{"id":"vmyg4yp3s8","doi":{"id":"10.17632/vmyg4yp3s8.2","status":"allocated","prefix":"10.17632"},"name":" Description of the SCADA dataset of an onshore La Houte Bourne wind farm in Villeneuve-d’Ascq, France","description":"1. Dataset Overview\nThis dataset contains Supervisory Control and Data Acquisition (SCADA) measurements collected from an onshore wind farm located in Villeneuve-d’Ascq, France, over eight years (from 1 January 2013 to 31 December 2020). The wind farm has four wind turbines of the MM82 model, manufactured by Senvion. Those wind turbines are labeled as R80736, R80721, R80711, and R80790. The rated power of each turbine is 2 MW. Each wind turbine at the wind farm has a nominal power of 2050 kW, a cut-in wind speed of 4 m/s, and a cut-out wind speed of 22 m/s. The blade length and hub height are 40 m and 80 m, respectively. \n\nThere were 34 process parameters measured at an interval of 10 min for each wind turbine (WT), and in total 1,057,868 samples were recorded. The dataset includes many parameters, such as wind speed, absolute wind direction, outdoor temperature, rotor bearing temperature, gearbox bearing temperature, generator bearing temperature, gearbox oil sump temperature, generator speed, generated power, torque, grid voltage, grid frequency, vane position, pitch angle, and more. For each parameter, the average value, standard deviation, maximum, and minimum values were collected at every interval. \n\nDuring the period from 1 January 2013 to 31 December 2016, the gearbox bearing temperature of the R80721 wind turbine reached a maximum value of 84.12°C at the data sample 70,995. This unusually high temperature indicates a failure of the gearbox bearing associated with the high-speed shaft, which was recorded on 2 January 2015 at 08:50. \nThe SCADA system records turbine operational parameters continuously and stores aggregated measurements for monitoring and performance analysis. The data include operational measurements recorded from wind turbines and can be used for research in wind turbine performance analysis, condition monitoring, and fault detection methods.\nThe raw SCADA dataset for the La Haute Borne Wind Farm was previously available at the link: https://www.engie.com/en/activities/renewable-energies/wind-energy. However, the dataset is currently no longer accessible online. To ensure continued access to the data, we have uploaded the SCADA dataset covering the period from 2013 to 2018. The dataset has been cleaned and preprocessed, and the resulting data are provided in the section below. A preprocessing step was conducted to eliminate erroneous samples present in the raw data. The data cleaning and preprocessing process involved removing missing, corrupted values, and negative power values. The preprocessing was performed using the method described in the paper at the link: https://doi.org/10.3390/en18225954. Dataset format: CSV (semicolon-separated values).  \n\n","version":2,"contributors":[{"institution":{"id":"ab38918f-5ba5-4fad-9dad-85858382c03c","name":"AGH University of Krakow","ror_id":"https://ror.org/00bas1c41"},"profile_id":"75abdf84-1074-4e88-8d9d-97841e518870","first_name":"Debela","last_name":"TeKlemariyem","orcid_id":"0000-0003-4948-9284"},{"institution":{"id":"ab38918f-5ba5-4fad-9dad-85858382c03c","name":"AGH University of Krakow","ror_id":"https://ror.org/00bas1c41"},"profile_id":"a2250a49-6c09-4c10-b89d-7152892aa75a","first_name":"Nasir Hussain Razvi","last_name":"Syed","orcid_id":"0009-0007-3014-9235"},{"institution":{"id":"ab38918f-5ba5-4fad-9dad-85858382c03c","name":"AGH University of Krakow","ror_id":"https://ror.org/00bas1c41"},"profile_id":"c0826947-b1ab-4f23-b943-1c7e017e24f3","first_name":"ABU AL","last_name":"HASSAN","orcid_id":"0000-0002-8284-9125"},{"institution":{"id":"ab38918f-5ba5-4fad-9dad-85858382c03c","name":"AGH University of Krakow","ror_id":"https://ror.org/00bas1c41"},"profile_id":"8bb720f9-c613-49ad-a364-e84e16dbd641","first_name":"Krzysztof","last_name":"Kijanowski","orcid_id":"0009-0008-9943-754X"},{"institution":{"id":"ab38918f-5ba5-4fad-9dad-85858382c03c","name":"AGH University of Krakow","ror_id":"https://ror.org/00bas1c41"},"first_name":"Tomasz ","last_name":"Barszcz","orcid_id":"0000-0002-1656-4930"},{"institution":{"id":"ab38918f-5ba5-4fad-9dad-85858382c03c","name":"AGH University of Krakow","ror_id":"https://ror.org/00bas1c41"},"first_name":"Wieslaw ","last_name":"J. Staszewski","orcid_id":"0000-0003-3071-7427"},{"institution":{"id":"ab38918f-5ba5-4fad-9dad-85858382c03c","name":"AGH University of Krakow","ror_id":"https://ror.org/00bas1c41"},"profile_id":"a5241969-a4d4-4f68-bafa-a930c63a3242","first_name":"Phong","last_name":"Dao","orcid_id":"0000-0002-9211-5619"}],"files":[{"filename":"SCADA dataset of the Engie La Haute Borne wind farm _onshore_ in France.zip","id":"143e95a2-e5ee-4d58-b955-f825d1f2b78e","content_details":{"id":"4d68ceda-e962-4d02-8c33-4e6ada44a642","sha256_hash":"2291f5c6c9016b5f48543bf212567bf1690cc54db19b354683479ed1145ec9f9","content_type":"application/x-zip-compressed","size":77066903,"created_date":"2026-08-28T11:18:03.532Z","download_url":"https://data.mendeley.com/public-files/datasets/vmyg4yp3s8/files/143e95a2-e5ee-4d58-b955-f825d1f2b78e/file_downloaded","view_url":"https://data.mendeley.com/public-files/datasets/vmyg4yp3s8/files/143e95a2-e5ee-4d58-b955-f825d1f2b78e/file_viewed","download_expiry_time":"2126-09-15T02:48:45.055997559Z"},"metrics":{"downloads":0,"previews":0},"size":77066903,"status":"COMPLETED"}],"versions":[{"version":2,"available":true,"publish_date":"2026-09-01T12:55:05.669Z"},{"version":1,"available":true,"publish_date":"2026-03-16T22:56:04.107Z"}],"articles":[],"categories":[{"id":"data.elsevier.com/vocabulary/OmniScience/Concept-191545042","label":"Wind Energy"},{"id":"data.elsevier.com/vocabulary/OmniScience/Concept-191545048","label":"Wind Turbine"},{"id":"data.elsevier.com/vocabulary/OmniScience/Concept-253440139","label":"Renewable Energy"},{"id":"data.elsevier.com/vocabulary/OmniScience/Concept-601751003","label":"Condition-Based Maintenance"}],"institutions":[{"id":"ab38918f-5ba5-4fad-9dad-85858382c03c","name":"AGH University of Krakow","ror_id":"https://ror.org/00bas1c41"}],"metrics":{"views":0,"file_downloads":0,"file_previews":0},"available":true,"method":"The following steps can be followed to reproduce.\ni. Import the dataset file using a data analysis environment such as R, Python, or MATLAB.\nii. Perform exploratory data analysis (EDA): Examine key operational variables such as wind speed, power output, rotor speed, generator speed, and temperature measurements. Visualization tools such as time-series plots and correlation matrices can help identify operational patterns.\niii. Identify turbine operational states: Compare turbines under healthy and faulty conditions to understand variations in their operational behavior.\niv. You can apply statistical monitoring methods using approaches such as cointegration analysis, the Augmented Dickey–Fuller (ADF) test, and the Wilcoxon rank-sum test, or other condition monitoring algorithms to evaluate turbine operational behavior. These techniques can help identify deviations from normal turbine behavior, and these methods are available at the link below for interested readers. Different methods, as shown in the references below [1 - 4], have been developed and published using the attached SCADA dataset, including the cleaning and preprocessing procedures applied to the dataset as discussed in reference [5].\n\nRelated published papers:\n1. Dao, P. B., Barszcz, T., & Staszewski, W. J. (2024). Anomaly detection of wind turbines based on stationarity analysis of SCADA data. Renewable Energy, 232. https://doi.org/10.1016/j.renene.2024.121076\n2. Dao, P. B. (2022). On Wilcoxon rank sum test for condition monitoring and fault detection of wind turbines. Applied Energy, 318. https://doi.org/10.1016/j.apenergy.2022.119209 \n3. Dao, P. B. (2023). On Cointegration Analysis for Condition Monitoring and Fault Detection of Wind Turbines Using SCADA Data. Energies, 16(5). https://doi.org/10.3390/en16052352 \n4. Knes, P., & Dao, P. B. (2024). Machine Learning and Cointegration for Wind Turbine Monitoring and Fault Detection: From a Comparative Study to a Combined Approach. Energies, 17(20), 5055. https://doi.org/10.3390/en17205055\n5. Kijanowski, K.; Barszcz, T.; Dao, P.B. A Cluster-Based Filtering Approach to SCADA Data Preprocessing for Wind Turbine Condition Monitoring and Fault Detection. Energies 2025, 18, 5954. https://doi.org/10.3390/en18225954\n","size":77066903,"owner":{"institution":{"id":"ab38918f-5ba5-4fad-9dad-85858382c03c","name":"AGH University of Krakow","ror_id":"https://ror.org/00bas1c41"},"profile_id":"75abdf84-1074-4e88-8d9d-97841e518870","first_name":"Debela","last_name":"TeKlemariyem","orcid_id":"0000-0003-4948-9284"},"channel":"WEB","owner_id":"75abdf84-1074-4e88-8d9d-97841e518870","publish_date":"2026-09-01T12:55:05.669Z","data_licence":{"id":"01d9c749-3c4d-4431-9df3-620b2dcfe144","description":"You can share, copy and modify this dataset so long as you give appropriate credit, provide a link to the CC BY license, and indicate if changes were made, but you may not do so in a way that suggests the rights holder has endorsed you or your use of the dataset. Note that further permission may be required for any content within the dataset that is identified as belonging to a third party.","url":"http://creativecommons.org/licenses/by/4.0","category":"Creative","short_name":"CC BY 4.0","full_name":"Creative Commons Attribution 4.0 International"},"related_links":[{"type":"dataset","rel":"compiles","href":"https://www.engie.com/en/activities/renewable-energies/wind-energy"},{"type":"article","rel":"related_to","href":"https://www.sciencedirect.com/science/article/pii/S0960148124011443"},{"type":"article","rel":"related_to","href":"https://www.sciencedirect.com/science/article/pii/S0306261922005748"},{"type":"article","rel":"related_to","href":"https://www.mdpi.com/1996-1073/17/20/5055"},{"type":"article","rel":"related_to","href":"https://www.mdpi.com/1996-1073/16/5/2352"},{"type":"article","rel":"related_to","href":"https://doi.org/10.3390/en19051169"},{"type":"article","rel":"related_to","href":"https://www.mdpi.com/2311-5521/7/12/371"},{"type":"article","rel":"related_to","href":"https://ieeexplore.ieee.org/document/9208852"},{"type":"article","rel":"related_to","href":"https://doi.org/10.1177/14759217261466147"},{"type":"article","rel":"related_to","href":"https://doi.org/10.3390/en19153696"}],"funders":[{"identity":"https://ror.org/03ha2q922","grant_id":"UMO-2023/51/B/ST8/01253, Non-classical Approaches for Condition Monitoring and Fault Detection of Wind Turbines, financed by the National Science Centre, Poland.","name":"National Science Centre","location":"Krakow"}],"customer_id":"7377952c-6404-4428-bbfc-77242cfc301e","modified_on":"2026-08-28T11:45:34.521Z","created_on":"2026-03-07T12:31:40.392Z","confidential":false,"links":{"view":"https://data.mendeley.com/datasets/vmyg4yp3s8"},"repository":{"id":"MENDELEY_DATA","name":"Mendeley Data"}}