Next Article in Journal
Small-Target Ship Detection with Joint Spatio-Temporal Features Across Multiple Frames
Previous Article in Journal
Magnetically Repulsive Cushion Triboelectric Nanogenerator for Rotating Machinery Structural Health Monitoring
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

AI Agent-Driven Intelligent Catalog Framework: A Governance-Centered Approach for Cleaning and Normalization of Heterogeneous Industrial Sensor Data

by
Hongyi Dong
1,
Yimeng Zhang
1,
Yifan Chu
1,*,
Hailing Zhou
1,
Mingxin Lu
1,2,
Zuojian Zhou
3 and
Xiaoyang Zhou
4,*
1
Department of Information Management, Nanjing University, Nanjing 210033, China
2
Nanjing University (Suzhou) High-Tech Institute, Suzhou 215123, China
3
School of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine, Nanjing 210033, China
4
China Mobile Zijin (Jiangsu) Innovation Research Institute, Nanjing 211899, China
*
Authors to whom correspondence should be addressed.
Sensors 2026, 26(11), 3589; https://doi.org/10.3390/s26113589
Submission received: 16 March 2026 / Revised: 23 May 2026 / Accepted: 1 June 2026 / Published: 4 June 2026
(This article belongs to the Section Intelligent Sensors)

Abstract

The rapid development of the Industrial Internet of Things (IIoT) generates massive heterogeneous
sensor data, complicating data cleaning and normalization. Existing algorithmcentric
methods often treat quality issues in isolation and lack unified governance. This
paper proposes a governance-centered framework for multi-source industrial sensor data.
We introduce an Intelligent Catalog as the semantic governance layer to standardize metadata
and achieve semantic alignment before numerical processing. Building upon this,
an AI Agent-driven mechanism dynamically orchestrates cleaning and normalization
strategies based on real-time data status and heterogeneous features. This framework
modularly integrates classical algorithms (e.g., PCA, KPCA, LSTM) without model dependency.
Experimental results on public IIoT datasets demonstrate that our framework
significantly outperforms baseline methods in normalization consistency, noise robustness,
and stability across heterogeneous data. By shifting from an algorithm-centered to a
governance-centered paradigm, this approach provides a scalable and adaptive solution
for complex industrial sensor data management.
Keywords: Industrial Internet of Things; data governance; heterogeneous sensor data; Intelligent Catalog; AI Agent; workflow orchestration Industrial Internet of Things; data governance; heterogeneous sensor data; Intelligent Catalog; AI Agent; workflow orchestration

Share and Cite

MDPI and ACS Style

Dong, H.; Zhang, Y.; Chu, Y.; Zhou, H.; Lu, M.; Zhou, Z.; Zhou, X. AI Agent-Driven Intelligent Catalog Framework: A Governance-Centered Approach for Cleaning and Normalization of Heterogeneous Industrial Sensor Data. Sensors 2026, 26, 3589. https://doi.org/10.3390/s26113589

AMA Style

Dong H, Zhang Y, Chu Y, Zhou H, Lu M, Zhou Z, Zhou X. AI Agent-Driven Intelligent Catalog Framework: A Governance-Centered Approach for Cleaning and Normalization of Heterogeneous Industrial Sensor Data. Sensors. 2026; 26(11):3589. https://doi.org/10.3390/s26113589

Chicago/Turabian Style

Dong, Hongyi, Yimeng Zhang, Yifan Chu, Hailing Zhou, Mingxin Lu, Zuojian Zhou, and Xiaoyang Zhou. 2026. "AI Agent-Driven Intelligent Catalog Framework: A Governance-Centered Approach for Cleaning and Normalization of Heterogeneous Industrial Sensor Data" Sensors 26, no. 11: 3589. https://doi.org/10.3390/s26113589

APA Style

Dong, H., Zhang, Y., Chu, Y., Zhou, H., Lu, M., Zhou, Z., & Zhou, X. (2026). AI Agent-Driven Intelligent Catalog Framework: A Governance-Centered Approach for Cleaning and Normalization of Heterogeneous Industrial Sensor Data. Sensors, 26(11), 3589. https://doi.org/10.3390/s26113589

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop