TY - GEN A1 - Rui, Xue A1 - Bestle, Dieter T1 - Reduced Multibody System Transfer Matrix Method Using Decoupled Hinge Equations T2 - International journal of mechanical system dynamics : IJMSD Y1 - 2021 U6 - https://doi.org/10.1002/msd2.12026 SN - 2767-1402 VL - 1 IS - 2 SP - 182 EP - 193 ER - TY - GEN A1 - Zhou, Qinbo A1 - Fehr, Jörg A1 - Bestle, Dieter A1 - Rui, Xiaoting T1 - Simulation of Elastic Body Dynamics with Large Motion Using Transfer Matrix Method T2 - Multibody System Dynamics Y1 - 2022 U6 - https://doi.org/10.1007/s11044-022-09869-2 SN - 1573-272X SN - 1384-5640 VL - 59 (2023) IS - 3 SP - 269 EP - 292 ER - TY - GEN A1 - Bestle, Dieter A1 - Bielitz, Timo T1 - Real‐time models for systems with costly or unknown dynamics T2 - Special Issue: 94th Annual Meeting of the International Association of Applied Mathematics and Mechanics (GAMM) N2 - Many applications require real‐time simulation where the computer model can be executed at least as fast as the underlying physical system. However, as the complexity of models grows, for example, in case of flexible multibody dynamics accounting for body elasticity, this becomes harder even with high‐end computers and parallel computing. Further the modeling itself could be too cumbersome to come up with causal models, especially in industrial applications, or modeling is inhibited by unknown physical effects. In such cases, data‐based modeling with AI‐strategies may be an alternative to come up with real‐time capable simulation models. Based on measured or costly simulated trajectories, state function values of the dynamic system are first identified from divided differences of subsequent states, and then used for training a feedforward neural network. This can then be used as an approximate surrogate for further simulations or as part of a real‐time application. Applications to the Duffing equation and a closed‐loop mechanism demonstrate high conformity of predicted and directly simulated trajectories reproducing even the bifurcation behavior of the Duffing equation. Y1 - 2024 U6 - https://doi.org/10.1002/pamm.202400008 SN - 1617-7061 VL - 24 IS - 2 ER - TY - GEN A1 - Niehoff, Malte A1 - Bestle, Dieter A1 - Kupijai, Philipp T1 - Model-based design optimization taking into account design viability via classification T2 - Engineering Modelling, Analysis and Simulation : the NAFEMS Journal Y1 - 2024 U6 - https://doi.org/10.59972/c7b5hzx7 SN - 3005-9763 VL - 1 IS - 1 SP - 1 EP - 12 PB - NAFEMS Ltd. CY - Knutsford ER - TY - GEN A1 - Mammen, Manasa Mariam A1 - Kayatas, Zafer A1 - Bestle, Dieter T1 - Evaluation of different generative models to support the validation of advanced driver assistance systems T2 - Applied mechanics N2 - Validating the safety and reliability of automated driving systems is a critical challenge in the development of autonomous driving technology. Such systems must reliably replicate human driving behavior across scenarios of varying complexity and criticality. Ensuring this level of accuracy necessitates robust testing methodologies that can systematically assess performance under various driving conditions. Scenario-based testing addresses this challenge by recreating safety-critical situations at varying levels of abstraction, from simulations to real-world field tests. However, conventional parameterized models for scenario generation are often resource intensive, prone to bias from simplifications, and limited in capturing realistic vehicle trajectories. To overcome these limitations, the paper explores AI-based methods for scenario generation, with a focus on the cut-in maneuver. Four different approaches are trained and compared: Variational Autoencoder enhanced with a convolutional neural network (VAE), a basic Generative Adversarial Network (GAN), Wasserstein GAN (WGAN), and Time-Series GAN (TimeGAN). Their performance is assessed with respect to their ability to generate realistic and diverse trajectories for the cut-in scenario using qualitative analysis, quantitative metrics, and statistical analysis. Among the investigated approaches, VAE demonstrates superior performance, effectively generating realistic and diverse scenarios while maintaining computational efficiency. KW - Advanced driver assistance system KW - Real cut-in maneuver KW - Synthetic data KW - Variational autoencoder KW - Generative adversarial networks KW - Machine learning Y1 - 2025 U6 - https://doi.org/10.3390/applmech6020039 SN - 2673-3161 VL - 6 IS - 2 SP - 1 EP - 26 PB - MDPI CY - Basel ER - TY - GEN A1 - Röder, Benedict A1 - Hajipour, Sanam A1 - Ebel, Henrik A1 - Eberhard, Peter A1 - Bestle, Dieter T1 - Automated design of a four-bar mechanism starting from hand drawings of desired coupler trajectories and velocity profiles T2 - Mechanics based design of structures and machines N2 - When a specific, relatively simple motion must be executed with high precision and high speed, simple mechanisms like the four-bar linkage are often the first choice. Combined with control of the crank speed, these systems are able to move the end-effector with any changing speed. Designing a certain mechanism for a pre-defined trajectory, however, usually requires an expert, which is why automatic design by a design assistant system is desirable. Modern AI methods may support such an automatic design, which shall function only based on hand drawings of the desired path and a corresponding velocity profile. For a planar four-bar mechanism, which serves only as an example, this article proposes a general data-driven procedure where first the geometry of a mechanism is synthesized by machine learning such that the track point follows approximately the desired trajectory. Then, the kinematic relation between the track point’s velocity profile and the crank’s angular velocity is learned. This learned inverse kinematics model may be applied to an arbitrary user-defined velocity profile of the track point. Finally, a controller governing the crank torque is designed purely based on data to track the resulting angular crank velocity. Not every drawn motion can necessarily be realized with a mechanism; however, the goal is to identify a mechanism that approximates the drawn curve as accurately as possible. While various design toolboxes already exist, especially for the design of four-bar linkages, this article presents a design pipeline using data-driven approaches that solely learn from forward simulation data. This nurtures the hope that presented approach is also applicable to more complex systems where analytic formulations cannot be easily derived. KW - Design assistant KW - Mechanism design KW - Four-bar linkage KW - Inverse kinematics KW - Machine learning KW - Tracking control Y1 - 2025 U6 - https://doi.org/10.1080/15397734.2025.2543559 SN - 1539-7742 VL - 2025 SP - 1 EP - 25 PB - Taylor & Francis CY - Philadelphia, Pa. ER - TY - GEN A1 - Bestle, Dieter A1 - Hajipour, Sanam T1 - Design of a tracking controller based on machine learning T2 - International journal of mechanical system dynamics N2 - Tracking control of multibody systems is a challenging task requiring detailed modeling and control expertise. Especially in the case of closed-loop mechanisms, inverse kinematics as part of the controller may become a game stopper due to the extensive calculations required for solving nonlinear equations and inverting complicated functions. The procedure introduced in this paper substitutes such advanced human expertise by artificial intelligence through the utilization of surrogates, which may be trained from data obtained by classical simulation. The necessary steps are demonstrated along a parallel mechanism called λ-robot. Based on its mechanical model, the workspace is investigated, which is required to set proper initial conditions for generating data covering the used operation space of the robot. Based on these data, artificial neural networks are trained as surrogates for inverse kinematics and inverse dynamics. They provide forward control information such that the remaining error behavior is governed by a linear ordinary differential equation, which allows applying a linear quadratic regulator (LQR) from linear control theory. An additional feedback loop of the tracking error accounts for model uncertainties. Simulation results validate the applicability of the proposed concept. KW - Artificial neural network KW - Inverse dynamics KW - Inverse kinematics KW - Machine learning KW - Tracking control Y1 - 2025 U6 - https://doi.org/10.1002/msd2.70006 SN - 2767-1402 VL - 5 / 2025 IS - 2 SP - 201 EP - 211 PB - Wiley CY - Hoboken, NJ ER - TY - GEN A1 - Mammen, Manasa Mariam A1 - Kayatas, Zafer A1 - Bestle, Dieter T1 - Generation of multiple types of driving scenarios with variational autoencoders for autonomous driving T2 - Future transportation N2 - Generating realistic and diverse driving scenarios is essential for effective scenario-based testing and validation in autonomous driving and the development of driver assistance systems. Traditionally, parametric models are used as standard approaches for scenario generation, but they require detailed domain expertise, suffer from scalability issues, and often introduce biases due to idealizations. Recent research has demonstrated that AI models can generate more realistic driving scenarios with reduced manual effort. However, these models typically focused on single scenario types, such as cut-in maneuvers, which limits their applicability to diverse real-world driving situations. This paper, therefore, proposes a unified generative framework that can simultaneously generate multiple types of driving scenarios, including cut-in, cut-out, and cut-through maneuvers from both directions, thus covering six distinct driving behaviors. The model not only learns to generate realistic trajectories but also reflects the same statistical properties as observed in real-world data, which is essential for risk assessment. Comprehensive evaluations, including quantitative metrics and visualizations from detailed latent and physical space analyses, demonstrate that the unified model achieves comparable performance to individually trained models. The shown approach reduces modeling complexity and offers a scalable solution for generating diverse, safety-relevant driving scenarios, supporting robust testing and validation. KW - Automated driving KW - Variational autoencoder KW - Unified generative model KW - Cut-in KW - Cut-out KW - Cut-through Y1 - 2025 U6 - https://doi.org/10.3390/futuretransp5040159 SN - 673-7590 VL - 5 IS - 4 SP - 1 EP - 20 PB - MDPI CY - Basel ER -