Semantic AI-Driven Deep Perceptual Framework for Fault Diagnosis in Smart Metering
International Journal on Semantic Web and Information Systems · 12.11.2026 · 22 (1) · 1-26
DOI: 10.4018/ijswis.427354 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal on Semantic Web and Information Systems, erschienen am 12.11.2026. Verfasst von Yongmin Zhang und 4 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 3.0).
Abstract (Originalsprache)
Accurate fault diagnosis of electric energy metering devices is vital for reliable smart-grid operation. However, statistical and shallow learning methods struggle with nonlinear, noisy, high-dimensional data and weakly support maintenance decisions. This study proposes a semantic artificial intelligence-driven deep perceptual framework based on a deep perceptual neural network (DPNN). It combines deep perception with a semantic layer that represents devices, conditions, faults, evidence, and maintenance actions as machine-interpretable relations. In DPNN, multi-scale residual convolution captures temporal patterns, residual multilayer perceptrons enhance nonlinear representation, and gated attention emphasizes key fault indicators. Experiments on 14,880 samples from 500 devices and five fault categories show that DPNN outperforms conventional and recent baselines, improving average accuracy by 6.12%–18.85% and remaining robust under overload, underload, high-voltage, and low-voltage conditions. The semantic layer converts outputs into fault labels, component cues, alarms, and maintenance priorities.
Zitieren
APA
Zhang, Y., Liu, S., Bao, J., Yang, Z., & Cai, Y. (2026). Semantic AI-Driven Deep Perceptual Framework for Fault Diagnosis in Smart Metering. International Journal on Semantic Web and Information Systems, 22(1), 1-26. https://doi.org/10.4018/ijswis.427354
Vancouver
Zhang Y, Liu S, Bao J, Yang Z, Cai Y. Semantic AI-Driven Deep Perceptual Framework for Fault Diagnosis in Smart Metering. International Journal on Semantic Web and Information Systems. 2026;22(1):1-26. doi:10.4018/ijswis.427354
BibTeX
@article{Zhang2026,
author = {Zhang, Yongmin and Liu, Shengnan and Bao, Jihua and Yang, Zhangjun and Cai, Yongmei},
title = {Semantic AI-Driven Deep Perceptual Framework for Fault Diagnosis in Smart Metering},
journal = {International Journal on Semantic Web and Information Systems},
year = {2026},
volume = {22},
number = {1},
pages = {1--26},
doi = {10.4018/ijswis.427354}
}
EUVIMED