SCORE-LM: State-Space Radar Representations with Language Models for Fault Diagnosis

2026-09-30

AI Summary

This study addresses the need for precise diagnosis and interpretable maintenance guidance in the automatic perception of radar hardware faults by proposing a novel framework that couples a small scatterer conditional encoder with a local language model. Methodologically, it pioneers the integration of selective state space branches, source-domain self-supervision, and nonlinear projectors to fuse complex trajectory encodings with physical descriptors, thereby precisely aligning diagnostic outcomes with maintenance text. Experimental results demonstrate that, despite a 119-fold reduction in parameter count, the proposed model achieves a fault recall rate of 88.39% and improves the accuracy of maintenance guidance responses to 82.7%. These findings confirm the framework's capability to deliver lightweight, high-precision, and interpretable intelligent operation and maintenance for radar systems.

Abstract

Radar hardware faults threaten automated perception, motivating accurate, compact diagnosis and understandable maintenance guidance. We introduce SCORE-LM, which couples a small scatterer-conditioned operator-response encoder (SCORE) to an adapted local language model. SCORE combines self-referenced complex trajectories, physical descriptors, and a selective state-space branch, with source-only self-supervision and directional fault inference. On eight capture-excluded Rad-R fault recordings, it achieves state-of-the-art performance within the evaluated nine-model comparison: 88.39% mean capture recall and 88.20% four-fault macro-F1 at ten frames. Its 39,520 radar inference coefficients are 119.7 times fewer than RadrNet-DS-CI's, while recall is 15.56 percentage points higher than this strongest competitor. In a separate low-label protocol, SCORE reaches 71.58% recall with one labeled source window per class. A nonlinear projector converts four frozen fault similarities into five soft tokens, linking compact diagnosis to class-conditioned maintenance guidance. On 75 development questions covering 24 radar windows, language adaptation raises correct-fault answers from 45 to 62 (60.0% to 82.7%) relative to removing the co-trained adapters, while retaining the same projector. SCORE-LM thus combines a compact radar specialist with a language interface for communicating fault-specific inspection guidance.

Problem

• radar fault diagnosis
• automated perception
• maintenance guidance
• hardware faults
• compact diagnosis

Innovation

• State-Space Model
• Self-Supervised Learning
• Language Model Adaptation
• Radar Fault Diagnosis
• Parameter Efficiency