This paper presents an end-to-end DiagnosisToken pathway based on vibration-diagnostic outputs, rule-based event aggregation, structured textual token generation, and LLM-based interpretation, and positions Industrial Tokenization as a semantic interface between domain-specific industrial intelligence and LLM- or agent-based reasoning.
Abstract
Industrial health management increasingly relies on heterogeneous information sources, including condition monitoring systems, supervisory control and data acquisition systems, maintenance records, inspection results, and prognostic models. Although large language models provide new opportunities for cross-source reasoning, industrial data and analytical outputs differ substantially in structure, temporal resolution, physical meaning, and reliability. Directly integrating such heterogeneous information into a monolithic model may reduce interpretability, traceability, and adaptability to equipment and data changes. This paper introduces Industrial Tokenization, a conceptual interface for transforming source-specific analytical outputs into structured and machine-interpretable units of industrial evidence, termed Industrial Tokens. Unlike numerical tokens used to encode raw time-series data, Industrial Tokens represent domain-grounded evidence together with source, temporal scope, operating context, analytical meaning, quality or confidence information, and provenance. Based on this concept, a federated industrial architecture is proposed, where heterogeneous analytical subsystems retain autonomy while exposing standardized Industrial Tokens to a central reasoning layer. As an initial implementation, this study presents an end-to-end DiagnosisToken pathway based on vibration-diagnostic outputs, rule-based event aggregation, structured textual token generation, and LLM-based interpretation. Other Industrial Tokens, including SCADA-based condition-monitoring tokens, maintenance tokens, and prognostic tokens, are reserved as future extensions. The proposed framework positions Industrial Tokenization as a semantic interface between domain-specific industrial intelligence and LLM- or agent-based reasoning, rather than another method for encoding raw industrial data.
Industrial artificial intelligence depends not only on advanced algorithms, but also on the unseen data pipelines that feed, organize, validate, and sustain them. This chapter examines how data pipelines shape the design, integration, and quality assurance of AI-driven industrial systems. It explores the movement of data from sensors, machines, production lines, enterprise platforms, and human inputs into structured workflows capable of supporting reliable decision-making. Particular attention is given to data accuracy, interoperability, traceability, governance, and continuous monitoring. The chapter also considers the operational realities of industrial environments, where legacy systems, fragmented data sources, and production pressures often complicate implementation. By linking technical architecture with quality culture, the chapter argues that robust data pipelines are not merely digital infrastructure; they are the foundation upon which trustworthy industrial AI becomes practical, scalable, and meaningful.
M. Foley· Research Journal of Maaref U...· 0 citations
Experiments on public benchmarks and real-world industrial BI workloads show that QwenPaw-Data improves both verifiable data access capability and higher-level analytical quality, offering a practical foundation for reliable, traceable, and continuously improving enterprise data agents.
Analysis of well plug and abandonment operations in the oil and gas industry requires comprehensive interpretation of historical data distributed across numerous heterogeneous sources, including daily drilling reports, well completion reports, cementing data, intervention reports, schematics, and well integrity assessment materials. In conventional practice, this process is largely performed manually, takes from several days to several weeks, and depends heavily on the individual experience of the engineer. Variations in document structure, data incompleteness, inconsistencies between sources, and limited traceability of engineering conclusions introduce risks of error and hinder the scalability of analysis.
This paper presents an agent-oriented approach to automating the analysis of well P&A operations. The proposed system transforms fragmented processing of historical documentation into a structured and traceable workflow, including document ingestion, parsing, data extraction, reconstruction of well state, validation, well schematic generation, and regulatory compliance assessment. Unlike monolithic solutions based on large language models (LLMs), the system decomposes a complex engineering task into a set of specialized agents coordinated by a central orchestration mechanism. This approach ensures modularity, controllability, reproducibility, and auditability of each processing stage.
The system was applied to representative sets of historical well documentation, including the Petrel-1 case study. The results demonstrate a significant reduction in initial analysis time: data extraction and consolidation were completed in 30–45 minutes compared to 1–3 working days, while a preliminary full P&A analysis required 60–90 minutes instead of 3–5 working days. At the same time, 85–95% of the required engineering parameters were automatically extracted from the documents, depending on input data quality, and all extracted values were linked to their original sources. The system also identified inter-document inconsistencies, missing data, and ambiguous parameters, not replacing engineering judgment but supporting it with more complete and structured information.
The results demonstrate that multi-agent architectures can serve as a practical foundation for automating complex engineering processes that require a combination of unstructured data interpretation, deterministic validation, domain-specific logic, and strict traceability. The proposed system does not replace engineers but augments their capabilities by reducing manual workload, improving analytical consistency, and providing a transparent basis for regulatory compliance verification.
V. K. Payrazyan, Oxana Gubaidullina, Rustam Galliamov et al.· SPE/IADC Asia Pacific Drilli...· 0 citations
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.
Baotong Chen, Lu Dai, Chuangjian Wang et al.· IEEE Access· 0 citations
Modern batch manufacturing environments generate large volumes of operational data through industrial historians; however, much of this information remains underutilised because it lacks process context and standardised representation. This paper suggests a framework for the data enablement of historian data to provide contextualised intelligence for agentic artificial intelligence applications in ISA-88 batch manufacturing systems. This framework brings together the historian records and the concepts of ISA-88, such as recipes, procedures, equipment, process stages, and information about the execution of the batches, providing a structured and context-aware data foundation. The raw manufacturing data is preprocessed, contextually mapped, enriched with meaning, and represented in the form of knowledge for establishing meaningful relationships between process events and operational assets. The contextualised information is then fed into an agentic AI layer that can make autonomous decisions, offer decision support, detect anomalies, optimise processes and provide operational recommendations. By combining industrial data management principles with intelligent agent technologies, the proposed framework enhances traceability, improves decision accuracy, and supports real-time manufacturing intelligence. Evaluation measures include accuracy of context extraction, effectiveness of the decision, process efficiency, and response time. By supporting the scalability, explainability, and context-awareness of AI solutions in today's batch manufacturing environment, the framework paves the way for the advancement of Industry 4.0.
Shriprakashan. L. Parapalli· 2026 International Conferenc...· 0 citations
Digital twins have become foundational in cyber-physical systems by mirroring asset state and enabling monitoring, simulation, and optimization. However, the data infrastructure that powers modern analytics and AI—including transformation logic, orchestration state, lineage, and data quality rules—is typically encoded across fragmented scripts, configuration artifacts, and logs, making it difficult to audit, evolve, or safely automate. This paper proposes Meta-Twins, a system-of-systems digital twin for data engineering infrastructure, where engineering intent is represented as normalized relational metadata (mirrored state) and continuously enforced by persistent daemon processes (autonomous behavior). Meta-Twins exposes a SQL-native control plane for defining transformations, dependencies, schedules, execution history, and quality gates, thereby decoupling semantics from tool-specific execution mechanics and providing a bounded interface for safe AI-assisted updates. We implement a prototype on Databricks to demonstrate feasibility and portability of the design, and we evaluate Meta-Twins through a structured comparison with procedural pipelines and declarative modeling tools across coupling, transparency, self-service readiness, and resilience. The results indicate that representing infrastructure intent as relational state enables consistent auditability, deterministic execution, and reduced operational coupling, supporting human-centric and resilient data engineering aligned with the conceptual goals of Industry 5.0, particularly in terms of transparency and human-centric interaction.
Z. T. Lee, Arvin Shadravan, Hamid R. Parsaei· Human-Intelligent Systems In...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
