Accès libre

Machine Learning Based Outlier Detection Algorithm for Distributed Flexible Sensing Module with Non-stationary Multi-Parametric Data

Suqin Xiong

Suqin Xiong

China Electric Power Research InstituteBeijing, China
Recherchez cet auteur sur
Sciendo|Google Scholar
Xiong, Suqin
, 
Yang Li

Yang Li

China Electric Power Research InstituteBeijing, China
Recherchez cet auteur sur
Sciendo|Google Scholar
Li, Yang
, 
Qiuyang Li

Qiuyang Li

China Electric Power Research InstituteBeijing, China
Recherchez cet auteur sur
Sciendo|Google Scholar
Li, Qiuyang
 et 
Zhiru Chen

Zhiru Chen

State Grid Shandong Electric Power Company Marketing Service Center (Metrology Center)Jinan, China
Recherchez cet auteur sur
Sciendo|Google Scholar
Chen, Zhiru
  
25 sept. 2025
Machine Learning Based Outlier Detection Algorithm for Distributed Flexible Sensing Module with Non-stationary Multi-Parametric Data's Cover Image
À propos de cet article
Article précédent
Article suivant
Citez
Télécharger la couverture
Publié en ligne: 25 sept. 2025
Reçu: 01 janv. 2025
Accepté: 18 avr. 2025
DOI: https://doi.org/10.2478/amns-2025-1028
Mots clés
© 2025 Suqin Xiong, Yang Li, Qiuyang Li and Zhiru Chen, published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1.

Diagram of AMI structure
Diagram of AMI structure

Figure 2.

Extension module design drawing
Extension module design drawing

Figure 3.

Electrical energy measurement data characteristics
Electrical energy measurement data characteristics

Figure 4.

Degraded data clustering
Degraded data clustering

Figure 5.

Calculation time comparison results
Calculation time comparison results

Figure 6.

Simulated data set
Simulated data set

Figure 7.

Comparison of detection results with the same parameters
Comparison of detection results with the same parameters

Figure 8.

Changes of accuracy rate with different parameters
Changes of accuracy rate with different parameters

Figure 9.

The effect of the survey of the group
The effect of the survey of the group

Figure 10.

Error comparison diagram under different temperatures
Error comparison diagram under different temperatures

Figure 11.

The monthly electrical error of the electric power measurement system
The monthly electrical error of the electric power measurement system

Energy metering data clustering effect

No. DBSCAN MAA COL GMM Ours
1 0.401 0.472 0.469 0.528 0.724
2 0.413 0.436 0.436 0.514 0.693
3 0.371 0.415 0.455 0.509 0.689
4 0.356 0.467 0.429 0.487 0.691
5 0.401 0.415 0.454 0.522 0.707
6 0.422 0.423 0.441 0.491 0.719
7 0.389 0.439 0.439 0.507 0.726
8 0.358 0.478 0.463 0.518 0.681
9 0.395 0.461 0.457 0.473 0.693
10 0.388 0.427 0.432 0.525 0.725
Means 0.389 0.443 0.448 0.507 0.705
Langue:
Anglais
Périodicité:
1 fois par an
Sujets de la revue:
Sciences de la vie, Sciences de la vie, autres, Mathématiques, Mathématiques appliquées, Mathématiques générales, Physique, Physique, autres
RSS Feed de la revue