Sürdürülebilir Kalkınma Amaçları

• 2

Yazarlar

• Akdağ, Mustafa(1)
• Akmaz, Düzgün(1)
• Karakose, Mehmet(1)
• Mamiş, Mehmet Salih(1)
• Yilmazer, Merve(1)

• MakaleAçık Erişim2026Scopus SJRQ2/r/munzur/1337
  Single-Ended Fault Detection and Fault Location in Transmission Lines Using Approximate Derivative

  Akdağ, Mustafa; Mamiş, Mehmet Salih; Akmaz, Düzgün

  Fault location in power transmission lines (PTLs) relies on impedance or traveling wave (TW) principles. TW approaches offer superior accuracy and high robustness against fault resistance. While multi-ended methods require precise terminal synchronization, single-ended TW (SETW) methods utilize measurements from one terminal, requiring accurate distinction of reflected waves. This study employs the computationally efficient approximate derivative (AD)—the difference between consecutive samples—for SETW fault detection and location. Normally near zero, the AD of modal signals produces sharp transitions during faults. Comparing AD output to a threshold achieves fault detection. The AD then identifies arrival times of the incident and reflected TWs. When using TW theory to distinguish reflections from the fault point and remote end, the fault distance is calculated from their arrival time difference. Validated through 293 diverse ATP simulated fault scenarios, the approach delivered highly accurate results despite using a lower sampling rate than established methods, utilizing an exceptionally short data window—only 2.03 ms for a 300 km line. Finally, operational boundaries for the signal-to-noise ratio (SNR) in noisy conditions are established.

  • 
  İncele
• BildiriAçık Erişim2022/r/munzur/2657
  Railway Condition Monitoring and Fault Detection Based on YOLOv4

  Yilmazer, Merve; Karakose, Mehmet

  Regular maintenance of the line is critical for safety in railway transportation, which constitutes an important part of the transportation system. Due to the high error rate of manual fault detection methods, non-contact fault detection methods have been developed. Railway switch state and level crossing faults are frequently encountered in the occurrence of train accidents. A new method based on YOLOv4 has been proposed for condition monitoring and fault detection in these rail sections. The YOLOv4 deep neural network was trained using four class label datasets consisting of real railway visual data. Model evaluated using test data. Performance evaluation was made using evaluation metrics. Experimental results showed that the model could detect correctly with 96.8% accuracy.

  • 
  AtıfScopus8·OpenAlex9

  İncele