Infrared thermal measurement in power system considering complex circumstances

Abstract Infrared thermal measurement is a vital tool in power systems for monitoring the temperature of electrical equipment without direct contact. This non-invasive technique helps detect hot spots, identify potential issues, and evaluate the performance of power system components. However, the accuracy of the thermal measurement for power system equipment suffers from complex situations and stochastic circumstances. This paper uses a machine-learning-based method to calculate the accurate surface temperature of equipment, which is mainly based on the feedforward network and backpropagation algorithm. At the same time, multiple regression algorithms are implemented and compared. The simulation results and the experiments show that the infrared thermal measurement based on the proposed method reduces the measurement error to 0.1%.