This review examines recent progress in large AI models for intelligent manufacturing, covering model architectures, adaptation strategies, system integration, and applications across product development, production processes, equipment maintenance, and manufacturing services.
Abstract
Large AI models are reshaping intelligent manufacturing from isolated automation toward knowledge-intensive, model-assisted production systems. Yet their industrial value depends not on model scale alone, but on how language, vision, code, sensor data, engineering knowledge, and feedback mechanisms are integrated into deployable manufacturing workflows. This review examines recent progress in large AI models for intelligent manufacturing, covering model architectures, adaptation strategies, system integration, and applications across product development, production processes, equipment maintenance, and manufacturing services. A lifecycle-based framework is used to organize the literature and distinguish model capabilities from the data resources, retrieval mechanisms, simulation and optimization tools, digital twins, edge-cloud infrastructure, and human validation required for deployment. Current evidence suggests that large models show more reliable value in bounded, information-rich tasks, whereas safety-critical control and production-scale autonomy remain insufficiently validated. The review further summarizes challenges in data quality, domain adaptation, reliability, interpretability, latency, cybersecurity, cost, benchmarking, and responsibility allocation. By linking application scenarios, system-level enablers, and evidence maturity, this review provides a structured perspective for assessing the practical value of large AI models in manufacturing.
The evidence indicates that LLMs are becoming useful semantic and coordination layers in engineering workflows, but not dependable engineering substitutes in human-in-the-loop, evidence-grounded systems where retrieval, validation, tool use, and structured knowledge help keep outputs useful and bounded in safety-relevant tasks.
It is argued that first-principles models (FPMs) remain essential for mission- and business-critical workflows in industrial automation, both in process design and operations and hybrid intelligence integrates mechanistic rigor with data-driven insights to deliver smarter design, safer operations, and more sustainable processes.
Hongzhi Zhao, Shu Wang, Salvador I. Pérez-Uresti et al.· Industrial & Engineering...· 0 citations
he rapid evolution of Industry 4.0 has accelerated the integration of artificial intelligence (AI), Internet of Things (IoT), cloud computing, and advanced analytics into modern manufacturing ecosystems. Among these technologies, AI-enabled digital twins have emerged as a transformative paradigm for creating dynamic virtual representations of physical manufacturing assets, production lines, and operational environments. This research review examines the role of artificial intelligence-driven digital twin frameworks in enhancing smart manufacturing capabilities, particularly focusing on predictive maintenance, operational optimization, real-time decision-making, and system resilience. The study develops a conceptual framework by synthesizing existing research contributions related to AI architectures, secure computing infrastructures, predictive analytics, automation, and intelligent decision systems.
The methodology adopts a structured literature synthesis approach using the provided research works to analyze technological convergence between digital twins and AI-enabled industrial applications. The proposed framework evaluates major components including data acquisition, virtual modeling, machine learning-based prediction, intelligent maintenance scheduling, cybersecurity mechanisms, and autonomous decision support. Findings indicate that AI-enabled digital twins significantly improve equipment reliability, reduce unexpected failures, enhance resource utilization, and enable proactive manufacturing strategies. However, challenges related to interoperability, cybersecurity, computational complexity, data quality, and governance remain critical barriers to widespread industrial adoption. The research highlights that future manufacturing systems will increasingly depend on trustworthy, scalable, and adaptive digital twin architectures integrated with responsible AI practices.
D. Mahmood· European International Journ...· 0 citations
Artificial intelligence (AI) is transforming smart manufacturing by enabling intelligent automation, data-driven decisions, and stronger collaboration between humans and manufacturing systems. The widespread adoption of collaborative robots, the industrial internet of things, and cyber-physical systems is driving demand for manufacturing environments that are safer, more flexible, and more efficient. Despite AI’s broad application in manufacturing, few studies have combined adaptive safety and intelligent task allocation within a single human-centered framework. This review offers a comprehensive look at AI applications that support these two complementary functions. Literature from Scopus, Web of Science, IEEE Xplore, ScienceDirect, SpringerLink, and the ACM Digital Library was systematically reviewed following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines and analysed thematically. The findings show that machine learning, deep learning, computer vision, reinforcement learning, knowledge-driven approaches, digital twins, and explainable AI contribute to improvements in predictive maintenance, quality inspection, production scheduling, adaptive safety, and collaborative decision-making. That said, challenges remain - such as interoperability, explainability, limited access to high-quality manufacturing data, industrial validation, and integrating multiple AI technologies. This review gives researchers and practitioners a holistic perspective and highlights integrated, human-centered AI frameworks as key enablers of resilient, efficient, and sustainable Industry 5.0 manufacturing systems.
Zaliha Baso, N. Yadav, P. Faujdar· Cureus Journal of Computer S...· 0 citations
The findings indicate that scalability should be understood not merely as increasing computational capacity but as the ability to expand AI-enabled construction processes without proportionally increasing coordination complexity, training requirements, or operational risk.
Takumi Suzuki, Mio Tanaka· International Journal of Adv...· 0 citations
Industrial operations need AI systems that can reason across live process data, engineering knowledge, and operator workflows. Yet conventional machine learning models often remain narrow predictors, while large language models lack grounding in plant behaviour, constraints, and real-time operating context. This talk presents Orbital, a grounded multi-agent system for decision support in industrial operations. Orbital combines three complementary layers: a time-series model for multivariable process dynamics and uncertainty-aware forecasting; a constraint-learning layer that extracts engineering relationships from plant documentation, including P&IDs, datasheets, mass and energy balances, and operating manuals; and a language-fusion layer that aligns process behaviour with engineering descriptions. These components are coordinated through specialist agents for planning, tool execution, verification, memory, and response composition. The system moves beyond prediction toward interpretable decision support: detecting abnormal behaviour, retrieving relevant historical events, explaining likely root causes, and grounding recommendations in both data and engineering constraints. More broadly, this work argues that the next generation of industrial AI must be grounded, multi-modal, and operationally trustworthy; connecting data, domain knowledge, and human decision-making in high-consequence environments.
Samyakh Tukra· Proceedings of the 3rd Found...· 0 citations