A fault detection, diagnosis, and reconfiguration method via support vector machines

Kabaoğlu, Rana Ortaç

doi:10.3906/elk-1301-96

Cited by 2 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is worth reminding that an electrotechnical system has two interesting peculiarities; first, it can be decomposed into several subsystems linked together, and second, the models used in these systems are generally linear; if they are not, they can be linearized. Studying the possible drawbacks and trying to find the appropriate solutions to the problem is a necessity in order to achieve good fault tolerant control architecture [10][11][12].…”

Section: Introductionmentioning

confidence: 99%

Diagnosis of speed sensor faults in an induction machine based on a robust adaptive super-twisting observer

Kari¹,

Mechernene²,

Meliani³

et al. 2020

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

The present paper aims to determine a robust sensor fault-tolerant controller based on fuzzy logic using a robust adaptive super-twisting observer for the control of an induction machine and an inverter set by a state estimation method. The speed sensor is considered in the present case. The modular structure of the fault-tolerant control (FTC) scheme allows integrating this sensor within the existing closed-loop system, and the observer can therefore be designed independently. This article presents a new method to develop a fuzzy decision system that provides faulttolerant control. This paper also aims at detecting the mechanical speed sensor faults. The proposed approach allows the automatic reconfiguration of the system in the event of a speed sensor failure. The defective fuzzy detection system makes a transition between the speed sensor and the robust observer based on a super-twisting algorithm that ensures the continuity and stability of the system; the fuzzy detection and transition system is required to be robust to parametric variations, and must be fast enough in order to locate the defect and eventually make a transition in the event of a fault. The output of the fuzzy block is injected into the control block to ensure super-twisting speed regulation. The performance of the proposed strategy also the robustness against parameter variation are assessed by simulation thanks to Matlab/Simulink software.

show abstract

Section: Introductionmentioning

confidence: 99%

Diagnosis of speed sensor faults in an induction machine based on a robust adaptive super-twisting observer

Kari¹,

Mechernene²,

Meliani³

et al. 2020

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

show abstract

“…As such, it requires an intelligent algorithm to support fault diagnosis in multibranch networks from the reflectometry trace provided. Artificial neural networks (ANNs) [14,15] and support vector machines (SVMs) [16][17][18] have been widely applied to fault diagnosis in distribution systems, in which SVM gives better results compared to ANN.…”

Section: Introductionmentioning

confidence: 99%

A novel perturbed particle swarm optimization-based support vector machine for fault diagnosis in power distribution systems

Thom¹,

Cho²,

Tuan³

2018

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Abstract:In this paper, a novel perturbed particle swarm optimization (PPSO) algorithm is investigated to improve the performance of a support vector machine (SVM) for short-circuit fault diagnosis in power distribution systems.In the proposed PPSO algorithm, the velocity of each particle is perturbed whenever the particles strike into a local optimum, in order to achieve a higher quality solution to optimization problems. Furthermore, the concept of proposed perturbation is applied to three variants of PSO, and improved corresponding algorithms are named perturbed C-PSO (PC-PSO), perturbed T-PSO (PT-PSO), and perturbed K-PSO (PK-PSO). For the purpose of fault diagnosis, the timedomain reflectometry (TDR) method with pseudorandom binary sequence (PRBS) excitation is considered to generate the necessary fault simulation data set. The proposed approaches are tested on a typical two-lateral radial distribution network.

show abstract

A fault detection, diagnosis, and reconfiguration method via support vector machines

Cited by 2 publications

References 29 publications

Diagnosis of speed sensor faults in an induction machine based on a robust adaptive super-twisting observer

Diagnosis of speed sensor faults in an induction machine based on a robust adaptive super-twisting observer

A novel perturbed particle swarm optimization-based support vector machine for fault diagnosis in power distribution systems

Contact Info

Product

Resources

About