Presentation 1

Aetheris Group’s Rail Temperature Monitor, ARM‑S 3.0

Brian Ross is the Managing Director at ACR Group (ACR Projects); bringing over three decades of experience delivering complex rail and infrastructure projects and is a strong advocate for innovation and collaboration across the sector. He is passionate about practical, systems-focused solutions that improve performance, safety, and whole-of-life value for customer assets. Please join me in welcoming Brian to present the Aetheris Rail Temperature Monitor (ARM-S 3.0).

Brian will present Aetheris Group’s Rail Temperature Monitor, ARM‑S 3.0, a practical technology designed to deliver near real‑time rail temperature data through simple, tool‑free installation. The ARM‑S 3.0 enables real‑time temperature visibility, supporting informed engineering decisions, strengthening maintenance planning, and facilitating more effective discussions around track risk and performance across the industry. As rail networks face increasing operational and environmental pressures, solutions like ARM‑S 3.0 help transform live field data into safer, smarter infrastructure management outcomes.

Presentation 2

TrackDefectX

Munish Kumar is a Specialist Track Engineer at Hancock Iron Ore, specialising in heavy haul rail infrastructure and strategic asset management. His expertise includes engineering studies, condition monitoring, and risk-based asset planning. Munish effectively leads teams and ensures adherence to rail standards, providing technical assurance for lifecycle decisions on complex rail assets. He has significantly advanced maintenance and renewal strategies across the Hancock network, contributing to engineering standards that ensure safety and reliability. Munish has also played a key role in developing TrackDefectX, an innovative AI-powered monitoring initiative aimed at transforming defect management and enhancing asset performance.

TrackDefectX is a cutting-edge in-house AI platform developed by Hancock Iron Ore to enhance rail surface condition monitoring across its heavy haul rail network. It uses high-resolution TMV imagery (RSIS/TCIS) and deep learning to automatically detect and classify Rolling Contact Fatigue (RCF) defects, replacing a manual process requiring ~1,000 images per km. The presentation illustrates how TrackDefectX detects defects such as squats, spalling, and cracking at gauge corners, improving defect visibility, reducing maintenance costs, and extending rail life, while emphasising AI’s role in proactive, data-driven rail asset management.