Back to Search
Start Over
Remaining Useful Life Prediction of Electromagnetic Release Based on Whale Optimization Algorithm—Particle Filtering
- Source :
- Energies, Vol 17, Iss 3, p 670 (2024)
- Publication Year :
- 2024
- Publisher :
- MDPI AG, 2024.
-
Abstract
- The DC circuit breaker is a crucial equipment for eliminating faults in DC transmission lines. The electromagnetic release functions as a critical component that restricts the circuit breaker’s lifespan. It is essential to prioritize its safety and reliability during usage and predicting its remaining useful life (RUL) is paramount. This paper proposes a new prediction technique based on particle filtering (PF) and the whale optimization algorithm (WOA) for the remaining useful life of electromagnetic release. The particle filtering algorithm is a commonly used technique in practical engineering fields such as target tracking and RUL prediction. It is a mainstream method for solving the parameter estimation of non-linear non-Gaussian systems. The WOA is introduced to improve the PF algorithm in order to ensure the diversity of particles and lessen the effect of particle degradation. The WOA replaces the traditional resampling process, and after each computation is finished, the weights of the particles in the particle set are reassigned in order to improve the particle distribution and increase algorithm accuracy. The rate of loss of the spring reaction force and the striker counterforce are chosen as the degradation characteristics after the degradation factors of electromagnetic release are analyzed. The degradation curves at different temperatures of electromagnetic release are obtained using the accelerated life test, and the full-life data during normal operation are derived using the Arrhenius equation. Finally, the RUL is predicted by comparing this paper’s method with the conventional PF method. The experimental results demonstrate that the method presented in this paper can more accurately predict the RUL of the electromagnetic release and has a higher prediction accuracy.
Details
- Language :
- English
- ISSN :
- 19961073 and 23047283
- Volume :
- 17
- Issue :
- 3
- Database :
- Directory of Open Access Journals
- Journal :
- Energies
- Publication Type :
- Academic Journal
- Accession number :
- edsdoj.3f94856c8cbd4ac5b230472832b48f3a
- Document Type :
- article
- Full Text :
- https://doi.org/10.3390/en17030670