Heterogeneous Model Alignment in Digital Twin

2025-12-17

AI Summary

In multi-layer model-driven digital twins, aligning heterogeneous models across abstraction levels remains challenging due to semantic mismatches, structural inconsistencies, and difficulties in dynamic synchronization. Method: This paper proposes a semantically consistent and dynamically adaptive automated alignment framework. It innovatively integrates an adaptive metamodel conformance mechanism with large language model (LLM)-driven semantic validation, augmented by ontology-based mapping inference and integration of the Ontology Alignment Evaluation Initiative (OAEI) standardized benchmarking suite, enabling domain-knowledge-guided, structure-preserving alignment. Contribution/Results: Evaluated on an air quality case study and multiple OAEI benchmarks, the framework achieves significant improvements in alignment accuracy and generalizability. It reduces reliance on manual mapping by over 90% and supports scalable, collaborative evolution of heterogeneous models across abstraction layers.

Technology Category

Knowledge Representation and Reasoning: OntologiesMachine Learning: Large Multimodal Models (LMMs)Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMsGraph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphsSearch and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Digital twin (DT) technology integrates heterogeneous data and models, along with semantic technologies to create multi-layered digital representation of physical systems. DTs enable monitoring, simulation, prediction, and optimization to enhance decision making and operational efficiency. A key challenge in multi-layered, model-driven DTs is aligning heterogeneous models across abstraction layers, which can lead to semantic mismatches, inconsistencies, and synchronization issues. Existing methods, relying on static mappings and manual updates, are often inflexible, error-prone, and risk compromising data integrity. To address these limitations, we present a heterogeneous model alignment approach for multi-layered, model-driven DTs. The framework incorporates a flexibility mechanism that allows metamodels to adapt and interconnect seamlessly while maintaining semantic coherence across abstraction layers. It integrates: (i) adaptive conformance mechanisms that link metamodels with evolving models and (ii) a large language model (LLM) validated alignment process that grounds metamodels in domain knowledge, ensuring structural fidelity and conceptual consistency throughout the DT lifecycle. This approach automates semantic correspondences discovery, minimizes manual mapping, and enhances scalability across diverse model types. We illustrate the approach using air quality use case and validate its performance using different test cases from Ontology Alignment Evaluation Initiative (OAEI) tracks.

Problem

• Aligning heterogeneous models across abstraction layers in digital twins
• Addressing semantic mismatches and synchronization issues in model-driven systems
• Automating semantic correspondences discovery to reduce manual mapping efforts

Innovation

• Adaptive conformance mechanisms link metamodels with evolving models
• LLM-validated alignment process grounds metamodels in domain knowledge
• Automates semantic correspondences discovery to minimize manual mapping