Mining scene anomaly detection method based on graph regular increment non-negative matrix factorization

Abstract

The invention provides a mining scene anomaly detection method based on graph regular increment non-negative matrix factorization, and belongs to the technical field of anomaly detection and diagnosis and the field of intelligent safety. The method comprises the following steps: firstly, collecting mining environment information in a normal state by using two sets of equipment, and respectively processing data obtained by the two sets of equipment; preprocessing the data to obtain a training set X '; secondly, obtaining an optimal basis matrix Wnew and a coefficient matrix Hnew through graph regular increment non-negative matrix factorization; establishing monitoring statistics N2 and SPE, and calculating control limits of two equipment training sets; then data (a test set X '') are collected again for detection, the statistical magnitude of the test set X'' is calculated, and finally the statistical magnitude is compared with the two sets of control limits, so that whether the mining scene is abnormal or not is judged; and when the scene is abnormal, uploading the maximum or larger contribution values to the control interface as abnormal reasons to be displayed. According to the method, the defects that traditional mining scene anomaly detection is not timely and inaccurate and the like are overcome, and the digital mining industry is created.

Description

technical field [0001] The invention relates to the technical field of anomaly detection and diagnosis and the field of intelligent security, in particular to a mining scene anomaly detection method based on graph regular incremental non-negative matrix decomposition. Background technique [0002] Mining security issues have always been a hot spot of concern. At present, most mines, especially metal mines, adopt underground mining methods. However, during underground construction, toxic gases and mine collapses pose a huge threat to the safety of construction workers; therefore, risk detection and early warning of underground construction environments have important Significance. At present, there are many anomaly detection methods, but it is a challenging task to not only ensure timeliness, ensure the effective use of network resources, but also comprehensively analyze multi-sensor (multi-factor) data to ensure accuracy and determine the root cause of scene anomalies. Wor...

AI Technical Summary

Problems solved by technology

At present, most mines, especially metal mines, adopt underground mining methods. However, during underground construction, toxic gases and mine collapses pose a huge threat to the safety of construction personnel; therefore, risk detection and early warning of underground construction environments are of great importance important meaning

At present, there are many anomaly detection methods, but it is a challenging task to not only ensure timeliness, ensure the effective use of network resources, but also comprehensively analyze multi-sensor (multi-factor) data to ensure accuracy and determine the root cause of scene anomalies. Work

Images