Optimizing Rail Temperature Management: A Time-Segmented K-Means Approach for Risk Mitigation and Resilient Infrastructure

ÇEÇEN F., SALTAN M., ACAR Ö. F.

Acta Polytechnica Hungarica, cilt.23, sa.1, ss.49-70, 2026 (SCI-Expanded, Scopus)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 23 Sayı: 1
  • Basım Tarihi: 2026
  • Doi Numarası: 10.12700/aph.23.1.2026.1.4
  • Dergi Adı: Acta Polytechnica Hungarica
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.49-70
  • Anahtar Kelimeler: k-means clustering, life cycle analysis, rail temperature, resilient infrastructure, risk management
  • Süleyman Demirel Üniversitesi Adresli: Evet

Özet

Proactive rail temperature management is vital for ensuring the structural integrity and safety of railway infrastructure, particularly to mitigate risks like thermal buckling and derailments. Existing empirical models, such as those by Hunt and Whittingham, have significant limitations in precision and adaptability, prompting the need for innovative approaches that align with modern infrastructure management practices. This study presents a novel methodology to optimize rail temperature prediction through time segmentation via K-means clustering. This approach represents a significant advancement in life cycle performance and risk assessment by providing a scalable, user-friendly solution. The proposed model integrates multivariate regression and Python-based automation to establish a relationship between air temperature, time, and rail temperature, designed for implementation in common spreadsheet tools like Microsoft Excel. Field validation across five Amtrak network stations, representing diverse climatic and structural conditions, demonstrated high predictive accuracy, with temperature deviations within ±2°C and an R² value of 0.943. This research contributes to resilient infrastructure management by enabling precise, low-cost temperature predictions, facilitating timely maintenance strategies, and enhancing risk-based decision making processes for railway operations.