AWAndreas Wagner

Andreas Wagner

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Andreas Wagner has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Hybrid Physics-Augmented Neural Network for Dynamic System Modeling with Partially Known Dynamics

    by Laurin Ludmann, Jaeyoun Choi, Jens Neubeck, Andreas Wagner, Chuchu Fan

    This paper introduces Hybrid Physics-Augmented Neural Network (HyPA-Net), a hybrid modeling framework that integrates physics-based linear time-invariant models with artificial neural networks (ANNs) to address dynamic system modeling when only partial physical knowledge is available. The approach leverages the interpretability and robustness of established physical models while using ANNs—such as long short-term memory architectures—to capture unknown or nonlinear system behaviors. The methodology normalizes state and input variables for compatibility with ANN training and expands traditional recursive state-space equations for efficient backpropagation over sequences. Vehicle dynamics, specifically using a rear-wheel steering test case, validate the proposed framework. Various HyPA-Net configurations are benchmarked against pure physics-based and pure data-driven models, demonstrating improved prediction accuracy and model flexibility. The experimental results in this application confirm that hybrid models yield superior performance over strict physical approaches and can implicitly approximate submodel dynamics within a unified, yet modular, architecture, opening avenues for applications in domains where partial physics-based knowledge is available but insufficient on its own.

  • Open Access

    A Hybrid Physics-Augmented Neural Network for Dynamic System Modeling with Partially Known Dynamics

    by Laurin Ludmann, Jaeyoun Choi, Jens Neubeck, Andreas Wagner, Chuchu Fan

    This paper introduces Hybrid Physics-Augmented Neural Network (HyPA-Net), a hybrid modeling framework that integrates physics-based linear time-invariant models with artificial neural networks (ANNs) to address dynamic system modeling when only partial physical knowledge is available. The approach leverages the interpretability and robustness of established physical models while using ANNs — such as Long Short-Term Memory architectures—to capture unknown or nonlinear system behaviors. The methodology normalizes state and input variables for compatibility with ANN training, and expands traditional recursive state-space equations for efficient backpropagation over sequences. Vehicle dynamics, specifically using a rear wheel steering test case, validate the proposed framework. Various HyPA-Net configurations are benchmarked against pure physics-based and pure data-driven models, demonstrating improved prediction accuracy and model flexibility. The experimental results confirm that hybrid models yield superior performance over strict physical approaches and can implicitly learn submodel dynamics within a unified, yet modular architecture, opening avenues for applications in domains where partial physics-based knowledge is available but insufficient on its own.

  • Influence of Tire Deformation on the Vehicle Aerodynamics

    by Johannes Burgbacher, Timo Kuthada, Felix Wittmeier, Andreas Wagner

  • Potentials in the dimensioning of brake components in BEVs

    by Matej Udovicic, Sebastian Kirch, Jens Neubeck, Andreas Wagner


  • Development of a tire sensor to determine the contact patch while driving

    by Victor Mappes, Johannes Burgbacher, Werner Krantz, Jens Neubeck, Andreas Wagner

  • Real-Driving Residual-Drag-Torque of Disc Brakes

    by Philipp Huchtkötter, Jens Neubeck, Andreas Wagner, Christian Wittke


  • Analysis of Brake-Drag in Disc Brakes on Vehicle-Level

    by Philipp Huchtkoetter, Jens Neubeck, Andreas Wagner


  • Open Access

    Influence of Lithium-Ion-Battery Equivalent Circuit Model Parameter Dependencies and Architectures on the Predicted Heat Generation in Real-Life Drive Cycles

    by Marcus Auch, Timo Kuthada, Sascha Giese, Andreas Wagner

    This study investigates the influence of the considered Electric Equivalent Circuit Model (ECM) parameter dependencies and architectures on the predicted heat generation rate by using the Bernardi equation. For this purpose, the whole workflow, from the cell characterization tests to the cell parameter identification and finally validation studies, is examined on a cylindrical 5 Ah LG217000 Lithium-Ion-Battery (LIB) with a nickel manganese cobalt chemistry. Additionally, different test procedures are compared with respect to their result quality. For the parameter identification, a Matlab tool is developed enabling the user to generate all necessary ECMs in one run. The accuracy of the developed ECMs is evaluated by comparing voltage prediction of the experimental and simulation results for the highly dynamic World harmonized Light vehicle Test Cycle (WLTC) at different states of charges (SOCs) and ambient temperatures. The results show that parameter dependencies such as hysteresis and current are neglectable, if only the voltage results are compared. Considering the heat generation prediction, however, the neglection can result in mispredictions of up to 9% (current) or 22% (hysteresis) and hence should not be neglected. Concluding the voltage and heat generation results, this study recommends using a Dual Polarization (DP) or Thevenin ECM considering all parameter dependencies except for the charge/discharge current dependency for thermal modeling of LIBs.


  • Open Access

    Experimental and Numerical Investigation of the Aerodynamic Ventilation Drag of Heavy-Duty Vehicle Wheels

    by Carlos Peiró Frasquet, Daniel Stoll, Timo Kuthada, Andreas Wagner

    Due to current EU regulations, constant-speed testing on test tracks is used for aerodynamic certification of heavy-duty vehicles (HDV). However, the aerodynamic development of HDVs is performed using wind tunnels and computational fluid dynamics (CFD). Both techniques commonly neglect the rotational aerodynamic losses of the wheels—the so-called ventilation drag—that are present when driving on the road. This is due to the fact that there is no full-scale wind tunnel for this type of vehicle with a suitable belt system for the simulation of the wheel rotation. Furthermore, the ventilation drag of HDV wheels has been neglected in CFD due to their almost completely closed rim design. These constraints lead to an underprediction of the aerodynamic forces in comparison to the results under on-road conditions when performing constant-speed tests. In order to investigate the ventilation drag of HDV wheels, measurements were carried out on a 1:4.5 scale generic tractor-trailer model in the Model Scale Wind Tunnel of the University of Stuttgart. The measured aerodynamic forces as well as the measured flow field data provide the basis for the definition and validation of a procedure for analyzing the ventilation drag in CFD. Accordingly, the ventilation drag of a full scale HDV was investigated in CFD. The results show that the tire treading and rim geometry have a significant influence on ventilation drag that contributes to the total aerodynamic drag of the HDV. The present work shows that the ventilation drag has a relevant impact on the total aerodynamic drag of HDVs and should therefore not be neglected. The presented CFD approach thus allows to assess the aerodynamic drag under real on-road conditions in an early stage of the vehicle development.


  • Open Access

    Thermal Management System of the UNICARagil Vehicles—A Comprehensive Overview

    by Daniel Gehringer, Timo Kuthada, Andreas Wagner

    The collaboration project UNICARagil aiming to develop new autonomous battery electric vehicle concepts has progressed and the four vehicle prototypes have been built up. All seven universities and six industrial partners have worked towards this milestone. At the time of writing the four vehicles are operational and can be driven by a safety driver using a sidestick. The automated driving functions are being applied on the test track and first demonstrations are carried out. This paper gives an overview of the results, which have been achieved within the work package of the thermal onboard network. The thermal management system including the heating, ventilation and air conditioning system and its development process is explained in detail. Furthermore, climate chamber measurements with prototype hardware of a sensor data processing computer and the integration of the air conditioning control unit into the vehicle’s automotive service-oriented architecture framework are described. A coupled simulation approach to predict occupant thermal comfort in one vehicle variant is presented. Simulation results using environmental conditions typical for a European summer show a comfortable environment for all six occupants. In addition, the simulation and development process of a thermoelectric heat pump is shown. First measurement results with the heat pump on a test bench are highlighted which show an achievable coefficient of performance greater than two.