Abstract:

The temperature measurement of the high voltage switchgear joints covered with insulating materials has always been the main concern of power design.For the problems such as difficulty in pre-positioning of the insulator epoxy resin casting buried sensor,internal magnetic field interference,and the creepage distance of the sensor lead,it is proposed the scheme that take the outer wall of the insulation layer and the ambient temperature of the body space as reference factors to indirectly calculate the conductor joint temperature.The cable joints of the high voltage cabinet are modeled by Ansys,and the temperature field distribution at the joints is obtained.The relationship between the joint temperature and the outer wall temperature of the insulating material and the ambient temperature is studied,and the conductor joint temperature is calculated by the support vector machine and neural network algorithm by using the outer wall temperature of the insulating material and the ambient temperature.The results show that the neural network algorithm has high accuracy and can be used for on-line monitoring of the joint temperature of high voltage switchgear covered with insulating materials,which has certain reference significance for related engineering applications.

Key words: high voltage switchgear, conductor joint, temperature measurement, on-line monitoring, neural network