Industrial sound anomaly detection system based on phase coding and equipment information

Abstract

The invention belongs to the technical field of industrial sound anomaly detection, and particularly relates to an industrial sound anomaly detection system based on phase coding and equipment information. The method can complement the fineness of an industrial sound signal by means of phase information, obtains high-precision acoustic features, can model the high-precision acoustic features, focuses on improving the sensitivity of the system to abnormal information, senses subtle differences between different industrial devices, avoids acoustic interference generated between the devices, and improves the reliability of the system. And the modeling result is subjected to high-efficiency and high-precision anomaly score judgment, and the industrial sound anomaly detection performance is excellent.

Description

technical field [0001] The invention belongs to the technical field of industrial sound abnormality detection, and in particular relates to an industrial sound abnormality detection system based on phase encoding and equipment information. Background technique [0002] In the social life of the information age, when analyzing real-world data, a common need is to determine which instances are different. Such instances are called anomalies. Anomalies are caused by malicious behavior, system failure, intentional fraud, etc. and does not match most of the data distribution or match the expected pattern. Anomaly detection, also known as outlier detection, aims to identify all such distinctive instances through methods, models, and algorithms in a data-driven manner. [0003] Sound anomaly detection is to detect abnormal events that cause abnormal sounds through the analysis of acoustic signals. On the one hand, because abnormal sounds often indicate abnormal symptoms or malicio...

AI Technical Summary

Problems solved by technology

[0005] Currently, the processing of sound data is based on spectral information, but the phase information about the vibration offset is lost during the processing, which leads to loss of information and increased false detection rate

In the real factory scene, the production situation is complex and changeable, usually involving different equipment operating conditions, and the difference between different sub-equipment in the same type of equipment cluster is difficult to distinguish from the abnormality that occurs in a short time, which poses a difficult problem for industrial sound detection

Images