Equipment performance-oriented electrical equipment automatic design system based on machine learning

Abstract

The invention provides a machine learning-based equipment performance-oriented electrical equipment automatic design system, which comprises the following steps of: constructing a reasonable mathematical model for electrical equipment expected to be designed, taking extracted and abstract data in a design instance as a training sample, learning a large amount of data of different types and function design instances, and calculating the design parameters of the electrical equipment. A forward prediction model and a reverse prediction model are trained, then the forward prediction model is used for correcting the reverse prediction model, and finally the automatic design system with the capacity of designing the electrical equipment is obtained. According to the equipment performance-oriented electrical equipment automatic design system based on machine learning, a distributed parallel information processing model is established on the basis of a neural network, and the equipment performance-oriented electrical equipment automatic design system for predicting, correcting and re-predicting required electrical equipment design parameters is provided. The electrical equipment design parameters are predicted through the neural network, and the trial and error cost in the design process is reduced.

Description

technical field [0001] The invention belongs to the field of electrical equipment, and in particular relates to an automatic design method of electrical equipment based on machine learning and guided by equipment performance. Background technique [0002] With the development of social economy and the continuous improvement of people's living standards, the market demand for electrical equipment with customized parameters continues to increase. In the process of traditional electrical equipment design, the design process, including the quality, heavily depends on the professionalism and design experience of the practitioners. Design experience needs to be continuously accumulated and updated. Cultivating a qualified designer often requires high time and economic costs. [0003] Electrical equipment, mechanical equipment and other equipment industries, as key areas of the manufacturing industry, have begun to introduce big data and machine learning technology to assist equi...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the present invention aims to propose an automatic design method of electrical equipment based on machine learning and guided by equipment performance, to solve the problem that the existing automatic design system design is difficult to reduce in the process of advancing from performance to parameters, and the prediction The problem that the result is not easy to converge

Images