TY - GEN A1 - Pechmann, Stefan A1 - Mai, Timo A1 - Völkel, Matthias A1 - Mahadevaiah, Mamathamba Kalishettyhalli A1 - Pérez, Eduardo A1 - Perez-Bosch Quesada, Emilio A1 - Reichenbach, Marc A1 - Wenger, Christian A1 - Hagelauer, Amelie T1 - A Versatile, Voltage-Pulse Based Read and Programming Circuit for Multi-Level RRAM Cells T2 - Electronics N2 - In this work, we present an integrated read and programming circuit for Resistive Random Access Memory (RRAM) cells. Since there are a lot of different RRAM technologies in research and the process variations of this new memory technology often spread over a wide range of electrical properties, the proposed circuit focuses on versatility in order to be adaptable to different cell properties. The circuit is suitable for both read and programming operations based on voltage pulses of flexible length and height. The implemented read method is based on evaluating the voltage drop over a measurement resistor and can distinguish up to eight different states, which are coded in binary, thereby realizing a digitization of the analog memory value. The circuit was fabricated in the 130 nm CMOS process line of IHP. The simulations were done using a physics-based, multi-level RRAM model. The measurement results prove the functionality of the read circuit and the programming system and demonstrate that the read system can distinguish up to eight different states with an overall resistance ratio of 7.9. KW - RRAM KW - Multilevel switching KW - Programming circuit Y1 - 2021 U6 - https://doi.org/10.3390/electronics10050530 SN - 2079-9292 VL - 10 IS - 5 ER - TY - GEN A1 - Pechmann, Stefan A1 - Mai, Timo A1 - Potschka, Julian A1 - Reiser, Daniel A1 - Reichel, Peter A1 - Breiling, Marco A1 - Reichenbach, Marc A1 - Hagelauer, Amelie T1 - A Low-Power RRAM Memory Block for Embedded, Multi-Level Weight and Bias Storage in Artificial Neural Networks T2 - Micromachines Y1 - 2021 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:29-opus4-174878 SN - 2072-666X VL - 12 IS - 11 ER - TY - GEN A1 - Suawa Fogou, Priscile A1 - Meisel, Tenia A1 - Jongmanns, Marcel A1 - Hübner, Michael A1 - Reichenbach, Marc T1 - Modeling and Fault Detection of Brushless Direct Current Motor by Deep Learning Sensor Data Fusion T2 - Sensors Y1 - 2022 U6 - https://doi.org/10.3390/s22093516 SN - 1424-8220 VL - 22 IS - 9 ER - TY - GEN A1 - Fritscher, Markus A1 - Knödtel, Johannes A1 - Mallah, Maen A1 - Pechmann, Stefan A1 - Perez-Bosch Quesada, Emilio A1 - Rizzi, Tommaso A1 - Wenger, Christian A1 - Reichenbach, Marc T1 - Mitigating the Effects of RRAM Process Variation on the Accuracy of Artifical Neural Networks T2 - Embedded Computer Systems: Architectures, Modeling, and Simulation. SAMOS 2021. Lecture Notes in Computer Science N2 - Weight storage is a key challenge in the efficient implementation of artificial neural networks. Novel memory technologies such as RRAM are able to greatly improve density and introduce non-volatility and multibit capabilities to this component of ANN accelerators. The usage of RRAM in this domain comes with downsides, mainly caused by cycle-to-cycle and device-to-device variability leading to erroneous readouts, greatly affecting digital systems. ANNs have the ability to compensate for this by their inherent redundancy and usually exhibit a gradual deterioration in the accuracy of the task at hand. This means, that slight error rates can be acceptable for weight storage in an ANN accelerator. In this work we link device-to-device variability to the accuracy of an ANN for such an accelerator. From this study, we can estimate how strongly a certain net is affected by a certain device parameter variability. This methodology is then used to present three mitigation strategies and to evaluate how they affect the reaction of the network to variability: a) Dropout Layers b) Fault-Aware Training c) Redundancy. These mitigations are then evaluated by their ability to improve accuracy and to lower hardware overhead by providing data for a real-word example. We improved this network’s resilience in such a way that it could tolerate double the variation in one of the device parameters (standard deviation of the oxide thickness can be 0.4 nm instead of 0.2 nm while maintaining sufficient accuracy.) KW - RRAM KW - memristive device KW - neural network Y1 - 2022 SN - 978-3-031-04579-0 SN - 978-3-031-04580-6 U6 - https://doi.org/10.1007/978-3-031-04580-6_27 SN - 0302-9743 SN - 1611-3349 SP - 401 EP - 417 PB - Springer ER - TY - GEN A1 - Hernandez, Hector Gerardo Muñoz A1 - Fricke, Florian A1 - Al Kadi, Muhammed A1 - Reichenbach, Marc A1 - Hübner, Michael T1 - Edge GPU based on an FPGA Overlay Architecture using PYNQ T2 - 35th SBC/SBMicro/IEEE/ACM Symposium on Integrated Circuits and Systems Design (SBCCI). 2022 Y1 - 2022 SN - 978-1-6654-8128-1 SN - 978-1-6654-8129-8 U6 - https://doi.org/10.1109/SBCCI55532.2022.9893229 ER - TY - GEN A1 - Suawa Fogou, Priscile A1 - Halbinger, Anja A1 - Jongmanns, Marcel A1 - Reichenbach, Marc T1 - Noise-Robust Machine Learning Models for Predictive Maintenance Applications T2 - IEEE Sensors Journal N2 - Predictive maintenance of equipment requires a set of data collected through sensors, from which models will learn behaviors that will allow the automatic detection or prediction of these behaviors. The objective is to anticipate unexpected situations such as sudden equipment stoppages. Industries are noisy environments due to production lines that involve a series of components. As a result, the data will always be obstructed by noise. Noise-robust predictive maintenance models, which include ensemble and deep learning models with and without data fusion, are proposed to enhance the monitoring of industrial equipment. The work reported in this article is based on two components, a milling tool, and a motor, with sound, vibration, and ultrasound data collected in real experiments. Four main tasks were performed, namely the construction of the datasets, the training of the monitoring models without adding artificial noise to the data, the evaluation of the robustness of the previously trained models by injecting several levels of noise into the test data, and the optimization of the models by a proposed noisy training approach. The results show that the models maintain their performances at over 95% accuracy despite adding noise in the test phase. These performances decrease by only 2% at a considerable noise level of 15-dB signal-to-noise ratio (SNR). The noisy training method proved to be an optimal solution for improving the noise robustness and accuracy of convolutional deep learning models, whose performance regression of 2% went from a noise level of 28 to 15 dB like the other models. KW - Accelerometer Y1 - 2023 UR - https://ieeexplore.ieee.org/document/10122864 U6 - https://doi.org/10.1109/JSEN.2023.3273458 SN - 1558-1748 SN - 1530-437X VL - 23 IS - 13 SP - 15081 EP - 15092 ER - TY - GEN A1 - Assafo, Maryam A1 - Lautsch, Martin A1 - Suawa, Priscile Fogou A1 - Jongmanns, Marcel A1 - Hübner, Michael A1 - Reichenbach, Marc A1 - Brockmann, Carsten A1 - Reinhardt, Denis A1 - Langendörfer, Peter T1 - The ForTune Toolbox: Building Solutions for Condition-Based and Predictive Maintenance Focusing on Retrofitting Y1 - 2023 SN - 978-3-8007-6204-0 SN - 978-3-8007-6203-3 N1 - Poster, Tagungsband MikroSystemTechnik Kongress 2023, Dresden, 23. - 25. Oktober 2023 SP - S. 541 PB - VDE Verlag CY - Berlin ER - TY - GEN A1 - Fricke, Florian A1 - Scharoba, Stefan A1 - Rachuj, Sebastian A1 - Konopik, Andreas A1 - Kluge, Florian A1 - Hofstetter, Georg A1 - Reichenbach, Marc ED - Orailoglu, Alex ED - Reichenbach, Marc ED - Jung, Matthias T1 - Application Runtime Estimation for AURIX Embedded MCU Using Deep Learning  T2 - Embedded computer systems : architectures, modeling, and simulation : 22nd International Conference, SAMOS 2022, Samos, Greece, July 3-7, 2022, proceedings Y1 - 2022 SN - 978-3-031-15073-9 SN - 978-3-031-15074-6 U6 - https://doi.org/10.1007/978-3-031-15074-6_15 SP - 235 EP - 249 PB - Springer CY - Cham ER - TY - GEN A1 - Mahmood, Safdar A1 - Scharoba, Stefan A1 - Schorlemer, Jonas A1 - Schulz, Christian A1 - Hübner, Michael A1 - Reichenbach, Marc T1 - Detecting Improvised Land-mines using Deep Neural Networks on GPR Image Dataset targeting FPGAs  T2 - IEEE Nordic Circuits and Systems Conference (NORCAS), 25-26 October 2022, Oslo, Norway Y1 - 2022 SN - 979-8-3503-4550-6 SN - 979-8-3503-4551-3 U6 - https://doi.org/10.1109/norcas57515.2022.9934735 SP - 1 EP - 7 PB - IEEE CY - Piscataway, NJ ER - TY - GEN A1 - Mahmood, Safdar A1 - Hübner, Michael A1 - Reichenbach, Marc ED - Palumbo, Francesca ED - Keramidas, Georgios ED - Voros, Nikolaos ED - Diniz, Pedro C. T1 - A Design-Space Exploration Framework for Application-Specific Machine Learning Targeting Reconfigurable Computing T2 - Applied Reconfigurable Computing. Architectures, Tools, and Applications, 19th International Symposium, ARC 2023, Cottbus, Germany, September 27-29, 2023 Y1 - 2023 SN - 978-3-031-42921-7 SN - 978-3-031-42920-0 U6 - https://doi.org/10.1007/978-3-031-42921-7_27 SP - 371 EP - 374 PB - Springer CY - Cham ER -