卷积神经网络在化工领域的应用综述  

Review of the Application of CNN in the Field of Chemical Engineering

作　　者：罗祉婧 韦振宇 郑荻凡 曾泽楷 钟汉斌[1] Luo Zhijing;Wei Zhenyu;Zheng Difan;Zeng Zekai;Zhong Hanbin(Engineering Research Center of Low Carbon Energy&Chemical,School of Chemistry and Chemical Engineering,Xi'an Shiyou University,Xi'an 710065,China)

机构地区：[1]西安石油大学,化学化工学院,低碳能源化工工程研究中心,陕西西安710065

出　　处：《云南化工》2023年第2期21-23,共3页Yunnan Chemical Technology

基　　金：西安石油大学2021年国家级大学生创新创业训练计划项目(202110705024)的资助。

摘　　要：作为实现人工智能的关键技术,深度学习在机器学习领域中备受关注。介绍了深度学习典型算法之一的卷积神经网络的基础知识与理论,阐述了卷积神经网络在反应器内参数测定、流场识别、流场重构、故障诊断等方面的应用进展,并展望了该技术在化工领域的发展趋势。Deep learning is a key technology for realizing artificial intelligence,and becomes one of the most concerned branch in the field of machine learning at present.This paper briefly introduces the basic knowledge and theory of conventional neural network(CNN)which is one of the classical algorithms of deep learning,and expounds the application progress of CNN in parameter measurement,flow field recognition,flow field reconstruction,and fault diagnosis of chemical reactor.The development trend of this technology in the field of chemical engineering is also discussed.

关 键 词：深度学习 卷积神经网络 图像识别 化工 反应器 人工智能 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]