Bearing Vibration Dataset of a Hydropower Project

<br>Twelve months of bearing vibration data acquired from the SCADA system installed at a Hydro Power Project Operating in<i> Pakistan,</i> having a total generation capacity of 969 MW. The number of units installed are four, each having a generation capacity of 242.25 MW. The data is recorded from the horizontal vibration runout system of the Turbine Guide Bearings installed at Unit No. 01. A fault had occurred in the Turbine Guide Bearings of Unit 01 during operation, hence the data contains both clean and faulty data points. Furthermore, the reason for acquiring twelve month data is to encompass both the lean water period where turbines face a lot of turbulence and the peak season where turbines normally operate seamlessly.The data has been used in the following research articlesAfridi, Yasir Saleem, et al. "A Fault Prognostic System for the Turbine Guide Bearings of a Hydropower Plant Using Long-Short Term Memory (LSTM)." <i>arXiv preprint arXiv:2407.19040</i> (2024)Afridi, Y.S.; Hasan, L.; Ullah, R.; Ahmad, Z.; Kim, J.-M. LSTM-Based Condition Monitoring and Fault Prognostics of Rolling Element Bearings Using Raw Vibrational Data. <i>Machines</i> <b>2023</b>, <i>11</i>, 531. https://doi.org/10.3390/machines11050531本数据集为巴基斯坦某运行中水电项目的数据采集与监视控制系统（Supervisory Control And Data Acquisition，简称SCADA）采集的12个月轴承振动数据，该项目总装机容量为969兆瓦，共安装4台机组，单台机组装机容量为242.25兆瓦。数据采集自1号机组的水轮机导轴承水平振动摆度系统。1号机组的水轮机导轴承在运行期间曾发生故障，因此本数据集同时包含正常与故障工况的数据样本。此外，本次采集12个月时长的数据，旨在覆盖水轮机面临较强紊流的枯水期，以及机组可平稳运行的发电高峰时段。该数据集已被应用于以下研究论文： Afridi, Yasir Saleem等人：《基于长短期记忆网络（Long Short-Term Memory，LSTM）的水电厂水轮机导轴承故障预测系统》，*arXiv预印本* arXiv:2407.19040（2024年） Afridi, Y.S.; Hasan, L.; Ullah, R.; Ahmad, Z.; Kim, J.-M.：《基于原始振动数据与长短期记忆网络的滚动轴承状态监测与故障预测》，*Machines*，2023年，第11卷，第531页，DOI：10.3390/machines11050531