Method And System For Creating Digital Twin Of A Sensor For A Vehicle In Real Time

Modern Vehicles have many sensors equipped with them to give an idea to the control systems of the vehicles related to what is happening in and around the vehicle. These sensors are very costly and they are critical in controlling the vehicle as well as emissions. There are different types of sensors used in a vehicle, which can detect different types of physical parameters such as temperature, pressure, range, speed etc. These readings play an important role in a vehicle as their readings are used to take critical decisions involved in keeping the vehicle running. If certain sensors fail, it can lead to the vehicle being stopped mid operation or increased emission levels. Hence, it is imperative that the sensors have a reliable fail-safe mechanism so that above mentioned problems can be prevented in order to provide a better customer experience. For some of the sensors the mechanism for diagnosing and handling the failure is a legislative requirement itself. However, the existing failsafe mechanisms for sensors such as limp home, empirical maps, mathematical models etc. have their own drawbacks. Most of the fail-safe mechanisms are not accurate, in those cases depending on its criticality for vehicle operation and the emission damage that failure can do, the driver is advised to visit the nearest service station. Some of the accurate failsafe mechanisms are resource intensive and serve no use for a new variant of the vehicle. This paper highlights a method, which overcomes the above-mentioned drawbacks. This paper deals with a method, which involves creation of a digital twin of a sensor in the vehicle. In order to achieve that an AI model has to be trained in the control unit of the vehicle in real time. However, training a model in the control unit in real time will not work in all scenarios; this paper provides a mathematical solution on how to practically create a digital twin in all kind of scenarios.