Formal framework guides AI use in safety critical engineering workflows
Dependable AI-Assisted Engineering: A Formal Framework for AI Participation and Assurance in Safety-Critical Workflows
Computer Vision and Pattern RecognitionArtificial Intelligence
Summary
The paper looks at how AI tools can safely help engineers with important tasks where mistakes could be dangerous. The authors created a detailed system for deciding when and how AI should be allowed to assist in each small step of an engineering process, including checks and backups. They then tested this system on a 17-step process for airplane wing analysis, combining AI-generated designs with human and computer verifications. The study shows how to carefully control AI’s role without claiming full safety or performance guarantees for the entire workflow.
What this means in practice
- •For structural engineering teams: Use formal steps to decide when AI-generated designs can enter safety-critical structural analysis workflows.
- •For aerospace engineering departments: Integrate AI participation with human and automated checks to support wing-spar safety evaluations.
Authors
Puxue Tan
Abstract
Generative AI can produce engineering artefacts, but generation alone does not determine whether or how those artefacts should enter safety-critical workflows. This paper develops a formal framework for assigning AI participation and assurance at the level of individual workflow units. Each unit has a participation and assurance record covering its engineering requirement, an approved operational formalization where applicable, the applicable mechanism, fallback where applicable, evidence obligations and the applicable guarantee, plus a deployment-readiness status. The framework distinguishes deterministic verification, statistically calibrated admission, authorized human judgement supported by AI advice, authorized human adjudication of AI-produced artefacts, retained deterministic tool paths and explicit non-participation; these arrangements carry different kinds of guarantee rather than levels on a common scale. The framework also separates formalization fidelity from verifier soundness, provides a staged classification and readiness procedure, and derives conditions for comparing a gated AI-assisted unit with an incumbent process under recurring-population assumptions. We instantiate and apply the framework in an executed 17-unit wing-spar structural-analysis workflow combining deterministically gated AI-generated CAD, retained deterministic computation and human judgement. The AI-generated CAD program passed all 23 deterministic checks and was admitted at the first attempt. Favourable stress magnitudes did not suffice to pass the stress criteria where the predeclared mesh-convergence evidence was insufficient; those criteria were instead referred to engineering judgement. The case demonstrates selective AI participation and explicit evidence handling at unit level; no claim is made of workflow-level dependability, certification, structural safety or productivity.