An Intelligent Time-Adaptive Data-Driven Method for Sensor Fault Diagnosis in Induction Motor Drive System

Интеллектуальный адаптивный по времени метод диагностики неисправностей датчиков на основе данных в системе электропривода с асинхронным двигателем
Yan Hui Xu, Shuyong Liu, Bin Gou, Yang Xia, Gary Wilson
2018-11-15

ensemble extreme learning machineinduction motor drive systempulsewidth modulation invertersensor fault diagnosistime-adaptive fault diagnosis
Three-phase pulsewidth modulation inverter fed induction motor drive system is widely applied in high power drive applications. Sensor faults are very common in the drive system, which, once occur, might result in degraded system performance or even system shutdown. In order to rapidly and accurately diagnose the sensor faults, this paper proposes an intelligent time-adaptive data-driven method to identify the fault location and fault type of sensors in the drive system. An emerging machine learning technology named extreme learning machine (ELM) is applied to learn the sensor fault dataset; an ensemble ELM classifier is then designed to improve diagnostic accuracy, based on which a time-adaptive fault diagnosis process is proposed to achieve a high and balanced diagnostic accuracy and speed. As a data-driven method, the proposed method only employs the phase current, dc-link voltage, and speed signals as the inputs to the ensemble ELM classifiers and requires no additional sensors and other hardware. Simulated and experimental tests show that the proposed method can rapidly and accurately detect the fault sensor location and identify offset fault, stuck fault, and noise faults with an average diagnostic accuracy of 98% and the average decision time of 10 ms after the fault occurs. Moreover, such diagnosis method is robust to the fluctuation of catenary voltage and dc-link voltage, fault severity, and variation of model parameters, speed, and load.
1
An ensemble extreme learning machine classifier improves diagnostic accuracy, while time-adaptive processing balances diagnosis speed and accuracy.
2
Simulation and experimental tests achieved 98% average diagnostic accuracy and a 10 ms average decision time after fault occurrence.
3
The method identifies offset, stuck, and noise faults and remains robust to voltage fluctuations, fault severity, parameter variation, speed, and load changes.
4
The method uses only phase currents, dc-link voltage, and speed signals, requiring no additional sensors or hardware.
5
The paper proposes an intelligent time-adaptive, data-driven method for diagnosing sensor fault locations and fault types in induction motor drive systems.

three-phase PWM inverter-fed induction motor drive system and its sensors

time-adaptive data-driven diagnosis of sensor fault location and type, including offset, stuck, and noise faults, with diagnostic accuracy, speed, and robustness

Publication Details
Publication Date
2018-11-15
Journal
Publisher
ISSN
Cited by
197
Access Type
Author Information
Authors
Yan Hui Xu
Shuyong Liu
Bin Gou
Yang Xia
Gary Wilson
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%