Device network offline event statistical analysis and batch-level stability evaluation method

By constructing a multi-source observation set and a reference time index, and combining CUSUM with a hysteresis threshold, offline event identification and common cause event clustering are performed. This solves the problem of heterogeneous multi-source data in large-scale device networks, achieves accurate offline event identification and batch-level stability assessment, and improves the operation and maintenance efficiency and reliability of device networks.

CN121967261BActive Publication Date: 2026-06-05SHANDONG HONGYI ENERGY SAVING SERVICE CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Patents(China)
Current Assignee / Owner
SHANDONG HONGYI ENERGY SAVING SERVICE CO LTD
Filing Date
2026-04-02
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

In large-scale device networks, existing technologies struggle to accurately identify offline events under multi-source heterogeneous state data, leading to distorted statistical results and difficulty in achieving batch-level stability assessment.

Method used

By constructing a multi-source observation set, generating device context vectors and reference time indexes, performing time alignment and confidence fusion, using CUSUM and hysteresis threshold to jointly identify offline events, constructing event feature packages and clustering common cause event clusters, and combining robust normalization and trend degradation terms to form a stability score.

Benefits of technology

It achieves accurate time alignment and reliability fusion of multi-source data, improves the accuracy of offline event identification and the reliability of batch-level stability assessment, and enhances the operation and maintenance efficiency and reliability of device networks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121967261B_ABST
    Figure CN121967261B_ABST
Patent Text Reader

Abstract

The application discloses a device network offline event statistical analysis and batch-level stability evaluation method, relates to the technical field of device monitoring, and realizes time alignment and credibility fusion of multi-source data by constructing a multi-source observation set, generating a device context vector and a reference time index. The offline event is identified by combining CUSUM and hysteresis threshold, and the true offline and false alarm are accurately distinguished by combining event probability type offline duration and other characteristics, so that the event identification precision is improved. Through common cause event clustering and batch multi-dimensional feature extraction, batch-level exposure normalization evaluation is realized. Based on the stability score of the robust normalization and the trend deterioration term, the stability level and the index contribution degree can be accurately output, data support is provided for operation and maintenance decision, and the operation and maintenance efficiency and reliability of the device network are improved. The problems of multi-source data heterogeneity, inconsistent time stamp, missing conflict and the like in the large-scale device network are solved, and the offline event identification accuracy and the batch-level stability evaluation reliability are improved.
Need to check novelty before this filing date? Find Prior Art