Keeping trains humming along safely and smoothly across Singapore’s rail network is a monumental task, especially when engineers have only a three-hour window each night to fix track faults. Now, rail operator SMRT has a new artificial intelligence (AI)-powered tool to help: Jarvis.
Playfully dubbed “Just Another Really Intelligent System” by SMRT staff, the intelligent analytics platform was developed by Strides Technologies – SMRT’s engineering and tech innovation arm – together with tech giant Oracle. Announced at the Oracle AI World Tour Singapore on 14 April 2026, the platform leverages Oracle Cloud Infrastructure (OCI) Enterprise AI and the Oracle Autonomous AI Database to consolidate more than 30 years of operational, engineering and failure pattern data.
This vast trove of data, previously distributed across multiple systems in the form of text, graphs and flowcharts, is now accessible to maintenance teams through a generative AI (GenAI) chatbot interface powered by large language models (LLMs) and vector search to help them make better-informed decisions. The result is a system capable of supporting predictive maintenance using machine learning algorithms, enabling faster fault resolution and contributing to SMRT’s mean kilometres between failure (MKBF) metric, an industry-standard used to measure rail service reliability. In Singapore, the Land Transport Authority sets a strict MKBF target of one million train-kilometres, a benchmark that public transport operators must consistently meet to ensure minimal commuter disruption.
During a discussion with Chin Ying Loong, Oracle’s senior vice-president and regional managing director for ASEAN and South Asia growing economies, SMRT group CEO Ngien Hoon Ping said one of Jarvis’s biggest benefits is its ability to convert textual and graphical information into precise geolocation data. “Suppose you are aware of certain faults that have been occurring. Now you need to translate that to exactly which point machine on the permanent way is acting up,” he said, referring to the mechanical devices used to control and switch railway tracks.
Instead of technicians searching across hundreds of kilometres of track to find the faulty equipment, Jarvis allows them to pinpoint the exact location. “They go directly to the point machine that same night window and deal with it,” Ngien said. “It achieves better effectiveness, high productivity and cost-savings.”
Despite the growing use of AI, Ngien stressed that the technology is meant to improve the effectiveness of SMRT’s workforce of more than 10,000 people, not replace them. “SMRT is still hiring, even in the face of this AI world. We still need engineers,” he said. “To us, AI is really about enabling the organisation to uplift our people.”
Jarvis is currently in its first phase of deployment, with more than 50 SMRT engineers actively participating in the process. Some are analysing existing data, while others are involved in coding AI agents. Ngien noted that managing a complex locomotive network, from signalling and power systems to railway tracks, requires a Kaizen culture of continuous improvement. “It’s a very challenging task, even for the engineers among us. But we have this culture to keep improving and make use of the tools available,” he said.
Chin added: “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.”
Moving forward, Ngien said SMRT hopes to share its experience with other rail operators facing similar challenges. “They also have a trove of data, so through the models we’ve developed with [Oracle], we would be happy to share with other operators,” he said.
The introduction of Jarvis is part of a broader trend in the global rail industry towards predictive maintenance driven by AI. Operators in countries like Japan, Germany, and the United Kingdom are increasingly adopting machine learning to forecast equipment failures before they cause service disruptions. For example, East Japan Railway Company uses AI to analyse vibration data from train axles, while Deutsche Bahn employs predictive analytics for its signalling infrastructure. SMRT’s initiative stands out for its integration of generative AI and vector search, which allows engineers to query decades of unstructured data in natural language — significantly reducing the time needed to diagnose issues.
SMRT operates one of the densest urban rail networks in the world, carrying over three million passengers daily across six lines. The pressure to maintain high reliability is immense, as even minor delays can cascade across the system. The three-hour nightly maintenance window, known as the “engineering hours,” is the only time when tracks are de-energised and accessible for repairs. Traditionally, engineers rely on paper reports, spreadsheets, and prior experience to locate faults. Jarvis changes this by providing a unified, AI-driven interface that instantly identifies the exact location and likely cause of a problem.
The underlying technology stack includes Oracle’s Autonomous AI Database, which automates data tuning and security, and OCI’s Enterprise AI services that deliver pre-trained models for natural language processing and anomaly detection. The vector search capability enables the system to understand semantic relationships in data — for instance, linking a recorded “signal failure” with a specific “point machine” based on contextual patterns from years of maintenance logs. This level of intelligence is critical given that SMRT’s data spans multiple formats, from PDF inspection reports to sensor readings and SCADA system logs.
Beyond immediate fault detection, Jarvis also enables predictive analytics by detecting subtle trends in equipment wear. For example, if a point machine gradually consumes more electrical current over several weeks, the system can flag it for proactive replacement during the next maintenance window, preventing a potential failure. This approach aligns with the industry’s shift from reactive to condition-based maintenance, reducing both costs and passenger inconvenience.
The development of Jarvis reflects SMRT’s long-term investment in digital transformation. In recent years, the operator has deployed Internet of Things (IoT) sensors across its network to monitor track geometry, switch positions, and train performance. Jarvis acts as the analytical brain that processes this sensor data and correlates it with historical records. Engineers can now receive alerts on their mobile devices, complete with geospatial maps and recommended actions.
Ngien emphasised that the platform is designed to complement human expertise rather than replace it. The AI handles data-intensive tasks, while engineers focus on complex troubleshooting and innovation. This human-AI collaboration is crucial in an environment where safety is paramount — the system can suggest probable causes, but final decisions always rest with trained staff. Oracle’s Chin noted that many enterprises struggle with data silos and legacy systems, making it difficult to deploy AI at scale. Jarvis demonstrates how a phased approach, starting with a specific use case like fault localisation, can deliver tangible results while building organisational trust in AI.
Looking ahead, SMRT plans to expand Jarvis’s capabilities to cover more asset types, such as signalling systems and overhead catenary lines. The operator is also exploring the use of computer vision AI to analyse CCTV footage for detecting track obstructions or vandalism. By sharing its models with other rail operators, SMRT aims to create a community of practice that accelerates AI adoption across the region. This open-sharing model could help smaller transit agencies leapfrog traditional development cycles, benefiting from SMRT’s 30 years of accumulated data and the machine learning models built on top of it.
The rail industry worldwide faces common challenges: aging infrastructure, increasing passenger demand, and pressure to reduce costs. AI-powered platforms like Jarvis offer a path to more resilient and efficient operations. For Singapore, where land constraints limit network expansion, maximising the capacity and reliability of existing lines is a strategic priority. Jarvis is not just a tool for maintenance — it is a cornerstone of SMRT’s vision for a self-healing railway, where AI continuously monitors, predicts, and initiates corrective actions with minimal human intervention. As the platform matures, it will likely become an integral part of daily operations, ensuring that commuters experience fewer delays and smoother journeys.
Source: ComputerWeekly.com News