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

An automotive MacPherson suspension unit is identified and modeled using a radial basis function network with local linear weighting functions (LOLIMOT). The output of the network represents the nonlinear force characteristic of the spring-and-damper unit in dependency of the measured spring travels at the front axle and the corresponding spring travel velocities. The network parameters are interpreted physically by comparing the five local linear models identified with the network to a physical second-order model of the wheel suspension unit. Implemented in an overall vehicle model the network or its look-up table representation represents an adaptable model of the nonlinear vehicle suspension characteristics.

Regarding the mechanical engineering area, over the last 40 years a lot of effort has been undertaken to find very exact descriptions for the dynamic behavior of road vehicles based on mathematical models. All those models include certain parameter values which may be taken from data sheets or which have to be measured or determined by real driving tests. Using these physical models for vehicle simulation purposes, the problem arises, that some of the model parameters are time-variant. They vary over a smaller or larger time period, e.g. due to aging, different vehicle loads or changing environmental conditions like a transition from dry to wet or icy road. Parameter variations lead to systematic modeling errors which makes simulation results turn out incorrect. To overcome that problem, this paper describes the use of hybrid models to reduce modeling errors. Within hybrid models, conventional mathematical process models are combined with adaptive learning structures, e.g. neural networks. In this contribution, an extended radial basis function network called LOLIMOT (local linear model tree) is used to compensate the influences of changing road conditions affecting a vehicle dynamics simulation model

Modem Adaptive Cruise Control Systems (ACC) providing additional comfort for the driver will become a common feature of series vehicles in the near future. The adjustment of their system parameters to different engine or gear types -even of the same vehicle body version is based on an extensive series of tests. To reduce these expensive tests, this contribution describes an approach to tune the controller parameters based on simulation results provided by a closed-loop simulation environment. In this case, only the controller fine-tuning which mostly has to consider comfort aspects has to be done on-board the vehicle.

In automotive technology, the behaviour of SI-combustion engines is often characterised by the dependency of the engine torque on the engine speed and the throttle angle. Especially for control and simulation purposes it is important to provide an easy possibility to extract a formal description of an engine characteristic map from data measured on an engine test stand. This paper describes a way to replace the conventionally used look-up-tables by neural network or fuzzy logic representations and to adapt them on-line to measured signals. In addition to that, a neuro-fuzzy approach is discussed as well.

As individual and commercial traffic flow on roads and highways grows enormously the number of traffic jams and accidents increases as well. Therefore, modern vehicle research is not only focused on adapting driving comfort to the growing traffic density in order to retain the advantages of individualized mobility, but also on improving passengers' safety. One way to improve safety and comfort of manually driven cars is to assist the driver by an Adaptive Distance and Cruise Control system (ACC). This paper deals with the design and implementation of a combined control structure using conventional techniques for vehicle acceleration control on the one hand and fuzzy control algorithms for vehicle velocity and intervehicle distance control on the other hand. In this application, the major advantage using a fuzzy representation is the possibility to describe the subjective comfort and safety demands of drivers by linguistic formulation.

As individual and commercial traffic flow on roads and highways grows enormously, the number of accidents increases as well. Therefore, modern vehicle research is focused on improving driving comfort as well as passengers' safety. Aiming at that, recent advances in control engineering and modern computer technology enable the engineer to design special control and supervision systems to support the driver. As an example, this contribution presents two possible solutions. An Adaptive Cruise Control system assists the driver in highway traffic, whereas a vehicle-supervision method is applied to detect critical driving situations and sensor faults.

Due to the rising consciousness of safety aspects, the supervision of vehicle's tyre pressures is a major aspect of improved active car safety. Therefore, in this paper a method for monitoring the tyre pressures is presented, using body acceleration signals. Analyzing the frequency spectrum of the virtual transfer function between the body acceleration at the front and rear wheel on one side of the vehicle, characteristic features are generated. Thereby, external interferences on the spectrum and their influences on the symptoms are discussed. To quantify the tyre pressure, a neuro-fuzzy classification of the characteristics is applied.

Providing a simple and effective way to describe the nonlinear input-output behaviour of a system, three-dimensional mappings (3-D maps) have gained a lot of importance in modern automotive technology. Applications cover a wide range from real-time control systems up to the area of vehicle simulation. Replacing the conventional look-up-tables by neural network or fuzzy logic representations offers an easy possibility to generate 3-D maps by measured data and to adapt them online using measured signals. This paper describes the modelling of engine characteristics for vehicle control and simulation purposes by multilayer perceptron and radial-basis function networks. In addition to that, a neuro-fuzzy approach is discussed as well