Analysis of device state parameter correlations and multimodal data model construction based on neural networks

Xiaoyang Li, Xiang Dong, Xiaokun Han, Bi Zhao, Shuwei Yi, Jian Bai and Xuanwei Zhang

International Journal of Low-Carbon Technologies, 2025, vol. 20, 488-494

Abstract: Traditional methods for monitoring equipment status struggle to meet the analytical demands of high-dimensional data inherent in complex systems. To address this, this paper proposes a neural network-based approach for analyzing the correlations among equipment status parameters, combined with a multimodal data model. A denoising autoencoder is employed to construct a deep neural network (DNN) for fault feature extraction, while a hierarchical DNN (HDNN) algorithm is introduced to optimize feature extraction in multimodal environments. The accuracy of fault classification reached 98.05%. Comparative analysis with various models demonstrates the superiority of HDNN in fault classification and severity recognition.

Keywords: device status recognition; deep neural networks; multimodal; autoencoders (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1093/ijlct/ctaf015 (application/pdf)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:oup:ijlctc:v:20:y:2025:i::p:488-494.

Access Statistics for this article

International Journal of Low-Carbon Technologies is currently edited by Saffa B. Riffat

More articles in International Journal of Low-Carbon Technologies from Oxford University Press
Bibliographic data for series maintained by Oxford University Press ().