The IBA-ISMO Method for Rolling Bearing Fault Diagnosis Based on VMD-Sample Entropy

Zhuang, Deyu; Liu, Hongrui; Zheng, Hao; Li, Xu; Gu, Zhengyang; Qiu, Jinbo

doi:10.3390/s23020991

Cited by 21 publications

(12 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2) Firstly, the FMD input parameter pair [K, L] is set as the two-dimensional population of SSA; ranges for these two parameters are set separately: a short filter length easily leads to a coarse filtering result; a too-long one may result in distortion and further increase the computational burden [16]. As described in chapter 2, L is assigned in the interval of [30,80]. A larger parameter K will increase the calculation time, setting the value of K as an integer in the range of [2,7].…”

Section: The Proposed Methodsmentioning

confidence: 99%

“…Firstly, simulated signal is processed by the step-by-step parameter-adaptive FMD method. Step one: parameter combination [K, L] is determined as [3,30] according to the minimum value of fitness1; Step two, with the fixed K and L, the optimal parameter n of FMD is determined as 1 according to the minimum fitness2; Subsequently, signal is processed by FMD with optimal value, since the value of n is 1, final decomposed mode is taken as sensitive mode; Finally, envelope spectrum is calculated as shown in figure 15. From the time-domain waveform, the signal has obvious fault characteristics, and the amplitude is enhanced by nearly ten times compared to the original signal.…”

Section: Comparative Analysis With Other Methodsmentioning

confidence: 99%

“…It measures the probability of generating a new pattern in a time series when the dimensionality changes, and when the probability is higher, the corresponding entropy value is greater. Zhihong et al [28] adopted SampEn for mechanical fault feature extraction and achieved good results; Ding et al [29] applied VMD to gear fault signals, then formed fault feature vectors by the use of SampEn to extract gear fault information; Zhuang et al [30] introduced a fault diagnosis method by combining sample entropy and VMD decomposition method, and the method was validated through both simulation and engineering application.…”

Section: Evaluation Indexmentioning

confidence: 99%

See 2 more Smart Citations

A step-by-step parameter-adaptive FMD method and its application in fault diagnosis

Wang,

Li,

Tian

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

A newly proposed method, Feature Mode Decomposition (FMD), can effectively enhance signal features while decomposing the signal. This feature is beneficial for analyzing weak vibration signals. However, input parameters (the segment number K, the filter length L, and the mode number n,) significantly influence the decomposition performance and efficiency. Based on the analysis of filter properties and decomposition performance of the FMD method, a step-by-step parameter-adaptive FMD method is proposed. First, parameters K and L are optimized; Secondly, parameter n is determined. In addition, a comprehensive evaluation indicator, the ratio of sample entropy and ensemble kurtosis (SEKR) is constructed considering both the periodic impact characteristics of fault signals and the noise intensity to created objective functions for each step. Compared with the methods of Variational Mode Decomposition (VMD) spectral kurtosis method and the wavelet packet(WP) decomposition, the proposed method exhibits better decomposition performance: the amplitude has increased by nearly 10 times for the simulation data and 6 times for the actual engineering data; and three evaluation factors (the crest factor, the impulse factor, and the kurtosis) have higher value. Therefore, it can be concluded that the proposed method has better superiority in identifying weak periodic fault features.

show abstract

Section: The Proposed Methodsmentioning

confidence: 99%

Section: Comparative Analysis With Other Methodsmentioning

confidence: 99%

Section: Evaluation Indexmentioning

confidence: 99%

See 1 more Smart Citation

A step-by-step parameter-adaptive FMD method and its application in fault diagnosis

Wang,

Li,

Tian

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Sample Entropy (SampEn), as a kind of information entropy, is a method proposed by Richman et al to detect the richness and complexity of time series 5 . Liu Jianchang 6 studied the fault mechanism of rolling bearings. Based on the original sample entropy, the fault mechanism of rolling bearings was fused with sample entropy, and the sample entropy was improved as the judgment basis.…”

Section: Introductionmentioning

confidence: 99%

Leakage detection of tailing pipeline based on multisensor and multientropy fusion

Chen,

Liu,

Luo

2024

Ninth International Symposium on Sensors, Mechatronics, and Automation System (ISSMAS 2023)

View full text Add to dashboard Cite

In view of the low leakage detection rate of tailings pipeline, a method of tailing pipeline leakage detection based on multi-sensor and multi-entropy fusion was proposed. Firstly, the parameters of VMD algorithm were optimized by Sparrow Search Algorithm. The signal is decomposed by an optimized VMD algorithm, and the decomposed modal components are screened and reconstructed by kurtosis analysis. After that, the leakage experiment platform is built, the signal is collected by infrasound and negative pressure wave sensors, and the singular spectrum entropy and sample entropy of the pipeline signal are calculated, and the threshold interval of the two are obtained as the basis for judgment. Leakage experiments show that this method can accurately judge the leakage signal, and compared with the single sensor and single entropy fusion method, the accuracy is significantly improved.

show abstract

“…As the integral parts of equipment, rotating components such as bearings and gears are prone to fault due to the harsh working environment, which will affect the stable operation of the equipment. Therefore, efficient fault diagnosis methods play an important role in early fault warning and maintenance [ 2 ], which can effectively reduce property losses and casualties caused by mechanical faults [ 3 ].…”

Section: Introductionmentioning

confidence: 99%

Cross-Domain Open Set Fault Diagnosis Based on Weighted Domain Adaptation with Double Classifiers

Wang

Tong

et al. 2023

Sensors

View full text Add to dashboard Cite

The application of transfer learning in fault diagnosis has been developed in recent years. It can use existing data to solve the problem of fault recognition under different working conditions. Due to the complexity of the equipment and the openness of the working environment in industrial production, the status of the equipment is changeable, and the collected signals can have new fault classes. Therefore, the open set recognition ability of the transfer learning method is an urgent research direction. The existing transfer learning model can have a severe negative transfer problem when solving the open set problem, resulting in the aliasing of samples in the feature space and the inability to separate the unknown classes. To solve this problem, we propose a Weighted Domain Adaptation with Double Classifiers (WDADC) method. Specifically, WDADC designs the weighting module based on Jensen–Shannon divergence, which can evaluate the similarity between each sample in the target domain and each class in the source domain. Based on this similarity, a weighted loss is constructed to promote the positive transfer between shared classes in the two domains to realize the recognition of shared classes and the separation of unknown classes. In addition, the structure of double classifiers in WDADC can mitigate the overfitting of the model by maximizing the discrepancy, which helps extract the domain-invariant and class-separable features of the samples when the discrepancy between the two domains is large. The model’s performance is verified in several fault datasets of rotating machinery. The results show that the method is effective in open set fault diagnosis and superior to the common domain adaptation methods.

show abstract

The IBA-ISMO Method for Rolling Bearing Fault Diagnosis Based on VMD-Sample Entropy

Cited by 21 publications

References 20 publications

A step-by-step parameter-adaptive FMD method and its application in fault diagnosis

A step-by-step parameter-adaptive FMD method and its application in fault diagnosis

Leakage detection of tailing pipeline based on multisensor and multientropy fusion

Cross-Domain Open Set Fault Diagnosis Based on Weighted Domain Adaptation with Double Classifiers

Contact Info

Product

Resources

About