Neuro-symbolic system audits engineering specifications for aircraft safety
NeSySpec: Neuro-Symbolic Technical Intelligence for Auditing Engineering Specifications with an Application to Aircraft
Artificial IntelligenceComputer Vision and Pattern RecognitionSymbolic Computation
Summary
Auditing engineering specifications ensures that aircraft meet physical safety rules, but it can be complicated to spot errors and fix them. The authors created NeSySpec, a system that combines logical rules with learned patterns from data to check these specifications, identify problems, and suggest fixes all at once. It also ties photos and satellite images to relevant parts to support the audit and avoids guessing when data is missing. Their tests on many aircraft types show NeSySpec is better at finding errors and naming what went wrong than previous methods.
What this means in practice
- •For aircraft maintenance teams: Automatically verify aircraft system specifications against physical constraints and suggest precise repairs based on detected errors and visual data.
- •For infrastructure inspection teams: Use a neuro-symbolic audit framework to detect and diagnose specification violations in complex engineered systems with visual support.
Authors
Pier Mattia Basciano, Gianvito Antenori, Cristiano Andolfi, Giovanni Farina, Salvatore Monteleone
Abstract
Engineers who audit a declared specification of an engineered system need to know which physical constraints it respects, which it violates, which field was altered and how to correct it. NeSySpec is an integrated and interpretable neuro-symbolic audit framework, built on Logic Tensor Networks, that answers these questions in one pipeline. Its axioms encode the physical relations of the domain as differentiable graded predicates whose tolerances are learned from a fleet of real records; from the same degrees, it diagnoses the violated constraint, identifies the altered field by abduction, proposes a minimum-change correction and ties image evidence to the parts it describes, abstaining exactly where evidence is missing, and returns all of it in one verification report. We validate NeSySpec on 107 aircraft types, with 16 test aircraft of 9 families held out of training, on specification records paired with ground photographs and satellite imagery and on synthetic errors: generated corruptions, edits labeled from the edit alone and deliberate falsifications. NeSySpec combines all the assessed audit outputs in one pipeline, which no learned, rule-based, solver-based, neuro-symbolic or language-model comparator does; on the test aircraft none is ahead of it in the macro-F1 of its constraint verdicts, in naming the violated constraint and the altered field or in the repair error, and it is competitive in record and image-pair detection. Its diagnosis names the violated constraint in 94.2% of corrupted test records, against 79.5% for classical Fellegi-Holt diagnosis, and on edits labeled from the edit alone, without retraining, abduction finds the altered field in 59.3% of records, against 30.6% for minimum-cardinality localization with random tie- breaking. Only the knowledge base, the visual predicates, the corruption generator and the data are specific to the domain.