An online soft-sensing method for power plant incoming coal quality combining mechanism and brain-inspired intelligence

Abstract

The invention discloses an on-line soft measurement method for coal quality in a power plant that combines a mechanism and brain-like intelligence. The method includes: collecting monitoring data of 190 conventional monitoring points in real time; extracting the original principal component characteristics of the monitoring data, and Input the pre-established online soft-sensing model of the incoming coal quality of the thermal power plant, and output the online element composition and soft-sensing values ​​of the industrial composition of the incoming coal quality. The method of the present invention can realize real-time and accurate online soft measurement of coal quality composition in the furnace without adding any hardware facilities, and can provide real-time online basis for combustion optimization and intelligent control and decision-making of thermal power plants; in addition, The method of the present invention utilizes the real-time data of the conventional monitoring points of the thermal power plant to realize the soft measurement of the coal quality of the furnace coal and simultaneously realizes the soft measurement of 5 kinds of element components and 4 kinds of industrial components; the absolute error of the soft measurement of each component is less than 1% , the soft measurement time is less than 1 second.

Description

technical field [0001] The invention relates to the field of smart power plants and artificial intelligence, in particular to an online soft measurement method for coal quality in a power plant that combines a mechanism with brain-inspired intelligence. Background technique [0002] At present, the analysis of the industrial and elemental components of coal quality mainly relies on the power plant operators to regularly sample and test the raw coal every 8 hours and every day. This method has the following shortcomings: the sampling process of raw coal is a random process, and the representativeness of the samples is not good. It must be guaranteed; the raw coal testing process is carried out regularly every day, the minimum period is 8 hours, and the coal composition cannot be analyzed online in real time, and the regular test value is used instead of the 8-hour average value, and there is a certain deviation; the elemental composition and industrial composition of a batch o...

AI Technical Summary

Problems solved by technology

[0002] At present, the analysis of the industrial and elemental components of coal quality mainly relies on the power plant operators to regularly sample and test the raw coal every 8 hours and every day. This method has the following shortcomings: the sampling process of raw coal is a random process, and the representativeness of the samples is not good. It must be guaranteed; the raw coal testing process is carried out regularly every day, the minimum period is 8 hours, and the coal composition cannot be analyzed online in real time, and the regular test value is used instead of the 8-hour average value, and there is a certain deviation; the elemental composition and industrial composition of a batch of coal samples The analysis results are obtained after 8 hours. It is difficult to guide the energy-saving power generation scheduling plan of coal-fired power plants, and it is difficult to optimize the power generation of coal-fired thermal power units more scientifically and fairly.

Images