Prediction system and method of circulating fluidized bed household garbage incineration boiler NOx discharge

Abstract

The invention discloses a prediction system and a method of circulating fluidized bed household garbage incineration boiler NOx discharge. An integrated modeling method of a BP neural network algorithm and a multi-swarm particle swarm optimization algorithm introducing a simplex operator is adopted to construct a rapid economic self-adaptive updating system and a method for carrying out real time prediction on the boiler flue gas NOx discharge, so that the tedious complex mechanism modeling work is avoided. A dynamic change characteristic of NOx discharge is represented by utilizing the non-linear dynamic characteristic, the generalization ability and the real time prediction ability of the BP neural network algorithm; an initial weight value and a threshold value of the BP neural network are optimized by utilizing the particle swarm optimization algorithm, and the possibility of reaching a local optimum of the BP neural network in a training process is reduced; the simplex operator and the multi-population migration mechanism are introduced, so that the diversity of the particle swarm optimization algorithm and the local searching ability are improved, and the possibility of reaching the local optimum of the particle swarm optimization algorithm is reduced.

Description

technical field [0001] The invention relates to the field of energy engineering, in particular to a system and method for predicting NOx emissions from a circulating fluidized bed domestic waste incineration boiler. Background technique [0002] Since waste incineration can well realize volume reduction, volume reduction, harmlessness and resource utilization of waste treatment technology, in the past ten years, under the guidance of relevant national industrial policies, the domestic waste incineration industry has achieved vigorous development. Since the 1990s, a number of domestic scientific research institutions have conducted a large number of in-depth studies on the combustion mechanism of municipal solid waste (MSW) in China, and have mastered the combustion characteristics of mixed collection, high moisture, and complex MSW. Based on my country's experience in the development of coal, coal gangue and other inferior fuel circulating fluidized bed (Circulating Fluidized...

AI Technical Summary

Problems solved by technology

However, as a random search algorithm, the particle swarm optimization algorithm has certain blindness, and the local search efficiency is low in the later stage of iteration.

Images