Fault feature extraction method based on local mean decomposition Shannon entropy and improved kernel principal component analysis model

Sheng, Jinlu; Dong, Shaojiang; Li, Zhu; Gao, Haowei

doi:10.1177/1687814016661087

Cited by 10 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Xi et al 23 presents refined composite multivariate multiscale fluctuation dispersion entropy to extract the recognition information of multi-channel signals with different scale factors. Sheng et al 24 constructed local mean decomposition Shannon entropy and Ma et al 25 employed wavelet packet-energy entropy respectively for bearing fault diagnosis with high accuracy.…”

Section: Introductionmentioning

confidence: 99%

Rolling bearing state assessment based on the composite multiscale weight slope entropy and hierarchical prototype-based approach

Zhang¹,

Pan

Zhang³

et al. 2022

Advances in Mechanical Engineering

View full text Add to dashboard Cite

To evaluate the state of rolling bearing more accurately, a new feature called composite multiscale weight slope entropy was proposed for the complexity measurement of vibration signals. On the basis of analyzing the fault signal structure, the new feature could consider the influence of the nonlinearity, the multiscale characteristics, the fluctuation of the amplitude, and the amplitude itself on the fault signals. In the following, different fault types and the corresponding damage degree of rolling bearings were identified with the hierarchical prototype-based approach. Compared with the results of different modified slope entropy, it is shown that composite multiscale weight slope entropy could significantly improve the identification accuracy. In the two designed testing schemes, ten and sixty state types of rolling bearings are respectively calculated, and the identification accuracy could reach up to 100% and 96.5% respectively, which illustrate the effectiveness and the validity of the proposed approach.

show abstract

Section: Introductionmentioning

confidence: 99%

Rolling bearing state assessment based on the composite multiscale weight slope entropy and hierarchical prototype-based approach

Zhang¹,

Pan

Zhang³

et al. 2022

Advances in Mechanical Engineering

View full text Add to dashboard Cite

show abstract

“…However, both decomposition methods are still deficient; the EMD method generates end effects [14], overshoots and undershoots [15], pattern mixing [16], and unexplained negative frequencies generated by the Hilbert transform [17], etc. The LMD method also suffers from local mutations and even large computational size due to the sliding iterative computation method, which increase the probability of the LMD method generating modal mixing problems [18,19]. Recently, Zhang et al proposed a new time-frequency analytical technique for adaptively decomposable signals-local oscillatory-characteristic decomposition (LOD), based on the LMD method [20].…”

Section: Introductionmentioning

confidence: 99%

“…Figs 18. and 19 show the fast ICA decomposition time-frequency and spectrum plots obtained from the mixed signal after pre-processing ( the source signal has a mean value of 0 and a variance of 1), respectively.…”

mentioning

confidence: 99%

A New Diagnostic Method Applied to Gearbox Missing Gear Faults ——LOD-ICA

Liao¹,

Xiao²,

Huang³

et al. 2022

Energy Engineering

View full text Add to dashboard Cite

With the increasingly stringent requirements for carbon emissions, countries have increased the scale of clean energy use in recent years. As an important new clean energy source, the ratio of wind power in energy utilization has been increasing. The horizontal axis wind turbine is the main form of wind power generation, which is subject to random wind loads during operation and is prone to various failures after a long period of operation, resulting in reduced power generation efficiency or even shutdown. In order to ensure stable external power transmission, it is necessary to perform fault diagnosis for wind turbines. However, the traditional time-frequency analysis method is defective. This paper proposes a new LOD-ICA method to realize the resolution of the vibration signals mode mixing problem incorporated the merits of both methods. The LOD-ICA method and the LOD method based on noise-assisted analysis decompose the same signal to produce different signal components. The feasibility of the LOD-ICA method was verified by comparing the correlation coefficients between each of the signal components generated by the two methods and the original signal. In the field of wind turbine fault diagnosis, the LOD-ICA method is employed to the fault characteristics of gearboxes to extract the fault signs of vibration signals, further demonstrated the superiority of the LOD-ICA method in processing vibration signals of rotating machinery.

show abstract

“…The concept of Shannon entropy was introduced in order to characterise system complexity where more random, discorded systems have higher information entropy. Sheng et al 19 used local mean decomposition followed by Shannon entropy and SVM in order to classify bearing running state. Sun et al 5 also used the Shannon entropy of individual IMFs following EMD to recognise leak apertures.…”

Section: Introductionmentioning

confidence: 99%

Prediction of leak flow rate in plastic water distribution pipes using vibro-acoustic measurements

Butterfield

Meruane

Collins

et al. 2017

Structural Health Monitoring

View full text Add to dashboard Cite

Leakage from water distribution systems is a worldwide issue with consequences including loss of revenue, health and environmental concerns. Leaks have typically been found through leak noise correlation by placing sensors either side of the leak and recording and analysing its vibro-acoustic emission. While this method is widely used to identify the location of the leak, the sensors also record data that could be related to the leak's flow rate, yet no reliable method exists to predict leak flow rate in water distribution pipes using vibro-acoustic emission. The aim of this research is to predict leak flow rate in medium-density polyethylene pipe using vibro-acoustic emission signals. A novel experimental methodology is presented whereby circular holes of four sizes are tested at several leak flow rates. Following the derivation of a number of features, least squares support vector machines are used in order to predict leak flow rate. The results show a strong correlation highlighting the potential of this technique as a rapid and practical tool for water companies to assess and prioritise leak repair.

show abstract

Fault feature extraction method based on local mean decomposition Shannon entropy and improved kernel principal component analysis model

Cited by 10 publications

References 19 publications

Rolling bearing state assessment based on the composite multiscale weight slope entropy and hierarchical prototype-based approach

Rolling bearing state assessment based on the composite multiscale weight slope entropy and hierarchical prototype-based approach

A New Diagnostic Method Applied to Gearbox Missing Gear Faults ——LOD-ICA

Prediction of leak flow rate in plastic water distribution pipes using vibro-acoustic measurements

Contact Info

Product

Resources

About