Tiny AI model could strengthen real-time fault diagnosis for high-speed train bogies
Peer-Reviewed Publication
Updates every hour. Last Updated: 9-Jun-2026 10:15 ET (9-Jun-2026 14:15 GMT/UTC)
Researchers have developed a lightweight fault-diagnosis framework for high-speed train bogies that is specifically designed for edge computing while still maintaining strong cross-domain diagnostic performance. The study addresses a practical obstacle in railway intelligence: how to deploy deep learning close to real operating equipment, where memory and computing power are limited, without losing the ability to diagnose faults accurately under changing working conditions.
Mass General Brigham researchers studied 21 widely used AI chatbots and found they can identify the correct diagnosis over 90% of the time when given complete patient information, but struggle with the step-by-step clinical reasoning doctors use, missing appropriate differential diagnoses in more than 80% of cases. The findings highlight a significant gap between AI accuracy and real-world medical decision-making.
Scientists report that a living reef coastal defense system can reduce wave power significantly, suggesting the approach could offer a new way to protect shorelines from storms and rising seas.
Their findings, published in the Proceedings of the National Academy of Sciences by an international team that included nine Rutgers University researchers, provide one of the most detailed tests to date of whether a hybrid reef system combining living organisms with artificial structures can function as coastal protection infrastructure.
Artificial intelligence could soon allow powerful companies to charge each customer a different price for the same product, based on what they think each individual is willing to pay.