Equipment state anomaly detection method and device and computer equipment

Abstract

The invention relates to an equipment state anomaly detection method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring a feature set of initial fault-free operation data of equipment as a historical initial feature set; searching the historical initial feature set according to a distance correlation coefficient between features in the historical initial feature set to obtain a historical correlation feature subset, and screening redundant features in the correlation feature subset according to a feature representative index of the historical correlation feature subset to obtain a historical feature set; obtaining a historical data matrix according to the historical feature set, and taking the historical data matrix as a training sample to obtain a trained convolutional noise reduction network; and inputting the real-time data matrix into the trained convolutional noise reduction network to obtain an abnormal level value, and judging whether the equipment is abnormal or not according to a size relationship between the abnormal level value and an abnormal threshold value. By adopting the method, higher anomaly detection precision can be obtained under a lower false alarm rate.

Description

technical field [0001] The present application relates to the technical field of equipment state monitoring and fault diagnosis, and in particular, to a method, apparatus, computer equipment and storage medium for detecting abnormality of equipment state. Background technique [0002] With the continuous improvement of the intelligence of modern mechanical equipment, a large number of sensors are arranged in the equipment to monitor the operation status of the equipment, providing a large amount of high-dimensional operation data for anomaly detection methods. During the actual operation of mechanical equipment, some anomalies often do not seriously affect the operation of the equipment in the early stage, and these potential anomalies make it difficult to accurately distinguish normal and abnormal data. In addition, the occurrence of abnormality may also cause equipment downtime and damage, making it difficult to collect operating data under abnormal equipment conditions, r...

AI Technical Summary

Problems solved by technology

[0003] However, this type of method has defects to a large extent. For example, the abnormal signal in the mechanical equipment can be transmitted through the mechanical structure, resulting in the abnormal signal being detected by multiple sensors, so there are inevitably redundant features.

However, the traditional method ignores the processing of these features, causing the fault signal to be covered by many superimposed noises, affecting the detection effect and making the detection network large-scale

In addition, the over-limit detection method widely used in the industry has the problem that the operating parameters are difficult to accurately calibrate in practical applications, and potential safety hazards cannot be detected by the rules

Moreover, the current equipment monitoring system operates independently, and the ability to comprehensively analyze data is insufficient

Images