A Compliance-Preserving Retrieval System for Aircraft MRO Task Search

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autore principale: Jo, Byungho
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914164351434752
author Jo, Byungho
author_facet Jo, Byungho
contents Aircraft Maintenance Technicians (AMTs) spend up to 30% of work time searching manuals, a documented efficiency bottleneck in MRO operations where every procedure must be traceable to certified sources. We present a compliance-preserving retrieval system that adapts LLM reranking and semantic search to aviation MRO environments by operating alongside, rather than replacing, certified legacy viewers. The system constructs revision-robust embeddings from ATA chapter hierarchies and uses vision-language parsing to structure certified content, allowing technicians to preview ranked tasks and access verified procedures in existing viewers. Evaluation on 49k synthetic queries achieves >90% retrieval accuracy, while bilingual controlled studies with 10 licensed AMTs demonstrate 90.9% top-10 success rate and 95% reduction in lookup time, from 6-15 minutes to 18 seconds per task. These gains provide concrete evidence that semantic retrieval can operate within strict regulatory constraints and meaningfully reduce operational workload in real-world multilingual MRO workflows.
format Preprint
id arxiv_https___arxiv_org_abs_2511_15383
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Compliance-Preserving Retrieval System for Aircraft MRO Task Search
Jo, Byungho
Computation and Language
Artificial Intelligence
Emerging Technologies
Information Retrieval
Aircraft Maintenance Technicians (AMTs) spend up to 30% of work time searching manuals, a documented efficiency bottleneck in MRO operations where every procedure must be traceable to certified sources. We present a compliance-preserving retrieval system that adapts LLM reranking and semantic search to aviation MRO environments by operating alongside, rather than replacing, certified legacy viewers. The system constructs revision-robust embeddings from ATA chapter hierarchies and uses vision-language parsing to structure certified content, allowing technicians to preview ranked tasks and access verified procedures in existing viewers. Evaluation on 49k synthetic queries achieves >90% retrieval accuracy, while bilingual controlled studies with 10 licensed AMTs demonstrate 90.9% top-10 success rate and 95% reduction in lookup time, from 6-15 minutes to 18 seconds per task. These gains provide concrete evidence that semantic retrieval can operate within strict regulatory constraints and meaningfully reduce operational workload in real-world multilingual MRO workflows.
title A Compliance-Preserving Retrieval System for Aircraft MRO Task Search
topic Computation and Language
Artificial Intelligence
Emerging Technologies
Information Retrieval
url https://arxiv.org/abs/2511.15383