Enhanced network learning model with intelligent operator for the motion reliability evaluation of flexible mechanism

Fei, Chengwei; Li, Huan; Liu, Hao-Tian; Lu, Cheng; An, Liqiang; Han, Lei; Zhao, Yongjun

doi:10.1016/j.ast.2020.106342

Cited by 63 publications

(16 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…And at last, we use the particle swarm optimization based support vector machine (PSO-SVM) classification method [37] - [41] to realize an intelligent fault diagnosis of rolling bearings. Compared with some learningbased methods [42], PSO-SVM has better robustness. Thus, a new fault diagnosis framework is proposed based on the EWT, GCMDiEn, LS and PSO-SVM.…”

Section: Introductionmentioning

confidence: 99%

Generalized Composite Multiscale Diversity Entropy and Its Application for Fault Diagnosis of Rolling Bearing in Automotive Production Line

Liang

Chen

2021

IEEE Access

View full text Add to dashboard Cite

This paper considers the entropy based feature extraction method for the fault diagnosis of rolling bearings in automobile production line, where the fault information is difficult to identify due to the strong nonlinear and non-stationary characteristics of the fault vibration signals. In our work, a novel entropy based method called generalized composite multiscale diversity entropy (GCMDiEn) is developed. This method can effectively track the inside pattern changes of the time series by the description of cosine similarity between adjacent orbits. Unlike most of the existing entropy based results which concentrate on the static orderliness, we analyze the dynamic complexity characteristics of the arbitrary time series. Moreover, compared with the multiscale diversity entropy, GCMDiEn calculates all coarse-grained time series entropy value with the same scale and extends the first-order moment to second-order moment to mitigate the shortcomings of the short time series instability and losing part of the frequency region information. This paper proposed a new rolling bearing fault diagnosis framework which combined the GCMDiEn with the empirical wavelet transform (EWT), Laplacian score (LS), and particle swarm optimization-based support vector machine (PSO-SVM). Finally, the simulation results show the superiority of the GCMDiEn method over the multiscale diversity entropy method. The proposed framework has a higher fault recognition rate (99.38%) than the existing methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Generalized Composite Multiscale Diversity Entropy and Its Application for Fault Diagnosis of Rolling Bearing in Automotive Production Line

Liang

Chen

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…For example, Han et al [10] proposed a probability-based prediction method by considering probabilistic feature parameters, to predict the service safety life (SSL) of aeroengine turbine blades effectively. Fei et al [11] proposed an Enhanced Network Learning Method (ENLM) by introducing Generalized Regression Neural Network (GRNN) and Multipopulation Genetic Algorithm (MPGA) into the Extreme Response Surface Method (ERSM), which improved the modeling accuracy, simulation efficiency, and the reliability of the flexible mechanism, and Fei and Bai [12] proposed the WCFSE FSVM method based on wavelet correlation feature scale entropy. Combining the advantages of the Wavelet Correlation Feature Scale Entropy method and Fuzzy Support Vector Machine method, it can analyze the vibration signal of the aeroengine more accurately and has high generalization ability and antinoise ability.…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis of Subway Traction Motor Bearing Based on Information Fusion under Variable Working Conditions

Cai

Xie

2021

Shock and Vibration

View full text Add to dashboard Cite

Under the variable working condition, the fault signal of the rolling bearing contains rich characteristic information. In view of the problem that the traditional fault diagnosis method of the rolling bearing depends on the prior knowledge and expert experience too much and the low recognition rate of some faults with the single signal, one method of rolling bearing fault diagnosis based on information fusion under the variable working condition is proposed. Firstly, one test and multi-information acquisition system of the rolling bearing is built. Secondly, the metro traction motor bearing nu216 is selected as the research object, and to prefabricate the defects, the data of acoustic emission and vibration acceleration signals during the test of the bearing is acquired. Then, the original signal is processed and extracted by the wavelet packet decomposition, and the normalized feature information is fused by the convolution neural network. Finally, the two-dimensional convolution neural network model is established to diagnose the bearing fault of the metro traction motor under different conditions. The test results show that the intelligent fault diagnosis method of the subway traction motor bearing based on information fusion under variable working conditions can accurately identify the fault type of the bearing, while the load and speed change. When the neural network training set and the test set cover the same working conditions, the accuracy can reach 100%.

show abstract

“…Rolling bearings play a pivotal role in modern industry and their applications are very extensive, such as aircraft engines [1,2], gas turbines [3], landing gear [4], flexible mechanism [5], and wind turbines [6][7][8][9][10][11]. However, the rolling bearing is very easy to cause damage in a strong vibration environment, and the rolling bearing is very prone to failure in most rotating machinery systems.…”

Section: Introductionmentioning

confidence: 99%

A Fault Feature Extraction Method for Rolling Bearing Based on Intrinsic Time‐Scale Decomposition and AR Minimum Entropy Deconvolution

Ding

Huang

Xiao

et al. 2021

Shock and Vibration

View full text Add to dashboard Cite

It is very difficult to extract the feature frequency of the vibration signal of the rolling bearing early weak fault and in order to extract its feature frequency quickly and accurately. A method of extracting early weak fault vibration signal feature frequency of the rolling bearing by intrinsic time-scale decomposition (ITD) and autoregression (AR) minimum entropy deconvolution (MED) is proposed in this paper. Firstly, the original early weak fault vibration signal of the rolling bearing is decomposed by the ITD algorithm to proper rotations (PRs) with fault feature frequency. Then, the sample entropy value of each PR is calculated to find the largest PRs of the sample entropy. Finally, the AR-MED filtering algorithm is utilized to filter and reduce the noise of the largest PRs of the sample entropy value, and the early weak fault vibration signal feature frequency of the rolling bearing is accurately extracted. The results show that the ITD-AR-MED method can extract the early weak fault vibration signal feature frequency of the rolling bearing accurately.

show abstract

Enhanced network learning model with intelligent operator for the motion reliability evaluation of flexible mechanism

Cited by 63 publications

References 45 publications

Generalized Composite Multiscale Diversity Entropy and Its Application for Fault Diagnosis of Rolling Bearing in Automotive Production Line

Generalized Composite Multiscale Diversity Entropy and Its Application for Fault Diagnosis of Rolling Bearing in Automotive Production Line

Fault Diagnosis of Subway Traction Motor Bearing Based on Information Fusion under Variable Working Conditions

A Fault Feature Extraction Method for Rolling Bearing Based on Intrinsic Time‐Scale Decomposition and AR Minimum Entropy Deconvolution

Contact Info

Product

Resources

About