New Fault Recognition Method for Rotary Machinery Based on Information Entropy and a Probabilistic Neural Network

Jiang, Quan; Shen, Yehu; Li, Hua; Xu, Fengyu

doi:10.3390/s18020337

Cited by 45 publications

(27 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The Hu invariant moments are calculated based on the image features. The procedure is based on (12), (13), (14), (15), (16), (17), (18), (19), (20), (21), and (22). The Hu invariant moments of the samples are shown in Table 2.…”

Section: Feature Extraction Based On Hu Invariant Momentsmentioning

confidence: 99%

“…At present, the widely used methods in the field of rotor system axis orbit feature recognition are the artificial neural network (ANN), support vector machine (SVM), fuzzy clustering, and gray correlation analysis [14][15][16]. Based on probabilistic neural network (PNN), [17] proposed a feature fusion model and applied it to the automatic identification of the axis orbit of a turbo generator and high-speed centrifugal compressor set. To directly classify the continuous wavelet transform scalogram (CWTS), [18] proposed a novel diagnosis method by using a convolutional neural network (CNN).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of Axis Orbit Image Optimization in Fault Diagnosis for Rotor System

Pang

Shao

Xue

et al. 2020

International Journal of Rotating Machinery

View full text Add to dashboard Cite

The shape characteristic of the axis orbit plays an important role in the fault diagnosis of rotating machinery. However, the original signal is typically messy, and this affects the identification accuracy and identification speed. In order to improve the identification effect, an effective fault identification method for a rotor system based on the axis orbit is proposed. The method is a combination of ensemble empirical mode decomposition (EEMD), morphological image processing, Hu invariant moment feature vector, and back propagation (BP) neural network. Experiments of four fault forms are performed in single-span rotor and double-span rotor test rigs. Vibration displacement signals in the X and Y directions of the rotor are processed via EEMD filtering to eliminate the high-frequency noise. The mathematical morphology is used to optimize the axis orbit including the dilation and skeleton operation. After image processing, Hu invariant moments of the skeleton axis orbits are calculated as the feature vector. Finally, the BP neural network is trained to identify the faults of the rotor system. The experimental results indicate that the time of identification of the tested axis orbits via morphological processing corresponds to 13.05 s, and the identification accuracy rate ranges to 95%. Both exceed that without mathematical morphology. The proposed method is reliable and effective for the identification of the axis orbit and aids in online monitoring and automatic identification of rotor system faults.

show abstract

Section: Feature Extraction Based On Hu Invariant Momentsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Application of Axis Orbit Image Optimization in Fault Diagnosis for Rotor System

Pang

Shao

Xue

et al. 2020

International Journal of Rotating Machinery

View full text Add to dashboard Cite

show abstract

“…Finally, support vector machine is optimized and the fault pattern is recognized. In [159], singular spectrum entropy, power spectrum entropy, and approximate entropy are extracted in vibration signals by Shannon entropy, and the feature fusion model is constructed to classify and diagnose the fault signals. Chen et al [145] variational mode decomposition + energy entropy 3 Tang et al [146] manifold learning + Shannon wavelet support vector machine 4 Xiao et al [147] dual-tree complex wavelet transform + energy entropy 5 Feng et al [148] information entropy + deep belief networks 6 Yin et al [149] time-frequency entropy enhancement + boundary constraint assisted relative gray relational grade 7 Chen et al [150] ensemble multiwavelet + Shannon entropy 8…”

Section: Typical Entropy Theories Application On Fault Diagnosis Of Omentioning

confidence: 99%

“…Fei et al [151] support vector machine + process power spectrum entropy 9 Fei and Bai [152] fuzzy support vector machine + wavelet entropy 10 Zhang and Liu [153] ensemble intrinsic time-scale decomposition + energy entropy 11 Ye [154] fuzzy cross-entropy 12 Fu et al [158] entropy-based feature extraction + support vector machine optimized by a chaos quantum sine cosine algorithm 13 Li et al [157] multi-scale symbolic dynamic entropy + improved support vector machine based on binary tree 14 Wang et al [156] optimized multi-scale permutation entropy 15 Xiao et al [155] smooth local subspace projection method + permutation entropy 16 Jiang et al [159] Shannon entropy + a probabilistic neural network…”

Section: Typical Entropy Theories Application On Fault Diagnosis Of Omentioning

confidence: 99%

Related Entropy Theories Application in Condition Monitoring of Rotating Machineries

Liu

Zhi

Zhang

et al. 2019

Entropy

View full text Add to dashboard Cite

Rotating machinery plays an important role in various kinds of industrial engineering. How to assess their conditions is a key problem for operating safety and condition-based maintenance. The potential anomaly, fault and failure information can be obtained by analyzing the collected condition monitoring data of the previously deployed sensors in rotating machinery. Among the available methods of analyzing sensors data, entropy and its variants can provide quantitative information contained in these sensing data. For implementing fault detection, diagnosis, and prognostics, this information can be utilized for feature extraction and selecting appropriate training data for machine learning methods. This article aims to review the related entropy theories which have been applied for condition monitoring of rotating machinery. This review consists of typical entropy theories presentation, application, summary, and discussion.

show abstract

“…Vibration analysis is among the most widely recognized technique utilized in the observing applications since an imperfection produces progressive driving forces at each contact of deformity [14]. Time domain analysis, frequency domain analysis, and spike energy analysis have been employed to identify different defects in rotating bearings [15,16,17].…”

Section: Introductionmentioning

confidence: 99%

Early Fault Detection in Bearing with Fault Seeded on Outer Raceway at Three Different Position: Orthogonal, Centered and Opposite

Omran*,

Hassan Ali,

Shankar

et al. 2019

IJRTE

View full text Add to dashboard Cite

Rotating machine such as a small low voltage motor or a power plant generator is an essential asset to the industrial applications. The execution and efficiency of these rotating machines are being reduced due to faulty rotating machinery parts. The faulty parts also generate various forces, thus increases the amplitude of vibration as well as energy consumption. Early fault detection and diagnosis have been widely used with various methods as they were able to reduce accidents and machine breakdowns along with economic losses. This study aims to present the faulty bearings which were seeded in the bearings. The fault size are ranging from 0.007 inches to 0.021 inches in diameter. Among the methods, vibration signal data is one of the champions. In this study, early fault detection was focused on bearing using the time domain technique and the data were analyzed. Particularly, the fault was introduced on the outer raceway at three different positions; orthogonal (3 o’clock), centered (6 o’clock) and opposite (12 o’clock). The MATLAB software was used to determine the time domain parameters, comprising of the standard deviation, Root Mean Square (RMS), skewness and shape factor as the representation of the best reflection of the failure. The time domain parameters for healthy and faulty bearing were plotted and compared in graphical presentation. The result shows all the four parameters have greater value in contrast with the healthy bearing value except for skewness data in the opposite (12 o’clock) position.

show abstract

New Fault Recognition Method for Rotary Machinery Based on Information Entropy and a Probabilistic Neural Network

Cited by 45 publications

References 29 publications

Application of Axis Orbit Image Optimization in Fault Diagnosis for Rotor System

Application of Axis Orbit Image Optimization in Fault Diagnosis for Rotor System

Related Entropy Theories Application in Condition Monitoring of Rotating Machineries

Early Fault Detection in Bearing with Fault Seeded on Outer Raceway at Three Different Position: Orthogonal, Centered and Opposite

Contact Info

Product

Resources

About