Modeling method for pulverized coal fired boiler combustion optimization

Abstract

The invention discloses a modeling method for pulverized coal fired boiler combustion optimization. The method concretely comprises the steps of (a) preprocessing data; (b) carrying out dimensionality reduction on independent variables: carrying out dimensionality reduction on the model independent variables in a boiler combustion process by an intelligent evolutionary genetic algorithm; (c) establishing models: based on the screening of the model independent variables, respectively establishing the soft measurement models taking nitrogen oxide (NOX) emission and unburned carbon in flue dust as targets by using a radial nerve network; (d) analyzing an error. According to the modeling method, screening and dimensionality reduction are carried out on the independent variables in the boiler combustion process by the intelligent evolutionary genetic algorithm, whether the independent variables take part in modeling or not can be selected according to an optimization result which is 0 or 1, and then modeling is carried out on the independent variables taking part in modeling by the radial nerve network; the modeling time and complexity are reduced while higher fitting precision and prediction accuracy are obtained, and a reliable model foundation is provided for boiler combustion optimization.

Description

【Technical field】 [0001] The invention relates to the technical field of pulverized coal boiler control, in particular to the technical field of optimal control of the combustion process of the pulverized coal boiler. 【Background technique】 [0002] Combustion optimization of pulverized coal boilers is an important measure to improve the economy and environmental protection of power plants, but before realizing combustion optimization, it is necessary to model the combustion process of the boiler. Generally speaking, the optimization target is boiler thermal efficiency and NO X emissions, but in the modeling process, usually consider the carbon content of fly ash and NO X Modeling the emissions, and then using heat balance formulas to convert the carbon content of fly ash into boiler thermal efficiency. On this basis, through intelligent algorithms to optimize the adjustable auxiliary variables, the boiler combustion modeling-optimization is realized. the whole process. ...

AI Technical Summary

Problems solved by technology

However, due to the large coupling of boiler combustion and the influence of many variables, when the input independent variables of the mathematical model are many and the independent variables are not independent of each other, the neural network is prone to over-fitting phenomenon, resulting in low accuracy of the established model and poor modeling performance. Long time and other issues, so it is necessary to screen the modeling independent variables in the modeling process. The above-mentioned patents either did not screen variables, or only used high-dimensional spatial mapping (PCA) for feature extraction, and did not reduce the model very well. The complexity, the modeling time is also longer

Images