Parallel multi-scale entropy and it's application in rolling bearing fault diagnosis

Zhao, Dongfang; Liu, Shulin; Cheng, Shouguo; Sun, Xin; Wang, Lu; Yuan, Wancheng; Zhang, Hongli

doi:10.1016/j.measurement.2020.108333

Cited by 27 publications

(17 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Schemes based on feature extraction from timedomain or frequency-domain improved the performance of fault diagnosis. Time-domain feature analysis methods usually determine the possible running states of rolling bearings by calculating and analyzing parameters and indexes of the vibration signals with various time-domain feature parameters, such as [7][8][9][10][11][12][13], while frequency-domain feature analysis methods focus on separating or strengthening the frequency components of the fault signals, such as [14][15][16][17][18][19][20], generally with higher accuracies than those of time-domain based methods. The time-frequency analysis methods combined the two to form a joint function, could describe the non-linear and non-stationary dynamic signals of complex mechanical equipment, such as [21,22].…”

Section: Existing Situationmentioning

confidence: 99%

“…The traditional research is focused on examining the properties of a single parameter, and fault diagnosis schemes combining multiple traditional time-domain features remain to be developed. In addition to traditional time-domain feature extraction methods, the information entropy theory has been applied for timedomain feature extraction [8][9][10][11][12][13]33]. However, the computation time of the information entropy algorithm is usually large because of its complexity.…”

Section: Related Workmentioning

confidence: 99%

“…Table 7 Predictive accuracy comparison between original ELM and logistic-ELM Sub Dataset Description of Fault Information Dataset-1 in DSLS-SVM [39] N(0 hp), IF-BF-OF(0 hp, 0.007") from CWRU dataset Dataset-2 in PMSEn [12] N(0 hp), N(1 hp), N(2 hp), N(3 hp), IF-BF-OF(0 hp, 0.021") from CWRU dataset Dataset-3 in VAEGAN-DRA [40] N (0 hp), IF-BF-OF(0 hp, 0.007"), IF-BF-OF(0 hp, 0.014"), IF-BF-OF(0 hp, 0.021") from CWRU dataset Dataset-4 in FuzzyMEn [13] N(0 hp) , IF-BF-OF(0 hp, 0.007"), IF-BF(0 hp, 0.021"), OF(0 hp, 0.028") from CWRU dataset Dataset-5 in RCFOA-ELM [30] N(2 hp), IF-BF-OF(0 hp, 0.014") from CWRU dataset Dataset-6 in DE-ELM [31] N(2 hp), IF-BF-OF(2 hp, 0.007") from CWRU dataset…”

Section: Experiments 5 Predictive Accuracy Under Different Operating ...mentioning

confidence: 99%

“…In this experiment, we select four existing fault diagnosis methods of rolling bearings for comparisons with proposed logistic-ELM, including DSLS-SVM [39], PMSEn [12], FuzzyMEn [13], VAEGAN-DRA [40], RCFOA-ELM [30] and DE-ELM [31], which were proposed from 2019 to 2021. Among these methods, DSLS-SVM is an extended algorithm of the SVM.…”

Section: Experiments 6 Predictive Accuracy Comparisons With Existing ...mentioning

confidence: 99%

See 3 more Smart Citations

Logistic-ELM: A Novel Fault Diagnosis Method for Rolling Bearings

Tan¹,

Ning²,

Peng³

et al. 2022

Preprint

View full text Add to dashboard Cite

Logistic-ELMcost, the experimental results indicate that the proposed logistic-ELM can predict the fault in 40 ms with a high accuracy, up to 21-1858 times more rapidly than existing methods based on SVM, CNN and multiscale entropy. Other experiments of fault diagnosis of the rolling bearings under four different loads, also indicate that the logistic-ELM can adapt to different operation conditions with high efficiency. The relevant code is publicly available at https://github.com/TAN-OpenLab/logistic-ELM.

show abstract

Section: Existing Situationmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Experiments 5 Predictive Accuracy Under Different Operating ...mentioning

confidence: 99%

Section: Experiments 6 Predictive Accuracy Comparisons With Existing ...mentioning

confidence: 99%

See 2 more Smart Citations

Logistic-ELM: A Novel Fault Diagnosis Method for Rolling Bearings

Tan¹,

Ning²,

Peng³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…With the rapid development of nonlinear dynamics, nonlinear dynamic analysis methods have been increasingly applied to the fault diagnosis of mechanical equipment to extract fault features, for instance, entropy [ 19 ]. Approximate entropy (AE) was the entropy method first introduced in the field of mechanical fault diagnosis [ 20 ], followed by permutation entropy (PE), sample entropy (SE), fuzzy entropy (FE), discrete entropy (DE), and their derived algorithms [ 21 , 22 , 23 , 24 , 25 , 26 ]. Among these entropies, SE has been widely used in feature extraction due to its simple calculation and low time cost.…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis of a Wind Turbine Gearbox Based on Improved Variational Mode Algorithm and Information Entropy

Zhang

Wang

2021

Entropy

View full text Add to dashboard Cite

The working environment of wind turbine gearboxes is complex, complicating the effective monitoring of their running state. In this paper, a new gearbox fault diagnosis method based on improved variational mode decomposition (IVMD), combined with time-shift multi-scale sample entropy (TSMSE) and a sparrow search algorithm-based support vector machine (SSA-SVM), is proposed. Firstly, a novel algorithm, IVMD, is presented for solving the problem where VMD parameters (K and α) need to be selected in advance, which mainly contains two steps: the maximum kurtosis index is employed to preliminarily determine a series of local optimal decomposition parameters (K and α), then from the local parameters, the global optimum parameters are selected based on the minimum energy loss coefficient (ELC). After decomposition by IVMD, the raw signal is divided into K intrinsic mode functions (IMFs), the optimal IMF(s) with abundant fault information is (are) chosen based on the minimum envelopment entropy criterion. Secondly, the time-shift technique is introduced to information entropy, the time-shift multi-scale sample entropy algorithm is applied for the analysis of the complexity of the chosen optimal IMF and extract fault feature vectors. Finally, the sparrow search algorithm, which takes the classification error rate of SVM as the fitness function, is used to adaptively optimize the SVM parameters. Next, the extracted TSMSEs are input into the SSA-SVM model as the feature vector to identify the gear signal types under different conditions. The simulation and experimental results confirm that the proposed method is feasible and superior in gearbox fault diagnosis when compared with other methods.

show abstract

Chatter detection in milling processes—a review on signal processing and condition classification

Navarro-Devia

Chen

Dao

et al. 2023

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Among the diverse challenges in machining processes, chatter has a significant detrimental effect on surface quality and tool life, and it is a major limitation factor in achieving higher material removal rate. Early detection of chatter occurrence is considered a key element in the milling process automation. Online detection of chatter onset has been continually investigated over several decades, along with the development of new signal processing and machining condition classification approaches. This paper presents a review of the literature on chatter detection in milling, providing a comprehensive analysis of the reported methods for sensing and testing parameter design, signal processing and various features proposed as chatter indicators. It discusses data-driven approaches, including the use of different techniques in the time–frequency domain, feature extraction, and machining condition classification. The review outlines the potential of using multiple sensors and information fusion with machine learning. To conclude, research trends, challenges and future perspectives are presented, with the recommendation to study the tool wear effects, and chatter detection at dissimilar milling conditions, while utilization of considerable large datasets—Big Data—under the Industry 4.0 framework and the development of machining Digital Twin capable of real-time chatter detection are considered as key enabling technologies for intelligent manufacturing.

show abstract

Parallel multi-scale entropy and it's application in rolling bearing fault diagnosis

Cited by 27 publications

References 34 publications

Logistic-ELM: A Novel Fault Diagnosis Method for Rolling Bearings

Logistic-ELM: A Novel Fault Diagnosis Method for Rolling Bearings

Fault Diagnosis of a Wind Turbine Gearbox Based on Improved Variational Mode Algorithm and Information Entropy

Chatter detection in milling processes—a review on signal processing and condition classification

Contact Info

Product

Resources

About