Industrial and Medical Imaging

Industrial and Medical Imaging

• Model-based Automated Adjustment of Complex Optical Systems

  The use of optical systems is steadily increasing in both industry and among private users. For example, interferometers are used in metrology, lasers in gravitational physics, telescopes in astronomy, and camera lenses for imaging processes. With this growing demand, the requirements and complexity of such systems are also increasing. Particularly, the assembly process of miniaturized and complex optical systems is still predominantly performed manually today and thus significantly depends on the expertise of trained personnel.

  Led by: Dr.-Ing. Nils Melchert

  Year: 2020

  Duration: 01.04.2020 - 01.04.2023
• Smart surgery through AI-based assistance systems

  As part of the research project, a digital OR assistant is to be developed, which will make it possible to relieve the staff in the OR by monitoring instruments and also to acquire data for planning more efficient and hygienically optimized ORs. Multiscale AI-based image processing for object recognition and coordinate regression will be central to the development of the OR assistant, which will make it possible to track relevant objects in the room with cost-effective and easy-to-install cameras and deliver robust results even in the event of occlusions. Central research questions include in particular network conditioning with synthetic data based on detailed virtual 3D environments and the development of network architectures in combination with state estimation methods. The recognition algorithm is used to monitor all tools in use and documents each individual tool in terms of duration of use, type of use, user and movement profile. All this information enables the creation of reliable statistics and the automated preparation of a surgical report, intelligent surgical planning or the design of gripper systems for automated instrument application. The project is funded by the Young Investigator Grands funding line of Leibniz Universität Hannover.

  Led by: Dr. Ing. Lennart Hinz

  Team: Leon Wiese, M. Sc.

  Year: 2024

  Funding: Young Investigator Grands LUH

  Duration: 01.01.2024 - 31.12.2025
• Cross-scale geometry inspection in mobile manufacturing

  The increasing individualization in production is pushing conventional manufacturing methods to their limits. As part of the SCALE research projects, novel scalable and autonomous processes are being investigated. In particular, the mobile machining of components requires precise and, above all, flexible measuring systems to determine different geometric properties of the workpieces as well as their global position during the process steps. Conventional commercial measurement systems based on fringe projection profilometry are often limited in such scenarios by the restricted measurement volume and finite resolution to certain scales. The aim of this research project is to develop an innovative fringe projection profilometry system, where adaptation of the triangulation angle enables location- and scale-adapted measurement to address the multitude of measurement tasks.

  Led by: Dr.-Ing. Lennart Hinz; PD Dr.-Ing. Dipl.-Phys. Markus Kästner

  Team: Peter Shobowale, M. Sc.

  Year: 2024
• Einrichtassistenzsystem für Transferpressen auf KI-Basis (SPP 2422)

  The quality of formed components depends on various factors, including process temperature, material and machine properties, as well as tool settings. The initial setup and readjustment of multi-stage tools pose a challenge due to complex interactions, where trained personnel utilize implicit knowledge to stabilize process conditions and ensure the production of defect-free parts. The project aims to utilize AI-based methods to process process data in conjunction with domain-specific knowledge, enabling better modeling of implicit process relationships. This involves generating recommendations for setting up forming processes. In the first phase, experimental conditions are established to develop a multi-stage model for setting up forming processes. AI models identify inherent system interactions and predict geometric quality characteristics.

  Led by: Dr.-Ing. Lennart Hinz

  Team: Malte Nagel, M. Sc.

  Year: 2024

  Funding: DFG

  Duration: 2023-2026
• Characterization of hybrid porous materials for process design (SFB/TRR 375 Project C03)

  To evaluate the material properties produced by the additive manufacturing process with porous materials, both porosity and material gradation must be measured and described using appropriate parameters. The challenge here is that established non-destructive methods, such as computed tomography (CT), require clear material boundaries. Additionally, there are no existing parameters to describe porosity and gradation at the micro-level. As part of project C03, a virtual CT is to be developed, allowing for non-destructive reconstruction of material and porosity gradations. A mathematical model will be created to represent the interaction between the measurement object, X-ray radiation, and the detector. Simultaneously, a destructive reconstruction based on real samples will be developed. This will determine the parameters that can describe porosity and material gradation at the micro-level. By combining the synthetic measurement data from the mathematical model with the measurement data from real samples, a holistic, model-based measurement and evaluation methodology will be developed. The goal is to achieve a precise and comprehensive description of material properties that can be obtained both non-destructively and destructively.

  Led by: Dr.-Ing. Lennart Hinz

  Team: Oumaima Guissem, M. Sc.

  Year: 2024

  Funding: DFG

  Duration: 2024-2027
• Modelling of sinter forging under consideration of uncertainty propagation (SPP2476 - project 9)

  The powder pressing, sintering and sinter forging process chain enables the powder metallurgical production of complex components with outstanding microstructural properties and high material utilization and precision. The sub-processes are subject to stochastic fluctuations in the process parameters. In interlinked processes, these uncertainties are propagated. In particular, the stochastic nature of the powdery base material leads to diverse interactions and fluctuations in the subsequent process steps. For example, density gradients formed during powder pressing can lead to distortions in the sintered or sinter-forged components. Existing modelling methods generally focus on an isolated process description without consideration of the interactions. The aim of the project is therefore the cross-process modeling of the sinter forging process chain, taking into account the uncertainties that occur as well as their interaction and propagation. One of the focal points of the project is in-situ component monitoring for the continuous reconstruction of geometry and surface temperature in the sintering process in order to collect data for modeling uncertainty propagation and to predict core temperature and density distribution during the sintering process using soft sensors. As the sub-processes are difficult to measure, the uncertainty quantification is carried out using fast-calculating metamodels, which are trained using FE simulations. For a final analysis of uncertainty development, the developed models of the sub-processes are linked and the development of uncertainty along the process chain is quantified. Finally, validation is carried out using the experimental process chain. The developed models form the basis for an inverse optimization of the process chain, taking into account the propagation and interaction of uncertainty. In this way, the overall robustness can be increased or the energy input can be minimized by adjusting the process parameters.

  Led by: Dr.-Ing. Lennart Hinz

  Team: Johannes Stegmann, M. Sc.

  Year: 2025

  Funding: DFG

  Duration: 2025-2028
• Inceasing resource efficiency of hot bulk forming processes by in-line error detection of hot forged components (SFB1153 T07)

  As part of Transfer Project T07 within the SFB 1153, together with the Institute of Forming Technology and Machines, a forging process is being optimized in a manner relevant to industrial practice with the aim of improving resource efficiency and reducing costs. This is achieved by measuring components while they are still hot in order to identify systematic errors in the forging process and compensate for them during operation. To this end, an adaptive forging process, including press peripherals, is being developed based on suitable component geometries and process boundary conditions. In parallel, based on findings from the basic research of SFB 1153 on the optical measurement of components at forging temperatures, an inline-capable measurement system for component measurement is being developed. Based on geometric features determined in these measurements, as well as a digital surrogate model of the forging process, conclusions are drawn regarding the causes of geometric deviations in the forging process. Based on these causes, recommendations for action during the forging process are provided to achieve optimal component geometries and reduce scrap. Finally, a transfer of these findings to an industrial forging process in collaboration with an industrial partner is planned.

  Led by: Dr.-Ing. Lennart Hinz

  Team: M. Sc. Darion Jobs

  Year: 2025

  Funding: DFG

  Duration: 2025-2028