Grading ring optimization design method based on finite elements and deep belief network

Abstract

The invention provides a grading ring optimization design method based on finite elements and a deep belief network. The method comprises the following steps: constructing a training sample set and atest sample set for optimizing structural parameters of the grading ring; training the training sample set through a deep belief network to obtain a trained deep belief network for fitting the relationship between each structure parameter of the grading ring and the maximum electric field intensity along the surface; performing deep belief network training for multiple times, calculating the output of the test sample, namely the maximum electric field intensity along the surface, by utilizing the trained deep belief network, comparing the output with the maximum electric field intensity alongthe surface in the test sample set to obtain an average absolute percentage error, and optimizing according to a genetic algorithm to obtain an optimal solution of the structural parameters of the grading ring. The test frequency and time are greatly reduced, and the working efficiency is improved.

Description

technical field [0001] The invention relates to the field of high-voltage insulation, in particular to a method for optimizing the design of voltage equalizing rings based on finite elements and deep belief networks. Background technique [0002] The square wave power supply for on-site testing of DC measuring devices can provide on-site calibration for high-voltage DC current transformers to ensure the safe operation of the DC transmission system. The energy storage component is an indispensable core part of the square wave power supply for field testing of DC measuring devices. Its function is to store energy and release energy at an appropriate time. Due to the high voltage applied to the top of the energy storage component, coupled with the shape characteristics of the energy storage component and the low conductivity of the insulating shell, the potential distribution decays rapidly from the high voltage end, and the voltage distribution is extremely uneven, resulting i...

AI Technical Summary

Problems solved by technology

However, not all pressure equalizing rings with structural parameters can play this role. Factors such as the installation position of the pressure equalizing ring and its own structural parameters will directly affect the potential distribution of the energy storage component along the surface.

Images