A Progressive Abnormal Detection Method for Water Treatment System Based on Autoencoder and Isolation Forest
With the deepening of informatization of water treatment systems integrated industrial internet technology are facing increasingly severe challenges of abnormal behavior intrusion.Aiming at such problems as single threshold detec-tion,low detection accuracy,high false alarm rate and so on in traditional anomaly detection methods,a progressive anoma-ly detection method for water treatment systems that integrates autoencoders and isolation forests is proposed.Firstly,by downsampling to filter duplicate data,the training and testing efficiency of the progressive anomaly detection model is ac-celerated;Secondly,the hidden layer neurons of the autoencoder are constructed to capture the key features of the data,opti-mize the weight and bias of the autoencoder,and set the reconstruction error threshold as the difference measurement be-tween input and reconstruction for basic detection;Finally,construct an isolation tree with the average path length as the anomaly measurement threshold to form an isolation forest,and further traverse the isolation tree to complete advanced de-tection based on the anomaly data discovered by basic detection;Improving detection performance based on two-stage pro-gressive anomaly detection.The experimental results show that the accuracy and F1 score of the proposed method in the se-cure water treatment dataset exceeds 95%,compared with the traditional method,the accuracy is improved by 31.86 percent-age points on average,especially,the false positive rate of anomaly detection is significantly reduced to 0.30%.The preci-sion rate,recall rate and other indicators obtained by the generalization analysis of the water distribution dataset are all over 94%.The training and testing time of the model has outstanding advantages in terms of comprehensive performance com-pared to comparative methods.
water treatment systemabnormal detectionautoencoderisolation forestprogressive
万方数据
维普
