【作者】 谢妍；

【导师】 吕锋； 黄晓理；

【作者基本信息】 武汉理工大学 ， 控制理论与控制工程， 2002， 硕士

【摘要】 近年来，我国已经建成许多新型干法水泥生产线，这些生产线技术新、自动化水平高，对生产操作人员的操作水平和工程技术人员的技术水平都提出了很高的要求，这就意味着水泥行业需要不断培训出大批合格的生产操作人员和工程技术人员。 本文所研究的系统为武汉理工大学“211工程”重点建设项目——水泥生产过程计算机仿真系统(CPPCSS)的子课题之一：水泥煤粉制备生产过程仿真系统。围绕此课题展开，本文主要包括以下内容： 第一，作者通过查阅大量国内外文献资料和实地参观学习等方式对水泥生产过程(主要为煤粉制备生产过程)进行了了解。这部分内容在本文中作了简要的介绍。 第二，根据水泥煤粉磨系统具有多变量、非线性和分布复杂的特点，运用神经网络对系统进行了建模与研究。提出了对传统EBP神经网络算法的改进方法。本文在此基础上，采集了来自于生产现场的数据，借助于MATLAB的神经网络工具箱对系统进行了训练与研究。仿真实验结果表明以上方法取得了较好的训练结果，满足了仿真系统建模的要求。 第三，在对煤粉制备系统的主要设备—磨煤机的工作原理、工艺特性进行深入地了解并结合专家经验知识的基础上，研究了模糊理论与神经网络理论及故障诊断技术，借助于MATLAB的模糊逻辑工具箱，构建了基于ANFIS网络结构的磨煤机三种运行状态的故障诊断模型。这个模型的建立是将模糊逻辑与神经网络相融合并用于水泥过程磨煤机故障诊断的一种尝试，有较大的理论研究价值。同时，仿真实验结果表明，该模型也有一定的实用性。 第四，对系统进行了分析与研究，介绍了系统的整体仿真框架及功能。此外，本文还对仿真程序中主要模块的实现进行了简要的介绍。 第五，介绍了运用VRML建立的仿真系统三维模型，对系统模型进行了展示。 最后，作者对全文进行了总结，并对今后的研究方式与方法作出了展望。 本文所研究的课题在水泥及其他行业的仿真领域具有一定的理论和使用价值，同时为系统的后续开发打下了坚实的基础。更多还原

【Abstract】 In recent years, many cement producing lines with new technology and advanced automatic level have been built up in our country. These producing lines need quantities of operators with high abilities of operating. This implies that a great deal of operators and engineers with high abilities should been trained continuously.Cement Producing Process Computer Simulation System (CPPCSS) is a highlight of 211 Engineering in Wuhan University of Technology. The Coal Powder Preparation System Computer Simulation described in this paper is one of the subsystems of it. The author researches the following contents based on this system.Firstly, according to referring to a lot of references and visiting on the spot, the author become familiar with the cement producing process, which includes the coal mill system producing process. These contents are introduces in the paper.Then, considering the complexity of coal mill system, the author build up the models of this system with neural network. The improved EBP neural network algorithm is used in this system. Based on this method, according to the data gathering from the producing spot, and by using the neural network toolbox for MATLAB, the author trains and researches the neural network model. The results indicate that the method was efficient.Thirdly, according to studying the running principles and the craftwork characteristics of the main machine of the cement coal mill system and expert knowledge about this system, researching the fuzzy theory, the neural network and fault diagnosis technique, and by using the fuzzy inference system toolbox for MATLAB, a fault diagnosis method is proposed based on ANFIS network for three working status of machine of coal milling(normal -, storehouse stop up with coal powder and molten steel too small to work in order)molten steel which is a try to build a method of combining the fuzzy logic and neural network and use it to fault diagnostic system of coal mill system. In this paper, the research has some theories and practical value .Fourthly, the author analyzes and researches this system in detail. And the whole simulation frame of it is introduced. Moreover, the programme of the algorithm, which is the main of the whole cement coal mill system computer simulation, is also introduced in this paper.Fifthly, the three-dimensional model of the simulation system based on VRML is introduced and shown in this paper.At last, the author summarizes the whole paper and points out the future direction of the development of the system.The research in this paper not only has important theoretical and practical values in cement and other industries, but also makes solid basis to the post-development of CPPCSS.更多还原