Search Results

Convolutional neural networks are the de facto method of processing camera, radar, and lidar data for use in perception in ADAS and L4 vehicles, yet their operation is a black box to many engineers. Unlike traditional rules-based approaches to coding intelligent systems, networks are trained and the internal structure created during the training process is too complex to be understood by humans, yet in operation networks are able to classify objects of interest at error rates better than rates achieved by humans viewing the same input data.

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.

On the path to decarbonizing road transport, electric commercial vehicles will play a significant role. The first applications were directed to the smaller trucks for distribution traffic with relatively moderate driving and range requirements, but meanwhile, the first generation of a complete portfolio of truck sizes is developed and available on the market. In these early applications, many compromises were accepted to overcome component availability, but meanwhile, the supply chain can address the specific needs of electric trucks. With that, the optimization towards higher usability and lower costs can be moved to the next level. Especially for long-haul trucks, efficiency is a driving factor for the total costs of ownership. Besides the propulsion system, all other systems must be optimized for higher efficiency. This includes thermal management since the thermal management components consume energy and have a direct impact on the driving range.

Autonomous Driving is being utilized in various settings, including indoor areas such as industrial halls. Additionally, LIDAR sensors are currently popular due to their superior spatial resolution and accuracy compared to RADAR, as well as their robustness to varying lighting conditions compared to cameras. They enable precise and real-time perception of the surrounding environment. Several datasets for on-road scenarios such as KITTI or Waymo are publicly available. However, there is a notable lack of open-source datasets specifically designed for industrial hall scenarios, particularly for 3D LIDAR data. Furthermore, for industrial areas where vehicle platforms with omnidirectional drive are often used, 360° FOV LIDAR sensors are necessary to monitor all critical objects. Although high-resolution sensors would be optimal, mechanical LIDAR sensors with 360° FOV exhibit a significant price increase with increasing resolution.

Modeling thermal systems in Battery Electric Vehicles (BEVs) is crucial for enhancing energy efficiency through predictive control strategies, thereby extending vehicle range. A major obstacle in this modeling is the often limited availability of detailed system information. This research introduces a methodology using neural networks for system identification, a powerful technique capable of approximating the physical behavior of thermal systems with minimal data requirements. By employing black-box models, this approach supports the creation of optimization-based operational strategies, such as Model Predictive Control (MPC) and Reinforcement Learning-based Control (RL). The system identification process is executed using MATLAB Simulink, with virtual training data produced by validated Simulink models to establish the method's feasibility. The neural networks utilized for system identification are implemented in MATLAB code.

For the purpose of achieving carbon-neutrality in the mobility sector by 2050, hydrogen can play a crucial role as an alternative energy carrier, not only for direct usage in fuel cell-powered vehicles, but also for fueling internal combustion engines. This paper focuses on the numerical investigation of high-pressure hydrogen injection and the mixture formation inside a high-tumble engine with a conventional liquid fuel injector for passenger cars. Since the traditional 3D-CFD approach of simulating the inner flow of an injector requires a very high spatial and temporal resolution, the enormous computational effort, especially for full engine simulations, is a big challenge for an effective virtual development of modern engines. An alternative and more pragmatic lagrangian 3D-CFD approach offers opportunities for a significant reduction in computational effort without sacrificing reliability.

The calibration of Engine Control Units (ECUs) for road vehicles is challenged by stringent legal and environmental regulations, coupled with short development cycles. The growing number of vehicle variants, although sharing similar engines and control algorithms, requires different calibrations. Additionally, modern engines feature increasingly number of adjustment variables, along with complex parallel and nested conditions within the software, demanding a significant amount of measurement data during development. The current state-of-the-art (White Box) model-based ECU calibration proves effective but involves considerable effort for model construction and validation. This is often hindered by limited function documentation, available measurements, and hardware representation capabilities. This article introduces a model-based calibration approach using Neural Networks (Black Box) for two distinct ECU functional structures with minimal software documentation.

Autonomous Emergency Braking (AEB) systems are critical in preventing collisions, yet their effectiveness hinges on accurately estimating the distance between the vehicle and other road users, as well as understanding road conditions. Errors in distance estimation can result in premature or delayed braking and varying road conditions alter road-tire friction coefficients, affecting braking distances. Advancements in sensor technology and deep learning have improved vehicle perception and real-world understanding. The integration of advanced sensors like LiDARs has significantly enhanced distance estimation. Cameras and deep neural networks are also employed to estimate the road conditions. However, AEB systems face notable challenges in urban environments, influenced by complex scenarios and adverse weather conditions such as rain and fog. Therefore, investigating the error tolerance of these estimations is essential for the performance of AEB systems.

Homologation is an important process in vehicle development and aerodynamics a main data contributor. The process is heavily interconnected: Production planning defines the available assemblies. Construction defines their parts and features. Sales defines the assemblies offered in different markets, where Legislation defines the rules applicable to homologation. Control engineers define the behavior of active, aerodynamically relevant components. Wind tunnels are the main test tool for the homologation, accompanied by surface-area measurement systems. Mechanics support these test operations. The prototype management provides test vehicles, while parts come from various production and prototyping sources and are stored and commissioned by logistics. Several phases of this complex process share the same context: Production timelines for assemblies and parts for each chassis-engine package define which drag coefficients or drag coefficient contributions shall be determined.

Investigating human driver behavior enhances the acceptance of the autonomous driving and increases road safety in heterogeneous environments with human-operated and autonomous vehicles. The previously established driver fingerprint model, focuses on the classification of driving style based on CAN bus signals. However, driving styles are inherently complex and influenced by multiple factors, including changing driving environments and driver states. To comprehensively create a driver profile, an in-car measurement system based on the Driver-Driven vehicle-Driving environment (3D) framework is developed. The measurement system records emotional and physiological signals from the driver, including ECG signal and heart rate. A Raspberry Pi camera is utilized on the dashboard to capture the driver's facial expressions and a trained convolutional neural network (CNN) recognizes emotion. To conduct unobtrusive ECG measurements, an ECG sensor is integrated into the steering wheel.

The pace of innovations in battery development is revolutionizing the landscape and opportunities for energy storage applications leading to a stronger market segmentation enabling a better suitability to fulfill specific application requirements. For automotive applications, several approaches to increase energy densities, to improve fast charging performance, and to reduce cost on a pack level are considered. Among them, a promising example is the direct integration of battery cells into the battery pack (Cell-to-pack; CTP) or vehicle (Cell-to-chassis, CTC) to increase energy densities and to reduce costs, as already commercialized by Tesla, CATL and others. In the pack development, especially Asian players are one of the frontrunners, where e.g., hybrid cell battery systems with a mixture of cells with different cathode chemistries as introduced by NIO, are experiencing a high interest of the market.

Commercial vehicle powertrain is called to respect a challenging roadmap for CO2 emissions reduction, quite complex to achieve just improving technologies currently on the market. In this perspective alternative solutions are gaining interest, and the use of green H2 as fuel for ICE is considered a high potential solution with fast and easy adoption. NOx emission is still a problem for H2 ICE and can be managed operating the engine with lean air fuel ratio all over the engine map. This combustion strategy will challenge the boosting system as lean H2 combustion will require quite higher air flow compared to diesel for the same power density in steady state. Similar problem will show up in transient response particularly when acceleration starts from low load and the exhaust gases enthalpy is very poor and insufficient to spin the turbine. The analysis presented in this paper will show and quantify the positive impact that a supercharger has on both the above mentions problems.

This 3-day Fundamentals of GD&T course provides an in-depth study of the terms, rules, symbols, and concepts of geometric dimensioning and tolerancing, as prescribed in the ASME Y14.5-2018 Standard. The course can be conducted in three 8-hour sessions or with flexible scheduling including five mornings or five afternoons. 

The modern automotive industry is facing challenges of ever-increasing complexity in the electrified powertrain era. On-board diagnostic (OBD) systems must be thoroughly validated and calibrated through many iterations to function effectively and meet the regulation standards. Their development and design process are more complex when prototype hardware is not available and therefore virtual testing is a prominent solution, including Software-in-the-loop (SiL) and Hardware-in-the-loop (HIL) simulations. Virtual prototype testing relying on real-time simulation models is necessary to design and test new era’s OBD systems quickly and in scale. The new fuel cell powertrain involves new and preciously unexplored fail modes. To make the system robust, simulations are required to be carried out to identify different fails.

The production of electric vehicles (EVs) has a significant environmental impact, with up to 50 % of their lifetime greenhouse gas potential attributed to manufacturing processes. The use of sustainable materials in EV design is therefore crucial for reducing their overall carbon footprint. Wood laminates have emerged as a promising alternative due to their renewable nature. Additionally, wood-based materials offer unique damping properties that can contribute to improved Noise, Vibration, and Harshness (NVH) characteristics. In comparison to conventional materials such as aluminum, ply wood structures exhibit beneficial damping properties. The loss factor of plywood structures with a thickness below 20 mm ranges from 0.013 to 0.032. Comparable aluminum structures however exhibit only a fraction of this loss factor with a range between 0.002 and 0.005.

Today’s engines used in Agriculture, Mining and Construction are designed for robustness and cost. Here, the Diesel powertrain is the established mainstream solution, offering long operation times without refueling at any desired power rating. In view of the steps towards Carbon Neutrality by 2050 this segment of the Transportation Sector needs to reduce its CO2 emissions. Currently, the EU and US emissions legislations (EU Stage V / EPA Tier4) do not include a CO2 reduction scheme but is expected to change with the next update towards EU Stage VI / EPA Tier5 coming into effect 2030 and after. Larger power and operation range still require the use of renewable, liquid fuels or hydrogen. The cost-up of such fuels could be counterbalanced by more efficient engines in combination with a hybridized powertrain.

Dampers (PDs) are passive devices employed in vibration and noise control applications. They consist of a cavity filled with particles that, when fixed to a vibrating structure, dissipate vibrational energy through friction and collisions among the particles. These devices have been extensively documented in the literature and find widespread use in reducing vibrations in structural machinery components subjected to significant dynamic loads during operation. However, their application in reducing vehicle interior sound has received, up to now, relatively little attention. Previous work by the authors has proven the effectiveness of particle dampers in mitigating vibrations in vehicle body panels, achieving a notable reduction in structure-borne noise within the vehicle cabin with an additional weight comparable to or even lower than that of bituminous damping treatments traditionally used for this purpose.

The societies around the world remain far from meeting the agreed primary goal outlined under the 2015 Paris Agreement on climate change: reducing greenhouse gas (GHG) emissions to keep global average temperature rise to well below 20°C by 2100 and making every effort to stay underneath of a 1.5°C elevation. Current emissions are rebounding from a brief decline during the economic downturn related to the Covid-19 pandemic. To get back on track to support the realization of the goal of the Paris Agreement, research suggests that GHG emissions should be roughly halved by 2030 on a trajectory to reach net zero by around mid-century.2 Although these are averaged global targets, every sector and country or market can and must contribute, especially higher-income and more developed countries bear the greater capacity to act. In 2020 direct tailpipe emissions from transport represented around 8 GtC02e, or nearly 15% of total emissions.

This research aims presents the method classifying the noise source and evaluating the sound quality of the noise caused by operating of electric power steering wheel in an electric vehicle. The steering wheel has been operated by the motor drive by electric power and it called motor-driven electric power (MDPS) system. If the motor is attached to the steering column of the steering device, it is called C-MDPS system. The steering device of the C-MDPS system comprises of motor, bearings, steering column, steering wheel and worm shaft. Among these components the motor and bearings are main noise sources of C-MDPS system. When the steering wheel is operated in an electric vehicle, the operating noise of the steering device inside the vehicle is more annoying than that in a gasoline engine vehicle since the operating noise is not masked by engine noise. Defects in the C-MDPS system worsen the operating noise of the steering system.