Towards General Industrial Intelligence: A Survey of Continual Large Models in Industrial IoT

2024-09-02

AI Summary

To address insufficient industrial AI intelligence and the practical challenges of deploying large language models (LLMs) in industrial settings, this paper proposes an IIoT-driven, full-lifecycle co-evolutionary framework for industrial large models. Methodologically, it systematically decomposes the lifecycle into four phases—data foundation, model training, connected deployment, and dynamic evolution; formally defines four industrial LLM paradigms (language, vision, time-series, and multimodal); and introduces an IIoT-native deployment mechanism based on modular design, dynamic routing, and model fusion. The key contributions include: (1) establishing the first theoretical framework for co-evolution between LLMs and IIoT; (2) advancing core technologies—including edge-cloud collaborative training, continual learning, and online model merging; and (3) identifying and addressing four critical implementation challenges with concrete solution pathways. The framework delivers a reusable methodology and actionable technology roadmap for manufacturing, enabling a paradigm shift from static models to adaptive, scalable, and emergent-capable general industrial intelligence.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Industrial AI is transitioning from traditional deep learning models to large-scale transformer-based architectures, with the Industrial Internet of Things (IIoT) playing a pivotal role. IIoT evolves from a simple data pipeline to an intelligent infrastructure, enabling and enhancing these advanced AI systems. This survey explores the integration of IIoT with large models (LMs) and their potential applications in industrial environments. We focus on four primary types of industrial LMs: language-based, vision-based, time-series, and multimodal models. The lifecycle of LMs is segmented into four critical phases: data foundation, model training, model connectivity, and continuous evolution. First, we analyze how IIoT provides abundant and diverse data resources, supporting the training and fine-tuning of LMs. Second, we discuss how IIoT offers an efficient training infrastructure in low-latency and bandwidth-optimized environments. Third, we highlight the deployment advantages of LMs within IIoT, emphasizing IIoT's role as a connectivity nexus fostering emergent intelligence through modular design, dynamic routing, and model merging to enhance system scalability and adaptability. Finally, we demonstrate how IIoT supports continual learning mechanisms, enabling LMs to adapt to dynamic industrial conditions and ensure long-term effectiveness. This paper underscores IIoT's critical role in the evolution of industrial intelligence with large models, offering a theoretical framework and actionable insights for future research.

Problem

• Industrial Internet of Things (IIoT)
• Large Models (LMs)
• Industrial AI

Innovation

• Industrial Internet of Things (IIoT)
• Large Models (LMs) in Industrial AI
• Modular Design and Dynamic Adjustment