The future of mobility is centered around software-driven vehicles that are always connected. With advancements in technology, vehicles are becoming more sophisticated and high-performing, but with this comes new challenges.
Automotive electronic systems have become incredibly complex, with software in modern cars containing more lines of code than software for a commercial aircraft. This complexity is only increasing with the integration of autonomous driving and electrification. To simplify this, automakers are consolidating electronics into domain controllers.
Ensuring reliable implementation of these advanced technologies is crucial, as fleet managers need to guarantee the availability and seamless experience of these always-on systems. However, current monitoring and diagnostic practices fall short in meeting these requirements.
This is where Predictive and Preventive Maintenance (PPM) comes in, by utilizing machine learning algorithms to extract and analyze data from within System-on-Chips (SoCs). This approach gives manufacturers deeper insight into Electronic Control Unit (ECU) health, allows for performance degradation monitoring, and predicts Time to Failure (TTF).
With this data, PPM practices can be improved to meet the high safety and reliability standards of today’s software-driven vehicles, while also reducing maintenance costs. Over-the-Air (OTA) technology and advanced device health monitoring capabilities are used to collect vehicle data and apply software updates to a pre-defined fleet subset.