摘要
如何准确地检测出储罐运行的异常状态是工业控制系统的核心问题,针对传统的有监督学习需要大量学习样本,而无监督学习准确率不足的问题,提出一种基于FCM-ANN的异常检测方法。该方法基于三层结构模型,FCM层不需要任何先验知识,对数据进行初步异常检测,ANN层对FCM层的每个类分别进行神经网络学习,最后通过ANN集成得到检测结果。对采集的储罐运行状态数据进行仿真后,结果表明该方法比ANN、FCM和Nave Bayes方法有更优的检测性能。
How to detect the abnormal state of the operation of the storage tank is the core problem in industrial control systems. Most of the detection methods proposed so far employ a supervised-learning or unsupervised-learning technique,the former fails to detect unknown anomalies while the latter requires large amounts of learning data. In order to solve the above problems,this paper presents a hybrid algorithm named FCM-ANN which is a mixture of Fuzzy CMeans clustering and Artificial Neural Network. There are three phases involved in the algorithm,in the first phase,namely the FCM layer,FCM algorithm is used to separate the data into several clusters and most of the abnormal data gather together. In second phase,different ANNs is trained based on various clusters and at last neural network ensemble is used to combine the results of different ANNs. Some experiments are conducted on the database of storage tank operation and the results indicate the proposed algorithm is able to detect anomalies with better detection performance compared with ANN,FCM and Nave Bayes.
出处
《计算机应用与软件》
2017年第2期214-219,共6页
Computer Applications and Software
