Research Article
Detection Method of Large Industrial CT Data Transmission Information Anomaly Based on Association Rules
@INPROCEEDINGS{10.1007/978-3-031-50577-5_7, author={Xiafu Pan and Chun Zheng}, title={Detection Method of Large Industrial CT Data Transmission Information Anomaly Based on Association Rules}, proceedings={Multimedia Technology and Enhanced Learning. 5th EAI International Conference, ICMTEL 2023, Leicester, UK, April 28-29, 2023, Proceedings, Part III}, proceedings_a={ICMTEL PART 3}, year={2024}, month={2}, keywords={Association Rules Large Industrial CT Data Transmission Information Wavelet Basis Function Anomaly Detection}, doi={10.1007/978-3-031-50577-5_7} }- Xiafu Pan
Chun Zheng
Year: 2024
Detection Method of Large Industrial CT Data Transmission Information Anomaly Based on Association Rules
ICMTEL PART 3
Springer
DOI: 10.1007/978-3-031-50577-5_7
Abstract
In the abnormal detection of large industrial CT data transmission information, the network is unstable and vulnerable to noise interference, resulting in the unstable output energy of the ray source, making the detection accuracy of data transmission information abnormal low. To solve this problem, a large industrial CT data transmission information anomaly detection method based on association rules is designed. Through association rule mining algorithm, the data transmission information of large-scale industrial CT is analyzed, and the association rules are obtained by introducing interest threshold. The improved Apriori algorithm is adopted to improve the accuracy of association rule mining. According to the results of association rule mining, the nonlinear wavelet transform threshold denoising algorithm based on the improved threshold function is used to denoise the information data. By calculating the abnormal probability of information entropy in data flow and sliding window, the abnormal detection of data transmission information is realized. Experimental results show that the proposed method has high detection accuracy and short average anomaly detection time.
