Publications Search Results
Now showing 1 - 9 of 9
PublicationPredictive maintenance enabled by machine learning: Use cases and challenges in the automotive industry( 2021)
;Theissler, Andreas ;Pérez-Velázquez, Judith ;Kettelgerdes, MarcelRecent developments in maintenance modelling fuelled by data-based approaches such as machine learning (ML), have enabled a broad range of applications. In the automotive industry, ensuring the functional safety over the product life cycle while limiting maintenance costs has become a major challenge. One crucial approach to achieve this, is predictive maintenance (PdM). Since modern vehicles come with an enormous amount of operating data, ML is an ideal candidate for PdM. While PdM and ML for automotive systems have both been covered in numerous review papers, there is no current survey on ML-based PdM for automotive systems. The number of publications in this field is increasing - underlining the need for such a survey. Consequently, we survey and categorize papers and analyse them from an application and ML perspective. Following that, we identify open challenges and discuss possible research directions. We conclude that (a) publicly available data would lead to a boost in research activities, (b) the majority of papers rely on supervised methods requiring labelled data, (c) combining multiple data sources can improve accuracies, (d) the use of deep learning methods will further increase but requires efficient and interpretable methods and the availability of large amounts of (labelled) data.
PublicationThermo-mechanical-optical coupling within a digital twin development for automotive LiDAR( 2021)
;Tavakolibasti, Majid ;Meszmer, Peter ; ;Kettelgerdes, Marcel ;Elger, Gordon ;Erdogan, Hüseyin ;Seshaditya, A.Wunderle, BernhardIn the current work, the steps of the development of a Reduced Complexity Model (RCM) of a Light Detection and Ranging (LiDAR) system and the requirements for the preparation of a Digital Twin (DT) from such system are discussed. Preliminary thermal and optical simulations are presented, along with different concepts for cooling of the system. Additionally, the current barrier of coupling of the thermo-mechanical simulations produced in Ansys Mechanical and optical simulations done by Zemax OpticStudio is discussed.
PublicationConcept of Infrastructure Based Environment Perception for IN2Lab Test Field for Automated Driving( 2021)
;Agrawal, ShivaAdvanced sensors like Radar, LiDAR and camera are used in development for autonomous vehicles for environment perception to do real time object detection, classification and tracking of dynamic objects. The process of environment perception is a crucial step in development of autonomous vehicles but it is unfortunately, one of the most challenging processes because the outside environment is unpredictable, continuously changing and full of uncertainties. In this situation, the maximum assistance to such vehicles is of utmost need. Development of intelligent infrastructure unit, known as road ride unit (RSU), which can be mounted at various specific locations on the road sides to perceive environment in real time from high angle view can assist automated driving. Such RSUs can consist of various types and combination of sensors and vehicle to infrastructure (V2I) communication unit. It can send the information about critical situations, traffic alerts and other important information to nearby vehicles in real time to further enhance automated driving. This paper describes the details of development of intelligent infrastructure for a test field within the research project IN2Lab. test field development. It describes the architecture of RSUs and the concept of environment perception including sensor requirement and selection, sensor field of view, sensor coordinate system and concept of sensor fusion.
PublicationAnalysis of package design of optic modules for automotive cameras to realize reliable image sharpness( 2020)
;Kühn, Stephan ;Pandey, Amit ;Zippelius, Andreas ;Schneider, Klaus ;Erdogan, HüseyinTo enable future autonomous driving, failure free operation is a requirement for safety relevant electronic and mechanical components. The paper investigates the health indicator (HI), change in sharpness (CIS), used for condition monitoring (CM) of optical modules of automotive stereo cameras. Driven by the cyclic thermo-mechanical stress, strain and displacement, the sharpness of the optical imaging system can change. Different root causes for change in sharpness (CIS) are identified and the contribution of the different failure modes for CIS are investigated. Failure modes are separated in two categories: Changes in the distance between focal and image plane by displacement of the image plane (failure mode -package) and changes in the lens stack of the objective (failure mode - objective). By combining DOE and accelerated life testing the contribution of different stress conditions, i.e. vibrations and temperature cycling, was quantified and compared. Strong evidence was found that vibration induced aging has no influence on optical performance of the objective. Moreover, the comparison showed that vibration induced CIS can be neglected compart to CIS induced by thermo-mechanical cycling. To investigate CIS as a health indicator for the entire camera sensor the specification and development of a novel in situ measurement system for CM of camera sensors is described.
PublicationThermal Modelling of a Prismatic Lithium-Ion Cell in a Battery Electric Vehicle Environment( 2020)
;Kleiner, Jan ;Komsiyska, Lidiya ;Endisch, ChristianIn electric vehicles with lithium-ion battery systems, the temperature of the battery cells has a great impact on performance, safety, and lifetime. Therefore, developing thermal models of lithium-ion batteries to predict and investigate the temperature development and its impact is crucial. Commonly, models are validated with experimental data to ensure correct model behaviour. However, influences of experimental setups or comprehensive validation concepts are often not considered, especially for the use case of prismatic cells in a battery electric vehicle. In this work, a 3D electro-thermal model is developed and experimentally validated to predict the cell's temperature behaviour for a single prismatic cell under battery electric vehicle (BEV) boundary conditions. One focus is on the development of a single cell's experimental setup and the investigation of the commonly neglected influences of an experimental setup on the cell's thermal behaviour. Furthermore, a detailed validation is performed for the laboratory BEV scenario for spatially resolved temperatures and heat generation. For validation, static and dynamic loads are considered as well as the detected experimental influences. The validated model is used to predict the temperature within the cell in the BEV application for constant current and Worldwide harmonized Light vehicles Test Procedure (WLTP) load profile.
PublicationFinite Element Analysis: A Tool for Investigation of Sharpness Changes in Automotive Cameras( 2020)
;Pandey, Amit ;Kühn, Stephan ;Erdogan, Hüseyin ;Schneider, KlausThis paper investigates the most common sources for Change in Sharpness (CIS) of an automotive camera system. Deformation related to mismatches in Coefficient of Thermal Expansion (CTE) and creep in the BGA-Solder interconnect has been identified as most important source of CIS. This paper focuses on the development of a Zero-Hour model for a later planned extensive thermal cycling simulation investigating CIS over system lifetime. The Model is based on a simplified camera module, simulated in the thermal operations window of the system. The Zero-Hour model includes the curing process of the adhesive, which accounts for residual deformation in the components during assembly. Using this as a baseline, temperature cycling was simulated to investigate creep in the solder interconnects.
PublicationTensor-Based Framework with Model Order Selection and High Accuracy Factor Decomposition for Time-Delay Estimation in Dynamic Multipath Scenarios( 2020)
;Rosa Zanatta, Mateus da ;Costa, Joao Paulo C.L. da ;Antreich, Felix ;Haardt, Martin ; ;Mendonca, Fabio Lucio Lopes deSousa, Rafael Timoteo deGlobal Navigation Satellite Systems (GNSS) are crucial for applications that demand very accurate positioning. Tensor-based time-delay estimation methods, such as CPD-GEVD, DoA/KRF, and SECSI, combined with the GPS3 L1C signal, are capable of, significantly, mitigating the positioning degradation caused by multipath components. However, even though these schemes require an estimated model order, they assume that the number of multipath components is constant. In GNSS applications, the number of multipath components is time-varying in dynamic scenarios. Thus, in this paper, we propose a tensor-based framework with model order selection and high accuracy factor decomposition for time delay estimation in dynamic multipath scenarios. Our proposed approach exploits the estimates of the model order for each slice by grouping the data tensor slices into sub-tensors to provide high accuracy factor decomposition. We further enhance the proposed approach by incorporating the tensor-based Multiple Denoising (MuDe).
PublicationThermal Behavior of an Intelligent Li-Ion Cell under Vehicle Conditions( 2020)
;Kleiner, Jan ;Heider, Alexander ;Hanzl, Christian ;Komsiyska, Lidiya ;Endisch, ChristianIntelligent battery cells follow the approach of having greater knowledge of the single cell state in a battery system by sensors on cell level. The further-reaching approach of reconfigurable battery systems pursues the principle of controlling each cell in a system independently by switches to maximize power and safety of the whole battery system. In the literature, different approaches for sensing, communication and battery management functionality are proposed. However, less attention has been paid to the power loss of such intelligent cells and the resulting thermal effects. Especially for large prismatic cells in an automotive application the temperature is important for power, safety and life-time. Therefore, in this work, an intelligent cell prototype is realized based on a prismatic 25 Ah Li-ion cell. In addition, a 3D thermal model of the intelligent cell is developed and validated experimentally. The model is used to investigate the thermal behavior of an intelligent cell under automotive conditions in detail. The results reveal that an useful application with an temperature increase in the jelly roll of 3 K is only possible with a reduced power loss of the electronics and a well thought-out design for an intelligent cell.
PublicationModelling of 3D Temperature Behavior of Prismatic Lithium-Ion Cell with Focus on Experimental Validation Under Battery Electric Vehicle Conditions( 2019)
;Kleiner, Jan ;Komsiyska, Lidiya ;Endisch, ChristianThe electrification of vehicles focuses on battery electric vehicle (BEV) concepts with lithium-ion battery systems where temperature has a great impact on performance, safety and lifetime. Modelling the thermal behavior of lithium-ion batteries enables researchers to investigate the temperature distribution under different cooling conditions in detail. Model validation with experimental tests is necessary to ensure meaningful simulation models. Therefore, experiments have to be performed under defined conditions with a distinct understanding of influences, so that they can be used for validation. In this paper, a 3D electro-thermal battery model is developed and parametrized. An experimental setup with defined external influences is designed which takes the conditions of a lithium-ion cell in a BEV use case into account. Experimental tests with prismatic cells are performed for different charging profiles and finally, the thermal behavior of the model is validated under experimental conditions of BEV scenario with a spatial resolution of temperature.