A New Method to Mechanical Fault Classification with Support Vector Machine

Sun, Laijun; Liu, Mingliang; Qian, Haibo; Ye, Guangzhong

doi:10.1109/isdea.2010.88

Cited by 2 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The comparative assessment of the feature vector is carried out with real time data with that of the pattern being stored in the memory. Since WPT is a strong feature extraction technique, it has been incorporated with a combination of SVM in order to interpret the severity assessment, detection of fault and detection of composite fault with higher accuracy [106], [107]. Similarly the concept of WPT is implemented in [108] for stationary stator current in order to explore the different fault condition which has been verified in the experimental test bed.…”

Section: Motor Diagnostic Using Artificial Intelligence and Deep Learningmentioning

confidence: 99%

A Comprehensive Review of Condition Based Prognostic Maintenance (CBPM) for Induction Motor

et al. 2019

View full text Add to dashboard Cite

This paper presents condition monitoring aspects of induction motor, its present status with possible mitigation schemes and future maintenance challenges. The induction motors constitute the major portion of motors in domestic and industrial applications. These motors experience different types of failures and faults associated with insulation, bearing, stator, rotor, and eccentricity. As a matter of fact, these faults may subsequently enhance the probability of failures unless proper introspection is not accomplished. In order to reduce the failure time and operating cost, early detection is indispensable which necessitates condition-based approach on contrary to scheduled maintenance. The condition monitoring is a strong candidate to address the diagnosis of machinery failure problems and unreliability. In this context, a comprehensive analysis is reported in the literature with a focus on different methodologies being addressed for such objective. Utmost efforts are made to comprehensively analyze in the reported literature in a sequential manner citing the advantage and limitations in this paper. The authors hopefully described and illustrated the associated problems with possible mitigation in the context of condition monitoring which would be immensely helpful for future researchers working in these aspects and the future roadmap would be clearly reflected.

show abstract

Section: Motor Diagnostic Using Artificial Intelligence and Deep Learningmentioning

confidence: 99%

A Comprehensive Review of Condition Based Prognostic Maintenance (CBPM) for Induction Motor

et al. 2019

View full text Add to dashboard Cite

show abstract

“…New methods have been introduced to analyze and detect anomalous events such as epileptic seizure, coronary artery disease, and Alzheimer's disease from biomedical signals using different entropy types [21][22][23][24][25][26][27][28][29][30][31][32][33][34][35][36][37][38][39]. The application of the entropy approach in mechanical engineering is given in [40][41][42][43][44][45]. The application of entropy in the power systems was started because the system under investigation will have different entropy values under different states.…”

Section: Introductionmentioning

confidence: 99%

Wavelet entropy and its application for flicker contribution evaluation

Silsüpür

Türkay

2018

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

As a result of the integration of various new load types and generation units into electric power systems, power quality disturbances such as sag–swell, harmonics, inter‐harmonics, and flicker have come into focus in the last decades. Among these disturbances, flicker is one of the serious power quality issues for both power system operators and users. In addition to having direct effects on human life such as the discomfort caused by visual disturbance, flicker may cause incorrect operations of electrical devices. Furthermore, finding a dominant flicker source in order to mitigate it and supply high‐quality power to users are the main tasks of network operators. The measurement of the flicker level is defined in the IEC 61000‐4‐15 standard as measured by a flicker meter; however, it deals only with voltage signals and is not sufficient to understand the contribution of the load and background power systems separately. Therefore, this paper proposes new approaches to the evaluation of flicker characteristics using simulated and real signals. The novelty of this paper is that it investigates the flicker characteristics in the light of multi‐resolution wavelet analysis and information‐theory‐based wavelet energy entropy analysis together and proposes a new index to interpret flickers' responsibility in load and flicker source detection. The proposed method uses only voltage and current signals and does not require additional calculation of any network parameter such as the system impedance. The proposed method is validated by simulations as well as site measurements, and the results show the accuracy and suitability of the proposed method. © 2018 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

show abstract

A New Method to Mechanical Fault Classification with Support Vector Machine

Cited by 2 publications

References 3 publications

A Comprehensive Review of Condition Based Prognostic Maintenance (CBPM) for Induction Motor

A Comprehensive Review of Condition Based Prognostic Maintenance (CBPM) for Induction Motor

Wavelet entropy and its application for flicker contribution evaluation

Contact Info

Product

Resources

About