Fan control multi-objective optimization method based on multi-parent optimization network and genetic algorithm

Abstract

The invention relates to a fan control multi-objective optimization method based on a multi-parent optimization network and a genetic algorithm. The method includes the following steps that: step 1, operating variables are collected, a wind pressure and air volume variation range is given, one of a fan operating efficiency and wind pressure combination and a fan operating efficiency and air volumecombination is selected according to actual fan operating requirements and is adopted as a target variable; step 2, a GA-optimized multi-parent BP neural network prediction model is established; step3, a second-generation genetic algorithm model is established, a non-dominated sorting operator, a congestion comparison operator and an elite strategy design operator are adopted; and step 4, the wind pressure, efficiency and air volume of a fan are predicted through the established GA-optimized multi-parent BP neural network model, predicted values are used for solving an objective function value in the second generation genetic algorithm model, so that pareto front edges are obtained, operation variables obtained after inverse normalization is performed on operation variables correspondingto the pareto front edges are fed back to the control component of the fan, so that the operating parameters of the fan can be adjusted accordingly. The method of the invention has advantages of highprecision, good effect and low time consumption.

Description

technical field [0001] The invention belongs to the field of control technology of fan operation process and simulation of industrial process, and relates to a multi-objective optimization method for fan operation control. Background technique [0002] The fan is a driven fluid machine, whose function is to increase the pressure of the gas and transport it. It is widely used in the ventilation of factories, vehicles and buildings, and the cooling of household appliances. [0003] If the fan can be effectively controlled, the high-efficiency range can be expanded to improve its efficiency, and reduce the consumption of mechanical energy, which will save energy and reduce emissions for industrial equipment and household equipment. Among them, the change of each control parameter of the fan is a comprehensive effect on the performance of the fan. That is, when each operating parameter is changed, the variation trends of each target parameter of the fan are not consistent. An...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the shortcomings of the existing fan control methods such as low precision, poor effect, and long time consumption, the present invention provides a multi-parent optimization network and genetic Algorithmic multi-objective optimization method for fan control

Images