Large high-speed rotary equipment blade sorting method based on multi-target regulation and control

Abstract

The invention discloses a large high-speed rotary equipment blade sorting method based on multi-target regulation and control. The method comprises the steps of 1, setting an initial population; 2, establishing a rotor mass, mass moment and frequency physical model, designing a fitness function according to the physical model and fitness function requirements, and performing fitness calculation onall chromosomes of the initial population; 3, performing selection operation on the initial population by adopting a roulette method; 4, performing the following steps by taking the probability generated by the cloud generator under the X condition as a necessary condition; 5, performing crossover operation by adopting a recombined crossover operator; 6, performing mutation operation by adoptinga two-element optimization mutation operator; 7, if the maximum number of iterations is not reached, repeating the steps 3-6; and if the maximum number of iterations is reached, ending the iteration,and outputting the optimal chromosome. Aiming at the requirement of poor quality of blade division quadrants, the rotor blades of the large high-speed rotary equipment are sorted through a cloud self-adaptive genetic algorithm to reduce the mass moment of the large high-speed rotary equipment.

Description

technical field [0001] The invention belongs to the technical field of large-scale high-speed rotary equipment; in particular, it relates to a method for sorting blades of large-scale high-speed rotary equipment based on multi-objective regulation. Background technique [0002] The unbalance optimization method of large-scale high-speed rotary equipment is an important content in engineering. A reasonable arrangement of blades can reduce the mass moment of the rotary equipment, improve the start-stop performance of the rotor and reduce the rotor vibration caused by blade resonance. In view of the above problems, the present invention proposes a three-objective optimization method for rotor blade mass, frequency, and mass moment. [0003] The quality characteristics of the rotor are related to the inertia, start-stop and acceleration characteristics of large-scale high-speed rotary equipment. Therefore, the general rotary equipment makes the following requirements on the qu...

AI Technical Summary

Problems solved by technology

[0006] General leaf sorting methods are slow and time-consuming, such as enumeration method and search method; the learning process of neural network algorithm is long, and it is easy to fall into local optimal situation; while particle swarm optimization algorithm is not good for discrete optimization problems, and the randomness of general genetic algorithm Strong, easy to mature, and easy to fall into local optimum

Images