https://fordatis.fraunhofer.de/handle/fordatis/100 2026-04-02T16:32:10Z 2026-04-02T16:32:10Z Mey, Oliver Neudeck, Willi Schneider, André Enge-Rosenblatt, Olaf https://fordatis.fraunhofer.de/handle/fordatis/151.3 2022-12-13T03:56:00Z 2020-03-25T00:00:00Z

Titel: Vibration Measurements on a Rotating Shaft at Different Unbalance Strengths Datenautorinnen und Datenautoren: Mey, Oliver; Neudeck, Willi; Schneider, André; Enge-Rosenblatt, Olaf Zusammenfassung: This dataset contains vibration data recorded on a rotating drive train. This drive train consists of an electronically commutated DC motor and a shaft driven by it, which passes through a roller bearing. With the help of a 3D-printed holder, unbalances with different weights and different radii were attached to the shaft. Besides the strength of the unbalances, the rotation speed of the motor was also varied. This dataset can be used to develop and test algorithms for the automatic detection of unbalances on drive trains. Datasets for 4 differently sized unbalances and for the unbalance-free case were recorded. The vibration data was recorded at a sampling rate of 4096 values per second. Datasets for development (ID "D[0-4]") as well as for evaluation (ID "E[0-4]") are available for each unbalance strength. The rotation speed was varied between approx. 630 and 2330 RPM in the development datasets and between approx. 1060 and 1900 RPM in the evaluation datasets. For each measurement of the development dataset there are approx. 107min of continuous measurement data available, for each measurement of the evaluation dataset 28min. Details of the recorded measurements and the used unbalance strengths are documented in the README.md file.; Dieser Datensatz enthält Vibrationsdaten, die an einem rotierenden Antriebsstrang aufgezeichnet wurden. Der Antriebsstrang besteht dabei aus einem elektronisch kommutierten Gleichstrommotor und einer von diesem angetriebenen Welle, die durch ein Wälzlager läuft. An der Welle wurden mithilfe eines 3D-gedruckten Halters Unwuchten mit verschiedenen Gewichten und an unterschiedlichen Radien befestigt. Neben der Stärke der Unwuchten wurde auch die Drehzahl des Motors variiert. Mit diesem Datensatz können Algorithmen für die automatische Erkennung von Unwuchten an Antriebssträngen entwickelt und getestet werden. Es wurden Datensätze für 4 unterschiedlich große Unwuchten und für den unwuchtfreien Fall aufgenommen. Die Vibrationsdaten wurden mit einer Abtastrate von 4096 Werten pro Sekunde aufgezeichnet. Für jede Unwuchtstärke stehen Datensätze sowohl für die Entwicklung (ID "D[0-4]") als auch für die Evaluation (ID "E[0-4]") von Klassifikationsmodellen zur Verfügung. Die Drehzahl wurde in den Entwicklungsdatensätzen zwischen ca. 630 und 2330 U/min und in den Auswertungsdatensätzen zwischen ca. 1060 und 1900 U/min variiert. Für jede Messung des Entwicklungsdatensatzes stehen ca. 107min an kontinuierlichen Messdaten zur Verfügung, für jede Messung des Evaluationsdatensatzes 28min. Details zu den aufgezeichneten Messungen und den verwendeten Unwuchtstärken sind in der Datei README.md dokumentiert.

2020-03-25T00:00:00Z Langer, Tim Hauke Widra, Matthias https://fordatis.fraunhofer.de/handle/fordatis/300 2022-12-09T02:30:24Z 2022-12-16T00:00:00Z

Titel: MillingVibes: 3-Axial Vibration Data of a Milling Process Performed by a Tooling Machine Datenautorinnen und Datenautoren: Langer, Tim Hauke; Widra, Matthias Zusammenfassung: This dataset contains 3-axial vibration data of an aluminium milling process recorded at a large industrial tooling machine (MAHO MH 800C). The data has been recorded by an enDAQ S5-E25D40 vibration sensor module. Each datapoint consists of 8000 samples (duration: 1 second) for 3-axial vibration data along x, y & z axis of the tooling machine. Each datapoint represents a segment of a 1-axial milling movement (+/-x, +/-y). The data is to be used for the investigation of process quality monitoring, therefore each signal segment has been assigned a label "1" (good) or "0" (bad). The label was given to all movements of a (partial) pattern by a domain expert, depending on the surface quality of the workpiece after milling.

2022-12-16T00:00:00Z Wicht, Jakob https://fordatis.fraunhofer.de/handle/fordatis/287.2 2022-12-08T02:30:30Z 2022-11-01T00:00:00Z

Titel: Spectrogram Data Set for Deep Learning Based RF-Frame Detection Datenautorinnen und Datenautoren: Wicht, Jakob Zusammenfassung: Automated spectrum analysis serves as a troubleshooting tool that helps to diagnose faults in wireless networks like difficult signal propagation conditions as well as coexisting wireless networks. It provides a higher monitoring coverage while requiring less expertise compared to manual spectrum analysis. In this publication, we introduce a data set that can be used to train and evaluate a deep learning model, capable to detect frames of different wireless standards as well as interference between single frames. Since manually labelling a high variety of frames in different environments is too challenging, an artificial data generation pipeline has been developed. The data set consists of 20000 augmented signal segments, each containing a random number of different Wi-Fi and Bluetooth frames, their spectral image representations and labels that describe the position and type of frame within the spectrogram. The dataset contains results of intermediate processing steps that enables the research or teaching community to create new datasets for specific requirements or to provide new interesting examination examples.

2022-11-01T00:00:00Z Mey, Oliver Schneider, André Enge-Rosenblatt, Olaf Yesnier, Bravo Stenzel, Pit https://fordatis.fraunhofer.de/handle/fordatis/215 2025-01-15T09:15:26Z 2021-01-01T00:00:00Z

Titel: Energy Consumption Curves of 499 Customers from Spain Datenautorinnen und Datenautoren: Mey, Oliver; Schneider, André; Enge-Rosenblatt, Olaf; Yesnier, Bravo; Stenzel, Pit Zusammenfassung: Predictions of energy consumption are crucial for energy retailers to minimize deviations from energy acquired in the day-ahead market and the actual consumption of their customers. The increasing spread of smartmeters means that retailers have access to hourly consumption values of all their contracted customers in realtime. Using machine learning algorithms, these hourly values can be used to calculate predictions for the future energy consumption of the customers. The present data set allows the training and validation of AI-based prediction models.

2021-01-01T00:00:00Z