Filtern
Erscheinungsjahr
- 2023 (8) (entfernen)
Dokumenttyp
- Vortrag (4)
- Zeitschriftenartikel (3)
- Beitrag zu einem Tagungsband (1)
Sprache
- Englisch (8)
Schlagworte
- Artificial Intelligence (8) (entfernen)
Organisationseinheit der BAM
Eingeladener Vortrag
- nein (4)
We employ in-house generated synthetic Al-Si matrix composite XCT data for training deep convolutional neural networks for XCT data conditioning and automatic segmentation. We propose an in-house multilevel deep conditioning framework capable of rectifying noise and blur in corrupted XCT data sequentially. Furthermore, for automatic segmentation, we utilize a special in-house network coupled with a novel iterative segmentation algorithm capable of generalized learning from synthetic data. We report a consistent SSIM efficiency of 92%, 99%, and 95% for the combined denoising/deblurring, standalone denoising, and standalone deblurring, respectively. The overall segmentation precision was over 85% according to the Dice coefficient. We used experimental XCT data from various scans of Al-Si matrix composites reinforced with ceramic particles and fibers.
It is shown that preconditioning of experimental X‐ray computed tomography (XCT) data is critical to achieve high‐precision segmentation scores. The challenging experimental XCT datasets and deep convolutional neural networks (DCNNs) are used that are trained with low‐resemblance synthetic XCT data. The material used is a 6‐phase Al–Si metal matrix composite‐reinforced with ceramic fibers and particles. To achieve generalization, in our past studies, specific data augmentation techniques were proposed for the synthetic XCT training data. In addition, two toolsets are devised: (1) special 3D DCNN architecture (3D Triple_UNet), slicing the experimental XCT data from multiple views (MultiView Forwarding), the i.S.Sy.Da.T.A. iterative segmentation algorithm, and (2) nonlocal means (NLM) conditioning (filtering) for the experimental XCT data. This results in good segmentation Dice scores across all phases compared to more standard approaches (i.e., standard UNet architecture, single view slicing, standard single training, and NLM conditioning). Herein, the NLM filter is replaced with the deep conditioning framework BAM SynthCOND introduced in a previous publication, which can be trained with synthetic XCT data. This leads to a significant segmentation precision increase for all phases. The proposed methods are potentially applicable to other materials and imaging techniques.
AbstractLaser beam welding has become widely applied in many industrial fields in recent years. Solidification cracks remain one of the most common welding faults that can prevent a safe welded joint. In civil engineering, convolutional neural networks (CNNs) have been successfully used to detect cracks in roads and buildings by analysing images of the constructed objects. These cracks are found in static objects, whereas the generation of a welding crack is a dynamic process. Detecting the formation of cracks as early as possible is greatly important to ensure high welding quality. In this study, two end-to-end models based on long short-term memory and three-dimensional convolutional networks (3D-CNN) are proposed for automatic crack formation detection. To achieve maximum accuracy with minimal computational complexity, we progressively modify the model to find the optimal structure. The controlled tensile weldability test is conducted to generate long videos used for training and testing. The performance of the proposed models is compared with the classical neural network ResNet-18, which has been proven to be a good transfer learning model for crack detection. The results show that our models can detect the start time of crack formation earlier, while ResNet-18 only detects cracks during the propagation stage.
The present work is part of the AIFRI project (Artificial Intelligence For Rail Inspection), where we and our project partners train a neural network for defect detection and classification. Our goal at BAM is to generate artificial ultrasound and eddy current training data for the A.I. This paper has an exploratory nature, where we focus on the simulation of eddy current signals for head check cracks, one of the most important rail surface defects. The goal of this paper is twofold. On the one hand, we present our general simulation setup. This includes geometric models for head check cracks with features like branching and direction change, a model for the HC10 rail testing probe, and the configuration of the Faraday simulation software.
On the other hand, we use the Faraday software to simulate eddy current testing signals with a strong focus on the influence of the damage depth on the signal, while differentiating between different crack geometries. Here, we observe an early saturation effect of the test signal at a damage depth of 2 mm (at a crack angle of 25◦ to the surface). That is about 2 mm earlier than we would expect from measurements at a crack angle of 90◦. This behavior will be investigated further in a future paper. Finally, we interpolate the simulated signals in a two-step curve fitting process. With these interpolations we may generate eddy current test signals for any damage depth within the simulated range.
The present work is part of the AIFRI project (Artificial Intelligence For Rail Inspection), where we and our project partners train a neural network for defect detection and classification. Our goal at BAM is to generate artificial ultrasound and eddy current training data for the A.I. This paper has an exploratory nature, where we focus on the simulation of eddy current signals for head check cracks, one of the most important rail surface defects. The goal of this paper is twofold. On the one hand, we present our general simulation setup. This includes geometric models for head check cracks with features like branching and direction change, a model for the HC10 rail testing probe, and the configuration of the Faraday simulation software.
On the other hand, we use the Faraday software to simulate eddy current testing signals with a strong focus on the influence of the damage depth on the signal, while differentiating between different crack geometries. Here, we observe an early saturation effect of the test signal at a damage depth of 2 mm (at a crack angle of 25◦ to the surface). That is about 2 mm earlier than we would expect from measurements at a crack angle of 90◦. This behavior will be investigated further in a future paper. Finally, we interpolate the simulated signals in a two-step curve fitting process. With these interpolations we may generate eddy current test signals for any damage depth within the simulated range.
The new crack luminescence method offers the possibility of making fatigue surface cracks in metallic materials more visible during inspections through a special coating system. This coating system consists of two layers, whereby the first layer has fluorescent properties and emits visible light as soon as it is irradiated by UV light. The top layer is black and is designed to prevent the fluorescent layer from emitting if no crack develops in the underlying material.
The technique proved particularly useful in a wide variety of fatigue tests of steel components under laboratory conditions. Moreover, it has the potential to be used in various industrial applications. To enable industrial deployment and integration into maintenance strategies, a concept study is developed in this contribution, resulting in a qualification framework that can serve as a foundation for determining the reliability of the crack luminescence system in terms of a probability of detection curve. Within this study, factors causing measurement variability and uncertainty are being determined and their influences assessed. Due to the extension of the system by a moving computer vision system for automated crack detection using artificial intelligence, additional long-term effects associated with structural health monitoring systems need to be incorporated into an extended probability of detection study as part of the technical justification.
Finally, important aspects and findings related to design of experiments are discussed, and a framework for reliability assessment of a new optical crack monitoring method is presented, emphasizing the influence of various uncertainty parameters, including long-term effects such as system ageing.
The new crack luminescence method offers the possibility of making fatigue surface cracks in metallic materials more visible during inspections through a special coating system. This coating system consists of two layers, whereby the first layer has fluorescent properties and emits visible light as soon as it is irradiated by UV light. The top layer is black and is designed to prevent the fluorescent layer from emitting if no crack develops in the underlying material. The technique proved particularly useful in a wide variety of fatigue tests of steel components under laboratory conditions. Moreover, it has the potential to be used in various industrial applications. To enable industrial deployment and integration into maintenance strategies, a concept study is developed in this contribution, resulting in a qualification framework that can serve as a foundation for determining the reliability of the crack luminescence system in terms of a probability of detection curve. Within this study, factors causing measurement variability and uncertainty are being determined and their influences assessed. Due to the extension of the system by a moving computer vision system for automated crack detection using artificial intelligence, additional long-term effects associated with structural health monitoring systems need to be incorporated into an extended probability of detection study as part of the technical justification. Finally, important aspects and findings related to design of experiments are discussed, and a framework for reliability assessment of a new optical crack monitoring method is presented, emphasizing the influence of various uncertainty parameters, including long-term effects such as system ageing.