Langanzeige der Metadaten
DC ElementWertSprache
dc.contributor.authorMey, Oliver-
dc.contributor.authorSchneider, André-
dc.contributor.authorEnge-Rosenblatt, Olaf-
dc.contributor.authorMayer, Dirk-
dc.contributor.authorSchmidt, Christian-
dc.contributor.authorKlein, Samuel-
dc.contributor.authorHerrmann, Hans-Georg-
dc.date.accessioned2021-06-08T11:16:26Z-
dc.date.available2021-06-08T11:16:26Z-
dc.date.issued2021-05-31-
dc.identifier.urihttps://fordatis.fraunhofer.de/handle/fordatis/205-
dc.identifier.urihttp://dx.doi.org/10.24406/fordatis/132-
dc.description.abstractEarly damage detection and classification by condition monitoring systems is crucial to enable predictive maintenance of manufacturing systems and industrial facilities. The data analysis can be improved by applying machine learning algorithms and fusion of data from heterogeneous sensors. The paper (see <REFERENCE>) presents an approach for a step-wise integration of classifications gained from vibration and acoustic emission sensors, in order to combine the information from signals acquired in the low and high frequency range. A test rig comprising a drive train and bearings with small artificial damages is used for acquisition of experimental data. The results indicate that an improvement of damage classification can be obtained using the proposed algorithm of combining classifiers for vibrations and acoustic emission. This dataset contains vibration data as well as acoustic emission data recorded on a rotating drive train. For vibration measurements, the setup is instrumented with ICP accelerometers (PCB 607A11, 100 mV/g) at the bearing holder frame of the motor and the bearing holder frame of the shaft. Both vibrational sensors are digitized by a DT 9837A USB-DAQ from (Measurement Computing GmbH). This 4-channel signal analyzer is equipped with a 24-bit ADC, that supports sample rates of up to 100 kSPS and is well suited for the vibration measurements. Acoustic emission signals (AE) are acquired by a piezo transducer (Vallen VS30V, 20 kHz – 80 kHz) connected to an AEP5 pre-amplifier for signal conditioning. These signals are digitized with an USB oscilloscope (PicoScope 2204A). This entry-level 2-channel oscilloscope features an 8-bit ADC with sample rates of up to 100 MSPS with an analog bandwidth of 10 MHz.en
dc.language.isoenen
dc.relation.isreferencedbyhttps://github.com/deepinsights-analytica/mdpi-arci2021-paper-
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en
dc.subjectCondition monitoring, Vibration, Acoustic emission, Drive train, Data fusion, Machine learning, Deep learningen
dc.subject.ddcDDC::600 Technik, Medizin, angewandte Wissenschaftenen
dc.titleCondition Monitoring of Drive Trains by Data Fusion of Acoustic Emission and Vibration Sensorsen
dc.title.alternativeMeasurements of Vibrations and Acoustic Emissions on a Rotating Shaften
dc.typeTabular Dataen
dc.contributor.funderFraunhofer-Gesellschaft FhGen
dc.description.technicalinformationThis dataset was published in connection with some Jupyter notebooks. The notebooks are freely available via Github (https://github.com/deepinsights-analytica/mdpi-arci2021-paper) and contain examples for reading, analyzing, classifying and visualizing the data. The dataset contains the measured raw data (data/<measurement>/<sensor>.csv) as well as metadata that describes the vibration and acoustic emission sensors (sensors/<sensor>.json) and the configuration of all measurements (measurements/<measurement>.json). A total of 29 measurements are included. For each measurement the the file vb.csv contains the vibration data: a timestamp in the first column followed by 8192 sensor values. It is sampled with a sampling rate of 8192 Hz. One line thus corresponds to a measurement time of one second. The ae.csv files with the acoustic emission data also contain a timestamp in the first column followed by 8000 sensor values. It is sampled at a sampling rate of 390625Hz. One line therefore corresponds to a measurement time of 20.48 ms. A file w.csv with the speeds was also recorded for each measurement. These files contain the time frames (begin and end timestamp) for the five rotational speeds: 600rpm, 1000rpm, 1400rpm, 1800rpm, 2200rpm). While the measurement for the vibration and the acoustic emission was carried out continuously for the different speeds, the phases with an almost constant speed can be extracted with the help of the time ranges based on the w.csv files.en
fordatis.groupMikroelektroniken
fordatis.instituteIZFP Fraunhofer-Institut für Zerstörungsfreie Prüfverfahrenen
fordatis.instituteIIS Fraunhofer-Institut für Integrierte Schaltungen - Institutsteil Entwicklung Adaptiver Systeme EASen
fordatis.project.fhgid600003en
fordatis.rawdatatrueen
fordatis.sponsorship.projectnameSkalierbare Sensornetzwerke für Condition Monitoringen
fordatis.sponsorship.projectacronymSKALISENSen
fordatis.date.start2021-03-25-
fordatis.date.end2021-05-31-
Enthalten in den Sammlungen:IIS Fraunhofer-Institut für Integrierte Schaltungen - Institutsteil Entwicklung Adaptiver Systeme EAS

Dateien zu dieser Ressource:
Datei Beschreibung GrößeFormat 
fraunhofer_iis_eas_dataset_vibrations_acoustic_emissions_of_drive_train_v1.ziptimeseries data (csv format) and metadata for sensors and measurements (json format)1,69 GBZIP (compressed CSV files)Öffnen/Download


Diese Ressource wurde unter folgender Copyright-Bestimmung veröffentlicht: Lizenz von Creative Commons Creative Commons