TY - CONF A1 - Charmi, Amir A1 - Mustapha, Samir A1 - Yilmaz, Bengisu A1 - Heimann, Jan A1 - Prager, Jens T1 - A Machine Learning Based-Guided Wave Approach for Damage Detection and Assessment in Composite Overwrapped Pressure Vessels N2 - The applications of composite overwrapped pressure vessels (COPVs) in extreme conditions, such as storing hydrogen gases at very high pressure, impose new requirements related to the system's integrity and safety. The development of a structural health monitoring (SHM) system that allows for continuous monitoring of the COPVs provides rich information about the structural integrity of the component. Furthermore, the collected data can be used for different purposes such as increasing the periodic inspection intervals, providing a remaining lifetime prognosis, and also ensuring optimal operating conditions. Ultimately this information can be complementary to the development of the envisioned digital twin of the monitored COPVs. Guided waves (GWs) are preferred to be used in continuous SHM given their ability to travel in complex structures for long distances. However, obtained GW signals are complex and require advanced processing techniques. Machine learning (ML) is increasingly utilized as the main part of the processing pipeline to automatically detect anomalies in the system's integrity. Hence, in this study, we are scrutinizing the potential of using ML to provide continuous monitoring of COPVs based on ultrasonic GW data. Data is collected from a network of sensors consisting of fifteen Piezoelectric (PZT) wafers that were surface mounted on the COPV. Two ML algorithms are used in the automated evaluation procedure (i) a long short-term memory (LSTM) autoencoder for anomaly detection (defects/impact), and (ii) a convolutional neural network (CNN) model for feature extraction and classification of the artificial damage sizes and locations. Additional data augmentation steps are introduced such as modification and addition of random noise to original signals to enhance the model's robustness to uncertainties. Overall, it was shown that the ML algorithms used were able to detect and classify the simulated damage with high accuracy. T2 - European Conference on Non-Destructive Testing (ECNDT) CY - Lisbon, Portugal DA - 03.07.2023 KW - Guided waves KW - Structural Health Monitoring KW - Machine learning KW - Damage localization KW - COPV PY - 2023 AN - OPUS4-58687 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Charmi, Amir A1 - Mustapha, Samir A1 - Yilmaz, Bengisu A1 - Heimann, Jan A1 - Prager, Jens T1 - A Machine Learning Based-Guided Wave Approach for Damage Detection and Assessment in Composite Overwrapped Pressure Vessels N2 - The applications of composite overwrapped pressure vessels (COPVs) in extreme conditions, such as storing hydrogen gases at very high pressure, impose new requirements related to the system's integrity and safety. The development of a structural health monitoring (SHM) system that allows for continuous monitoring of the COPVs provides rich information about the structural integrity of the component. Furthermore, the collected data can be used for different purposes such as increasing the periodic inspection intervals, providing a remaining lifetime prognosis, and also ensuring optimal operating conditions. Ultimately this information can be complementary to the development of the envisioned digital twin of the monitored COPVs. Guided waves (GWs) are preferred to be used in continuous SHM given their ability to travel in complex structures for long distances. However, obtained GW signals are complex and require advanced processing techniques. Machine learning (ML) is increasingly utilized as the main part of the processing pipeline to automatically detect anomalies in the system's integrity. Hence, in this study, we are scrutinizing the potential of using ML to provide continuous monitoring of COPVs based on ultrasonic GW data. Data is collected from a network of sensors consisting of fifteen Piezoelectric (PZT) wafers that were surface mounted on the COPV. Two ML algorithms are used in the automated evaluation procedure (i) a long short-term memory (LSTM) autoencoder for anomaly detection (defects/impact), and (ii) a convolutional neural network (CNN) model for feature extraction and classification of the artificial damage sizes and locations. Additional data augmentation steps are introduced such as modification and addition of random noise to original signals to enhance the model's robustness to uncertainties. Overall, it was shown that the ML algorithms used were able to detect and classify the simulated damage with high accuracy. T2 - 13th European Conference on Non-Destructive Testing (ECNDT) 2023 CY - Lisbon, Portugal DA - 03.07.2023 KW - Machine learning KW - Structural health monitoring KW - COPV KW - Guided waves KW - Damage localization PY - 2023 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:kobv:b43-590789 SN - 2941-4989 VL - 1 IS - 1 SP - 1 EP - 6 PB - NDT.net CY - Germany AN - OPUS4-59078 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - THES A1 - Charmi, Amir T1 - A multiscale numerical framework for the simulation of anistropic material response of additively manufactured stainless steel 316L undergoing large plastic deformation N2 - Additive manufacturing (AM) offers significantly greater freedom of design compared to conventional manufacturing processes since the final parts are built layer by layer. This enables metal AM, also known as metal 3D printing, to be utilized for improving efficiency and functionality, for the production of parts with very complex geometries, and rapid prototyping. However, despite many technological advancements made in recent years, several challenges hinder the mass adoption of metal AM. One of these challenges is mechanical anisotropy which describes the dependency of material properties on the material orientation. Therefore, in this work, stainless steel 316L parts produced by laser-based powder bed fusion are used to isolate and understand the root cause of anisotropy in AM parts. Furthermore, an efficient and accurate multiscale numerical framework is presented for predicting the deformation behavior of actual AM parts on the macroscale undergoing large plastic deformations. Finally, a novel constitutive model for the plastic spin is formulated to capture the influence of the microstructure evolution on the material behavior on the macroscale. KW - Additive Fertigung KW - Austenitischer Stahl KW - Finite-Elemente-Methode KW - Mehrskalenmodell KW - Simulation PY - 2024 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:wim2-20240207-173356-002 SP - 1 EP - 163 PB - Bauhaus-Universität Weimar CY - Weimar AN - OPUS4-59511 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Charmi, Amir A1 - Beinlich, Lukas A1 - Barzegar, Mohsen A1 - Bulling, Jannis A1 - Lugovtsova, Yevgeniya A1 - Yilmaz, Bengisu T1 - Closing the gap between simulation and experiment using autoencoders N2 - Structural Health Monitoring (SHM) mittels geführter Ultraschallwellen ermöglicht eine kontinuierliche Überwachung komplexer Bauteile und liefert umfangreiche Informationen über deren strukturelle Integrität. Die aufgezeichneten Signale sind jedoch komplex und werden daher zunehmend mittels KI verarbeitet, um Anomalien in der Systemintegrität automatisch zu erkennen. Eine Herausforderung dabei ist jedoch das Trainieren solcher KI-Modelle, da dafür große Mengen an Trainingsdaten inklusive diverser Schadensfälle benötigt werden, um eine hohe Genauigkeit und Zuverlässigkeit zu gewährleisten. Experimentelle Generierung dieser Daten ist wegen des enormen Zeit- und Kostenaufwands nicht möglich. Eine Alternative hierfür bieten die numerischen Simulationen, da dadurch Trainingsdaten für beliebige Anzahl an Schadenskonfigurationen erzeugt werden können. Das Hauptproblem dabei ist jedoch die Abweichung zwischen den experimentellen und simulierten Daten (durch z.B. Abweichungen bei der Geometrie, Randbedingungen oder Materialparameter). Um diese Abweichungen zu reduzieren bzw. zu eliminieren, wird ein KI-Modell mit einer Autoencoder-Decoder Architektur vorgestellt, die mittels eines Experiments kalibriert werden kann und anschließend in der Lage ist, die Genauigkeit der Simulationsergebnisse nachträglich zu erhöhen. T2 - 28. DEGA-Workshop „Physikalische Akustik“ - Maschinelles Lernen in der physikalischen Akustik CY - Bad Honnef, Germany DA - 19.10.2023 KW - KI KW - SHM KW - Simulation KW - Geführte Ultraschallwellen PY - 2023 AN - OPUS4-58686 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Yilmaz, Bengisu A1 - Heimann, Jan A1 - Mustapha, S. A1 - Charmi, Amir A1 - Prager, Jens T1 - Guided wave ultrasonic feature determination in Type IV composite overwrapped pressure vessels towards the digital twin N2 - The digitalization of quality control processes and the underlying data infrastructures for safety relevant components, such as hydrogen pressure vessels, plays a significant role in the transition towards Industry 4.0. In the current safety regulations for hydrogen pressure vessels, there is no established concept for structural health monitoring. The development of a reliable structural health monitoring methodology for monitoring the structural integrity of pressure vessels enables a fast-forward transition from personnel- and costintensive recurring inspections, a.k.a. periodic maintenance, to predictive maintenance. In the work presented; we investigated the application of ultrasonic guided wave propagation to monitor and assess the condition of Type IV composite overwrapped pressure vessel (COPV). A sensor network of fifteen piezo-electric wafers is placed on the carbon fibre reinforced composite cylinder. Five different artificial damage configurations are created by gluing two different weight blocks on three different locations. The database containing measured guided wave data sets is enriched by two different boundary conditions. We utilized an open-source software, openBIS labnotebook, to store and analyse experimental datasets. The guided wave ultrasonic signals were investigated and analysed by using commonly used ultrasonic features (e.g., amplitude, frequency, time of flight) as well as non-traditional time-series features (kurtosis, skewness, variance). The features were used to calculate damage index and the detection performance for the results has been evaluated. The results suggest that both traditional and non-traditional features assume significant importance in artificial damage detection. The future works will additionally involve the impacts of operational conditions, such as periodic pressure variations temperature loadings as well as material degradations. T2 - 13th European Conference on Non-Destructive Testing (ECNDT) CY - Lisbon, Portugal DA - 03.07.2023 KW - Industry 4.0 KW - Composite overwrapped pressure vessels KW - Structural health monitoring KW - Ultrasonic guided waves KW - Predictive maintenance PY - 2023 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:kobv:b43-591094 SN - 2941-4989 VL - 1 IS - 1 SP - 1 EP - 6 PB - NDT.net CY - Mayen, Germany AN - OPUS4-59109 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Yilmaz, Bengisu A1 - Heimann, Jan A1 - Mustapha, Samir A1 - Charmi, Amir A1 - Prager, Jens T1 - Guided wave ultrasonic features in composite overwrapped pressure vessels towards digital twin N2 - The digitalization of quality control processes and the underlying data infrastructures for safety relevant components, such as hydrogen pressure vessels, plays a significant role in the transition towards Industry 4.0. In the current safety regulations for hydrogen pressure vessels, there is no established concept for structural health monitoring. The development of a reliable structural health monitoring methodology for monitoring the structural integrity of pressure vessels enables a fast-forward transition from personnel- and costintensive recurring inspections, a.k.a. periodic maintenance, to predictive maintenance. In the work presented; we investigated the application of ultrasonic guided wave propagation to monitor and assess the condition of Type IV composite overwrapped pressure vessel (COPV). A sensor network of fifteen piezo-electric wafers is placed on the carbon fibre reinforced composite cylinder. Five different artificial damage configurations are created by gluing two different weight blocks on three different locations. The database containing measured guided wave data sets is enriched by two different boundary conditions. We utilized an open-source software, openBIS labnotebook, to store and analyse experimental datasets. The guided wave ultrasonic signals were investigated and analysed by using commonly used ultrasonic features (e.g., amplitude, frequency, time of flight) as well as non-traditional time-series features (kurtosis, skewness, variance). The features were used to calculate damage index and the detection performance for the results has been evaluated. The results suggest that both traditional and non-traditional features assume significant importance in artificial damage detection. The future works will additionally involve the impacts of operational conditions, such as periodic pressure variations temperature loadings as well as material degradations. T2 - European Conference on Non-Destructive Testing (ECNDT) 2023 CY - Lisbon, Portugal DA - 03.07.2023 KW - NDT4.0 KW - CComposite overwrapped pressure vessels KW - Structural health monitoring KW - Ultrasonic guided waves KW - Predictive maintenance PY - 2023 AN - OPUS4-57950 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Charmi, Amir T1 - Mechanical anisotropy of additively manufactured stainless steel 316l: an experimental and numerical study N2 - This work aims for a yield function description of additively manufactured (AM) parts of stainless steel 316L at the continuum-mechanical macro-scale by means of so-called virtual experiments using a crystal plasticity model at meso-scale. T2 - 1st Workshop on In-situ Monitoring and Microstructure Development in Additive Manufacturing CY - BAM, Berlin DA - 10.12.2020 KW - Anisotropy KW - Crystal plasticity KW - Additive manufacturing PY - 2020 AN - OPUS4-51941 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Charmi, Amir A1 - Falkenberg, Rainer A1 - Ávila, Luis A1 - Mohr, Gunther A1 - Sommer, Konstantin A1 - Ulbricht, Alexander A1 - Sprengel, Maximilian A1 - Saliwan Neumann, Romeo A1 - Evans, Alexander A1 - Skrotzki, Birgit T1 - Mechanical anisotropy of additively manufactured stainless steel 316L: An experimental and numerical study N2 - The underlying cause of mechanical anisotropy in additively manufactured (AM) parts is not yet fully understood and has been attributed to several different factors like microstructural defects, residual stresses, melt pool boundaries, crystallographic and morphological textures. To better understand the main contributing factor to the mechanical anisotropy of AM stainless steel 316L, bulk specimens were fabricated via laser powder bed fusion (LPBF). Tensile specimens were machined from these AM bulk materials for three different inclinations: 0◦, 45◦, and 90◦ relative to the build plate. Dynamic Young’s modulus measurements and tensile tests were used to determine the mechanical anisotropy. Some tensile specimens were also subjected to residual stress measurement via neutron diffraction, porosity determination with X-ray micro-computed tomography (μCT), and texture analysis with electron backscatter diffraction (EBSD). These investigations revealed that the specimens exhibited near full density and the detected defects were spherical. Furthermore, the residual stresses in the loading direction were between −74 ± 24 MPa and 137 ± 20 MPa, and the EBSD measurements showed a preferential ⟨110⟩ orientation parallel to the build direction. A crystal plasticity model was used to analyze the elastic anisotropy and the anisotropic yield behavior of the AM specimens, and it was able to capture and predict the experimental behavior accurately. Overall, it was shown that the mechanical anisotropy of the tested specimens was mainly influenced by the crystallographic texture. KW - Mechanical anisotropy KW - Residual stress KW - Crystal plasticity KW - Selective laser melting (SLM) KW - Laser beam melting (LBM) PY - 2021 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:kobv:b43-511719 SN - 0921-5093 VL - 799 SP - 140154 PB - Elsevier B.V. AN - OPUS4-51171 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Charmi, Amir T1 - Mechanical anisotropy of LPBF 316L: a modeling approach N2 - The underlying cause of mechanical anisotropy in additively manufactured (AM) parts is not yet fully understood and has been attributed to several different factors like microstructural defects, residual stresses, melt pool boundaries, crystallographic and morphological textures. To better understand the main contributing factor to the mechanical anisotropy of AM stainless steel 316L, bulk specimens were fabricated via laser powder bed fusion (LPBF). Tensile specimens were machined from these AM bulk materials for three different inclinations relative to the build plate. Dynamic Young's modulus measurements and tensile tests were used to determine the mechanical anisotropy. Some tensile specimens were also subjected to residual stress measurement via neutron diffraction, porosity determination with X-ray micro-computed tomography, and texture analysis with electron backscatter diffraction (EBSD). A crystal plasticity model was used to analyze the elastic anisotropy and the anisotropic yield behavior of the AM specimens, and it was able to capture and predict the experimental behavior accurately. Overall, it was shown that the mechanical anisotropy of the tested specimens was mainly influenced by the crystallographic texture. T2 - 2. Online-Workshop "In-situ Monitoring and Microstructure Development in Additive Manufactured Alloys " CY - Online meeting DA - 20.04.2021 KW - Anisotropy KW - Crystal plasticity KW - Additive manufacturing PY - 2021 AN - OPUS4-52603 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Heimann, Jan A1 - Yilmaz, Bengisu A1 - Charmi, Amir A1 - Duffner, Eric A1 - Schukar, Marcus A1 - Prager, Jens T1 - Structural Health Monitoring (SHM) for continuous monitoring of hydrogen pressure vessels N2 - While hydrogen is one of the most promising energy carriers, the safety of hydrogen storage technology remains one of the most important factors for technological and societal approval. While the engineering safety factors of the pressure vessels are kept high, the periodic inspection and the limited lifetime are making the application very costly considering manpower, time, money, and material waste. The development of an integrated structural health monitoring system can allow an easy transition from the current situation to cost-effective predictive maintenance. Hence, we propose to integrate three different SHM systems into hydrogen pressure vessels, namely guided wave ultrasonics, acoustic emission, and fibre optic sensing, to continuously monitor the condition and integrity. In this work, we evaluated the condition of a Type IV composite overwrapped pressure vessel using ultrasonic guided wave propagation. We mounted fifteen piezo-electric wafers on the composite cylinder by shaping three rings containing five sensors each. We acquired data from the sensor network following different boundary conditions with artificial damages on the selected locations. The data were evaluated with guided wave tomography techniques using ultrasonic features (amplitude, frequency, etc.) as well as artificial intelligence (AI). The results suggest that both traditional guided wave fusion techniques and AI-based characterization methods can detect artificial damages. In future work, it is planned to integrate acoustic emission and fibre optic sensing. Moreover, the measurement and the test results will be implemented into a digital twin to derive trends and make predictions on the damage propagation as well as the remaining useful lifetime. This work has received funding from German Ministry of Economic Affairs and Climate Actions within the QI-Digital initiative (www.qi-digital.de). T2 - SCHALL 23 CY - Wetzlar, Germany DA - 21.03.2023 KW - Structural Health Monitoring KW - Ultrasonic Guided Waves KW - Composite Overwrapped Pressure Vessel KW - Hydrogen PY - 2023 AN - OPUS4-58026 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -