垃圾热解实验研究及其神经网络预测模型  

EXPERIMENTAL STUDY ON MSW PYROLYSIS AND ITS NEURAL NETWORKS PREDICTION MODEL

作　　者：温俊明[1] 池涌[1] 金余其[1] 严建华[1] 倪明江[1] 岑可法[1] 

机构地区：[1]浙江大学热能工程研究所能源洁净利用与环境工程教育部重点实验室,浙江省杭州市310027

出　　处：《中国电机工程学报》2005年第5期154-158,共5页Proceedings of the CSEE

基　　金：国家自然科学基金(50076037)。~~

摘　　要：利用自行设计的较大物量(10g 左右)的热重分析装置,就城市生活垃圾典型有机组分的混合热解特性进行了实验研究。参照该实验结果,利用化学反应动力学原理和 BP神经网络理论建立了由热解动力学部分和 7 个 BP 神经网络子模型组成的垃圾热解预测模型。利用该模型可以通过输入垃圾的组分比例,方便地预测垃圾的总体热解特性,从而为垃圾焚烧装置的设计和运行提供指导。A thermogravimetry analysis system was designed, in which more massive sample (about 10g) can be analyzed. Experimental studies were performed on the mixed pyrolysis characteristics of typical organic components of MSW. Based on these experimental results, a prediction model was established for MSW pyrolysis by using the principle of chemical reaction kinetics and the theory of BP neural networks, which consists of a pyrolysis kinetics submodel and seven BP neural networks submodels. This model is able to predict the overall pyrolysis characteristics of MSW by inputting the component proportions of MSW. Accordingly, it is able to guide the design and operation of MSW incinerator.

关 键 词：城市生活垃圾 热解实验 垃圾焚烧 热解特性 有机组分 装置 热解动力学 混合 热重分析 组成 

分 类 号：TM621[电气工程—电力系统及自动化] X705[环境科学与工程—环境工程]