Jul 2026· PHM Society European Conference· Vol 9, pp. 1-13· 0 citations· 43 references
TL;DR
An innovative High-Level Reasoner (HLR) decision support architecture for aircraft systems that provides a reusable framework for extension across aircraft systems and wider IVHM applications and serves as an enabling technology that advances beyond existing diagnostics and prognostics solutions for asset utilisation.
Abstract
State-of-the-art Integrated Vehicle Health Management (IVHM) systems and digital twins (DTs) integrate physics-based and data-driven methodologies for predictive maintenance. Such systems commonly incorporate multiple DT instances to estimate substantive outputs. Nonetheless, they exhibit key limitations: lack of multi-DT orchestration mechanisms, limited uncertainty quantification, and insufficient prescriptive decision-support capability. To this end, this paper introduces an innovative High-Level Reasoner (HLR) decision support architecture for aircraft systems. The proposed HLR architecture comprises a multi-layer data-transfer structure, with the principal HLR layer consisting of adaptable specialist modules that facilitate a robust decision support implementation for query-driven prescriptive maintenance. The developed architecture is illustrated on an aircraft landing gear system (ATA 32), orchestrating multiple federated subsystems; represented by the Brake Temperature DT and Tyre Pressure DT. The contribution is a modular architecture that provides a reusable framework for extension across aircraft systems and wider IVHM applications. It therefore serves as an enabling technology that advances beyond existing diagnostics and prognostics solutions for asset utilisation.
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
Military command and control system (C2-system) design is increasingly shaped by emerging technologies such as AI-enabled decision support, multi-sensor fusion and autonomous intelligence, surveillance and reconnaissance (ISR) capabilities. Architecture frameworks such as the NATO Architecture Framework (NAF) provide a structure for describing complex systems, but are less explicit about how to select entry points and sequence modeling activities. This article proposes a modular, context-informed framework, an extension to NAF, that combines Navigation Guidance with a repository of seven reusable Method Chunks (MCs) to support architectural design activities in a C2-system context. Using Design Science Research (DSR) as the overarching framework, this work is based on Situational Method Engineering (SME) and MAP-based formalization. A demonstration instantiates the framework for integrating a next-generation ISR capability into a C2-system. The resulting architecture and modeling activities link operational workflow to capability framing and cross-level capability dependencies and are consolidated through documentation and traceability artifacts. Collectively, the architecture supports reasoning about mission impact, capability motivation, coordination requirements, and traceability, while keeping later models anchored in a relevant operational context and workflow. The contribution of this work is methodological. The demonstration illustrates how a specific NAF-aligned modeling progression can be instantiated for an ISR integration case.
Jan Lundberg, K. Andersson, Janis Stirna· Complex Systems Informatics...· 0 citations
A dependency-aware OTA orchestration framework that addresses challenges in improving update success rates, efficiency in execution time and update requests through optimized scheduling, and feasibility in maintaining system-wide integrity by successfully reconciling stringent safety requirements and diverse update sensitivity constraints is proposed.
Juyeon Park, In-Young Ko· SIGSOFT FSE Companion· 0 citations
As Large Language Model (LLM) agents transition from general-purpose assistants to specialized enterprise tools, grounding them in industrial reality remains a significant challenge. To address this, we developed AssetOpsBench, a comprehensive framework for the lifecycle of AI agents in Industrial Asset Operations and Maintenance, built around the Model Context Protocol (MCP) as the standard for connecting agents to complex enterprise data silos. In this hands-on tutorial, participants will learn to build reliable industrial agents using MCP and AssetOpsBench. The session is divided into two parts. In the first part, we dive into an end to end MCP grounded agent pipeline that connects specialized MCP servers to high velocity industrial data including time series telemetry, IoT streams, failure mode records, and work order histories while orchestrating workflows with Plan Execute and Reflexion planners. In the second part, we unlock predictive analytics such as anomaly detection and Remaining Useful Life (RUL) prediction within agentic workflows, assess agent reliability through multi-dimensional evaluation, and ground agents against physical constraints. Whether for researchers or practitioners, this tutorial provides the foundations for building auditable, production-grade agents for Industry 4.0. AssetOpsBench is accessible at: https://github.com/IBM/AssetOpsBench.
Dhaval Patel, Chathurangi Shyalika, Shuxin Lin et al.· Proceedings of the 32nd ACM...· 0 citations
Autonomous Unmanned Aerial Vehicles (UAVs) are complex cyber-physical systems that require the coordinated integration of flight control, navigation, perception, communication, power management, and mission-level decision-making under safety, timing, and reliability constraints. However, many autonomous UAV development workflows still rely on document-centric requirements, separated architectural descriptions, and software implementation artifacts, which can lead to ambiguity, interface inconsistencies, and weak traceability during early design. This paper presents a Model-Based Systems Engineering (MBSE) design framework for the SysML-driven development of autonomous UAVs. The proposed framework uses the Systems Modeling Language (SysML) as a formal design backbone to structure UAV development across four connected layers: stakeholder requirements, functional decomposition, logical architecture, and physical/software allocation. SysML requirement diagrams, activity diagrams, block definition diagrams, internal block diagrams, state machine diagrams, and parametric diagrams are used to capture the functional, structural, behavioral, interface, and performance aspects of the UAV system. The logical architecture is then systematically mapped to a Robot Operating System 2 (ROS 2) software architecture by relating SysML blocks to ROS 2 nodes, flow ports and connectors to topics, request-response interactions to services, and goal-oriented behaviors to actions. The framework is illustrated at the design level using representative autonomous UAV mission scenarios, including autonomous take-off, waypoint navigation, hover stabilization, obstacle avoidance, return-to-home, and emergency handling. The resulting model supports requirement allocation, interface definition, subsystem responsibility assignment, and verification planning before simulation or physical deployment.
Deekshitha Angadi, Naveena Budda, Vikas Agarwal et al.· 0 citations
This systematic review explores the intersection between Multi-Agent Systems and Digital Twins, with a particular focus on predictive maintenance applications in resource-constrained contexts and reveals that, despite significant progress, no existing system offers an integrated embedded-distributed hierarchical solution that simultaneously meets the requirements of Industry 5.0.