AI summaryⓘ
The authors developed a system called MAKA to help improve precision in machining aerospace parts by combining human input with multiple AI tools and checks. Unlike typical AI models that struggle with complex, step-by-step calculations and tracking decisions, MAKA separates tasks like interpreting goals, running simulations, retrieving relevant data, and verifying results for safety and accuracy before suggesting actions for humans to approve. They tested MAKA on turbine blades and showed it better handled complex workflows and made more accurate machining adjustments in a digital simulation, helping reduce surface errors significantly. This approach supports safer, more reliable decision-making in high-precision manufacturing.
CNC machiningfree-form aerospace componentslarge language models (LLM)multi-agent systemsknowledge graphvirtual machiningdigital twincompensation strategieserror decompositionhuman-in-the-loop
Authors
Danny Hoang, Ryan Matthiessen, Christopher Miller, Nasir Mannan, Ruby ElKharboutly, David Gorsich, Matthew P. Castanier, Farhad Imani
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.