氧化铝生产的蒸发过程故障检测仿真研究.pdfVIP

第32 卷 第10 期 计 算 机 仿 真 20 15 年10 月 文章编号:1006 －9348 (20 15)10 －0378－05 氧化铝生产的蒸发过程故障检测仿真研究 李 根，刘雄飞，胡志坤 (中南大学物理与电子学院，湖南长沙4 100 12) 摘要:研究氧化铝蒸发过程故障检测问题。氧化铝蒸发过程是一个非线性，时变的过程，结构错综复杂，样本数据少和难以 建立精确模型进行实时检测问题。为此，提出了一种采用贝叶斯网络的小数据集蒸发过程故障检测方法。首先，在贝叶斯 理论基础上，提出了一种结合领域知识的贪婪结构学习算法，由领域知识引导加边、减边和转边算子搜索，加速找到评分最 高的网络结构。然后，小数据集通过Bootstrap 抽样法获得大样本数据，经由改进的结构学习算法得到贝叶斯故障检测网 络，检测网络包含变量的拓扑结构图及其条件概率表。用已知数据对检测网络进行验证，结果表明上述网络是有效的，同时 亦能锁定故障所在位置，为蒸发过程实时优化控制开拓了一种新思路。 关键词:人工智能;故障检测;贝叶斯网络;结构学习;氧化铝蒸发过程 中图分类号:TP274. 5 文献标识码:B Fault Detection Simulation for Evaporation Process of Alumina Production LI Gen ，LIU Xiong－fei ，HU Zhi－kun (School of Physics and Electronics ，Central South University ，Changsha Hunan 4 10012 ，China) ABSTＲACT :A small datasets fault detection method for Alumina evaporation process based on Bayesian network is proposed． Firstly ，a greedy structure learning algorithm combined with domain knowledge is studied． Guided by the domain knowledge ，three kinds of searches are conducted :edge－insertion ，edge－deletion and edge－reversal ，so as to find the highest score of the network structure fast． After that ，a large sample of data is obtained by Bootstrap sam- pling method from a small datasets and Bayesian fault detection network of Alumina is calculated by the improved structure learning algorithm which includes variables topology structure and the conditional probability tables． Final- ly ，the diagnostic network is tested with the known data． The simulation proves that this method is accuracy and can also lock the location of the fault at the same time ，which provides a new idea for the real－t