Search Results

Computational models directly derived from data gained increased interest in recent years. Data-driven approaches have brought breakthroughs in different research areas such as image-, video- and audio-processing. Often denoted as Machine Learning (ML), today these approaches are not widely applied in the field of vehicle Noise, Vibration and Harshness (NVH). Works combining ML and NVH mainly discuss the topic with respect to psychoacoustics, traffic noise, structural health monitoring and as improvement to existing numerical simulation methods. Vehicle interior noise is a major quality criterion for today’s automotive customers. To estimate noise levels early in the development process, deterministic system descriptions are created by utilizing time-consuming measurement techniques. This paper examines whether pattern-recognizing algorithms are suitable to conduct the prediction process for a steering system.

Existing electronic combustion engine control systems only guarantee a desired air-to-fuel-ratio λ in stationary operation. In order to achieve the desired λ also in in-stationary use of the engine, it is necessary to use new-technology-based control systems. Artificial Intelligence provides methods to cope with difficulties like wide operation range, unknown nonlinearities and time delay. We will propose a strategy for control of a Spark Ignition Engine to determine the mass of air inside the combustion chambers with the highest accuracy. Since Neural Networks are universal approximators for multidimensional nonlinear static functions they can be used effectively for identification and compensation purposes of unknown nonlinearities in closed control loops.

In this paper the design of a robust control system for a parallel hybrid drivetrain is presented The drivetram is based on a continuously variable transmission (CVT) and is therefore a highly nonlinear multiple-input-multiple-output system (MIMO-System) Input-Output-Linearization offers the possibility of linearizing and of decoupling the system Since for example the vehicle mass varies with the load and the efficiency of the gearbox depends strongly on the actual working point, an exact linearization of the plant will mostly fail Therefore a robust control algorithm based on sliding mode is used to control the drivetrain

In order to reduce emissions of spare ignition engines using a three way catalyst, a stoichiometric air-fuel ratio must be guaranteed in stationary and transient operation of the engine. This aim can be reached by using a specific feed-forward structure for the control of the paths of air and fuel based on identification abilities of Artificial Intelligence. As approximators for multidimensional nonlinear static functions we will use specific Neural Networks (NN) together with sophisticated stability-proven learning structures. The acquired knowledge within the NN determines our control action mainly through using feed-forward structures. Our investigations are based on the so-called mean-value-modelling approach of SI engines; it is our aim to present this strategy.

The increasing complexity of automotive functions which are necessary for improved driving assistance systems and automated driving require a change of common vehicle architectures. This includes new concepts for E/E architectures such as a domain-oriented vehicle network based on powerful Domain Control Units (DCUs). These highly integrated controllers consolidate several applications on different safety levels on the same ECU. Hence, the functions depend on a strictly separated and isolated implementation to guarantee a correct behavior. This requires middleware layers which guarantee task isolation and Quality of Service (QoS) communication have to provide several new features, depending on the domain the corresponding control unit is used for. In a first step we identify requirements for a middleware in automotive DCUs. Our goal is to reuse legacy AUTOSAR based code in a multicore domain controller.

In motorsports, aerodynamic development processes target to achieve gains in performance. This requires a comprehensive understanding of the prevailing aerodynamics and the capability of analysing large quantities of numerical data. However, manual analysis of a significant amount of Computational Fluid Dynamics (CFD) data is time consuming and complex. The motivation is to optimize the aerodynamic analysis workflow with the use of deep learning architectures. In this research, variants of 3D deep learning models (3D-DL) such as Convolutional Autoencoder (CAE) and U-Net frameworks are applied to flow fields obtained from Reynolds Averaged Navier Stokes (RANS) simulations to transform the high-dimensional CFD domain into a low-dimensional embedding. Consequently, model order reduction enables the identification of inherent flow structures represented by the latent space of the models.

Bicycle-drawn cargo trailers with an electric drive to enable the transportation of high cargo loads are used as part of the last-mile logistics. Depending on the load, the total mass of a trailer can vary between approx. 50 and 250 kg, potentially more than the mass of the towing bicycle. This can result in major changes in acceleration and braking behavior of the overall system. While existing systems are designed primarily to provide sufficient power, improvements are needed in the powertrain control system in terms of driver safety and comfort. Hence, we propose a novel prototype that allows measurement of the tensile force in the drawbar which can subsequently be used to design a superior control system. In this context, a sinusoidal force input from the cyclist to the trailer according to the cadence of the cyclist is observed. The novelty of this research is to analyze whether torque impulses of the cyclist can be reduced with the help of Model Predictive Control (MPC).

Deep neural network models have been widely used for environment perception of intelligent vehicles. However, due to models’ innate probabilistic property, the lack of transparency, and sensitivity to data, perception results have inevitable uncertainties. To compensate for the weakness of probabilistic models, many pieces of research have been proposed to analyze and quantify such uncertainties. For safety-critical intelligent vehicles, the uncertainty analysis of data and models for environment perception is especially important. Uncertainty estimation can be a way to quantify the risk of environment perception. In this regard, it is essential to deliver a comprehensive survey. This work presents a comprehensive overview of uncertainty estimation in deep neural networks for environment perception of intelligent vehicles.

Software complexity of vehicles is constantly growing especially with additional autonomous driving features being introduced. This increases the risk for bugs in the system, when the car is delivered. According to a car manufacturer, more than 90% of availability problems corresponding to Electronic Control Unit (ECU) functionality are either caused by software bugs or they can be resolved by applying software updates to overcome hardware issues. The main concern are sporadic errors which are not caught during the development phase since their trigger condition is too unlikely to occur or is not covered by the tests. For such systems, there is a need of safe and secure infield diagnosis. In this paper we present a tool software architecture with remote access, which facilitates standard read/write access, an efficient channel interface for communication and file I/O, and continuous trace.

Electrified vehicles are particularly quiet, especially at low speeds due to the absence of combustion noises. This is why there are laws worldwide for artificial driving sounds to warn pedestrians. These sounds are generated using a so-called Acoustic Vehicle Alerting System (AVAS) which must maintain certain minimum sound pressure levels in specific frequency ranges at low speeds. The creation of the sound currently involves an iterative and sometimes time-consuming process that combines composing the sound on a computer with measuring the levels with a car on an outside noise test track. This continues until both the legal requirements and the subjective demands of vehicle manufacturers are met. To optimize this process and reduce the measurement effort on the outside noise test track, the goal is to replace the measurement with a simulation for a significant portion of the development.