Your search results

611 Results Found

Enhancing railway safety in permanent way through big data analytics and artificial intelligence (AI) for smart maintenance

cape-town

The MTR Corporation is committed to constantly seeking ways to improve safety and efficiency in our railway network. Given the size of the network, there are numerous maintenance tasks that must be performed to ensure safety. However, with over 19 hours of operation each day, the maintenance window is limited. To address this challenge, MTR seeks to leverage advancements in technology to enhance maintenance efficiency, prioritize maintenance tasks, and safeguard operational safety through smart maintenance. This paper proposes an innovative approach to enhancing railway safety through the use of big data analytics and AI-powered for smart maintenance.

The paper aims to explore the potential of these technologies to improve safety in the permanent way. By leveraging big data analytics, potential defects or areas of high risk can be identified, while artificial intelligence can predict potential failures before they occur, allowing for predictive maintenance and reducing downtime. With the increasing demand for faster and more efficient services, railway companies are facing challenges in ensuring safety and reliability. One of the critical areas that need constant attention is the state of the railway infrastructure, including the track, crossing, and other components of the permanent way. To address these challenges, MTR has adopted big data analytics and artificial
intelligence (AI) to enhance railway safety. Big data analytics can provide valuable insights into the state of the railway infrastructure, enabling the identification of potential defects or areas of high risk. By analyzing massive amounts of data generated by railway operations, patterns and trends in track performance can be identified, leading to a more proactive approach to maintenance. For instance, by analyzing sensor data from trains and tracks, potential weaknesses and defects can be detected before they escalate into serious safety hazards.

In conclusion, the paper highlights the importance of embracing new technologies to enhance railway safety and efficiency. The proposed approach of using big data analytics and artificial intelligence for smart maintenance has significant potential to transform the way railway safety is managed and improve the overall performance of the railway system.

Year of Publication: 2023

Document: View

Coaching to Enhance Performance – How Successful Leaders Create Sustainability Differently

cape-town

Why use a strong observation and coaching process? In today’s high-risk rail industry, the demanding nature of the work, the fast pace, and resource constraints leads to rail workers adapting in unforeseen ways often reducing established safety margins.

Observations and the associated leadership presence in the work environment are needed to ensure high, uncompromising standards are being maintained every day. Regular observations provide management with insights into the current work culture (behaviors) while also identifying systems and processes that may need improvement.

The purpose of this presentation is to present proven methodologies that will enhance your organization’s employee engagement. Without engagement, improvement for individual and organizational performance is at considerable risk of failure. Consider that any time an organization strives to improve performance, it must ask people to change their behavior. Desired behavior is the only way a business can accomplish and sustain any new initiative. When seeking performance improvements, it’s essential to recognize that behavioral change is necessary. Effective observation and coaching present a valuable opportunity to leverage feedback, yielding immediate behavior changes that align with your organization’s safety expectations for personnel, assets, processes, and the environment. Additionally, this process fosters high-quality work, improved morale, enhanced ownership, and greater productivity when executed correctly. To facilitate effective learning, this presentation will leverage cutting-edge technology in adult learning, specifically video-based training (VBT). By harnessing the power of visual immersive learning, VBT offers a faster and more comprehensive learning experience, enabling efficient and accurate coverage of presentation material.

The presentation will conclude with actionable solutions that stakeholders can readily implement, to enhance observation and feedback in rail operations and foster a culture of safety throughout the industry.

Year of Publication: 2023

Document: View

Traction Energy Management Solutions for Energy Efficiency and Loadshedding

cape-town

Railway network has been regarded as one of the modes of transport amongst others to transport masses of people from their communities to areas of work opportunities. In South Africa it is regarded as the affordable mode of transport since it is subsidized by the government. The South African railway network is mostly operated by Transnet (Freight) as well as by PRASA which is for passenger trains. The rail network is generally operated at 750 VDC, 1 500 VDC, 3 000 VDC, 25 kV AC and 50 kV AC voltage levels
as well as with diesel in certain instances. The South African passenger rail network is operated at 3 kV DC voltage.

The railway network is one of the bulk energy users due to the high passenger capacity/demand which also determines the train frequency. Eskom is the South African grid and has been struggling to keep up with the energy demand and this has resulted to loadshedding measures being implemented which have affected a lot of energy users including railway signaling power supply.

Electricity has been increasing drastically from the utility and the energy users are paying these high tariffs which have been exponentially increasing from 2002 to date. The traction power supply is dedicated and exempted from loadshedding but the train stations and signaling power supplies are heavily affected by loadshedding. Due to the high cost of electricity and this constant loadshedding, bulk energy users are forced to come up with ways of minimizing energy cost and energy management efficiency solutions. PRASA has introduced new trains that are capable of regenerating energy for use by other accelerating trains in the same power supply region.

This paper is discussing different ways of energy management solutions in traction electricity network through load shifting, time shifting, regenerative braking as well as energy storage for later use. The excess energy is transferred to 11 kV AC and 33 kV AC for use in other sections or corridors. The results are based on simulations as well as measurements to achieve 30% energy reduction. Load is shifted from expensive substations to low-cost substations. Drivers are trained to drive efficiently using speed profiles through acceleration, cruising, coasting and regenerative braking to save energy.

Year of Publication: 2023

Document: View

The evolution of computer-based railway signalling interlocking systems

cape-town

The ever-changing demands for secure railway systems necessitate significant developments in technology within and surrounding railway operations across the globe. The most fundamental and significant component of the railway signalling system is the interlocking system. It ensures the safety of train movement. The railway signalling system has evolved through three stages: mechanical interlocking system, relay interlocking system, and computer-based interlocking system. This study presents the evolution of interlocking system and examines the future development direction of railway interlocking system based on a review of the history of railway signal development. Despite its rapid evolution, the new computer-based interlocking systems are designed and developed in line with European Committee for Electrotechnical Standardization (CENELEC) standards that meet Safety Integrity Level (SIL).

Both freight and commuter train operations require similar highly safe and always available signaling systems to control and prevent tragic events. Railways, like the mining business, prioritize safety because one incident is one too many. As a result, higher availability is continually necessary for signalling systems to operate effectively, suggesting that external environmental conditions must be consistent, and a lack of physical security may impede system performance due to theft and vandalism. Power supplies, severe weather conditions, resilient communications systems, strengthened data center facilities, and cyber-security systems are among the crucial enabling systems and critical environmental conditions.

This paper examines the level to which South African railway operators have installed and are using modernized safe computer-based interlockings, as well as whether these systems provide some aspects of safety performance in the form of fallback functionality. This paper will provide global comparison of asset life cycle management of computer-based interlocking systems. Furthermore, the influence of using a computer-based signalling system that uses cloud-based architectural technology on safety performance and physical security needs is assessed in this paper. It is critical for South African railway operators to embrace hybrid innovation technologies to ensure dependability and high availability in signalling solutions for future usage in both freight and passenger rail.

The design, development, testing and implementation of computer-based interlocking systems follows the V-model of systems engineering’s stringent systems engineering procedures of verification and validation. Integrated processes of system design, technical management, and product realization guarantee that all phases completely meet the requirements. Ultimately, cloud-based interlocking solutions are desperately needed to reduce installation costs while safeguarding assets from theft and damage.

Year of Publication: 2023

Document: View

Deep learning based breakage and cracks detection in rail track joint bars

cape-town

Railway provides a safe and comfortable way of transportation for the passengers. The reason for railway accidents can vary which includes human error, mechanical failures such as track misalignment, crack, broken rails, insufficient ballast, defective fasteners, wear and tear, natural disasters, and even acts of sabotage. Therefore, track inspection is significant to ensure the safety and efficiency of railway transportation. It helps to prevent accidents, reduces maintenance costs, ensures regulatory compliance, and enhances the reputation of railway companies. Joint bars are important component serving a crucial role in connecting two sections of rail in a railway track, maintaining the overall continuity and stability of the track system, providing stability, durability, safety and maintenance in tracks. Joint bars are vulnerable to various factors that can compromise its structural integrity thereby increase the risk of rail accidents. A deep learning approach is proposed for identifying the cracks in the joint bar from the images captured by drone footage. The proposed model utilizes five pre-trained models: VGG16 (Visual Geometry Group 16), VGG19 (Visual Geometry Group 19), Inception-V3 (Inception Version 3), DenseNet121 (Densely Connected Convolutional Network-121), and ResNet-50 (Residual Network-50). Additionally, OpenCV (Open Source Computer Vision) is employed to detect and identify cracks. By conducting a comprehensive comparison with other models, it becomes evident that VGG-19 has attained remarkably high accuracy of 90.83, thus highlighting its effectiveness and superiority.

Year of Publication: 2023

Document: View

Segmentation of overlapping ballast coverage on wooden railway sleepers using transfer learning technique

cape-town

The periodic examination of wooden sleepers in railway tracks is examined with the help of human intervention. Using instance segmentation, the wooden texture on sleepers of railway tracks is detected, labelled, and masks are created for each class object. Segmentation is a combination of object detection, classification, and object localization. Mask R-CNN architecture is used to extract wooden sleeper regions from railway track images. The Mask R-CNN architecture is state of art in bounding box detection, keypoint detection and segmentation. Custom datasets are used for training the Mask R-CNN model. The custom dataset is prepared from drone, pre-processed and labelled using Make Sense AI tool. Then the model is evaluated based on IoU (intersection over union) of COCO dataset format.

Year of Publication: 2023

Document: View