This work aims at improving the energy consumption forecast of electric vehicles by enhancing the prediction with a notion of uncertainty. The algorithm itself learns from driver and traffic data in a training set to generate accurate, driver-individual energy consumption forecasts.

In this work, an extension of the federated averaging algorithm, FedAvg-Gaussian, is applied to train probabilistic neural networks. The performance advantage of probabilistic prediction models is demonstrated and it is shown that federated learning can improve driving range prediction. Using probabilistic predictions, routing and charge planning based on destination attainability can be applied. Furthermore, it is shown that probabilistic predictions lead to reduced travel time.

This work describes a method for weighted least squares approximation of an unbounded number of data points using a B-spline function. The method can shift the bounded B-spline function definition range during run-time. The approximation method is used for optimizing velocity trajectories for an electric vehicle with respect to travel time, comfort and energy consumption. The trajectory optimization method is extended to a driver assistance system for automated vehicle longitudinal control.

With the further development of automated driving, the functional performance increases resulting in the need for new and comprehensive testing concepts. This doctoral work aims to enable the transition from quantitative mileage to qualitative test coverage by aggregating the results of both knowledge-based and data-driven test platforms. The validity of the test domain can be extended cost-effectively throughout the software development process to achieve meaningful test termination criteria.

Sheet Molding Compounds (SMC) are discontinuous fiber reinforced composites that are widely applied due to their ability to realize composite parts with long fibers at low cost. A novel Direct Bundle Simulation (DBS) method is proposed in this work to enable a direct simulation at component scale utilizing the observation that fiber bundles often remain in a bundled configuration during SMC compression molding.

This work presents novel simulation techniques for injection molding of fiber reinforced polymers. These include approaches for anisotropic flow modeling, hydrodynamic forces from fluid on fibers, contact forces between fibers, a novel fiber breakage modeling approach and anisotropic warpage analysis. Due to the coupling of fiber breakage and anisotropic flow modeling, the fiber breakage directly influences the modeled cavity pressure, which is validated with experimental data.

Infrastructure construction is society's cornerstone and economics' catalyst. Therefore, improving mobile machinery's efficiency and reducing their cost of use have enormous economic benefits in the vast and growing construction market. In this thesis, I envision a novel concept smart working site to increase productivity through fleet management from multiple aspects and with Artificial Intelligence (AI) and Internet of Things (IoT).