Fly ash carbon content prediction method and system based on neural network, and readable medium

Abstract

The invention belongs to the technical field of carbon content detection, and relates to a fly ash carbon content prediction method and system based on a neural network and a readable medium, and the method comprises the following steps that: S1, known industrial analysis components of fly ash are collected; S2, the industrial analysis components are substituted into the primary neural network for training, and a plurality of models representing the fly ash combustion degree are established respectively; S3, the combustion degree predicted by the model representing the combustion degree of the fly ash and industrial analysis components are substituted into a secondary neural network for training, and a fly ash carbon content model is obtained; and S4, the industrial analysis components of the to-be-detected fly ash are introduced into the fly ash carbon content model to obtain the carbon content of the to-be-detected fly ash. According to the method, the influence weight of each operation parameter and coal type on the boiler fly ash carbon content can be effectively distinguished, and the prediction accuracy of the boiler fly ash carbon content is improved, so that the boiler operation optimization can be guided, and the combustion efficiency is finally improved.

Description

technical field [0001] The invention relates to a method, system and readable medium for predicting carbon content of fly ash based on a neural network, and belongs to the technical field of carbon content detection. Background technique [0002] Circulating fluidized bed (CFB) boilers are widely used in the combustion of low calorific value coals because of their strong adaptability to coal types. In recent years, achieving the "three super" standards of supercritical, ultra-low energy consumption, and ultra-low emissions has become the goal of the new generation of CFB boiler technology. For boilers, in order to achieve ultra-low energy consumption, it is necessary to improve combustion efficiency. Among them, the carbon content of fly ash is an important indicator affecting the combustion efficiency of boilers. During boiler operation, the actual coal type often deviates from the design coal type, resulting in an increase in the carbon content of fly ash. Therefore, it...

AI Technical Summary

Problems solved by technology

There are many factors that affect the carbon content of boiler fly ash, including coal type, boiler design structure, operating parameters, etc., so it cannot be estimated with a simple formula

At present, most domestic power plants use the combustion weight loss method to measure the carbon content of fly ash once a day. However, the actual furnace test workload is heavy, the test conditions are limited, and there are many influencing factors that overlap each other, making data analysis difficult.

However, the coal type and operating parameters of the boiler are ever-changing, and it is impossible to guarantee the operation under the test conditions, resulting in deviation from the best working conditions obtained by combustion adjustment, and the lowest carbon content in fly ash cannot be obtained.

Images