The electronic nose technology based on Pt-WO3 sensor array for precise detection of fault gases in GIS systems

Gas insulated switchgear (GIS) optimizes the integration of all primary equipment in a substation, except for the transformer, and is widely used in power systems due to its strong insulation and high reliability. Once a fault occurs in GIS, it poses a significant threat to grid safety, necessitating the establishment of an effective early insulation condition assessment mechanism to prevent further deterioration of the fault. CO, HF, and SO 2 are key characteristic gases reflecting GIS faults, and there is an urgent need for detection technologies that can monitor equipment status in real-time, accurately, and provide timely warnings. This study proposes the use of a differentiated sensor array combined with recognition algorithms to achieve precise detection of GIS fault gases. The WO 3 modified with different amounts of Pt shows good gas-sensing performance for CO, HF, and SO 2 , with distinct responses. Based on an optimized four-sensor array and feature extraction algorithms, high-precision qualitative classification (98.04%) of CO, HF, SO 2 , and their mixed gases was achieved, with high R 2 values in concentration prediction (0.9213 for CO, 0.9082 for HF, and 0.8947 for SO 2 ). Furthermore, an in-depth study of the differentiation mechanism of the sensor array was conducted. Finally, the developed IoT electronic nose system successfully demonstrated the precise detection of GIS fault gases. This research not only proposes a new solution for GIS fault detection but also provides a “boost” for the development of electronic noses.