In modern manufacturing the ability of retracing produced components is crucial for quality management and process optimization. Tracking is essential, especially for analyzing the influence of the production parameters on the final quality of the castings. In the iron foundry industry, common marking methods, such as a datamatrix code, cannot be used due to harsh environmental conditions and the rough surface of the cast parts. This work presents a new coding and reading system that guarantees unique marking in the casting process.The coding is built up over several beveled pins and is read out using an optical 2D handheld scanner. With a deep convolutional neural network approach of object detection and classification, a stable image processing algorithm is presented. With a first prototype a reading accuracy of 99.86% for each pin was achieved with an average scanning time of 0.43 s. The presented code is compatible with existing foundry processes, while the handheld scanner is intuitive and reliable. This allows immediate benefits for process optimization.
The laser sintering of polymers is an additive manufacturing technology that is becoming increasingly established in the industrial environment. This study investigated the thickness-dependent permeation properties of laser-sintered (LS) polymers as required to design and produce components with a special barrier performance to gaseous substances. Helium and oxygen permeation experiments were carried out on quenched and standard LS polyamide 12 (PA12) sheets generated with two, four, six, and eight layers at a constant powder layer thickness of 100 µm. The structural properties of the sheets were examined by differential scanning calorimetry, light microscopy, and X-ray micro-computed tomography. A reduction in thickness resulted in higher diffusion coefficients for both types of LS sheets. An explanation could be the large volume fraction of poorly sintered powder particles adhering to the surfaces and incomplete melting and low consolidation of the polymer at small thicknesses. The thickness-dependency of the solubility coefficients was the opposite, especially for the standard LS sheets, which might be related to the larger pore volume in thicker sheets. As both effects compensated for each other, nearly constant permeation coefficients for all thicknesses were observed. The results provide further insights into different material characteristics of thin LS PA12 structures and offer new information on factors relevant to their solution and diffusion behavior.
12 July 2023 in The International Journal of Advanced Manufacturing Technology
Punching is a process that is sensitive to a multitude of parameters. The estimation of part and punch quality is often based on expert knowledge and trial-and-error methods, mostly carried out as a separate offline process analysis. In a previous study, we developed an optical inline monitoring system with subsequent image processing which showed promising results in terms of capturing every manufactured part, but was limited by slow image processing. Here, we present a more efficient image processing technique based on neural networks. For our approach, we manually identify the burnish parts in images based on criteria established via an expert survey in order to generate a training dataset. We then employ a combination of region-based and boundary-based losses to optimize the neural network towards a segmentation of the burnish surface which allows for an accurate measurement of the burnish height. The hyperparameter optimization is based on custom evaluation metrics that reflect the requirements of the burnish surface identification problem as well. After comparing different neural network architectures, we focus on optimizing the backbone of the UNet++ structure for our task. The promising results demonstrate that neural networks are indeed capable of an inline segmentation that can be used for measuring the burnish surface of punching parts.
3 September 2026 in Machine Vision and Applications
In industrial applications, AI-based methods are gaining increasing significance in optical systems for tasks such as identification, inspection, and classification. The appeal of these methods lies in their operator-friendly implementation and often superior performance, particularly in complex classification tasks. However, despite the substantial potential of AI-based methods, their application is frequently constrained by the significant resources needed to acquire an appropriate training dataset. For instance, in the sand casting industry, the complexity of optical inspection for cast parts is compounded by considerable variation in local surface topography and global object geometry. This challenge pertains not only to the volume of images required but also to the extensive process of accurate labelling. In this work, we investigate the effectiveness and limitations of synthetic training data for an AI-based optical code reader, designed for the identification and tracking of cast parts. This scanner is capable of detecting and classifying a unique code, called Cast Code, developed specifically for the casting industry, enabling the identification of individual cast part numbers. For synthetic image generation, we utilize physically based rendering, which allows comprehensive control over all rendering parameters. This approach facilitates both a systematic investigation of parameter relevance and an automated labelling process for the training datasets. Our results indicate that detailed geometric modelling of both, the local surface topography and the global object geometry of the pins has a notable positive impact on the neural network’s recognition accuracy, achieving accuracy rates of up to 84 %, on real pin images, using synthetic training datasets, only.
High-resolution imaging in small animal models of neurologic disease is a technical challenge. In a pilot project, we have explored a non-destructive synchrotron imaging technique for the 3D visualization of intracerebral tissue transplants in a well-established small animal model of Huntington’s disease. Four adult female Sprague Dawley rats each received injections of 0.12 M quinolinic acid (QA) into two target positions in the left striatum, thus creating unilateral left-sided striatal lesions similar to those frequently seen in patients suffering from Huntington’s disease. One week after lesioning, the animals received transplants prepared from whole ganglionic eminences (wGEs) obtained from 13- to 14-day-old rat embryos. Of the four lesioned animals, three received transplants of GNP-loaded cells and one animal received a transplant of naïve cells, serving as control. Post-mortem synchrotron-based microCT was used to obtain images of the neurotransplants. The images obtained of GNP-loaded tissue transplants at the synchrotron corresponded in size and shape to the histological images of transplants developed from naïve cells. Thus, we conclude that non-destructive synchrotron imaging techniques such as phase-contrast imaging are suitable to obtain high-resolution images of GNP-loaded tissue transplants.
The utilization of unmanned aerial vehicles (UAVs) in search and rescue (SAR) operations has become increasingly prevalent because the deployment of UAVs is expected to facilitate a higher degree of operational flexibility while simultaneously reducing costs. Currently, commercially available UAVs can be equipped with lowresolution thermal infrared (IR) cameras with typical resolutions of 640×512 pixels, which generally are evaluated manually by the SAR teams during a operation. Automatic person detection in IR images still remains a challenge. The objective of the proposed AIResQ dataset is to significantly enhance the performance of object detectors in the IR domain, employed in SAR operations for missing and potentially injured persons. AIResQ comprises 9,788 IR images with a resolution of up to 2048×1536 pixels captured from drone perspectives with a handheld camera under varying weather conditions and in different terrains. Additionally, AIResQ displays persons in atypical poses. In order to test new object detectors in the context of SAR, we established a benchmark dataset together with SAR organizations.