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