Refine
Document Type
- Conference Paper (72)
- Article (27)
Institute
- Institut für Innovative Mobilität (IIMo) (95)
- Fakultät Elektro- und Informationstechnik (70)
- Fraunhofer-Anwendungszentrum "Vernetzte Mobilität und Infrastruktur" (24)
- Fakultät Elektrotechnik und Informatik (19)
- AImotion Bavaria (3)
- CARISSMA Institute of Electric, Connected and Secure Mobility (C-ECOS) (1)
- Fakultät Maschinenbau (1)
Review
- peer-review (79)
- nein (8)
- ja (6)
- editorial review (5)
Version
- published (37)
Global 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).
Local thermomechanical stress can cause failures in semiconductor packages during long-time operation under harsh environmental conditions. This study helps to explain the packaging-induced stress in blue GaN-LEDs soldered onto copper substrates using AuSn alloy as lead-free interconnect material. Based on the finite element method, a virtual prototype is developed to simulate the thermomechanical behavior and stress in the LED and in the complete LED/AuSn/Cu assembly considering plastic and viscoplastic strain. The investigations were performed by varying the temperature between −50°C and 180°C. To validate the model, the simulation results are compared to experimental data collected with Raman spectroscopy. Studies of the urn:x-wiley:03770486:media:jrs5947:jrs5947-math-0003 phonon mode of GaN semiconductor are elaborated to understand the induced thermomechanical stress. The model enables evaluation of the stress in the interfaces of the assembly, which otherwise cannot be accessed by measurements. It serves to predict how assemblies would perform, before committing resources to build a physical prototype.
Recent 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.
Finite Element simulations and Raman measurements to investigate thermomechanical stress in GaN-LEDs
(2020)
Concept of infrastructure based environment perception for IN2Lab test field for automated driving
(2021)
Failure Identification in LED packages by Transient Thermal Analysis and Calibrated FE Models
(2019)
The smart infrastructure units can play a vital role to develop smart cities of the future and in assisting automated vehicles on the road by providing extended perception and timely warnings to avoid accidents. This paper focuses on the development of such an infrastructure unit, that is specifically designed for a pedestrian crossing junction. It can control traffic lights at the junction by real-time environment perception through its sensors and can optimize the flow of vehicles and passing vulnerable road users (VRUs). Moreover, it can assist on-road vehicles by providing real-time information and critical warnings via a v2x module. This paper further describes different use-cases of the work, all major hardware components involved in the development of smart infrastructure unit, referred to as an edge, different sensor fusion approaches using the camera, radar, and lidar mounted on the edge for environment perception, various modes of communication including v2x, system design
Combined Accelerated Stress Test with In-Situ Thermal Impedance Monitoring to Access LED Reliability
(2019)
In 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.
Environment perception using camera, radar, and/or lidar sensors has significantly improved in the last few years because of deep learning-based methods. However, a large group of these methods fall into the category of supervised learning, which requires a considerable amount of annotated data. Due to uncertainties in multi-sensor data, automating the data labeling process is extremely challenging; hence,
it is performed manually to a large extent. Even though full automation of such a process is difficult, semiautomation can be a significant step to ease this process. However, the available work in this regard is still very limited; hence, in this paper, a novel semi-automatic annotation methodology is developed for labeling RGB camera images and 3D automotive radar point cloud data using a smart infrastructure-based sensor setup. This paper also describes a new method for 3D radar background subtraction to remove clutter and a new object category, GROUP, for radar-based object detection for closely located vulnerable road users. To validate the work, a dataset named INFRA-3DRC is created using this methodology, where 75% of the
labels are automatically generated. In addition, a radar cluster classifier and an image classifier are developed, trained, and tested on this dataset, achieving accuracy of 98.26% and 94.86%, respectively. The dataset and Python scripts are available at https://fraunhoferivi.github.io/INFRA-3DRC-Dataset/.
Sensor data fusion is essential for environmental perception within smart traffic applications. By using multiple sensors cooperatively, the accuracy and probability of the perception are increased, which is crucial for critical traffic scenarios or under bad weather conditions. In this paper, a modular real-time capable multi-sensor fusion framework is presented and tested to fuse data on the object list level from distributed automotive sensors (cameras, radar, and LiDAR). The modular multi-sensor fusion architecture receives an object list (untracked objects) from each sensor. The fusion framework combines classical data fusion algorithms, as it contains a coordinate transformation module, an object association module (Hungarian algorithm), an object tracking module (unscented Kalman filter), and a movement compensation module. Due to the modular design, the fusion framework is adaptable and does not rely on the number of sensors or their types. Moreover, the method continues to operate because of this adaptable design in case of an individual sensor failure. This is an essential feature for safety-critical applications. The architecture targets environmental perception in challenging time-critical applications. The developed fusion framework is tested using simulation and public domain experimental data. Using the developed framework, sensor fusion is obtained well below 10 milliseconds of computing time using an AMD Ryzen 7 5800H mobile processor and the Python programming language. Furthermore, the object-level multi-sensor approach enables the detection of changes in the extrinsic calibration of the sensors and potential sensor failures. A concept was developed to use the multi-sensor framework to identify sensor malfunctions. This feature will become extremely important in ensuring the functional safety of the sensors for autonomous driving.
Cameras mounted on intelligent roadside infrastructure units and vehicles can detect humans on the road using state-of-the-art perception algorithms, but these algorithms are presently not trained to distinguish between human and adult. However, this is a crucial requirement from a safety perspective because a child may not follow all the traffic rules, particularly while crossing the road. Moreover, a child may stop or may start playing on the road. In such situations, the separation of a child from an adult is necessary. The work in this paper targets to solve this problem by applying a transfer-learning-based neural network approach to classify child and adult separately in camera images. The described work is comprised of image data collection, data annotation, transfer learning-based model development, and evaluation. For the work, Mask-RCNN (region-based convolutional neural network) with different backbone architectures and two different baselines are investigated and the perception precision of the architectures after transfer-learning is compared. The results reveal that the best performing trained model is able to detect and classify children and adults separately in different road scenarios with segmentation mask AP (average precision) of 85% and bounding box AP of 92%.
Thermomechanical local stress in assembled GaN LEDs investigated by Raman optical spectroscopy
(2019)
Sensor data fusion is essential for environmental perception within smart traffic applications. By using multiple sensors cooperatively, the accuracy and probability of the perception are increased, which is crucial for critical traffic scenarios or under bad weather conditions. In this paper, a modular real-time capable multi-sensor fusion framework is presented and tested to fuse data on the object list level from distributed automotive sensors (cameras, radar, and LiDAR). The modular multi-sensor fusion architecture receives an object list (untracked objects) from each sensor. The fusion framework combines classical data fusion algorithms, as it contains a coordinate transformation module, an object association module (Hungarian algorithm), an object tracking module (unscented Kalman filter), and a movement compensation module. Due to the modular design, the fusion framework is adaptable and does not rely on the number of sensors or their types. Moreover, the method continues to operate because of this adaptable design in case of an individual sensor failure. This is an essential feature for safety-critical applications. The architecture targets environmental perception in challenging time-critical applications. The developed fusion framework is tested using simulation and public domain experimental data. Using the developed framework, sensor fusion is obtained well below 10 milliseconds of computing time using an AMD Ryzen 7 5800H mobile processor and the Python programming language. Furthermore, the object-level multi-sensor approach enables the detection of changes in the extrinsic calibration of the sensors and potential sensor failures. A concept was developed to use the multi-sensor framework to identify sensor malfunctions. This feature will become extremely important in ensuring the functional safety of the sensors for autonomous driving.