煤气化过程的神经网络直接辨识  

Identification of Coal Gasification via a Neural Network Model

作　　者：郭兵[1] 沈幼庭[1] 李定凯[1] 吕子安[1] 

机构地区：[1]清华大学热能工程系

出　　处：《燃烧科学与技术》1999年第1期83-90,共8页Journal of Combustion Science and Technology

基　　金：国家自然科学基金

摘　　要：煤在水蒸汽环境中气化时，煤的热解和焦的气化同时发生，两个过程有一些相同的产物，因此无法通过测量确定两个过程各自的进行情况。如果用煤的热解模型和焦的气化模型共同描述煤在水蒸汽中的气化过程，由于缺乏必要的数据，难以保证模型参数的合理性。要直接描述煤热解和焦气化形成的综合过程，传统的数学回归方法又难以胜任。本文用神经网络方法对煤在水蒸汽中气化的综合过程进行了直接辨识，取得了较好的模拟效果，并对煤在水蒸汽中的气化过程有了更深入的了解，为煤气化过程的“活性焦比”模型提供了支持。As coal being gasified in the presence of steam,pyrolysis of coal and gasification of char occur concurrently.Usually coal pyrolysis model is incorporated with char gasification model to describe steam gasification of coal.Since the two parallel processes have some common products,it has been difficult to reasonably identify the parameters for each process individually.A new exploration of modeling approach to coal gasification is presented in this article,which uses a neural network model to directly identify the comprehensive process involving both coal pyrolysis and char gasification.Good simulation results and further insight into the mechanism of coal gasification have been obtained in this work.

关 键 词：煤气化 直接辨识 神经网络 水蒸汽环境 

分 类 号：TQ54[化学工程—煤化学工程]