Deep Learning for High-Impedance Fault Detection: Convolutional Autoencoders

被引:24
作者
Rai, Khushwant [1 ]
Hojatpanah, Farnam [1 ]
Ajaei, Firouz Badrkhani [1 ]
Grolinger, Katarina [1 ]
机构
[1] Univ Western Ontario, Dept Elect & Comp Engneering, London, ON N6A 5B9, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
high-impedance fault; power system protection; unsupervised learning; deep learning; convolutional autoencoder; convolutional neural network; ANOMALY DETECTION; CLASSIFICATION; INTELLIGENCE; NETWORKS;
D O I
10.3390/en14123623
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
High-impedance faults (HIF) are difficult to detect because of their low current amplitude and highly diverse characteristics. In recent years, machine learning (ML) has been gaining popularity in HIF detection because ML techniques learn patterns from data and successfully detect HIFs. However, as these methods are based on supervised learning, they fail to reliably detect any scenario, fault or non-fault, not present in the training data. Consequently, this paper takes advantage of unsupervised learning and proposes a convolutional autoencoder framework for HIF detection (CAE-HIFD). Contrary to the conventional autoencoders that learn from normal behavior, the convolutional autoencoder (CAE) in CAE-HIFD learns only from the HIF signals eliminating the need for presence of diverse non-HIF scenarios in the CAE training. CAE distinguishes HIFs from non-HIF operating conditions by employing cross-correlation. To discriminate HIFs from transient disturbances such as capacitor or load switching, CAE-HIFD uses kurtosis, a statistical measure of the probability distribution shape. The performance evaluation studies conducted using the IEEE 13-node test feeder indicate that the CAE-HIFD reliably detects HIFs, outperforms the state-of-the-art HIF detection techniques, and is robust against noise.
引用
收藏
页数:25
相关论文
共 43 条
  • [1] An ensemble learning framework for anomaly detection in building energy consumption
    Araya, Daniel B.
    Grolinger, Katarina
    ElYamany, Hany F.
    Capretz, Miriam A. M.
    Bitsuamlak, Girma
    [J]. ENERGY AND BUILDINGS, 2017, 144 : 191 - 206
  • [2] High impedance fault detection methodology using wavelet transform and artificial neural networks
    Baqui, Ibrahem
    Zamora, Inmaculada
    Mazon, Javier
    Buigues, Garikoitz
    [J]. ELECTRIC POWER SYSTEMS RESEARCH, 2011, 81 (07) : 1325 - 1333
  • [3] An Intelligent Detection of High-Impedance Faults for Distribution Lines Integrated With Distributed Generators
    Chaitanya, Bokka Krishna
    Yadav, Anamika
    Pazoki, Mohammad
    [J]. IEEE SYSTEMS JOURNAL, 2020, 14 (01): : 870 - 879
  • [4] Application of Smart Meters in High Impedance Fault Detection on Distribution Systems
    Chakraborty, Soham
    Das, Sarasij
    [J]. IEEE TRANSACTIONS ON SMART GRID, 2019, 10 (03) : 3465 - 3473
  • [5] Chi C. Y., 2006, Blind Equalization and System Identification: Batch Processing Algorithms, Performance and Applications
  • [6] A Feature Selection Method for High Impedance Fault Detection
    Cui, Qiushi
    El-Arroudi, Khalil
    Weng, Yang
    [J]. IEEE TRANSACTIONS ON POWER DELIVERY, 2019, 34 (03) : 1203 - 1215
  • [7] HIGH IMPEDANCE FAULT ARCING ON SANDY SOIL IN 15KV DISTRIBUTION FEEDERS - CONTRIBUTIONS TO THE EVALUATION OF THE LOW-FREQUENCY SPECTRUM
    EMANUEL, AE
    CYGANSKI, D
    ORR, JA
    SHILLER, S
    GULACHENSKI, EM
    [J]. IEEE TRANSACTIONS ON POWER DELIVERY, 1990, 5 (02) : 676 - 686
  • [8] Analytical investigation of autoencoder-based methods for unsupervised anomaly detection in building energy data
    Fan, Cheng
    Xiao, Fu
    Zhao, Yang
    Wang, Jiayuan
    [J]. APPLIED ENERGY, 2018, 211 : 1123 - 1135
  • [9] Detection of High Impedance Fault in Power Distribution Systems Using Mathematical Morphology
    Gautam, Suresh
    Brahma, Sukumar M.
    [J]. IEEE TRANSACTIONS ON POWER SYSTEMS, 2013, 28 (02) : 1226 - 1234
  • [10] High impedance fault detection: A review
    Ghaderi, Amin
    Ginn, Herbert L., III
    Mohammadpour, Hossein Ali
    [J]. ELECTRIC POWER SYSTEMS RESEARCH, 2017, 143 : 376 - 388