基于人工神经网络和遗传算法的火电厂锅炉实时燃烧优化系统  

An On-Line Boiler Operating Optimization System Based on the Neural Network and the Genetic Algorithms

作　　者：周昊[1] 朱洪波[2] 岑可法[1] 

机构地区：[1]能源清洁利用和环境工程教育部重点实验室浙江大学热能工程研究所,杭州310027 [2]广东省电力集团公司,广州510600

出　　处：《动力工程》2003年第5期2665-2669,共5页Power Engineering

基　　金：国家重点基础研究专项经费资助

摘　　要：大型燃煤电站锅炉燃烧效率的提高和污染气体的低排放对于节约能源和保护环境都有重要意义。通过燃烧优化可以提高锅炉效率、降低锅炉的氮氧化物排放、防止锅炉结焦和受热面爆管等,因而广泛得到应用。但目前燃烧优化方法往往采用现场试验方法,耗时费力,而且由于锅炉输入输出特性复杂,耦合性强,燃用煤种和操作条件变化较大,现场燃烧优化方法往往效果不佳。同时提出从DCS下载实时数据,利用人工神经网络对锅炉特性建模,并利用遗传算法实现操作参数的实时寻优。实践证明:这种方法能够实时地获得目前最佳的锅炉燃烧调整方式,对锅炉的节能降耗和降低环境污染都有重要意义。The present work introduces an online low NOx combustion optimization system based on the neural network and genetic algorithms for the pulverized coal burned utility boiler. The NOx emission characteristic of a 600MW capacity boiler operated under different conditions is experimentally investigated and on the basis of experimental results, the artiticial neural network is used to describe its NOx emission property to develop a neural network based model. A genetic algorithm is employed to perform a search to determine the optimum solution of neural network model, identifying appropriate setpoints for the current operating conditions and the low NOx emission of the pulverized coal burned boiler is achieved. Figs 2, tables 4 and refs 8.

关 键 词：锅炉 燃烧优化 神经网络 遗传算法 实时系统 

分 类 号：TK223[动力工程及工程热物理—动力机械及工程]