Slurry circulating pump optimization method and system based on data driving

Abstract

The invention provides a slurry circulating pump optimization method and system based on data driving, and the method comprises the steps: obtaining the historical operation data of related equipmentas the training data of a model, and selecting an index for data preprocessing; constructing a working condition division model by adopting a mean shift algorithm, and obtaining optimal values under different working conditions according to an optimal criterion; acquiring real-time operation data of related equipment as test data, and selecting indexes to perform data preprocessing; and matching the working condition types of the test data based on the working condition division model of the training data to obtain an optimization value, namely an optimization target value of the test data. According to the method, massive historical data of the slurry circulating pump equipment is fully mined through a clustering modeling method, an efficient and practical model is established to performindex optimization and optimization on the slurry circulating pump in real time, and the result relatively more conforms to production operation and is more reasonable and accurate.

Description

Technical field [0001] The technical field of desulfurization of the present invention specifically relates to a data-driven method and system for optimizing a slurry circulating pump. Background technique [0002] The application of flue gas desulfurization in large thermal power plants is becoming more and more extensive. The high operating cost of desulfurization systems has always been a problem for power plants. Among them, the slurry circulation pump is one of the main power-consuming equipment of the wet desulfurization system. Consumption is of great significance. Many thermal power plants mainly use limestone-gypsum wet flue gas desulfurization technology for desulfurization. This process technology is also a relatively mature desulfurization technology currently used. The main principle is to mix limestone and slaked lime into a slurry to absorb power The SO2 generated during power generation reacts to produce gypsum. The technological process of this process is to co...

AI Technical Summary

Problems solved by technology

[0008] (2) The slurry circulating pump is optimized by using the traditional index optimization method: on the one hand, the index is a single index, and the comprehensive situation of multiple indexes is not considered; on the other hand, the intricate relationship between data is difficult to express through simple indexes. Instructive, not on-site operational

The method of setting the indicator library ignores the correlation between indicators. One indicator does not necessarily reflect the operation optimization of the equipment. Multiple indicators act at the same time to comprehensively represent the operation optimization of the equipment. Therefore, there are many indicators for this kind of equipment, it is difficult to obtain a comprehensive operation optimization result only by establishing an index library, so this method lacks certain scientific rationality

Images