Paper Detail
Mohammad Abboush, Hamza Ouarrad, Andreas Rausch
The pre-series validation of automotive software on hardware-in-the-loop (HIL) platforms produces large volumes of multivariate sensor recordings whose assessment against functional safety requirements exceeds what manual review can sustain at campaign scale. Threshold-based tooling reports that a deviation has occurred but neither identifies its nature nor locates its source, while data-driven classifiers, although accurate, rely on large labelled datasets and return opaque decisions that sit uneasily with the traceability demanded by ISO 26262. This study examines whether open-source instruction-tuned large language models (LLMs), given a textual description of sensor behaviour, can serve as data-efficient and interpretable engines for fault detection and diagnosis inside the validation loop. A two-phase framework is proposed: automated requirement checking on a dSPACE real-time platform first isolates the recordings that violate a safety requirement, and only these are inspected, with sliding windows of the signals reduced to statistical, relational, and contextual descriptors, embedded in a fixed prompt, and mapped by a 4-bit low-rank-adapted LLM to a fault location accompanied by a written justification. Four model families ranging from two to eight billion parameters were adapted and tested on a gasoline-engine case study spanning six injected fault classes. The smallest model matched the largest at 81.6\% accuracy, whereas a comparably sized model failed to converge, indicating that diagnostic competence under task-specific adaptation follows convergence rather than parameter count, with the entire adapt-and-evaluate cycle fitting on a single commodity accelerator.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{abboush2026sensor,
title = {Sensor-Level Fault Diagnosis for Automotive Software Validation Using Large Language Models},
author = {Mohammad Abboush and Hamza Ouarrad and Andreas Rausch},
year = {2026},
abstract = {The pre-series validation of automotive software on hardware-in-the-loop (HIL) platforms produces large volumes of multivariate sensor recordings whose assessment against functional safety requirements exceeds what manual review can sustain at campaign scale. Threshold-based tooling reports that a deviation has occurred but neither identifies its nature nor locates its source, while data-driven classifiers, although accurate, rely on large labelled datasets and return opaque decisions that sit u},
url = {https://arxiv.org/abs/2608.05921},
keywords = {cs.SE},
eprint = {2608.05921},
archiveprefix = {arXiv},
}
{}