| Abstract: | The flue temperature is one of the important indicators to characterize the combustion state of an ethylene cracker furnace, the outliers of temperature data can lead to the false alarm. Conventional outlier detection algorithms such as the Isolation Forest algorithm and 3-sigma principle cannot detect the outliers accurately. In order to improve the detection accuracy and reduce the computational complexity, an outlier detection algorithm for flue temperature data based on the CLOF (Clipping Local Outlier Factor, CLOF) algorithm is proposed. The algorithm preprocesses the normalized data using the cluster pruning algorithm, and realizes the high accuracy and high efficiency outlier detection in the outliers candidate set. Using the flue temperature data of an ethylene cracking furnace in a petrochemical plant, the main parameters of the CLOF algorithm are selected according to the experimental results, and the outlier detection effect of the Isolation Forest algorithm, the 3-sigma principle, the conventional LOF algorithm and the CLOF algorithm are compared and analyzed. The results show that the appropriate clipping coefficient in the CLOF algorithm can significantly improve the detection efficiency and detection accuracy. Compared with the outlier detection results of the Isolation Forest algorithm and 3-sigma principle, the accuracy of the CLOF detection results is increased, and the amount of data calculation is significantly reduced. |
