基于SVM和MCGS的生化过程故障诊断设计  

The Design of Fault Diagnosis of Biochemical Process Based on SVM and MCGS

作　　者：王鲜芳[1] 王平[1] 张帅[1] 李贺[1] 

机构地区：[1]河南师范大学计算机与信息工程学院,河南新乡453007

出　　处：《郑州师范教育》2015年第6期35-38,共4页Journal of Zhengzhou Normal Education

基　　金：国家自然科学基金项目(61173071);2013年国家公派高级研究学者及访问学者项目([2013]3018);河南省高校创新人才支持计划项目(2012HASTIT011)

摘　　要：针对生化过程故障不易发现的问题,提出了一种将支持向量机故障诊断和MCGS组态软件相结合的在线故障诊断方法。该方法借助LIBSVM工具箱在MATLAB软件中完成SVM分类器模型的训练,利用OPC接口标准实现MCGS组态软件与MATLAB软件的实时数据交换,根据训练得到的SVM分类器对实时采集到的数据进行分类判断,然后通过OPC接口将诊断结果回送给MCGS组态软件,最终在组态软件人机界面中将故障信息显示出来,从而实现故障诊断的智能化。测试运行证明了本方法的有效性。In accordance with the problem that the faults are difficult to find in biochemical process,a fault diagnosis method was put forward based on the combination of vector machine fault diagnosis and the MCGS configuration software. The training of SVM classifier model was completed by using LIBSVM toolbox in MATLAB software and the real-time data exchange between the MCGS configuration software and MATLAB software was finished by using the OPC interface standard. The method made a judgment for the real-time collected data according to the SVM classifier,and then sent the results to the MCGS configuration software through the OPC interface. Last,it displayed the fault information in the interface of the configuration software so as to realize the intelligent fault diagnosis. The validity of the method was proved by some tests.

关 键 词：SVM MCGS组态软件 生化过程 在线故障诊断 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]