Research Article
Wear Analysis of Freight Train Within Different Curve Parameters
Mazuri Erasto Lutema*
,
Tindiwensi Edison
Issue:
Volume 10, Issue 1, March 2025
Pages:
1-8
Received:
28 April 2025
Accepted:
14 May 2025
Published:
25 June 2025
Abstract: Wheel profile optimization has improved the performance between the wheel tread and rail on freight railways, which are primarily made up of tangent tracks and large curved tracks. However, it is impossible to overlook the flange wear brought on by the sharp curves that run along the tracks and toward the yards. This paper aims at analyzing how different parameters like curve radius, superelevation and curving speed after a given distance of operation, such as 20000 km influence wear along the curve during operation. A multifaceted research approach combining modeling and data analysis techniques was required to fully understand freight wheel wear in curves. Mathematical models estimated stresses and wear rate based on curve geometry, speed, and loading conditions. Simulations examined complex interactions between influential factors. The results show that when the above distance is run under different curve radius creep, the wear volume increases from 6.8 mm to 3.7 mm as the radius increases from 600 to 1200 m, especially on the outside wheels. Wear increased from 6.6 to 7.8 mm as the speed increased from 40 to 100 km/hr. after a distance of 20000 km. Increasing the superelevation from 80 to 140 mm reduced wear due to improved curves from 7.1 to 6.7 mm after 20.00 km, and a significant decrease in wear volume from 8.9 to 2.3 mm outside wheels after a 20.00 km operational distance.
Abstract: Wheel profile optimization has improved the performance between the wheel tread and rail on freight railways, which are primarily made up of tangent tracks and large curved tracks. However, it is impossible to overlook the flange wear brought on by the sharp curves that run along the tracks and toward the yards. This paper aims at analyzing how dif...
Show More
Research Article
U-Paint: Image Inpainting and Object Detection via Partial Convolutions
Rahul Singh*,
Martin Bruder,
Akshay Kumar,
Rohan Joshi
Issue:
Volume 10, Issue 1, March 2025
Pages:
9-19
Received:
18 February 2025
Accepted:
6 March 2025
Published:
13 September 2025
DOI:
10.11648/j.ijimse.20251001.12
Downloads:
Views:
Abstract: Image inpainting and object detection are two well-established research areas with significant real-world applications in computer vision, digital forensics, media editing, and augmented reality. Image inpainting is a technique used to restore missing, distorted, or removed sections of an image, often to recreate its original appearance. It can also be applied to remove objects from an image while reconstructing the background in a visually coherent manner. Traditional inpainting methods relied on manual editing or simple interpolation techniques, whereas modern deep learning-based approaches utilize convolutional neural networks (CNNs) and generative adversarial networks (GANs) to achieve realistic results. Object detection, on the other hand, involves identifying and localizing specific objects, such as people, buildings, or vehicles, within digital images and videos. This paper presents a system that integrates object detection with image inpainting to automate object removal and image restoration. By detecting an object and applying advanced inpainting techniques, the system seamlessly reconstructs the image without noticeable artifacts. The proposed approach has broad applications in image editing, surveillance, content moderation, and privacy protection, providing an effective and automated solution for object removal and background restoration.
Abstract: Image inpainting and object detection are two well-established research areas with significant real-world applications in computer vision, digital forensics, media editing, and augmented reality. Image inpainting is a technique used to restore missing, distorted, or removed sections of an image, often to recreate its original appearance. It can als...
Show More
