Rolling bearing fault diagnosis based on MEEMD sample entropy and SSA-SVM

Li, Xuguang; Fu, Liyou

doi:10.1088/1742-6596/2125/1/012003

Cited by 5 publications

(6 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is one of the common kernel learning methods. More and more scholars are using SVM for fatigue damage detection in bearings [19][20][21][22][23][24]. It is proved by the above scholars that the SVM algorithm can have an exciting effect on the detection of fatigue damage in bearings.…”

Section: Introductionmentioning

confidence: 99%

Data-Driven Fatigue Damage Monitoring and Early Warning Model for Bearings

Deng

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Since the manual extraction of features is not sufficient to accurately characterize the health status of rolling bearings, machine learning algorithms are gradually being used for fault diagnosis of bearings, which can adaptively learn the required features from the input data. In this paper, k -nearest neighbor, support vector machines, and convolutional neural networks are successfully applied to the fault diagnosis of bearings, for the benefit of achieving the detection and early warning of bearing fatigue damage. The original samples are segmented into semioverlapping samples. When using k -nearest neighbor and support vector machines as early warning models, we searched their hyperparameters with random search and grid search, and the results showed that support vector machines could achieve 87.1% of bearing detection accuracy and k -nearest neighbor could achieve 100% of detection accuracy. When convolutional neural networks are used as the early warning model, the accuracy can reach 99.75%.

show abstract

Section: Introductionmentioning

confidence: 99%

Data-Driven Fatigue Damage Monitoring and Early Warning Model for Bearings

Deng

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…When the signal sequence is not complex, its own signal similarity is high, and the corresponding sample entropy is small [30,31]. Li Xuguang [32] extracted fault features from the processed rolling bearing signals through MEEMD sample entropy and realized rolling bearing fault diagnosis. Zhang Decai [33] extracted gearbox fault features using Euclidean matrix sample entropy and realized gearbox composite fault diagnosis with a one-dimensional convolutional neural network.…”

Section: Literature Analysismentioning

confidence: 99%

Fault Diagnosis of Mine Truck Hub Drive System Based on LMD Multi-Component Sample Entropy Fusion and LS-SVM

Xu,

Li,

Zhang

et al. 2023

Actuators

View full text Add to dashboard Cite

As the main transportation equipment in ore mining, the wheel drive system of mining trucks plays a crucial role in the transportation capacity of mining trucks. The internal components of the hub drive system are mainly composed of bearings, gears, etc. The vibration signals caused during operation are nonlinear and nonstationary complex signals, and there may be more than one factor that causes faults, which causes certain difficulties for the fault diagnosis of the hub drive system. A fault diagnosis method based on local mean decomposition (LMD) multi-component sample entropy fusion and LS-SVM is proposed to address this issue. Firstly, the LMD method is used to decompose the vibration signals in different states to obtain a finite number of PF components. Then, based on the typical correlation analysis method, the distribution characteristics and correlation coefficients of vibration signals in the frequency domain under different states are calculated, and effective PF multi-component sample entropy features are constructed. Finally, the LS-SVM multi-fault classifier is used to train and test the extracted multi-component sample entropy features to verify the effectiveness of the method. The experimental results show that, even in small-sample data, the LMD multi-component sample entropy fusion and LS-SVM method can accurately extract fault features of vibration signals and complete classification, achieving fault diagnosis of wheel drive systems.

show abstract

“…Optimization algorithms, commonly utilized to determine optimal results of penalty factor c and kernel function parameter k p , include cross-validation and grid search method, genetic algorithm (GA), particle swarm optimization (PSO), 25 sparrow search algorithms (SAA), 26 and differential evolution-gray wolf algorithm (hybrid gray wolf optimization, HGWO). 27 However, these algorithms are prone to problems with local optimum or slow convergence speed in searching for optimal solutions, which in turn affects the prediction efficiency of SVR model.…”

Section: Svr Modelmentioning

confidence: 99%

“…Although remarkable achievements have been obtained by scholars in references, [13][14][15][16][17][18] difficulties still exist to construct a clear multifactor mathematical model using the conventional fatigue life estimation models, 19,20 as well as the prediction accuracy of the models needs to be further improved. With the advancement and popularization of machine learning (ML) algorithms, artificial intelligence methods are recently used in several studies to develop models for forecasting performances of materials and components including fatigue characteristics, [21][22][23][24] battery state of charge, 25 fault diagnosis, 26 karst tunnel water inrush, 27 airport taxiway planning and gate allocation, 28,29 and bearing performance. 30 Among them, the support vector regression (SVR) algorithm, which is based on support vector machines (SVM), has encouraging learning performance in solving the regression problem with small samples.…”

Section: Introductionmentioning

confidence: 99%

“…30 Among them, the support vector regression (SVR) algorithm, which is based on support vector machines (SVM), has encouraging learning performance in solving the regression problem with small samples. [25][26][27] The present study focuses on the intelligent prediction method for rubber fatigue life. The main contributions of this paper are summarized as follows.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent prediction of fatigue life of natural rubber considering strain ratio effect

Wang

Liu

2023

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

An intelligent prediction model of rubber fatigue life considering strain ratios based on the support vector regression (SVR) and an improved sparrow search algorithm (ISSA) is proposed. In order to solve the problem that traditional methods may lead to unsatisfactory prediction results, we establish a prediction model based on SVR. To further improve the prediction accuracy, we utilize the ISSA algorithm to optimize various hyper‐parameters in the model. Fatigue tests of filled natural rubber on dumbbell‐type specimens are performed and applied to verify the effectiveness of the proposed model. The results show that the ISSA optimized SVR (ISSA‐SVR) model is superior in terms of prediction accuracy, convergence speed, and stability compared with SVR models using the grid search or some standard optimization algorithms. Furthermore, comparisons of some published related models demonstrate that the ISSA‐SVR has the most accurate predictive results, which gather within 1.5 times the dispersion lines.

show abstract

Rolling bearing fault diagnosis based on MEEMD sample entropy and SSA-SVM

Cited by 5 publications

References 3 publications

Data-Driven Fatigue Damage Monitoring and Early Warning Model for Bearings

Data-Driven Fatigue Damage Monitoring and Early Warning Model for Bearings

Fault Diagnosis of Mine Truck Hub Drive System Based on LMD Multi-Component Sample Entropy Fusion and LS-SVM

Intelligent prediction of fatigue life of natural rubber considering strain ratio effect

Contact Info

Product

Resources

About