Thermal Alarm Handling in Safety Critical Electronic Control Units for Automated Vehicle Using AI and Machine Learning

As a rule of thumb, autonomous vehicle platforms demand for a safety stringent electronic control unit (Ex: Steering Control, Brake control). In such complex systems, monitoring the thermal behavior of the electronic sub-components is very essential. The thermal behavior of individual sub-components in electronic control unit like ICs, MOSFETs, microcontrollers can be modelled by its appropriate thermal characterization. Proper thermal characterization of the sub-components shall assure reduced thermal events. Currently, there are techniques like inter-dependent temperature monitoring between sub-components for detecting and mitigating thermal events on a sub-component within the electronic control unit as a safety mechanism. But these techniques can fail in real time if certain use-cases are not taken into consideration during the design phase of the electronic control unit. This paper focusses on enhancing the thermal characterization of the electronic control unit components especially for the inter-dependent temperature monitoring technique in the electronic control unit by considering plausible use-cases that can take place in real-time. These use-cases could be physical exposure of the electronic sub-components in redundant systems to environmental conditions like thermal shocks, moisture, water splash and real-time thermal cycles and also the placement of electronic sub-components which might be overlooked during the design phase of the electronic control unit or its complete system. Inter-dependency of the thermal behavior of the sub-electronic components shall be designed, verified, and validated considering the aforementioned use-cases in addition to the existing use-cases to make the system more robust with AI and Machine Learning. This shall ensure to avoid false triggering of thermal events warning and mitigation in the electronic control unit. It saves the warranty cost for the OEMs and also reduces the validation cost of the product. Finally, the end users are not panicked.