ARTÍCULO
TITULO

Bearing/Incipient/Open Phase Fault Detection and Diagnosis of Multi-Phase Induction Motor Drives Equipped By GBDTI2HO Technique

Annamalai Balamurugan    
Thangavel Swaminathan Sivakumaran    

Resumen

In this paper, a hybrid system is performed with fault detection and diagnosis on multi-phase induction motor (IM). The proposed method is hybrid of integrated Harris Hawk optimization (IHHO) and gradient boosting decision trees (GBDT) thus called the GBDTI2HO method. Here, additional operators are included in this paper to improve HHO?s search behaviour namely crossover and mutation. Distorted waveforms are generated by different frequency patterns to indicate the time domain frequency as an assessment of failure. For this signal representation, the discrete wavelet transformation (DWT) is suggested. It extracts the characteristics and forwards them to IHHO technique to form the possible data sets. After the generation of the data set, GBDT classifies the ways of failure reached as winding of stator in multi-phase IM. The implementation of the proposed system is compared with existing systems, such as ANN, S-Transform and GBDT. The proposed method is executed on MATLAB/Simulink work platform to demonstrate the successfulness of proposed system, statistical measures are determined, as precision, sensitivity and specificity, mean median and standard deviation. For demonstrating the successfulness of proposed system, statistical measures are determined as precision, sensitivity, specificity, mean median as well as standard deviation. In 50 trails the proposed method, 0.98 for accuracy, 0.96 for specificity, 1.60 for recall as well as 0.97 for precision. In 100 trail the proposed method, 0.96 for accuracy, 0.93 for specificity, 0.87 for recall as well as 0.99 for precision.

 Artículos similares

       
 
Issarachai Ngamroo, Wikorn Kotesakha, Suntiti Yoomak and Anantawat Kunakorn    
This study aims to evaluate the impact of the distributed generator (DG) connection to the grid. The simulated results present the parameters of the system required to install DG on the end of the main distribution feeder. Various parameters, such as vol... ver más
Revista: Applied Sciences

 
Hong Je-Gal, Seung-Jin Lee, Jeong-Hyun Yoon, Hyun-Suk Lee, Jung-Hee Yang and Sewon Kim    
Ensuring operational reliability in machinery requires accurate fault detection. While time-domain vibration pulsation signals are intuitive for pattern recognition and feature extraction, downsampling can reduce analytical complexity, but may result in ... ver más

 
Yueheng Liu and Xinding Zhang    
Nonadiabatic Abelian geometric quantum computation has been extensively studied, due to its fast manipulation and inherent noise resistance. However, to obtain the pure geometric phase, the quantum state is required to evolve along some special paths to ... ver más
Revista: Applied Sciences

 
Qiongfang Yu, Liang Zhao and Yi Yang    
For low-voltage three-phase systems, the deep fault arc features are difficult to extract, and the phase information has strong timing. This phenomenon leads to the problem of low accuracy of fault phase selection. This paper proposes a three-phase fault... ver más
Revista: Applied Sciences

 
Jakub Kellner, Slavomír Ka?cák and ?elmíra Ferková    
Multiphase electric motors in cooperation with power semiconductor converters belong to the future of electric drives. This is because of their better properties compared to three-phase motors, such as better fault tolerance. How a multiphase motor will ... ver más
Revista: Applied Sciences