Acoustic Fault Diagnosis of Rotor Bearing System

Liu, Yuwei; Cheng, Yuqiang; Zhang, Zhenzhen; Wu, Jianjun

doi:10.1155/2022/8028599

Cited by 10 publications

(9 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The greater the amount of information a signal contains, the higher its information entropy value becomes, increasing the likelihood of it encompassing extensive failure characteristic information. 24 Conversely, if a signal contains less information, its information entropy value will be smaller, and it will contain less failure information. In instances of compound failures in bearings, the impact features present within the signal tend to be more pronounced.…”

Section: Introductionmentioning

confidence: 99%

A failure diagnosis method of ball bearing based on optimized multiscale variational modal extraction with synchro squeezing transformation

Li,

Yu,

et al. 2024

Noise & Vibration Worldwide

View full text Add to dashboard Cite

When a compound failure occurs in a bearing, the failure information included in vibration signals is featured by being weak, complex and combined. This fact makes it difficult to identify a compound failure precisely. Variational mode extraction (VME) solves the problem of variational mode decomposition (VMD) in being difficult to determine the number of decomposition layers and has certain applications in the identification of bearing failures. However, the initial expected central frequency of VME and option of penalty factor is crucial to the extraction of expected mode. To precisely determine the central frequency and penalty factor of VME and fulfill the correct extraction of feature information of compound failures in bearing, the paper has proposed a method based on synchro squeezing transform (SST) and information entropy to adaptively determine the parameters in VME (SST-VME). Firstly, SST is used to make time-frequency analysis of original vibration signals and characteristic frequency bands with larger energy are chosen from time-frequency spectrum to adaptively determine the expected central frequency of VME. Secondly, as information entropy has representation capacity for information included in the signal, penalty factor of VME was adaptively determined according to information entropy. Thirdly, original signals were subjected to VME according to expected central frequency and penalty factor adaptively determined; the expectation mode obtained was denoised by singular value decomposition algorithm. Finally, the type of compound failures of bearing is determined according to the frequency spectrum of denoised signals. To verify the effectiveness of proposed method, a comparison with VMD algorithm is conducted. As indicated by the result, the proposed method is more precise and comprehensive than VMD algorithm to extract the feature information corresponding to compound faults of bearing, and thereby correctly determines the type of compound failures.

show abstract

Section: Introductionmentioning

confidence: 99%

A failure diagnosis method of ball bearing based on optimized multiscale variational modal extraction with synchro squeezing transformation

Li,

Yu,

et al. 2024

Noise & Vibration Worldwide

View full text Add to dashboard Cite

show abstract

“…The vibration signal [3][4][5] found in numerous pieces of literature is used to indicate the working condition for fault diagnosis. Moreover, the diagnosis can also be achieved by sound signals [6], acoustic emission signals [7], or abrasive grains in lubricant oil [8].…”

Section: Introductionmentioning

confidence: 99%

SWT-KELM-based rolling bearing fault diagnosis method under noise conditions with different SNRs

Wang¹,

Ye²,

Jiang³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

Most existing studies realize bearing fault diagnosis tasks in labs with weak noise. However, field noise is so heavy under actual conditions that some methods may suffer from degradation or failure. To solve this problem, a fault diagnosis framework is proposed based on synchrosqueezing wavelet transform and kernel extreme learning machine (SWT-KELM). First, vibration signals are collected, and white Gaussian noise is added. Second, SWT is employed for signal decomposition in the time-frequency domain, and inverse SWT (ISWT) is applied for sub-signal reconstruction. Sub-signals with high correlation coefficients are selected for further feature extraction, specifically by singular value decomposition (SVD) to obtain singular values as the fault feature. Third, the KELM model, in which the beetle antennae search algorithm (BAS) is employed for parameters optimization, is constructed to classify the faults. For verification, the proposed method is implemented on the Case Western Reserve University (CWRU) dataset and Lab-625 dataset, and the results show that it maintains satisfactory outcomes on original and noise-contaminated data. Specifically, under noise conditions, the accuracies of the two datasets average at 96% and 83%, respectively, indicating the robustness and generalization of the method compared to other methods.

show abstract

“…ese strategies can enhance the algorithm's global and local search capabilities, with the disadvantage that the method requires a lot of memory. erefore, addressing the problems of random selection of initial parameters of wavelet neural networks, low diagnostic accuracy, and poor stability, this paper introduces the improved GWO algorithm into the WNN model and [22,23], vibration signal [24,25], and acoustic signals [26,27].…”

Section: Introductionmentioning

confidence: 99%

Early Detection of Network Fault Using Improved Gray Wolf Optimization and Wavelet Neural Network

Pan

Jin

Yang

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

To address the problem of diagnostic accuracy and stability degradation caused by random selection of the initial parameters for the wavelet neural network (WNN) fault diagnosis model, this paper proposes a network troubleshooting model based on the improved gray wolf algorithm (IGWO) and the wavelet neural network. First, the convergence factor and policy for the weight update are redesigned in the IGWO algorithm. This study uses a nonlinear convergence factor to balance the global and local search capabilities of the algorithm and dynamically adjusts the weights according to the adaptability of the head wolf α to strengthen its leadership position. Thereafter, the initial weights and biases of the WNN are optimized using the IGWO algorithm. During the backpropagation of the WNN error, momentum factors are introduced to prevent the model from falling into local optimization. Experimental results show that the IGWO algorithm is far better than GWO in terms of convergence speed and convergence accuracy. Furthermore, the average diagnostic accuracy of the IGWO-WNN model on the KDD-CUP99 dataset reaches 99.22%, which is 1.15% higher than that of the WNN model, and the stability of the diagnostic results is significantly improved.

show abstract

Acoustic Fault Diagnosis of Rotor Bearing System

Cited by 10 publications

References 16 publications

A failure diagnosis method of ball bearing based on optimized multiscale variational modal extraction with synchro squeezing transformation

A failure diagnosis method of ball bearing based on optimized multiscale variational modal extraction with synchro squeezing transformation

SWT-KELM-based rolling bearing fault diagnosis method under noise conditions with different SNRs

Early Detection of Network Fault Using Improved Gray Wolf Optimization and Wavelet Neural Network

Contact Info

Product

Resources

About