To address gear tooth damage and the difficulty of acquiring performance data under high-speed and high-load operating conditions of planetary gearboxes, a digital twin-based system for operational state recognition and performance prediction is proposed, integrating morphological and functional characteristics. Driven by experimental data, the system incorporates finite element analysis, multibody dynamics simulation, artificial intelligence algorithms, and 3D visualization to achieve a virtual mapping of the gearbox’s geometric configuration, structural properties, and dynamic behavior. Structural performance is represented using finite element and dynamic simulation techniques combined with texture mapping, visualized through color gradients; dynamic performance is captured through multibody dynamics simulations and stored in a time-series database, presented as sequential images. The integrated system is constructed by combining a structural performance surrogate model, a system-driven model, and a dynamic performance database, enabling comprehensive functionality. Results demonstrate that the maximum error of the structural performance model is 3%, occurring only under specific working conditions, with negligible impact on the overall meshing performance evaluation of the sun gear. The maximum error in dynamic performance prediction is 1.68%, showing strong consistency with experimental data.

To address the challenges in personnel detection in underground coal mines, such as uneven lighting, dust occlusion, cluttered backgrounds, and significant scale variation of targets, this paper proposes a lightweight object detection method named YOLO-SCC. Based on the lightweight detection network YOLO26n, the SCC lightweight enhancement structure, composed of SPDConv, CBAM, and ContextAggregation, is constructed to improve feature representation and target recognition capability in complex underground environments while striving to maintain model compactness. Specifically, SPDConv optimizes the downsampling process to reduce the loss of feature details, which helps preserve edge and texture information of miners under low-light conditions, at long distances, or at small scales. CBAM adaptively weights features from both channel and spatial dimensions, enhancing the model’s focus on the main body of miners and suppressing irrelevant interference from light reflections, equipment structures, and dust noise. The ContextAggregation module aggregates richer contextual semantic information, strengthening the model’s discriminative ability for personnel targets under occlusion, dense distribution, and complex backgrounds. Experimental results show that with only a modest increase in parameters (from 2.38 MB to 2.88 MB) and computational cost (from 5.2 GFLOPs to 6.0 GFLOPs), YOLO-SCC achieves precision of 88.8%, recall of 82.2%, mAP50 of 85.3%, and mAP50-95 of 51.2%. These represent improvements of 6.1, 0.9, 0.1, and 3.3 percentage points, respectively, over the baseline YOLO26n. The results suggest that YOLO-SCC primarily improves false-positive suppression and localization quality in complex underground environments while maintaining a lightweight model scale.