Physics-Grounded Multi-Agent Architecture for Traceable, Risk-Aware Human-AI Decision Support in Manufacturing

2026-05-05

AI Summary

This study addresses the lack of a traceable, risk-aware, and physics-constrained multi-step decision-making framework in high-precision CNC machining. The authors propose a Multi-Agent Knowledge Analysis (MAKA) architecture that, for the first time, integrates physical plausibility, safety margins, and full provenance into a multi-agent collaborative reasoning pipeline. By leveraging intent routing, tool-augmented quantitative analysis, knowledge graph retrieval, and critic-based validation, the approach decomposes machining deviations into four interpretable components: path error, tool wear evolution, system compliance, and instability. Combining virtual path tracking, cutting force and deflection simulation, and 3D scan-based deviation mapping, the method achieves up to an 87.5 percentage-point improvement in task success rate on a three-stage tool orchestration benchmark and enhances surface deviation prediction accuracy in digital twin experiments from 10⁻² inches to ±10⁻³ inches.

Abstract

High-precision CNC machining of free-form aerospace components requires bounded compensations informed by inspection, simulation, and process knowledge. Off-the-shelf large language model (LLM) assistants can generate text, but they do not reliably execute risk-constrained multi-step numerical workflows or provide auditable provenance for high-stakes decisions. We present multi-agent knowledge analysis (MAKA), a human-in-the-loop decision-support architecture that separates intent routing, tools-only quantitative analysis, knowledge graph retrieval, and critic-based verification that enforces physical plausibility, safety bounds, and provenance completeness before recommendations are surfaced for human approval. MAKA is instantiated on a Ti-6Al-4V rotor blade machining testbed by fusing virtual-machining path-tracking error fields, cutting-force and deflection simulations, and scan-based 3D inspection deviation maps from 16 blades. The analysis decomposes deviation into an evidence-linked pathing component, a drift-based wear proxy capturing systematic evolution across parts, a residual systematic compliance term, and a variability proxy for instability-aware escalation. In a three-level tool-orchestration benchmark (single-step through $\geq$3-step stateful sequences), MAKA improves successful tool execution by up to 87.5 percentage points relative to an unstructured single-model interaction pattern with identical tool access. Digital twin what-if studies show MAKA can coordinate traceable compensation candidates that reduce predicted surface deviation from order $10^{-2}$in to approximately $\pm 10^{-3}$in over most of the blade within the simulation environment, providing a pre-deployment verification signal for risk-aware human decision-making.

Problem

• CNC machining
• risk-aware decision support
• traceability
• multi-agent systems
• digital twin

Innovation

• multi-agent architecture
• risk-aware decision support
• physics-grounded AI
• digital twin
• provenance traceability