ZF Friedrichshafen

The efficiency of drive trains used in electric vehicles is affected by the employed modulation scheme. This paper proposes an optimal modulation approach, in the form of optimized pulse patterns (OPPs), that limits the converter and winding losses in the machine while minimizing the stator current harmonic distortions. To do so, the OPP problem is reformulated such that the aforementioned losses are constrained. As shown with the presented numerical results, by setting different constraints to the system losses a better trade-off between stator current harmonics and losses is achieved compared with conventional modulation solutions, resulting in increased system efficiency.

In-depth evaluations of an electric drive's behavior typically result from co-simulation, combining models of motor, power electronics and control software. This approach can be used to evaluate pulse patterns for a given operating point, e.g., for electric vehicle applications, preventing real-world experiments. Here, the co-simulation model is fed with offline calculated optimized pulse patterns (OPPs) that are used to increase, among others, the drive's efficiency. Due to the large motor time constant compared to the fundamental wave period, reaching steady state using a simple open-loop control requires unnecessary long simulation times. Hence, a model predictive closed-loop control implementation of the OPPs is proposed which reduced the overall computational effort significantly. However, it turns out that the OPP evaluation using a finite-element-method-based co-simulation for a permanent magnet synchronous motor remains largely uncertain in terms of the predicted power losses which led to the development of a semi-analytical model to further reduce the required computational time. As none of the approaches was able to deliver a suitable trade-off between model accuracy and calculation time, this investigation highlights the remaining challenges of evaluating OPPs based on drive co-simulations motivating further research towards the surrogate-assisted or direct experimental OPP optimization in the future.

This paper documents the results of the PIM.3 (Process Improvement Management) working group in INTACS (International Assessor Certification Schema) supported by the VDA‐QMC (Verband der Deutschen Automobilindustrie/German Automotive Association–Quality Management Center). INTACS promotes Automotive SPICE, which is an international standard that allows process capability assessment of projects, which implement systems that integrate mechanics, electronics, and software including optionally cybersecurity, functional safety, and machine learning. The paper outlines that for the first time since more than 20 years, the INTACS and VDA‐QMC included a process like PIM.3 Process Improvement Management in the scope for the assessor training. Before that, the assessments focused on the management, engineering, and support processes of series projects, while the improvement management has not been trained or assessed.

The generation and optimization of simulation data for electrical machines remain challenging, largely due to the complexities of magneto-static finite element analysis. Traditional methodologies are not only resource-intensive, but also time-consuming. Deep learning models can be used to shortcut these calculations. However, challenges arise when considering the unique parameter sets specific to each machine topology. Building on two recent studies (Parekh et al. in IEEE Trans. Magn. 58(9):1–4, 2022; Parekh et al., Deep learning based meta-modeling for multi-objective technology optimization of electrical machines, 2023, arXiv:2306.09087), that utilized a variational autoencoder to cohesively map diverse topologies into a singular latent space for subsequent optimization, this paper proposes a refined architecture and optimization workflow. Our modifications aim to streamline and enhance the robustness of both the training and optimization processes, and compare the results with the variational autoencoder architecture proposed recently.

In this paper, we propose a method for addressing the issue of unnoticed catastrophic deployment and domain shift in neural networks for semantic segmentation in autonomous driving. Our approach is based on the idea that deep learning-based perception for autonomous driving is uncertain and best represented as a probability distribution. As autonomous vehicles’ safety is paramount, it is crucial for perception systems to recognize when the vehicle is leaving its operational design domain, anticipate hazardous uncertainty, and reduce the performance of the perception system. To address this, we propose to encapsulate the neural network under deployment within an uncertainty estimation envelope that is based on the epistemic uncertainty estimation through the Monte Carlo Dropout approach. This approach does not require modification of the deployed neural network and guarantees expected model performance. Our defensive perception envelope has the capability to estimate a neural network’s performance, enabling monitoring and notification of entering domains of reduced neural network performance under deployment. Furthermore, our envelope is extended by novel methods to improve the application in deployment settings, including reducing compute expenses and confining estimation noise. Finally, we demonstrate the applicability of our method for multiple different potential deployment shifts relevant to autonomous driving, such as transitions into the night, rainy, or snowy domain. Overall, our approach shows great potential for application in deployment settings and enables operational design domain recognition via uncertainty, which allows for defensive perception, safe state triggers, warning notifications, and feedback for testing or development and adaptation of the perception stack.

An approach to constraint nonlinear optimisation is proposed, where the variables of the objective function and of the constraint function belong to the state of a nonlinear dynamical system. A nonlinear closed-loop feedback system is designed, whose solutions converge to a target set consisting of the optimal points of the underlying optimisation problem. The feedback law for the control input of the nonlinear dynamical system is designed by exact linearisation of a dynamical formulation of a first-order optimality condition. For the problem formulation and the stability analysis of the nonlinear closed-loop feedback system, the notion of V-detectability is considered. An application to energy-optimal feed-forward torque control for different types of synchronous machines is presented, which demonstrates the usefulness of the method. In this regard, anisotropic permanent magnet synchronous machines and electrically excited synchronous machines are covered.