Dataset concerning the vibration signals from wind turbines in northern Sweden Dataset of A dictionary learning approach to monitoring of wind turbine drivetrain bearings Dataset concerning the vibration signals from wind turbines in northern Sweden 2024-248-1 https://doi.org/10.5878/bcmv-wq08 Swedish National Data Service Svensk nationell datatjänst Landing page Dataset concerning the vibration signals from wind turbines in northern Sweden Dataset of A dictionary learning approach to monitoring of wind turbine drivetrain bearings Dataset concerning the vibration signals from wind turbines in northern Sweden 2024-248-1 https://doi.org/10.5878/bcmv-wq08 oai:DiVA.org:ltu-63111 urn:nbn:se:ltu:diva-63111 10.2991/ijcis.d.201105.001 Martin del Campo Barraza, Sergio Martin del Campo Barraza, Sergio Sandin, Fredrik Sandin, Fredrik Strömbergsson, Daniel Strömbergsson, Daniel Swedish National Data Service Svensk nationell datatjänst Landing page In the manuscript, we investigate condition monitoring methods based on unsupervised dictionary learning. The dataset includes the raw time-domain vibration signals from six turbines within the same wind farm (near geographical location). All the wind turbines are of the same type and possess a three-stage gearbox. All measurement data corresponds to the axial direction of an accelerometer mounted on the housing of the output shaft bearing of each turbine. The sampling rate is 12.8 kilosamples/second and each signal segment is 1.28 seconds long (16384 samples). There are six files, which contains the vibration data from each of the six wind turbines. Within each file, each row corresponds to a different measurement. Furthermore, the first column represents the time expressed in years since the vibration data started to be recorded. The second column is the speed expressed in cycles per minute. The remaining columns are the vibration signal time series expressed in Gs. The dataset was originally published in DiVA and moved to SND in 2024. In the manuscript, we investigate condition monitoring methods based on unsupervised dictionary learning. The dataset includes the raw time-domain vibration signals from six turbines within the same wind farm (near geographical location). All the wind turbines are of the same type and possess a three-stage gearbox. All measurement data corresponds to the axial direction of an accelerometer mounted on the housing of the output shaft bearing of each turbine. The sampling rate is 12.8 kilosamples/second and each signal segment is 1.28 seconds long (16384 samples). There are six files, which contains the vibration data from each of the six wind turbines. Within each file, each row corresponds to a different measurement. Furthermore, the first column represents the time expressed in years since the vibration data started to be recorded. The second column is the speed expressed in cycles per minute. The remaining columns are the vibration signal time series expressed in Gs. Datasetet har ursprungligen publicerats i DiVA och flyttades över till SND 2024. Numeric Access to data through SND. Data are freely accessible. Åtkomst till data via SND. Data är fritt tillgängliga. openAccess Martin-del-Campo, S., Sandin, F., & Strömbergsson, D. (2021). Dictionary Learning Approach to Monitoring of Wind Turbine Drivetrain Bearings. In International Journal of Computational Intelligence Systems (Vol. 14, Issue 1, pp. 106–121). https://doi.org/10.2991/ijcis.d.201105.001 Martin-del-Campo, S., Sandin, F., & Strömbergsson, D. (2021). Dictionary Learning Approach to Monitoring of Wind Turbine Drivetrain Bearings. In International Journal of Computational Intelligence Systems (Vol. 14, Issue 1, pp. 106–121). https://doi.org/10.2991/ijcis.d.201105.001 urn:nbn:se:ltu:diva-63111 10.2991/ijcis.d.201105.001 oai:DiVA.org:ltu-63111 2021 oai:DiVA.org:ltu-63111