基于区间Ⅱ型FNN的MSWI过程炉膛温度控制  

Interval Type-Ⅱ FNN-based Furnace Temperature Control for MSWI Process

作　　者：汤健 田昊 夏恒 乔俊飞 TANG Jian;TIAN Hao;XIA Heng;QIAO Junfei(Faculty of Information Technology,Beijing University of Technology,Beijing 100124,China;Beijing Laboratory of Smart Environmental Protection,Beijing 100124,China)

机构地区：[1]北京工业大学信息学部,北京100124 [2]智慧环保北京实验室,北京100124

出　　处：《北京工业大学学报》2025年第2期157-172,共16页Journal of Beijing University of Technology

基　　金：科技创新2030重大项目(2021ZD0112301,2021ZD0112302)。

摘　　要：针对城市固废焚烧(municipal solid waste incineration,MSWI)过程的炉膛温度难以实现有效控制的问题,提出基于区间Ⅱ型模糊神经网络(interval type-Ⅱfuzzy neural network,IT2FNN)的炉膛温度控制方法。首先,进行炉膛温度控制特性分析以确定对其产生影响的关键操作变量;然后,根据上述操作变量基于线性回归决策树(linear regression decision tree,LRDT)建立多入单出(multiple-input single-output,MISO)炉膛温度模型;最后,构建具有自适应参数学习的IT2FNN控制器,并证明其稳定性。在MSWI过程数据集上构建模型并进行控制,实验结果验证了所提方法的有效性。Addressing the challenge that it is difficult to effectively control the furnace temperature in the municipal solid waste incineration(MSWI) process,a furnace temperature control method based on interval type-Ⅱ fuzzy neural network(IT2FNN) is proposed.First,the furnace temperature control characteristics were analyzed to determine the key operating variables that affect it.Subsequently,according to the above operational variables,a multiple-input single-output(MISO) furnace temperature model was fomulated based on the linear regression decision tree(LRDT).Finally,an IT2FNN controller with adaptive parameter learning was developed and its stability was proven.The experimental results of model construction and control on the MSWI process dataset confirm the efficacy of the proposed method.

关 键 词：城市固废焚烧(municipal solid waste incineration MSWI) 炉膛温度控制 线性回归决策树(linear regression decision tree LRDT) 区间Ⅱ型模糊神经网络(interval type-Ⅱfuzzy neural network IT2FNN) 梯度下降法 李雅普诺夫稳定性分析 

分 类 号：U461[机械工程—车辆工程] TP308[交通运输工程—载运工具运用工程]