Automatic Methodology for Multiple Fault Detection in Induction Motor Under Periodic Low-Frequency Fluctuating Load Based on Stray Flux Signals

被引:2
作者
Saucedo-Dorantes, J. J. [1 ]
Elvira-Ortiz, D. A. [1 ]
Jaen-Cuellar, A. Y. [1 ]
Antonino-Daviu, J. A. [2 ]
Osornio-Rios, R. A. [1 ]
机构
[1] Autonomous Univ Queretaro, HSPdigital CA Mecatron Engn Fac, San Juan Del Rio 76806, Mexico
[2] Univ Politecn Valencia, Inst Tecnol Energia, Valencia 46022, Spain
关键词
Circuit faults; Rotors; Induction motors; Self-organizing feature maps; Proposals; Vibrations; Stator windings; Condition monitoring; stray flux; fluctuating load; induction motor; self-organizing maps; statistical features; BROKEN ROTOR BAR; ECCENTRICITY; TRANSFORM; DIAGNOSIS; SYSTEM; CAGE;
D O I
10.1109/TEC.2023.3294392
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
Induction Motors are widely used in industrial facilities to perform energy conversion from electrical to mechanical. Hence, the detection of faults in these machines may lead to reduced losses and avoid unwanted stoppages. On the other hand, fault identification is often difficult since most of the processes are operating under non-stationary conditions produced by fluctuating loads, among others. Thereby, this work lies on the proposal of an automatic diagnosis methodology for detecting the occurrence of multiple faults in an induction motor that operates under the effect of a fluctuating load; the proposal is based on the processing of stray flux signals and on their characterization through a meaningful set of statistical features and then, a feature learning procedure is performed by Self-Organizing Maps to achieve a 2d grid modeling that preserves the most relevant topological properties for each assessed condition. Subsequently, the linear discriminant analysis is considered to carry out the dimensionality reduction of the previously modeled grids; all considered conditions are projected into a 2d space and finally, the identification of five different conditions in the induction motor is achieved by a proposed Neural Network classifier. Moreover, in the article, the analysis of the stator current signatures is also carried out for validation purposes. The proposed method is evaluated with experimental data. The obtained results make this proposal suitable for being applied in the monitoring of industrial applications that operate under fluctuating load conditions.
引用
收藏
页码:2744 / 2753
页数:10
相关论文
共 37 条
  • [1] Broken Rotor Bar and Rotor Eccentricity Fault Detection in Induction Motors Using a Combination of Discrete Wavelet Transform and Teager-Kaiser Energy Operator
    Agah, Gholam Reza
    Rahideh, A.
    Khodadadzadeh, Hosein
    Khoshnazar, Seyed Moslehoddin
    Kia, Shahin Hedayati
    [J]. IEEE TRANSACTIONS ON ENERGY CONVERSION, 2022, 37 (03) : 2199 - 2206
  • [2] Demodulation Technique for Broken Rotor Bar Detection in Inverter-Fed Induction Motor Under Non-Stationary Conditions
    Alberto Garcia-Calva, Tomas
    Morinigo-Sotelo, Daniel
    Garcia-Perez, Arturo
    Camarena-Martinez, David
    de Jesus Romero-Troncoso, Rene
    [J]. IEEE TRANSACTIONS ON ENERGY CONVERSION, 2019, 34 (03) : 1496 - 1503
  • [3] Machine Learning-Based Fault Diagnosis for Single- and Multi-Faults in Induction Motors Using Measured Stator Currents and Vibration Signals
    Ali, Mohammad Zawad
    Shabbir, Md Nasmus Sakib Khan
    Liang, Xiaodong
    Zhang, Yu
    Hu, Ting
    [J]. IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 2019, 55 (03) : 2378 - 2391
  • [4] On-field experience with Online diagnosis of large induction motors cage failures using MCSA
    Bellini, A
    Filippetti, F
    Franceschini, G
    Tassoni, C
    Passaglia, R
    Saottini, M
    Tontini, G
    Giovannini, M
    Rossi, A
    [J]. IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 2002, 38 (04) : 1045 - 1053
  • [5] Stray Flux Analysis for the Detection and Severity Categorization of Rotor Failures in Induction Machines Driven by Soft-Starters
    Biot-Monterde, Vicente
    Navarro-Navarro, Angela
    Antonino-Daviu, Jose A.
    Razik, Hubert
    [J]. ENERGIES, 2021, 14 (18)
  • [6] Sensorless Speed Estimation for the Diagnosis of Induction Motors via MCSA. Review and Commercial Devices Analysis
    Bonet-Jara, Jorge
    Quijano-Lopez, Alfredo
    Morinigo-Sotelo, Daniel
    Pons-Llinares, Joan
    [J]. SENSORS, 2021, 21 (15)
  • [7] Caesarendra W, 2017, MACHINES, V5, DOI 10.3390/machines5040021
  • [8] Vibration signatures of a rotor-coupling-bearing system under angular misalignment
    da Silva Tuckmantel, Felipe Wenzel
    Cavalca, Katia Lucchesi
    [J]. MECHANISM AND MACHINE THEORY, 2019, 133 : 559 - 583
  • [9] Fault Indexing Parameter Based Fault Detection in Induction Motor via MCSA with Wiener Filtering
    Deekshit, Kompella K. C.
    Rao, Mannam V. Gopala
    Rao, Rayapudi S.
    [J]. ELECTRIC POWER COMPONENTS AND SYSTEMS, 2021, 48 (19-20) : 2048 - 2062
  • [10] Bearing Health Monitoring Based on the Orthogonal Empirical Mode Decomposition
    Delprete, C.
    Brusa, E.
    Rosso, C.
    Bruzzone, F.
    [J]. SHOCK AND VIBRATION, 2020, 2020