Energy consumption analysis method and device based on AHP model self-learning

Abstract

The embodiment of the invention provides an energy consumption analysis method and device based on AHP model self-learning, and the method comprises the steps: obtaining energy consumption information, determining an energy consumption factor, and obtaining a factor attribute; establishing a first-layer structure of the AHP model according to the energy consumption information, and establishing a second-layer structure and a third-layer structure of the AHP model according to the factor attributes of the energy consumption factors; acquiring historical data of a production line corresponding to the energy consumption information, acquiring a data size and a data label corresponding to the historical data, performing traversal matching from bottom to top on an energy consumption factor of the AHP model according to the data size and the data label, and adjusting a factor weight of the energy consumption factor in the AHP model; and obtaining real-time data of any energy consumption factor of the production line, inputting the real-time data into the model, and obtaining energy consumption data, factor weights and total energy consumption of other energy consumption factors except the any energy consumption factor in the production line. By adopting the method, the core index of energy consumption can be quickly and accurately provided, the production efficiency is improved, and powerful help is provided for energy conservation and emission reduction decision making of production.

Description

Technical field [0001] The invention involves the field of energy computing technology, especially a energy consumption analysis method and device based on the AHP model. Background technique [0002] In recent years, with the rapid development of industrial manufacturing, manufacturing companies have gradually shifted from extensive management to refined and high -quality development under the strategic traction of manufacturing power. At this stage, almost all of the industrial industries are involved in energy consumption. Traditional data analysis of water, electricity, and coal consumed in production is mainly collected and reported to the computer system through manual methods. Analysis of work. Due to the large amount of data -related data such as production index data and equipment running parameters, it is difficult to fully collect and enter the report throughout the process. At the same time, because the definition standards for data abnormalities are not uniform and t...

AI Technical Summary

Problems solved by technology

Due to the large amount of data related to energy consumption such as production index data and equipment operating parameters, it is difficult to manually collect, input and report the entire process; It is difficult to manually judge the degree of abnormal energy consumption from the perspective of expert experience, so it is impossible to quickly find opportunities for energy consumption optimization;

[0003] In the existing technology, there is an energy consumption analysis through the AHP analysis method, but the pure AHP analysis method cannot consider the scientificity of its index selection and the various unpredictable constraints and feedback relationships that exist in the empowerment process

Images