A Parameter-Adaptive VME Method Based on Particle Swarm Optimization for Bearing Fault Diagnosis

Zhong, Xianyou; Xia, Tianyi; Mei, Quan

doi:10.1007/s40799-022-00553-w

Cited by 9 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3 , firstly, power system fault data is input, and the input data is denoised by Variational Mode Decomposition (VMD) 25 . Then, the parameters of DBN 26 and PSO algorithm 27 are initialized. The model takes the accuracy of fault prediction as the fitness function of PSO algorithm to guide it to search for individual and global optimal solutions.…”

Section: Methodsmentioning

confidence: 99%

ESG guidance and artificial intelligence support for power systems analytics in the energy industry

Li,

Zou,

Zeng

et al. 2024

Sci Rep

View full text Add to dashboard Cite

In order to increase the precision and effectiveness of power system analysis and fault diagnosis, this study aims to assess the power systems in the energy sector while utilizing artificial intelligence (AI) and environmental social governance (ESG). First, the ESG framework is presented in this study to fully account for the effects of the power system on the environment, society, and governance. Second, to coordinate the operation of various components and guarantee the balance and security of the power system, the CNN-BiLSTM power load demand forecasting model is built by merging convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM). Lastly, the particle swarm optimization (PSO) algorithm is used to introduce and optimize the deep belief network (DBN), and a power grid fault diagnostic model is implemented using the PSO technique and DBN. The model’s performance is assessed through experimentation. The outcomes demonstrate how the CNN-BiLSTM algorithm significantly increases forecasting accuracy while overcoming the drawback of just having one dimension of power load data. The values of 0.054, 0.076, and 0.102, respectively, are the root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). Effective processing of large-scale nonlinear data is achieved in the area of power grid fault diagnosis, resulting in prediction accuracy of 96.22% and prediction time of only 129.94 s. This is clearly better than other algorithms and increases fault prediction efficiency and accuracy. Consequently, the model presented in this study not only produces impressive results in fault diagnosis and load demand forecasting, but also advances the field of power system analysis in the energy industry and offers a significant amount of support for the sustainable and intelligent growth of the energy industry.

show abstract

Section: Methodsmentioning

confidence: 99%

ESG guidance and artificial intelligence support for power systems analytics in the energy industry

Li,

Zou,

Zeng

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…To further show the effectiveness and superiority of the proposed method in extracting bearing fault signatures, we conducted the comparisons among the proposed method and several representative methods (i.e., GWO–VME, PSO–VME, 42,43 grasshopper optimization algorithm (GOA)–VMD, 58 and fast kurtogram 11 ). The details and results of comparison are as follows:…”

Section: Simulation Analysismentioning

confidence: 99%

“…For instance, Pang et al 42 adopted the particle swarm optimization (PSO) with a new index named ensemble impulsiveness and cyclostationarity to automatically determine the optimal parameters of VME. Zhong et al 43 proposed a parameter-adaptive VME method, where a comprehensive index (L-KCIE) consisting of correlation coefficient, L-Kurtosis, and information entropy is regarded as the fitness function of PSO to search the optimal parameters of VME. Guo et al 44 combined short-time Fourier transform with a new index named the standard deviation of differential values of envelope maxima positions (SDE) to choose the penalty factor and center-frequency in VME.…”

Section: Introductionmentioning

confidence: 99%

An adaptive variational mode extraction method based on multi-domain and multi-objective optimization for bearing fault diagnosis

Yan

Yuen

et al. 2022

Structural Health Monitoring

View full text Add to dashboard Cite

When a local fault in the rolling element bearing appears during operational running, the induced bearing vibration signal is essentially equivalent to a mixed multi-component signal, which usually includes multiple frequency components (e.g., periodic impulses, random impulses, discrete harmonics, and heavy environmental noise). This indicates that it is difficult to detect the weak periodic impulses related to bearing faults by traditional signal processing methods. Variational mode extraction (VME) as a new signal processing method with band-pass filtering properties can separate the desired periodic impulse component from the mixed multi-component signal due to its similar basis as the popular variational mode decomposition (VMD). However, the filtering performance of VME is significantly influenced by two parameters (i.e., penalty factor and center-frequency). To address this issue, all the previous work focused on single-domain and single-objective parameter optimization from the filtering signal or its envelope, whereas the objective function with a single-criterion cannot depict bearing fault signatures from the impulsiveness and cyclostationarity simultaneously in general cases. Therefore, to improve the bearing fault feature extraction ability and avoid the problem of artificial parameter selection of VME, this paper proposes an adaptive variational mode extraction method based on multi-domain and multi-objective optimization (AVME-MDMO), in which two key parameters of VME are automatically determined by multi-objective gray wolf optimizer (MOGWO) with a novel multi-objective function named integrated measure of sparsity-impact (IMSI) of square envelope (SE) and square envelope spectrum (SES). As a result, the optimal VME is employed to obtain the specific mode component and its corresponding SES for achieving bearing fault diagnosis. The effectiveness of the proposed method has been validated on simulation signal and experiment data of rolling element bearing. Besides, the comparison results demonstrate its superiority and robustness in excavating fault signatures over the VME or VMD with single-objective function, and the fast kurtogram.

show abstract

Spectral structure inducing efficient variational model for enhancing bearing fault feature

Wang,

Jiang,

Song

et al. 2024

Signal Processing

View full text Add to dashboard Cite

A Parameter-Adaptive VME Method Based on Particle Swarm Optimization for Bearing Fault Diagnosis

Cited by 9 publications

References 33 publications

ESG guidance and artificial intelligence support for power systems analytics in the energy industry

ESG guidance and artificial intelligence support for power systems analytics in the energy industry

An adaptive variational mode extraction method based on multi-domain and multi-objective optimization for bearing fault diagnosis

Spectral structure inducing efficient variational model for enhancing bearing fault feature

Contact Info

Product

Resources

About