부산대학교 도서관

Globalization and growing new markets force the car manufacturers to work faster and more efficient in developing new safety and comfort features for their vehicles. Hence, time-consuming expensive testing is more and more replaced by computer simulations. Normally, these simulations are based on complex physical models describing the dynamic behavior of the vehicle and its components. Sometimes, physical modeling of the nonlinear behavior of certain vehicle components can be very difficult. In these cases, neural networks may be used to model the systems' nonlinearities. The paper discusses the advantages of combining physical modeling with neural networks for a semi-physical process model. The vertical vehicle dynamics are used as example.