Natalia Bieberach Guija

Mrs. Natalia Bieberach Guija


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 June 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
NGNatalia Bieberach Guija
Natalia Bieberach Guija
Brake discs are critical components of a train’s pneumatic braking system and require monthly preventive maintenance, including cleaning, measurement, and visual inspection. Visual inspections, guided by standards such as UNE-EN 14535-3 and the Faiveley Transport technical manual, involve assessing cracks classified by size and type (penetrating, incipient and superficial). This study presents an automated solution for crack detection and classification using thermal imaging and artificial intelligence. A low-cost Flir Lepton 3.1R thermal camera was used to identify cracks based on size and location. The Artificial Intelligence contribution lies in the integration of the proposed method, which combines the You Only Look Once (YOLO) v8m model with a U-Net (Residual Network (ResNet) 50 backbone) and a Convolutional Neural Network (CNN) for improved detection and segmentation. Compared to previous approaches using You Only Look Once (YOLO) v4 or Mask - Region-based Convolutional Neural Network (R-CNN), this combination provides higher precision in identifying thermal cracks on railway brake discs. The process begins with thermal image acquisition and data augmentation through noise injection and geometric transformations, producing a robust dataset for training the neural networks. Experimental results demonstrate the feasibility of applying Artificial Intelligence (AI) and thermal imaging for predictive maintenance, achieving a 90% detection accuracy. Furthermore, the study confirms that using higher-resolution thermal datasets enhances model performance, making this approach a cost-effective and reliable tool for automated brake disc inspection.

15 October 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
NGNatalia Bieberach Guija
Natalia Bieberach Guija
JDJorge Luis Arce Díaz
Jorge Luis Arce Díaz
JBJose Luis Becerra
Jose Luis Becerra
JRJulio Ronceros
Julio Ronceros
José Sánchez del Río SáezJosé Sánchez del Río Sáez
José Sánchez del Río Sáez
Brake discs are critical components of a train’s pneumatic braking system and require monthly preventive maintenance, including cleaning, measurement, and visual inspection. Visual inspections, guided by standards such as UNE-EN 14535-3 and the Faiveley Transport technical manual, involve assessing cracks classified by size and type (penetrating, incipient, superficial). This study presents an automated solution for crack detection and classification using thermal imaging and artificial intelligence. A low-cost Flir Lepton 3.1R thermal camera was used to identify cracks based on size and location. The proposed method integrates the YOLOv8m model with a U-Net (ResNet50 backbone) and a CNN for improved detection and segmentation. Compared to previous approaches using YOLOv4 or Mask-RCNN, this combination provides higher precision in identifying thermal cracks on railway brake discs. The process begins with thermal image acquisition and data augmentation through noise injection and geometric transformations, producing a robust dataset for training the neural networks. Experimental results demonstrate the feasibility of applying AI and thermal imaging for predictive maintenance, achieving a 97% detection accuracy. Furthermore, the study confirms that using higher-resolution thermal datasets enhances model performance, making this approach a cost-effective and reliable tool for automated brake disc inspection.