M4E Research #6: March 2024
Generation of Asset Administration Shell with Large Language Model Agents: Interoperability in Digital Twins with Semantic Node
Abstract: This research introduces a novel approach for assisting the creation of Asset Administration Shell (AAS) instances for digital twin modeling within the context of Industry 4.0, aiming to enhance interoperability in smart manufacturing and reduce manual effort. We construct a "semantic node" data structure to capture the semantic essence of textual data. Then, a system powered by large language models is designed and implemented to process "semantic node" and generate AAS instance models from textual technical data. Our evaluation demonstrates a 62-79% effective generation rate, indicating a substantial proportion of manual creation effort can be converted into easier validation effort, thereby reducing the time and cost in creating AAS instance models. In our evaluation, a comparative analysis of different LLMs and an in-depth ablation study of Retrieval-Augmented Generation (RAG) mechanisms provide insights into the effectiveness of LLM systems for interpreting technical concepts. Our findings emphasize LLMs' capability in automating AAS instance creation, enhancing semantic interoperability, and contributing to the broader field of semantic interoperability for digital twins in industrial applications. The prototype implementation and evaluation results are released on our GitHub Repository with the link: this https URL
Authors: Yuchen Xia, Zhewen Xiao, Nasser Jazdi, Michael Weyrich
When Industry meets Trustworthy AI: A Systematic Review of AI for Industry 5.0
Abstract: Industry is at the forefront of adopting new technologies, and the process followed by the adoption has a significant impact on the economy and society. In this work, we focus on analysing the current paradigm in which industry evolves, making it more sustainable and Trustworthy. In Industry 5.0, Artificial Intelligence (AI), among other technology enablers, is used to build services from a sustainable, human-centric and resilient perspective. It is crucial to understand those aspects that can bring AI to industry, respecting Trustworthy principles by collecting information to define how it is incorporated in the early stages, its impact, and the trends observed in the field. In addition, to understand the challenges and gaps in the transition from Industry 4.0 to Industry 5.0, a general perspective on the industry's readiness for new technologies is described. This provides practitioners with novel opportunities to be explored in pursuit of the adoption of Trustworthy AI in the sector.
Authors: Eduardo Vyhmeister, Gabriel G. Castane
A Novel Hybrid Feature Importance and Feature Interaction Detection Framework for Predictive Optimization in Industry 4.0 Applications
Abstract: Advanced machine learning algorithms are increasingly utilized to provide data-based prediction and decision-making support in Industry 4.0. However, the prediction accuracy achieved by the existing models is insufficient to warrant practical implementation in real-world applications. This is because not all features present in real-world datasets possess a direct relevance to the predictive analysis being conducted. Consequently, the careful incorporation of select features has the potential to yield a substantial positive impact on the outcome. To address the research gap, this paper proposes a novel hybrid framework that combines the feature importance detector - local interpretable model-agnostic explanations (LIME) and the feature interaction detector - neural interaction detection (NID), to improve prediction accuracy. By applying the proposed framework, unnecessary features can be eliminated, and interactions are encoded to generate a more conducive dataset for predictive purposes. Subsequently, the proposed model is deployed to refine the prediction of electricity consumption in foundry processing. The experimental outcomes reveal an augmentation of up to 9.56% in the R2 score, and a diminution of up to 24.05% in the root mean square error.
Authors: Zhipeng Ma, Bo Nørregaard Jørgensen, Zheng Grace Ma