Fast Spectral Correlation Based on Sparse Representation Self-Learning Dictionary and Its Application in Fault Diagnosis of Rotating Machinery

Rolling element bearing and gear are the typical supporting or rotating parts in mechanical equipment, and it has important economy and security to realize their quick and accurate fault detection. As one kind of powerful cyclostationarity signal analyzing method, spectral correlation (SC) could identify the impulsive characteristic component buried in the vibration signals of rotating machinery effectively. However, the fault feature such as impulsive characteristic component is often interfered by other background noise, and the situation is serious especially in early weak fault stage. Besides, the traditional SC method has a drawback of low computation efficiency which hinders its wide application to some extent. To address the above problems, an impulsive feature-enhanced method which combines fast spectral correlation (FSC) with sparse representation self-learning dictionary is proposed in the paper. Firstly, the sparse representation self-learning dictionary method-K-means singular value decomposition (KSVD) is improved and the improved KSVD (IKSVD) method is used to denoise the original signal, and the periodic impulses are highlighted. Then, the FSC algorithm is applied on the denoised signal and spectral correlation image could be obtained. Finally, the calculated enhanced envelope spectrum (EES) of the denoised signal is obtained by using the spectral correlation image to identify the accurate fault position. The feasibility and superiority of the proposed method is verified through simulation, experiment, and engineering application.

Download Full-text

Image super‐resolution via adaptive sparse representation and self‐learning

IET Computer Vision ◽

10.1049/iet-cvi.2017.0153 ◽

2018 ◽

Vol 12 (5) ◽

pp. 753-761 ◽

Cited By ~ 5

Author(s):

Jianwei Zhao ◽

Tiantian Sun ◽

Feilong Cao

Keyword(s):

Sparse Representation ◽

Super Resolution ◽

Image Super Resolution ◽

Self Learning

Download Full-text

Rolling element bearing fault diagnosis for rotating machinery using vibration spectrum imaging and convolutional neural networks

The International Journal of Advanced Manufacturing Technology ◽

10.1007/s00170-019-04726-7 ◽

2019 ◽

Vol 106 (5-6) ◽

pp. 1737-1751 ◽

Cited By ~ 6

Author(s):

Abdelraouf Youcef Khodja ◽

Noureddine Guersi ◽

Mohamed Nacer Saadi ◽

Nadir Boutasseta

Keyword(s):

Neural Networks ◽

Fault Diagnosis ◽

Convolutional Neural Networks ◽

Vibration Spectrum ◽

Rotating Machinery ◽

Rolling Element Bearing ◽

Bearing Fault Diagnosis ◽

Rolling Element ◽

Element Bearing ◽

Spectrum Imaging

Download Full-text

Development of Compact Damper Bearing

Volume 1: 20th Biennial Conference on Mechanical Vibration and Noise, Parts A, B, and C ◽

10.1115/detc2005-84775 ◽

2005 ◽

Author(s):

Hiroshi Kanki ◽

Yosichika Sato ◽

Takayuki Ueshima

Keyword(s):

Rotating Machinery ◽

Rolling Element Bearing ◽

Squeeze Film ◽

Test Results ◽

Thin Ring ◽

Compact Size ◽

Standard Design ◽

Rolling Element ◽

Aero Engine ◽

Element Bearing

The squeeze film damper bearings have been successfully applied for important rotating machinery such as aero engine, high pressure centrifugal compressors[1] and steam turbine[2]. This paper proposes the expansion of application of the damper bearing for small and medium sized rotating machinery. The new damper has a compact size that enable standard design combined with rolling element bearing. A new design of the damper is presented. The new design consists of thin ring and special patterned wire cut grooves. The design analysis and experimental study are presented. The dynamic tests were carried out for this model damper, one is no side seal and the other is with side seals in both ends. Test results showed the sufficient damping effect for actual applications.

Download Full-text

Sparse feature extraction based on periodical convolutional sparse representation for fault detection of rotating machinery

Measurement Science and Technology ◽

10.1088/1361-6501/abb0bf ◽

2020 ◽

Vol 32 (1) ◽

pp. 015008

Author(s):

Chuancang Ding ◽

Ming Zhao ◽

Jing Lin

Keyword(s):

Feature Extraction ◽

Fault Detection ◽

Sparse Representation ◽

Rotating Machinery

Download Full-text

Adaptive parametric dictionary design of sparse representation based on fault impulse matching for rotating machinery weak fault detection

Measurement Science and Technology ◽

10.1088/1361-6501/ab6f2f ◽

2020 ◽

Vol 31 (6) ◽

pp. 065101 ◽

Cited By ~ 2

Author(s):

Feiyue Deng ◽

Yawen Qiang ◽

Yongqiang Liu ◽

Shaopu Yang ◽

Rujiang Hao

Keyword(s):

Fault Detection ◽

Sparse Representation ◽

Rotating Machinery ◽

Weak Fault

Download Full-text

Fault Diagnosis Based on Acoustic Emission Signal for Low Speed Rolling Element Bearing

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.199-200.1020 ◽

2011 ◽

Vol 199-200 ◽

pp. 1020-1023 ◽

Cited By ~ 1

Author(s):

Hua Qing Wang ◽

Yong Wei Guo ◽

Jian Feng Yang ◽

Liu Yang Song ◽

Jia Pan ◽

...

Keyword(s):

Acoustic Emission ◽

Fault Diagnosis ◽

Acoustic Emission Signal ◽

Rotating Machinery ◽

Rolling Element Bearing ◽

Low Speed ◽

Rotating Speed ◽

Emission Signal ◽

Rolling Element ◽

Element Bearing

The fault of a bearing may cause the breakdown of a rotating machine, leading to serious consequences. A rolling element bearing is an important part of, and is widely used in rotating machinery. Therefore, fault diagnosis of rolling bearings is important for guaranteeing production efficiency and plant safety. Although many studies have been carried out with the goal of achieving fault diagnosis of a bearing, most of these works were studied for rotating machinery with a high rotating speed rather than with a low rotating speed. Fault diagnosis for bearings under a low rotating speed, is more difficult than under a high rotating speed. Because bearing faults signal is very weak under a low rotating speed. This work acquires vibration and acoustic emission signals from the rolling bearing under low speed respectively, and analyzes the both kinds of signals in time domain and frequency domain for diagnosing the typical bearing faults contrastively. This paper also discussed the advantages using the acoustic emission signal for fault diagnosis of rolling speed bearing. From the results of analysis and experiment we can find the effectiveness of acoustic emission signal is better than vibration signal for fault diagnosis of a bearing under the low speed.

Download Full-text

Bearing Fault Classification Based on Conditional Random Field

Shock and Vibration ◽

10.1155/2013/943809 ◽

2013 ◽

Vol 20 (4) ◽

pp. 591-600 ◽

Cited By ~ 8

Author(s):

Guofeng Wang ◽

Xiaoliang Feng ◽

Chang Liu

Keyword(s):

Random Field ◽

Graphical Model ◽

Conditional Random Field ◽

Wavelet Packet ◽

Rolling Element Bearing ◽

Fault Classification ◽

Mechanical Equipment ◽

Conditional Probability Distribution ◽

Outer Race ◽

Feature Vectors

Condition monitoring of rolling element bearing is paramount for predicting the lifetime and performing effective maintenance of the mechanical equipment. To overcome the drawbacks of the hidden Markov model (HMM) and improve the diagnosis accuracy, conditional random field (CRF) model based classifier is proposed. In this model, the feature vectors sequences and the fault categories are linked by an undirected graphical model in which their relationship is represented by a global conditional probability distribution. In comparison with the HMM, the main advantage of the CRF model is that it can depict the temporal dynamic information between the observation sequences and state sequences without assuming the independence of the input feature vectors. Therefore, the interrelationship between the adjacent observation vectors can also be depicted and integrated into the model, which makes the classifier more robust and accurate than the HMM. To evaluate the effectiveness of the proposed method, four kinds of bearing vibration signals which correspond to normal, inner race pit, outer race pit and roller pit respectively are collected from the test rig. And the CRF and HMM models are built respectively to perform fault classification by taking the sub band energy features of wavelet packet decomposition (WPD) as the observation sequences. Moreover, K-fold cross validation method is adopted to improve the evaluation accuracy of the classifier. The analysis and comparison under different fold times show that the accuracy rate of classification using the CRF model is higher than the HMM. This method brings some new lights on the accurate classification of the bearing faults.

Download Full-text

Novel Cyclo-Non-Stationary Indicators for Monitoring of Rotating Machinery Operating Under Speed and Load Varying Conditions

Journal of Engineering for Gas Turbines and Power ◽

10.1115/1.4049778 ◽

2021 ◽

Author(s):

Alexandre Mauricio ◽

Dustin M Helm ◽

Markus Timusk ◽

Jerome Antoni ◽

Konstantinos Gryllias

Keyword(s):

Industrial Process ◽

Rotating Machinery ◽

Operating Conditions ◽

Cyclic Behavior ◽

Spectral Correlation ◽

Rotating Speed ◽

Modulation Spectrum ◽

Novel Approach ◽

Cyclostationary Signals ◽

Bearing Damage

Abstract Condition monitoring arises as a valuable industrial process in order to assess the health of rotating machinery, providing early and accurate warning of potential failures and allowing for the planning and effective realization of preventative maintenance actions. In complex machines the failure indications of an early bearing damage are weak compared to other sources of excitations. Vibration analysis is most widely used and various methods have been proposed. In a number of applications, changes in the operating conditions (speed/load) influence the vibration sources and change the frequency and amplitude characteristics of the vibroacoustic signature, making them nonstationary. Recently an emerging interest has been focused on modelling rotating machinery signals as cyclostationary. Classical cyclostationary tools, such as Cyclic Spectral Correlation Density (CSCD) and Cyclic Modulation Spectrum (CMS), can be used to extract information about the cyclic behavior of cyclostationary signals, under the assumption of nearly constant rotating speed. Global diagnostic indicators have been proposed as a measure of cyclostationarity under steady operating conditions. In order to overcome this limitation a generalization of both SCD and CMS functions have been proposed displaying cyclic Order versus Frequency as well as diagnostic indicators of cyclo-non-stationarity in order to cover the speed varying operating conditions. The scope of this paper is to propose a novel approach for the analysis of cyclononstationary signals to cover the simultaneous and independently varying speed and load operating conditions. The effectiveness of the approach is evaluated on simulated and real signals captured on a dedicated test rig.

Download Full-text