摘要
流程工业作为一个国家的主导行业,对国民经济的发展起着举足轻重的作用。然而,流程工业生产过程的高度复杂性、强非线性、强关联性、不确定性等特点,使其优化问题无论在理论研究,还是实际应用上都面临巨大困难。如何针对流程工业优化命题的结构、特点,开发高效可靠的优化算法与技术,则是当前企业信息化发展中亟待解决的问题。生产过程优化作为工业企业综合自动化的关键一环,亦是企业挖潜增效的核心所在。
在对国内外现有研究成果及技术发展脉络进行系统总结及把握的基础上,立足于流程工业生产过程优化的现实需求,将人工智能引入流程工业的生产线控制中,改变传统的设备单元、装置级的局部优化思路,转向全厂、全流程级的整体优化。并结合配置了DCS系统的水泥生产企业的实际,探索生产过程优化系统中涉及的关键技术。
文章首先分析了企业生产流程的层次结构、流程间的相互关系,和流程行业生产工艺特点;并在上述基础上,阐述了流程工业的生产过程的优化问题,以流程生产为背景,水泥为对象,重点研究操作优化问题的必要性及其优化方法。论述了基于案例的优化方法在流程行业生产过程优化中的强大适应性,并建立了水泥生产的优化控制模型。
然后,本文主要研究了优化系统案例库的初始建立阶段案例的提取、案例的表示,以及案例的检索;论述了数据挖掘技术在企业案例工况分析中的应用;另外,还简单介绍了案例的修改策略和自学习机制,以建立比较完整的CBR优化控制系统。
最后,根据本文所建立的案例优化控制模型及系统的一般设计步骤,将案例优化应用于典型流程行业水泥的生产过程中,进行简单的实例验证。
Process industry as a dominant industry plays an important role in the development of the national economy. Because of the high complicacy, strong nonlinear, relevancy, uncertainties and other features, production optimization of process industry, however, continues to present a major challenge both in academia and practical application. So how to optimize the industrial processes becomes a first and foremost problem to be resolved in the development of enterprise information. Furthermore, the optimization of production process, which has emerged as one of the most valuable techniques for the industry integrated automation, is also the core to make an enterprise benefit more.
The global behavior of the control optimization is mainly discussed in process industries by artificial intelligence based on the reality of demand for process optimization and the research status quo at home and abroad. The chief contributions are as follows:
The hierarchical structure and characteristics of production process are analysed at the beginning of this artical. And the strong adaptability of the case-based optimization method is demonstrated in this aspect. Then the optimization control model of production process is done based on CBR.
The method of cases extraction is studied using data mining technology in the initial phase of CBR optimization system, while the necessity on application of data mining technology indicated in the analysis of the case status. At the same time, the clustering algorithm process on work status classifying and the grades case searching algorithm process are also elaborated.
Finally, the CBR process optimization is applied in the cement enterprise, according to the case optimal control system model and the general design steps, which is a typical process industry, for a simple example.
引文
1史蒂夫麦格盖瑞等.水泥工业的过程控制优化及Pavilion方案介绍.水泥工业. 2005,(3):75~76
2林隆福.新型干法水泥的生产优化体系.第六届新型干法水泥技术经验交流会.北京, 2005:96~97
3赵小强,荣冈.流程工业生产调度问题综述.化工自动化及仪表, 2004,31(6):8~10
4采峰,曾凤章.一种流程型企业主生产计划优化方法研究.工业工程与管理. 2006,4:16~20
5褚健,孙优贤.流程工业综合自动化技术发展的思考.制造业信息化, 2002,31(增刊):24-28
6王东生,秦守民.流程工业MES系统的分析与设计.控制系统. 2006,(4):52~55
7隋刚.集散控制系统(DCS)在睛纶生产中的应用[D].吉林大学. 2006:6~9
8 Yuanfang Hu, Suqin Zhang, Weidu Jiang. Applying Object-Oriented Method to CSIE System. Foundations of Software Engineering. Nov. 1998
9赖海军.新型干法水泥生产线DCS的方案设计与控制策略组态研究.南昌大学. 2005:10~12 26~33
10竺建敏.高级过程控制和闭环实时优化.石油炼制与化工. 1997,7(26):42~47
11 V. Dua, K. P. Papalexandri, E. N. Pistikopoulos. Global Optimization Issues in Multiparametric Continuous and Mixed-Integer Optimization Problems. Journal of Global Optimization. Sep.2004,30(1):59~89
12 Tim Van Voorhis. A Global Optimization Algorithm Using Lagrangian Underestimates and the Interval Newton Method. Journal of Global Optimization. Nov.2002,24(3):349~370
13李兵,蒋慰孙.一种新的全局优化方法及应用.华东理大学学报. 1995,21(3):338~342
14李兵,蒋慰孙.混沌优化方法其应用.控制理论与应用. 1997,4(4):613-615
15 Biegler,L.T., Nocedal,J. and Sclmid,C. A Reduced Hessian Method for Large-Scale Constrained Optimization. SLAM J.Optimization. 1995,5(2):314-347
16 Walter Murray, Sequential Quadratic Programming Methods for Large-Scale Problems. Computational Optimization and Applications. 1997,7(1):127~142
17 P. Gill, W. Murray, and M. A. Saunders. An SQP Algorithm for Large-Scale Constrained Optimization. SLAM J.Optimization. 2005,47(1):99-131
18 Edgar Chacon, Isabel Besembel, Jean Claude Hennet. Coordination and Optimization in Oil and Gas Production Complexes. Computers in Industry. Jan. 2004,53(1):17~37
19 Zhihua Xiong, PJie Zhang. Optimal Control of Fed-Batch Processes Based on Multiple Neural Networks. Applied Intelligence. Mar,2005,22(2):149~161
20 I.M. Mujtaba and M.A. Hussain. Application of Neural Networks and Other Learning Technologies in Process Engineering. Imperial College Press. 2001
21 Oscar Montiel, Oscar Castillo, Patricia Melin, Antonio Rodriguez Diaz, Roberto Sepulveda. Human Evolutionary Model: A New Approach to Optimization. Information Sciences. May.2007,177(10)
22韩璞,张丽静.热工过程控制系统参数优化方法的研究.华北电力学院学报. 1993(1):50~57
23杨凯尧.精馏生产过程稳态建模及其优化.吉林大学. 2006:46~54
24蒋国璋.面向钢铁流程知识网系统的生产计划与调度模型及其优化研究.武汉科技大学. 2006:14~16
25 Daina Dennis, Jack Meredith. An Empirical Analysis of Process Industry Transformation Systems. Management Science. Aug.2000,46(8):1085~1099
26 Vladimir Jovan. The Specifics of Production Scheduling in Process Industries. IEEE ICIT. Bangkok. THAILAND. 2002:1049~1054
27朱明磊.流程企业管控一体化系统体系结构研究.山东大学. 2005:1~10
28蔡韵.制浆造纸企业生产调度系统建模与优化研究.浙江大学. 2005:19~38 10~13
29王君伟.新型干法水泥生产工艺读本.北京:化学工业出版社. 2007:1~7
30马保国,新型干法水泥生产工艺.北京:化学工业出版社. 2007:180~182
31 Kolodner J L. An Introduction to Case-Based Reasoning. San Francisco, California: Morgan Kaufmann Publishers. 1993:3~16
32 David W A. The Omnipresence of Case-Based Reasoning in Science and Application. Knowledge-Based System, 1998, 11:261-273
33 Kesh S. Case-based reasoning. Journal of Systems Management. 1995,46(4):14-19
34 Aamodt A, Plaza E. Case-Based Reasoning: Foundational Issues Methodological Variations and System Approaches. AI Communications, 1994,7(1):39-59
35张代胜,王悦,陈朝阳.融合实例与规则推理的车辆故障诊断专家系统.机械工程学报. 2002,38(7):91~95
36 Sabatsr J, Arcos J L, and Lopez de Mantaras R. Using Rules t Support Case-Based Reasoning for Harmonizng Melodies. InMultimodal Reasoning: Papers from the 1988 AAAI Spring Symposium. Menlo Park. Calif.: AAAI Press.1998:147~151
37 Sewon Oh, Jooyung Han and Hyumbo Cho. Intelligent Process Control System for Quality Improvement by Data Mining in the Process Industry. Data Mining for Design and Manufacturing:Methods and Aapplications. Nov. 2001:289~309
38 Z Huang. Extensions to the k-means Algorithm for Clustering Large Data Sets with Categorical Values. Data Mining and Knowledge Discovery. 1998.2:283-304
39 Jiawei Han and Micheline Kamber. Data Mining: Concepts and Techniques. Morgan Kaufmann Publidhers, Ins. 2001
40于泓漪.道路交通事故原因的聚类分析[D].吉林大学. 2004:4~7 37~42
41李晓明. k-means类型变量加权聚类算法的研究与实现[D].哈尔滨工业大学. 2006:18~20