Fuel Cell Fault Simulation and Detection for on Board Diagnostics Using Real-Time Digital Twins

<div class="section abstract"><div class="htmlview paragraph">The modern automotive industry is facing challenges of ever-increasing complexity in the electrified powertrain era. On-board diagnostic (OBD) systems must be thoroughly calibrated and validated through many iterations to function effectively and meet the regulation standards. Their development and design process are more complex when prototype hardware is not available and therefore virtual testing is a prominent solution, including Model-in-the-loop (MIL), Software-in-the-loop (SIL) and Hardware-in-the-loop (HIL) simulations. Virtual prototype testing relying on real-time simulation models is necessary to design and test new era’s OBD systems quickly and in scale. The new fuel cell powertrain involves new and previously unexplored fail modes. To make the system robust, simulations are required to be carried out to identify different fails. Thus, it is imminent to build simulation models which can reliably reproduce failures of components like the compressor, recirculation pump, humidifier, or cooling systems. This paper shows the development of high-fidelity fuel cell model which is used as digital twin to reproduce relevant failure modes. As the OBD regulations become more stringent and advanced, it is difficult to keep pace with it and perform comprehensive testing in real world environment. In such scenarios, MIL, SIL and HIL testing becomes more prevalent. MIL and SIL testing provide a quick way for controls engineers to develop new strategies at system level to adhere to new OBD regulations. On the other hand, simulating high fidelity physics based Real Time plant model on HIL systems, allows the engineers to perform fault insertions tests on the software and leave the lab environment with a certain degree of guarantee that the software would fare well in real world conditions. The model used can reproduce failure modes consistently while staying in real time which in turn can be detected by controls and can take action promptly. The viability of this approach is demonstrated by showing MIL and HIL test results.</div></div>