A time series anomaly detection method for an online monitoring system of a selective metallurgy residue field

By constructing statistical and temporal features, and combining supervised algorithms with unsupervised algorithms, the problem of poor model stability in the online monitoring system of metallurgical slag yards was solved, achieving efficient anomaly detection and improved accuracy.

CN115545115BActive Publication Date: 2025-12-30SINOSTEEL MAANSHAN INST OF MINING RES CO LTD +1
2 Cites 0 Cited by

Patent Information

Application Number
CN202211322936.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-10-27
Publication Date
2025-12-30
Estimated Expiration
2042-10-27

AI Technical Summary

Technical Problem

In existing online monitoring systems for slag beneficiation sites, traditional unsupervised learning methods suffer from poor model stability due to a lack of labels and inconsistent expert experience. This makes it difficult to effectively detect anomalies in multiple indicators, and the high randomness of single-base models can easily lead to false alarms or missed alarms.

Method used

By constructing statistical features, time features, and time series features, and combining supervised algorithms with unsupervised algorithms to select important features, multiple unsupervised algorithms are used for detection. Pseudo-labels are corrected in accordance with industry standards, and majority voting strategy and weighted fusion method are adopted to improve detection performance.

Benefits of technology

This system enables efficient anomaly detection in the online monitoring system for metallurgical slag yards, improves the performance of unsupervised algorithms, reduces false alarms and false negatives, and ensures the stability and accuracy of the model.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application discloses a time series anomaly detection method for an online monitoring system of a dressing and smelting residue field, and belongs to the technical field of the online monitoring of the dressing and smelting residue field. The steps of the application are as follows: data is extracted from a database, missing values are filled, some original indexes with relatively high correlation coefficients are deleted, statistical features, time features and time sequence features are constructed for the remaining indexes through feature engineering; all the features are normalized, and an unsupervised algorithm is used to determine an abnormal label through majority voting; feature selection is performed on the processed label data, and the importance indexes are used to improve the detection performance of the unsupervised algorithm; then, the pseudo label is corrected in combination with an industry standard; finally, the detection results of the unsupervised algorithm are weighted and fused, the statistical features, the time features and the time sequence features are constructed based on a small amount of monitoring projects, the important features are selected with the aid of a supervised algorithm, and the performance of the unsupervised anomaly detection algorithm is improved.
Need to check novelty before this filing date? Find Prior Art