A Novel Time-Domain Fault Diagnosis Method With ELM for Aviation Intermediate Frequency Inverter
- 26 February 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-9
Abstract
The fault diagnosis for the intermediate frequency inverter in the aviation industry has always been a difficult problem. However, most of the existing fault diagnosis methods are not directly applicable to it due to changes in system characteristics. In order to solve this problem, a new fault diagnosis model is proposed. Firstly, preliminary parameters are extracted from the measured current sequence. Secondly, two types of features values are obtained directly using the proposed current amplitude-deviation feature complement method, which can effectively distinguish usual open-circuit fault modes of the inverter. Thirdly, the dataset consisting of the above feature values is acquired under different load condition and fault modes. Finally, based on low-dimensional feature values data, the extreme learning machine is used to generate a fault diagnosis model rapidly through matrix operations. By experiments, the method proposed can accurately realize the fault diagnosis of aviation intermediate frequency inverter. Compared with most existing methods, proposed feature extraction method has advantages in fault discrimination ability and implementation difficulty. And extreme learning machine speeds up the training process and facilitates debugging.Keywords
Funding Information
- National Natural Science Foundation of China (62003274, 62073267)
- Shanxi Provincial Youth Project (5113220040)
- Fundamental Research Funds for the Central Universities (G2020KY05110)
This publication has 22 references indexed in Scilit:
- A Transferrable and Noise-Tolerant Data-Driven Method for Open-Circuit Fault Diagnosis of Multiple Inverters in a MicrogridIEEE Transactions on Industrial Electronics, 2023
- On the Assessment of Sampling Rate Impacts on Responses of Digital Protective RelaysIEEE Transactions on Industry Applications, 2023
- Open-circuit fault diagnosis in voltage source inverter for motor drive by using deep neural networkEngineering Applications of Artificial Intelligence, 2023
- Fast In-Loop Single-Tube Open-Circuit Fault Diagnosis for Voltage Source Inverter Based on Duality of Current-Time PairsIEEE Transactions on Industrial Electronics, 2022
- Investigation of Analytical Models for Surface-Mounted Permanent Magnet Motor Using Voltage Source InverterIEEE Transactions on Industry Applications, 2022
- Fault Diagnosis Based on Attention Collaborative LSTM Networks for NPC Three-Level InvertersIEEE Transactions on Instrumentation and Measurement, 2022
- Minimization of DC-Link Capacitance for a DC-Link-Based Variable Speed Constant Frequency Aircraft Power SystemIEEE Transactions on Industry Applications, 2022
- The More-Electric Aircraft and BeyondProceedings of the IEEE, 2022
- Diagnosis and distinguishment of open-switch and current sensor faults in PMSM drives using improved regularized extreme learning machineMechanical Systems and Signal Processing, 2022
- High-Voltage Hybrid IGBT Power Modules for Miniaturization of Rolling Stock Traction InvertersIEEE Transactions on Industrial Electronics, 2021