Singapore's SMRT is advancing AI‑enabled rail maintenance through a pilot project with Oracle Cloud Infrastructure Enterprise AI and Oracle Autonomous AI Database.
The collaboration centres on JARVIS, SMRT’s intelligent data‑and‑maintenance platform, to improve predictive insights, fault resolution and service reliability across its rail network, which supports over two million passenger journeys each day.
AI‑driven, data‑centric maintenance
JARVIS was developed by STRIDES Technologies, SMRT’s engineering and innovation arm, to unify data scattered across multiple standalone systems into a single source of truth. The platform uses machine learning and a generative AI chatbot interface to help maintenance teams perform faster, more accurate diagnostics and proactive interventions.
Oracle’s Autonomous AI Database consolidates and analyses condition‑monitoring and asset lifecycle data, from sensor readings and train performance to maintenance history, enabling predictive fault detection and targeted interventions.
The platform’s natural‑language interface allows engineers to query historical and real‑time data in plain language, shortening diagnosis time and reducing reliance on manual, ad‑hoc analysis.
This “intelligent data layer” is designed to bridge cutting‑edge AI with safety‑critical operations, so that AI‑driven recommendations support, rather than replace, human‑led decision‑making on the rail network.
Oracle’s AI and cloud backbone
Oracle’s AI Customer Excellence Centre in Singapore supported the development, testing and validation of JARVIS, using Oracle Cloud Infrastructure Enterprise AI and Oracle Autonomous AI Database as the core stack.
The Autonomous AI Database acts both as a transactional store and as an analytics and AI platform, with built‑in vector search and generative AI capabilities that allow SMRT to run large‑language‑model‑powered insights alongside engineered maintenance logic.
OCI Enterprise AI and vector search underpin conversational AI interfaces that feed operational staff context‑rich, data‑driven guidance during live incidents.
“SMRT is committed to providing a safe, efficient, and high‑performing railway network. We will leverage technology— including AI—to improve our safety, operations and reliability,” said Ngien Hoon Ping, group chief executive officer of SMRT.
“With JARVIS, we have a platform that makes intelligent use of SMRT’s data, STRIDES Technologies’ domain expertise and Oracle’s industry‑leading AI and cloud database capabilities. This aligns with our Kaizen philosophy of continuous improvement while remaining human‑centric and uplifting our people’s skills and capabilities.” Ngien Hoon Ping
Human‑centric AI in transport
Chin Ying Loong, senior vice president and regional managing director, ASEAN & SAGE, Oracle, commented that rail operators depend on timely, accurate data to keep services running safely, reliably, and on schedule for millions of commuters each day.
"Running on OCI, JARVIS demonstrates how Oracle can help bring AI to where enterprise data resides to improve efficiency and operational responsiveness. The collaboration with SMRT helps create new possibilities for rail operators worldwide to deliver more consistent and dependable services for commuters.” Chin Ying Loong
For the IoT and smart‑infrastructure community, SMRT’s pilot demonstrates how AI‑driven predictive maintenance, anchored in a cloud‑native data platform, can modernise complex, high‑volume transit networks without compromising safety or service continuity.
