The placement of temperature sensitive and safety-critical components is crucial in the automotive industry. It is therefore inevitable, even at the design stage of new vehicles that these components are assessed for potential safety issues. However, with increasing number of design proposals, risk assessment quickly becomes expensive. We therefore present a parameterized surrogate model for the prediction of three-dimensional flow fields in aerothermal vehicle simulations. The proposed physics-informed neural network (PINN) design is aimed at learning families of flow solutions according to a geometric variation. In scope of this work, we could show that our nondimensional, multivariate scheme can be efficiently trained to predict the velocity and pressure distribution for different design scenarios and geometric scales. The proposed algorithm is based on a parametric minibatch training which enables the utilization of large datasets necessary for the three-dimensional flow modeling. Further, we introduce a continuous resampling algorithm that allows to operate on one static dataset. Every feature of our methodology is tested individually and verified against conventional CFD simulations. Finally, we apply our proposed method in context of an exemplary real-world automotive application.
Using Vehicle Thermal Management (VTM) simulations to predict the thermal load experienced by components is a popular method within the automotive industry. The VTM simulation approach is fast becoming equivalent to conducting thermal load tests with prototypes for vehicles powered by internal combustion engines. This is especially true in the early development phase of the vehicle. The accuracy of the VTM simulations plays a pivotal role at them being accepted as an eventual replacement for physical testing. The correct prediction of thermal loads in VTM simulations depends on a multitude of different parameters, but the modelling of the exhaust system plays a central role in it. This is because the exhaust gas, and with it the exhaust system, is the primary source of heat in a vehicle powered by an internal combustion engine. The developed approach not only needs to be accurate but also modular enough to allow for different exhaust configurations to be tested. It also needs to be capable of integration into any VTM simulation workflow while maintaining an industrially acceptable turnaround time. This paper explores a new methodology to achieve these requirements. A 1D/3D hybrid approach to exhaust system modelling is presented. In this, the components that have an enthalpy change of the exhaust gas, such as the turbocharger, have been modelled as 1D and simple components such as pipes have been modelled in 3D. This has the advantage of combining the speed of 1D simulations with the spatial accuracy of 3D simulations. The method uses a unique three-code co-simulation technique for full vehicle VTM simulations. The coupling is between a 3D CFD software, a 1D simulation tool, and a Finite Element based thermal solver. The methodology was validated against experimental data for multiple loadcases. The results show good agreement with experiment within acceptable tolerances.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.