A method and system for detecting abnormalities in refrigeration valves

By constructing spatial and temporal reference sets and dynamically adjusting thresholds, the problem of low accuracy in refrigeration valve detection by the traditional LOF algorithm is solved, and efficient identification and accurate judgment of refrigeration valve anomalies are achieved.

CN120744779BActive Publication Date: 2025-12-02SHANDONG DOFUN REFRIGERATION TECH CO LTD
2 Cites 0 Cited by

Patent Information

Application Number
CN202511193379.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-08-25
Publication Date
2025-12-02
Estimated Expiration
2045-08-25

AI Technical Summary

Technical Problem

Traditional LOF algorithms have low accuracy in detecting refrigeration valve anomalies. They cannot effectively distinguish between sparse data areas caused by changes in operating conditions and genuine data anomalies, which easily leads to false alarms and missed alarms.

Method used

The sparsity and initial anomaly scores of the spatially nearby reference set and the temporally nearby reference set are calculated by constructing a spatially nearby reference set. The threshold is then dynamically adjusted in combination with the trend anomaly level to improve detection accuracy, including the construction of a dynamic threshold to adapt to different operating states.

Benefits of technology

It effectively distinguishes between sparse areas caused by changes in operating conditions and genuine abnormal data, reducing false alarm rates and improving the accuracy and robustness of refrigeration valve anomaly detection.

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

Abstract

This application relates to the field of data processing technology, and in particular to a method and system for anomaly detection of refrigeration valves. The method includes: acquiring preprocessed operating data of the refrigeration valve; for any data point in the operating data, calculating the sparsity of the data point based on its distribution in the local area; simultaneously, constructing a temporal neighbor reference set for the data points, and using the LOF algorithm to obtain the initial anomaly score for each data point in the neighbor reference set; constructing a trend anomaly degree based on the initial anomaly scores of the data points in the temporal neighbor reference set and the changes in data values; adjusting a preset initial anomaly threshold based on the trend anomaly degree and the sparsity to obtain a dynamic threshold, wherein the dynamic threshold is negatively correlated with the trend anomaly degree; and judging the operating data of the refrigeration valve based on the dynamic threshold. This application has the effect of improving the accuracy of anomaly detection in refrigeration valves.
Need to check novelty before this filing date? Find Prior Art