Search Results

The adequate dimensioning of drive train components such as gearbox, clutch and driveshaft presents a major technical task. The one of manual transmissions represents a special significance due to the customer’s ability of inducing high force, torque and thermic energy into the powertrain through direct mechanical interconnection of gearstick, clutch pedal and gearbox. Out of this, the question about how to capture behavior and strain of the components during real operation, as well as their objective evaluation evolves. Furthermore, the gained insights must be considered for designing and development. As a basis for the examination, measuring data from imposing driving tests are adduced. Therefore, a trial study has been conducted, using a representative circular course in the metropolitan area of Stuttgart, showing the average German car traffic. The more than 40 chosen drivers constitute the average driver in Germany with respect to age, gender and annual mileage.

Predictive physical modeling is an established method used in the development process for automotive components and systems. While accurate predictions can be issued after tuning model parameters, long computation times are expected depending on the complexity of the model. As requirements for components and systems continuously increase, new optimization approaches are constantly being applied to solve multidimensional objectives and resulting conflicts optimally. Some of those approaches are deemed not feasible, as the computational times for required single predictions using conventional simulation models are too high. To address this issue it is proposed to use data-driven model such as neural networks. Previous efforts have failed due to sparse data sets and resulting poor predictive ability. This paper introduces an AI Toolchain used for data-driven modeling of combustion engine components. Two methods for generating scalable and fully variable datasets will be shown.

Automotive vehicles operate in complex, transient aerodynamic conditions that can potentially influence their operational efficiency, performance and safety. A moving-model facility combined with a wind-tunnel is an experimental methodology that can be utilized to model some of these transient aerodynamic conditions. This experimental methodology is an alternative to wind-tunnel experiments with additional crosswind generators or actively yawing models, and has the added benefit of modelling the correct relative motion between the vehicle and the ground/infrastructure. Experiments using a VW Golf 7 were performed with a 1:10 scale model at the moving-model facility at DLR, Göttingen and a full-scale, operational vehicle at the BMW Ascheim side-wind facility.

Whether as an optimization problem or a development tool, neural networks help engineers to work more efficiently. This paper’s central aspect is to add metadata to the core files of the project simulation data. To understand the project and its simulation models, a pre-processing methodology and convolutional neural network architecture are presented. With the added labels, it is possible to access the content of the model files of an engine performance simulation tool without examining them. At first, a pre-processing approach and its design are introduced to extract and filter the desired data from the XML data structure. Then, the data is split into sequences and paired with labels. Expert knowledge is used to label the models. These labels are further paired with the extracted sequences.

High-efficient simulations are mandatory to manage the ever-increasing complexity of automotive powertrain system and reduce development time and costs. Integrating AI methods into the development process provides an ideal solution thanks to massive increase in computational power. Based on an 1D physical engine model of a turbo-charged direct injection gasoline engine with variable valve timing (VVT), a high-performance hybrid simulation model has been developed for increasing computing performance. The newly developed model is made of a physics-based low-pressure part including intake and exhaust peripheries and a neural-network-based high-pressure part for combustion chamber calculations. For the training and validation of the combustion chamber neural networks, a data set with 10.5 million operating points was generated in a short time thanks to the parallelizable combustion chamber simulations in stand-alone mode.

Driving simulators allow the testing of driving functions, vehicle models and acceptance assessment at an early stage. For a real driving experience, it's necessary that all immersions are depicted as realistically as possible. When driving manually, the perceived haptic steering wheel torque plays a key role in conveying a realistic steering feel. To ensure this, complex multi-body systems are used with numerous of parameters that are difficult to identify. Therefore, this study shows a method how to generate a realistic steering feel with a nonlinear open-loop model which only contains significant parameters, particularly the friction of the steering gear. This is suitable for the steering feel in the most driving on-center area. Measurements from test benches and real test drives with an Electric Power Steering (EPS) were used for the Identification and Validation of the model.