On-Line Vacuum Degree Detection of Vacuum Circuit Breaker Based on Laser-Induced Breakdown Spectroscopy Combined with WTD-RF

In the field of high-voltage switchgear, the vacuum circuit breaker has the advantages of strong breaking capacity, compact structure, and environmental protection. However, online monitoring of vacuum degree of vacuum interrupter remains a challenge. The vacuum detection method based on laser-induced plasma breakdown spectroscopy (LIBS) technology is expected to achieve safe and reliable online monitoring of vacuum degree in vacuum interrupters. Therefore, a model combined with wavelet threshold denoising and random forest regression (WTD-RF) is proposed to measure the vacuum degree of vacuum interrupter. Firstly, WTD is used to reduce the background noise and improve the spectral signal-to-noise ratio. Then, the relationship of spectral line integral intensity and the vacuum degree is trained by RF. The prediction results of vacuum degree are compared by multiple machine learning models. It is found that the proposed model in this paper has better generalization ability and higher accuracy obtained by the comprehensive evaluation matrix. The study shows that the WTD-RF improve the detection ability of vacuum degree and can be the suitable method for monitoring the LIBS-based vacuum degree detection of vacuum interrupter.