Air compressor group optimization scheduling method based on hybrid model

Abstract

The invention relates to an air compressor group optimization scheduling method based on a hybrid model, belonging to the field of information technology. In order to solve the blindness in present air compressor group scheduling, a hybrid model combining a simulation technology and a combined scheduling optimization decision is established. The method comprises the steps of dynamically updating an air compressor energy consumption model sample set constructed by expert experience by using an industrial field real-time sample, then performing on-line learning on relevant parameters of an air compressor energy consumption model by using a least squares algorithm, solving an air compressor group multi-objective optimization scheduling model by using a simulation technology and a hierarchicaltree search algorithm, and finally, comprehensively evaluating the acquired scheduling plan by using an entropy weight method and a TOPSIS method, thereby assisting on-site dispatchers in making a safe, energy-saving, environment-friendly and economic scheduling plan. The method also has wide application value in different industrial fields.

Description

technical field [0001] The invention belongs to the field of information technology, and relates to theories such as data-based dynamic modeling of air compressors, online update of model parameters, combined model optimization and solution based on simulation technology and hierarchical tree search algorithm, and is a hybrid model-based Air compressor group optimal scheduling method. The present invention utilizes the real-time samples of the industrial site to dynamically update the sample set of the air compressor energy consumption model constructed by expert experience, and then uses the least squares algorithm to conduct online learning on the relevant parameters of the air compressor energy consumption model, and applies simulation technology and analysis The layer tree search algorithm solves the multi-objective optimal scheduling model of the air compressor group, and finally uses the entropy weight method and the distance method of superior and inferior solutions to ...

AI Technical Summary

Problems solved by technology

There are multiple air compressor groups in the metallurgical energy system. How to realize the reasonable allocation of air compressors in different groups is an intelligent scheduling problem in the field of artificial intelligence. Air compressors have different operating mechanisms and model parameters, so it is difficult to establish a universal air compressor mechanism model; equipment wear and parameter drift during the operation of the air compressor require air compressor performance The consumption model should be real-time in order to accurately reflect the actual production energy consumption of the air compressor; it is very difficult to exhaustively enumerate the possible combination schemes of air compressors, and a method that can quickly and accurately solve the air compressor group is needed. The method of multi-objective optimization model; from the perspective of practical application, there are multiple evaluation indicators in the air compressor group combination scheme, so each evaluation index should be considered comprehensively, and an optimal scheduling scheme should be selected from many feasible schemes

At present, there is still a lack of an effective method that can systematically solve the above problems at the same time

Images