基于T-S模糊控制神经网络的工业锅炉运行控制分析  

Analysis on the operation control of industrial boiler based on T-S fuzzy neural network

作　　者：朱佳彬 陆彬盛 王伟琦[1] 龚路远[2] ZHU Jiabin;LU Binsheng;WANG Weiqi;GONG Luyuan(Shanghai Tobacco Group Co.,Ltd.,Shanghai 200082,China;School of Energy and Power Engineering,Dalian University of Technology,Dalian 116024,China)

机构地区：[1]上海烟草集团有限责任公司,上海200082 [2]大连理工大学能源与动力学院,辽宁大连116024

出　　处：《热科学与技术》2024年第2期189-197,共9页Journal of Thermal Science and Technology

摘　　要：锅炉是传统的蒸汽生产设备,广泛应用于电力、化工、机械等领域,也在城乡居民供热中发挥重要作用。随着工业水平的不断发展,锅炉系统已经发展成为了一个庞大且复杂的控制对象,其输入输出参数众多,各参数之间相互影响、紧密关联,存在惯性大、延迟大、非线性等特征,难以建立精确的数学模型控制锅炉的运行。将锅炉运行过程划分为:给水控制系统、燃烧控制系统、过热蒸汽系统,分析了燃气锅炉的运行过程及控制方法。结合锅炉众多输入输出参数间的非线性关联特征,构建了一种以模糊神经网络模型控制锅炉运行的方法。以某锅炉的实际运行特点,优选合适的输入、输出参数,利用T-S模糊理论和BP神经网络结合的方式,建立T-S模糊神经网络模型,控制锅炉系统的运行。进行仿真实验,将神经网络的计算结果与燃气锅炉实际运行结果进行对比,仿真结果表明建立的T-S模糊神经网络模型误差在合理范围内,能较好的预测锅炉运行结果,提升燃烧的稳定性。Boiler is a traditional steam production equipment,widely used in electric power,chemical industry,machinery and other fields,as well as plays an important role in urban and rural residents heating.With the continuous development of the industrial level,the boiler system has developed into a large and complex control object witha large number of input and output parameters,which affect each other and are closely related,so it is difficult to establish an accurate mathematical model to control the operation of the boiler for the parameters characteristics of large inertia,large delay and nonlinear.The boiler operation process is divided into feed water control system,combustion control system and superheated steam system,and the operation process and control method of gas boiler are analyzed.Based on the nonlinear correlation of the input and output parameters of boiler,a fuzzy neural network model is proposed to control boiler operation.According to the actual operation characteristics of a boiler,the appropriate input and output parameters are selected,and the T-S fuzzy neural network model is established by combining T-S fuzzy theory and BP neural network to control the operation of the boiler system.A simulation experiment is carried out to compare the calculation results of the neural network with the actual operation results of the gas boiler.The simulation results show that the error of the T-S fuzzy neural network model is within a reasonable range,which can well predict the operation results of the boiler and improve the combustion stability.

关 键 词：燃气锅炉 神经网络 模糊理论 锅炉运行控制 

分 类 号：TK39[动力工程及工程热物理—热能工程]