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 - Assafo, Maryam A1 - Städter, Jost Philipp A1 - Meisel, Tenia A1 - Langendörfer, Peter T1 - On the Stability and Homogeneous Ensemble of Feature Selection for Predictive Maintenance: A Classification Application for Tool Condition Monitoring in Milling T2 - Sensors N2 - Feature selection (FS) represents an essential step for many machine learning-based predictive maintenance (PdM) applications, including various industrial processes, components, and monitoring tasks. The selected features not only serve as inputs to the learning models but also can influence further decisions and analysis, e.g., sensor selection and understandability of the PdM system. Hence, before deploying the PdM system, it is crucial to examine the reproducibility and robustness of the selected features under variations in the input data. This is particularly critical for real-world datasets with a low sample-to-dimension ratio (SDR). However, to the best of our knowledge, stability of the FS methods under data variations has not been considered yet in the field of PdM. This paper addresses this issue with an application to tool condition monitoring in milling, where classifiers based on support vector machines and random forest were employed. We used a five-fold cross-validation to evaluate three popular filter-based FS methods, namely Fisher score, minimum redundancy maximum relevance (mRMR), and ReliefF, in terms of both stability and macro-F1. Further, for each method, we investigated the impact of the homogeneous FS ensemble on both performance indicators. To gain broad insights, we used four (2:2) milling datasets obtained from our experiments and NASA’s repository, which differ in the operating conditions, sensors, SDR, number of classes, etc. For each dataset, the study was conducted for two individual sensors and their fusion. Among the conclusions: (1) Different FS methods can yield comparable macro-F1 yet considerably different FS stability values. (2) Fisher score (single and/or ensemble) is superior in most of the cases. (3) mRMR’s stability is overall the lowest, the most variable over different settings (e.g., sensor(s), subset cardinality), and the one that benefits the most from the ensemble. KW - classification KW - feature selection KW - homogeneous feature selection ensemble KW - predictive maintenance KW - milling KW - sensor fusion KW - stability of feature selection KW - tool condition monitoring Y1 - 2023 U6 - https://doi.org/10.3390/s23094461 SN - 1424-8220 VL - 23 IS - 9 ER - TY - GEN A1 - Meisel, Tenia A1 - Melnikov, Anton A1 - Alexander, Adrian A1 - Brändel, Tim A1 - Monsalve, Jorge M. A1 - Kaiser, Bert A1 - Schenk, Haral T1 - Directivity optimization of MEMS ultrasonic transducers by implementing acoustic horns T2 - Proceedings of the 24th International Congress on Acoustics, Gyeongju, Republic of Korea, 24–28 October 2022 N2 - The applications of microscopic ultrasonic transducers are often limited due to their non-optimal directivity pattern. The aim of this work is to design passive structures to adapt the directivity pattern to an intended application, e.g. range finder. The horns were designed and optimized using a Finite-Element-Method (FEM) model and manufactured by a conventional 3d-printing technique. The experimental validation was done using a novel MEMS-based ultrasonic transducer based on lateral actuation developed by Fraunhofer IPMS. This transducer type generates sound waves by displacing air inside a 3x3 mm² silicon chip using microscopic sized beams instead of using a diaphragm. This article presents several horn structures that exhibit a pronounced main lobe, inter alia an exponential horn and a folded horn with reduced overall dimensions, both optimized for an operatin g frequency of 40 kHz. We have shown numerically and experimentally that directivity properties of the transducer were significantly improved considering peak pressure, reduction of the side lobes and main lobe width by simple horn geometries. The implementation of the designed horns will enable additional applications where a specific directivity pattern is required. Furthermore, the given results imply th at the presented design strategies can be used to create various directivity patterns. KW - Acoustics KW - Acoustic horn KW - Directivity optimization KW - Ultrasonic transducer KW - Ultrasound Y1 - 2022 UR - https://www.researchgate.net/publication/365285295_Directivity_optimization_of_MEMS_ultrasonic_transducers_by_implementing_acoustic_horns ER -