne EMD method can improve the frequency resolution of EMD by shifting the original frequencies to enlarge the frequencies ratio between components. It proves that the method can enhance the performance of EMD easily and effectively. The paper discusses the principle and steps of this method in detail and uses it to analyse rotor complex fault signals. The result shows that frequency heterodyne EMD method can separate different faults and detect the weaker faults in complex fault more effectively than that of normal EMD method.

scholarly journals The Novel Successive Variational Mode Decomposition and Weighted Regularized Extreme Learning Machine for Fault Diagnosis of Automobile Gearbox

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Yijiao Wang ◽  
Guoguang Zhou
Keyword(s):  
Fault Diagnosis ◽  
Extreme Learning Machine ◽  
The Novel ◽  
Variational Mode Decomposition ◽  
Mode Decomposition ◽  
Diagnosis Method ◽  
Diagnosis Accuracy ◽  
Nonparametric Kernel Density ◽  
Learning Machine ◽  
Nonparametric Kernel

In order to improve the diagnosis accuracies of the current diagnosis methods, a novel fault diagnosis method of automobile gearbox based on novel successive variational mode decomposition and weighted regularized extreme learning machine is presented for fault diagnosis of gearbox in this paper. The novel successive variational mode decomposition (SVMD) is presented to improve the traditional variational mode decomposition, which finds modes one after the other, and this succession helps increase convergence rate and also not extract the unwanted modes; weighted regularized extreme learning machine (WRELM) is presented to improve the traditional extreme learning machine, which uses the weight of each sample with the nonparametric kernel density estimation and can find the optimal weight for each sample. The test results indicate that the diagnosis accuracy of SVMD-WRELM for gearbox is better than that of VMD-WRELM, VMD-ELM.

Study on novel signal processing and simultaneous-fault diagnostic method for wind turbine

2019 ◽  
Vol 41 (14) ◽  
pp. 4100-4113
Author(s):  
Xian-Bo Wang ◽  
Pu Miao ◽  
Kun Zhang ◽  
Xiaoyuan Zhang ◽  
Jun Wang
Keyword(s):  
Signal Processing ◽  
Wind Turbine ◽  
Extreme Learning Machine ◽  
Feature Learning ◽  
Mode Decomposition ◽  
Vibrational Signals ◽  
Fault Diagnostic ◽  
Diagnostic Framework ◽  
Learning Machine ◽  
Signal Processing Methods

High-precision fault diagnosis is important for the widely installed complex industrial product, the wind turbine. However, intelligent monitoring is difficult due to the fuzzy boundaries and individual different variations of the unseen single or simultaneous-fault of such intricate equipment. To solve this problem, this study proposes an ensemble fault diagnostic framework for simultaneous and coupling failure. First, this paper develops novel signal processing methods for effective feature learning and mapping from the non-stationary and nonlinear raw vibrational signals. The adapted variational mode decomposition is introduced based on the particle swarm optimization that applies the minimum mean envelope entropy to optimize the parameters settings. Second, the novel ensemble extreme learning machine-based network is proposed to isolate the faults that applies one extreme learning machine network to count the number of fault scenarios, and the other one to identify the specific single or simultaneous-fault labels. With this scheme, the self-adaptive ensemble extreme learning machine-based fault diagnostic framework is more accurate and faster than the prevailing probabilistic classifier-based methods, as the proposed method does not rely on empirically specified decision-making threshold and generates all the candidate fault labels at the same time. Finally, this study builds the test platform and compares the overall results with the existing feature analysis methods and classifiers. The experimental results verify that the proposed framework detects both single and simultaneous-fault accurately and quickly.

scholarly journals Diesel Engine Valve Clearance Fault Diagnosis Based on Improved Variational Mode Decomposition and Bispectrum

Energies ◽  
2019 ◽  
Vol 12 (4) ◽  
pp. 661 ◽  
Author(s):  
Xiaoyang Bi ◽  
Shuqian Cao ◽  
Daming Zhang
Keyword(s):  
Fault Diagnosis ◽  
Diesel Engine ◽  
Frequency Domain ◽  
Time Domain ◽  
Frequency Domain Analysis ◽  
Variational Mode Decomposition ◽  
Vibration Signals ◽  
Engine Valve ◽  
Mode Decomposition ◽  
Reconstructed Signal

The evaluation and fault diagnosis of a diesel engine’s health conditions without disassembly are very important for diesel engine safe operation. Currently, the research on fault diagnosis has focused on the time domain or frequency domain processing of vibration signals. However, early fault signals are mostly weak energy signals, and the fault information cannot be completely extracted by time domain and frequency domain analysis. Thus, in this article, a novel fault diagnosis method of diesel engine valve clearance using the improved variational mode decomposition (VMD) and bispectrum algorithm is proposed. First, the experimental study was designed to obtain fault vibration signals. The improved VMD method by choosing the optimal decomposition layers is applied to denoise vibration signals. Then the bispectrum analysis of the reconstructed signal after VMD decomposition is carried out. The results show that bispectrum image under different working conditions exhibits obviously different characteristics respectively. At last, the diagonal projection method proposed in this paper was used to process the bispectrum image, and the fourth order cumulant is calculated. The calculation results show that three states of the valve clearance are successfully distinguished.

The Method Based on Pattern Filter for Sonnd & Vibration Signal

2013 ◽  
Vol 333-335 ◽  
pp. 526-530
Author(s):  
Miao Rong Lv ◽  
Bao Jian Wei ◽  
Jian Lu ◽  
Jian Bo Diao
Keyword(s):  
Signal Processing ◽  
Model Building ◽  
Fourier Method ◽  
Vibration Signal ◽  
Complete Separation ◽  
Processing Method ◽  
Signal Extraction ◽  
Filter Method ◽  
Vibration Signals ◽  
Signal Processing Method

The difficulty of the signal processing is not the acquisition of the signals, but how to get the reasonble interpretations from the signals. Since the 1960s, Wavelet Transform, Fast Fourier method and other theoryies have done some works by some innovative processing methods to achieve a breakthrough. But for their limitions, these methods can not achieve a complete separation if the there are two or more signals in one time domain or frequency domain. In this article, a new engineering signal processing method-pattern filter method has is introduced, by which the signal extraction, sepration and noise reduction can be achieved successfully. Experiments show that this method can not only make a reasonable separation of the various vibration signals, but also give the typical signal extractions and model building ways.

Sign in / Sign up

Export Citation Format

Share Document