Multi-target coal blending method based on preference of decision maker

Abstract

The invention relates to a decision maker preference-based multi-target coal blending method, which comprises the following steps of: constructing a decision variable representing a coal blending scheme and a plurality of target functions, and obtaining an optimal coal blending scheme through an NSGA-II algorithm according to the decision variable and the plurality of target functions; wherein the NSGA-II algorithm comprises the following steps: 1) performing population initialization by taking a decision variable as an individual; 2) performing selection, crossover and mutation operation on the population; 3) combining the parent population and the offspring population; 4) performing preference-angle non-dominated layering on the population; 5) calculating individual aggregation distances of the individuals, and reserving the individual with the maximum individual aggregation distance in each non-dominated layer; and 6) judging whether the population evolution generation number is greater than the maximum number of iterations, if so, ending, selecting individuals meeting the preference angle judgment conditions from the population as a preference solution set, and otherwise, executing the step 2). Compared with the prior art, the method is high in efficiency and high in pertinence.

Description

technical field [0001] The invention relates to the technical field of coal blending in power plants, in particular to a multi-objective coal blending method based on decision maker preference. Background technique [0002] Power coal blending technology is a clean coal technology in line with my country's national conditions. It can effectively alleviate the pressure on coal blending work in power plants due to the complexity and variability of coal types in my country and the large difference in coal quality. Therefore, coal blending and blending technology It has broad application prospects in our country. [0003] In order to ensure the flexibility and scientificity of power coal blending technology, theoretical research on power coal blending has been carried out in China. Because the classic single-objective coal blending model has one-sided considerations and cannot adapt to the actual coal blending problem, the current multi-objective coal blending method has become ...

AI Technical Summary

Problems solved by technology

Because the classic single-objective coal blending model has one-sided considerations and cannot adapt to the actual coal blending problem, the current multi-objective coal blending method has become a research hotspot.

Although the theoretical method of multi-objective coal blending and blending has made some progress, the multi-objective optimization algorithm always has problems such as high computational complexity and too many optimization results, which makes it impossible for decision makers to select the most suitable coal blending scheme, lacking in efficiency and practicality. value

Images