ABSTRACT The structural integrity of railway fasteners is a critical determinant of track safety, load transfer stability, and long‐term infrastructure reliability. In practice, fastener loosening often develops gradually and manifests through subtle geometric, depth, and mechanical changes that are difficult to capture using single‐modality or label‐dependent inspection methods. Existing deep learning approaches largely rely on manually annotated datasets, isolated visual cues, or single‐sensor inputs, which limit their robustness under real‐world variability, noise, and data scarcity. To address these challenges, this paper proposes TrinityNet, a cross‐modality generative reasoning framework for zero‐label fastener tightness evaluation. TrinityNet jointly exploits RGB imagery, monocular depth estimation, and 3D mesh representations to capture complementary structural and geometric information without requiring manual annotations. A self‐supervised dual‐evaluator architecture independently validates each modality through adversarial and contrastive learning, improving training stability and cross‐modal consistency. Experimental results demonstrate a 99.64% reduction in discriminator loss, an 80.55% decrease in contrastive error, and a 409.67% improvement in generative consistency. Fastener tightness is quantitatively assessed using a multi‐metric diagnostic scheme incorporating fatigue life, principal component analysis–based degradation indices, cyclic load response, and energy strain measures. The framework reliably distinguishes tight fasteners from loose, enabling interpretable and actionable maintenance decisions. Owing to its label‐free learning, multimodal robustness, and real‐time applicability, TrinityNet provides a practical and scalable solution for autonomous railway fastener integrity monitoring.
Wang et al. (Thu,) studied this question.