{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:04:58Z","timestamp":1765357498681,"version":"build-2065373602"},"reference-count":65,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2020YFB1709700"],"award-info":[{"award-number":["2020YFB1709700"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In order to solve low-quality problems such as data anomalies and missing data in the condition monitoring data of hydropower units, this paper proposes a monitoring data quality enhancement method based on HDBSCAN-WSGAIN-GP, which improves the quality and usability of the condition monitoring data of hydropower units by combining the advantages of density clustering and a generative adversarial network. First, the monitoring data are grouped according to the density level by the HDBSCAN clustering method in combination with the working conditions, and the anomalies in this dataset are detected, recognized adaptively and cleaned. Further combining the superiority of the WSGAIN-GP model in data filling, the missing values in the cleaned data are automatically generated by the unsupervised learning of the features and the distribution of real monitoring data. The validation analysis is carried out by the online monitoring dataset of the actual operating units, and the comparison experiments show that the clustering contour coefficient (SCI) of the HDBSCAN-based anomaly detection model reaches 0.4935, which is higher than that of the other comparative models, indicating that the proposed model has superiority in distinguishing between the valid samples and anomalous samples. The probability density distribution of the data filling model based on WSGAIN-GP is similar to that of the measured data, and the KL dispersion, JS dispersion and Hellinger\u2019s distance of the distribution between the filled data and the original data are close to 0. Compared with the filling methods such as SGAIN, GAIN, KNN, etc., the effect of data filling with different missing rates is verified, and the RMSE error of data filling with WSGAIN-GP is lower than that of other comparative models. The WSGAIN-GP method has the lowest RMSE error under different missing rates, which proves that the proposed filling model has good accuracy and generalization, and the research results in this paper provide a high-quality data basis for the subsequent trend prediction and state warning.<\/jats:p>","DOI":"10.3390\/s24010118","type":"journal-article","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T22:59:09Z","timestamp":1703545149000},"page":"118","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Enhancement Methods of Hydropower Unit Monitoring Data Quality Based on the Hierarchical Density-Based Spatial Clustering of Applications with a Noise\u2013Wasserstein Slim Generative Adversarial Imputation Network with a Gradient Penalty"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3054-4517","authenticated-orcid":false,"given":"Fangqing","family":"Zhang","sequence":"first","affiliation":[{"name":"Intelligent Power Equipment Technology Research Center, Wuhan University, Wuhan 430072, China"},{"name":"School of Power and Mechanical Engineering, Wuhan University, Wuhan 430072, China"}]},{"given":"Jiang","family":"Guo","sequence":"additional","affiliation":[{"name":"Intelligent Power Equipment Technology Research Center, Wuhan University, Wuhan 430072, China"},{"name":"School of Power and Mechanical Engineering, Wuhan University, Wuhan 430072, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2812-4211","authenticated-orcid":false,"given":"Fang","family":"Yuan","sequence":"additional","affiliation":[{"name":"Intelligent Power Equipment Technology Research Center, Wuhan University, Wuhan 430072, China"},{"name":"School of Power and Mechanical Engineering, Wuhan University, Wuhan 430072, China"}]},{"given":"Yuanfeng","family":"Qiu","sequence":"additional","affiliation":[{"name":"School of Water Resources and Hydropower Engineering, Wuhan University, Wuhan 430072, China"}]},{"given":"Pei","family":"Wang","sequence":"additional","affiliation":[{"name":"Intelligent Power Equipment Technology Research Center, Wuhan University, Wuhan 430072, China"},{"name":"School of Power and Mechanical Engineering, Wuhan University, Wuhan 430072, China"}]},{"given":"Fangjuan","family":"Cheng","sequence":"additional","affiliation":[{"name":"Intelligent Power Equipment Technology Research Center, Wuhan University, Wuhan 430072, China"},{"name":"School of Power and Mechanical Engineering, Wuhan University, Wuhan 430072, China"}]},{"given":"Yifeng","family":"Gu","sequence":"additional","affiliation":[{"name":"Intelligent Power Equipment Technology Research Center, Wuhan University, Wuhan 430072, China"},{"name":"School of Power and Mechanical Engineering, Wuhan University, Wuhan 430072, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,12,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.future.2021.09.033","article-title":"Handling missing data in near real-time environmental monitoring: A system and a review of selected methods","volume":"128","author":"Zhang","year":"2022","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_2","first-page":"141","article-title":"Improved K-means based anomaly data detection for wind turbine","volume":"42","author":"Tao","year":"2023","journal-title":"For. Electron. Meas. Technol."},{"key":"ref_3","first-page":"91","article-title":"Anomaly detection of distribution network voltage data based on improved K-means clustering k-value selection algorithm","volume":"37","author":"Liu","year":"2022","journal-title":"Electr. Power Sci. Technol."},{"key":"ref_4","first-page":"84","article-title":"Anomalous dynamic data detection method for smart meters based on k-means clustering","volume":"31","author":"Liu","year":"2023","journal-title":"Electron. Des. Eng."},{"key":"ref_5","first-page":"50","article-title":"Research on clustering optimization algorithm for high-dimensional power data","volume":"37","author":"Liu","year":"2021","journal-title":"Sci. Technol. Bull."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"120396","DOI":"10.1016\/j.apenergy.2022.120396","article-title":"Federated fuzzy k-means for privacy-preserving behavior analysis in smart grids","volume":"331","author":"Wang","year":"2023","journal-title":"Appl. Energy"},{"key":"ref_7","first-page":"430","article-title":"A method for recognizing station-household relationship based on discrete wavelet transform and fuzzy K-mean clustering","volume":"37","author":"Li","year":"2022","journal-title":"Electr. Power."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"012059","DOI":"10.1088\/1742-6596\/2355\/1\/012059","article-title":"Smart Grid Demand-side Response Model Based on Fuzzy Clustering Analysis","volume":"2355","author":"Li","year":"2022","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"104769","DOI":"10.1016\/j.imavis.2023.104769","article-title":"Deep robust multi-channel learning subspace clustering networks","volume":"137","author":"Fang","year":"2023","journal-title":"Image Vis. Comput."},{"key":"ref_10","first-page":"10","article-title":"Adaptive weighted multi-view subspace clustering algorithm based on latent representation","volume":"19","author":"Liu","year":"2023","journal-title":"Comput. Knowl. Technol."},{"key":"ref_11","first-page":"207","article-title":"Multi-view subspace clustering algorithm based on information entropy weighting","volume":"41","author":"Li","year":"2023","journal-title":"J. Shaanxi Univ. Sci. Technol."},{"key":"ref_12","first-page":"357","article-title":"Anomaly detection algorithm based on SSC-BP neural network","volume":"48","author":"Shi","year":"2021","journal-title":"Comput. Sci."},{"key":"ref_13","first-page":"67","article-title":"A non-intrusive load identification method based on Mean-shift clustering and twin networks","volume":"52","author":"Shi","year":"2022","journal-title":"Electr. Drives"},{"key":"ref_14","first-page":"63","article-title":"Partial discharge anomaly detection in switchgear based on mean-drift clustering","volume":"52","author":"Li","year":"2022","journal-title":"Electr. Drives"},{"key":"ref_15","first-page":"90","article-title":"A collaborative filtering recommendation algorithm incorporating PCA dimensionality reduction and mean drift clustering","volume":"03","author":"Xiang","year":"2023","journal-title":"J. Nanjing Univ. Posts Telecommun. Nat. Sci. Ed."},{"key":"ref_16","first-page":"59","article-title":"A method for assessing the impact of large-scale new energy on power grid line loss based on Mean-shift clustering","volume":"38","author":"Chen","year":"2021","journal-title":"Power Supply"},{"key":"ref_17","first-page":"152","article-title":"Research on dissimilarity rejection method for passive direction finding accuracy test","volume":"15","author":"Zhang","year":"2019","journal-title":"Syst. Simul. Technol."},{"key":"ref_18","first-page":"96","article-title":"Temperature and humidity detection system based on Leyet criterion and data fusion","volume":"33","author":"Wu","year":"2017","journal-title":"Sci. Technol. Bull."},{"key":"ref_19","first-page":"524","article-title":"Application of outlier detection method in civil aviation alarm","volume":"49","author":"Zhao","year":"2017","journal-title":"J. Nanjing Univ. Aeronaut. Astronaut."},{"key":"ref_20","first-page":"9","article-title":"Wind turbine anomaly data cleaning method based on quartiles and CFSFDP","volume":"39","author":"Ma","year":"2023","journal-title":"Electr. Power Sci. Eng."},{"key":"ref_21","first-page":"141","article-title":"Identification of wind farm power anomaly data based on variance rate of change criterion-quadratic","volume":"42","author":"Wu","year":"2023","journal-title":"Power Eng. Technol."},{"key":"ref_22","first-page":"68","article-title":"Fault aware task scheduling in cloud using min-min and DBSCAN","volume":"4","author":"Syed","year":"2024","journal-title":"IoT Cyber-Phys. Syst."},{"key":"ref_23","first-page":"72","article-title":"Construction and application of anomaly identification model of average price of electricity sales based on DBSCAN algorithm","volume":"42","author":"Yang","year":"2023","journal-title":"Zhejiang Electr. Power"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Zhou, N., Ma, H., Chen, J., Fang, Q., Jiang, Z., and Li, C. (2023). Equivalent Modeling of LVRT Characteristics for Centralized DFIG Wind Farms Based on PSO and DBSCAN. Energies, 16.","DOI":"10.3390\/en16062551"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"085118","DOI":"10.1088\/1361-6501\/accbda","article-title":"A novel abnormal data detection method based on dynamic adaptive local outlier factor for the vibration signals of rotating parts","volume":"34","author":"Wang","year":"2023","journal-title":"Meas. Sci. Technol."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Lv, Z., Di, L., Chen, C., Zhang, B., and Li, N. (2023). A Fast Density Peak Clustering Method for Power Data Security Detection Based on Local Outlier Factors. Processes, 11.","DOI":"10.3390\/pr11072036"},{"key":"ref_27","first-page":"629","article-title":"Discovery of arbitrary-shapes clusters using DENCLUE algorithm","volume":"17","author":"Khader","year":"2020","journal-title":"Int. Arab J. Inf. Technol."},{"key":"ref_28","first-page":"86","article-title":"Algorithms for hierarchical clustering: An overview","volume":"Volume 2","author":"Murtagh","year":"2012","journal-title":"Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery"},{"key":"ref_29","first-page":"623","article-title":"A method for identifying thunderstorm monoliths from radar data based on OPTICS clustering algorithm","volume":"50","author":"Pan","year":"2022","journal-title":"Meas. Sci. Technol."},{"key":"ref_30","first-page":"110","article-title":"A homologous identification method for voltage dips based on Hausdorff distance and OPTICS clustering","volume":"48","author":"Li","year":"2022","journal-title":"China Test"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1145\/2733381","article-title":"Hierarchical density estimates for data clustering, visualization, and outlier detection","volume":"10","author":"Campello","year":"2015","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"205","DOI":"10.21105\/joss.00205","article-title":"Hdbscan: Hierarchical density based clustering","volume":"2","author":"McInnes","year":"2017","journal-title":"Open Source Softw."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Stewart, G., and Al-Khassaweneh, M. (2022). An implementation of the HDBSCAN* clustering algorithm. Appl. Sci., 12.","DOI":"10.3390\/app12052405"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Wang, L., Chen, P., Chen, L., and Mou, J. (2021). Ship AIS trajectory clustering: An HDBSCAN-based approach. J. Mar. Sci. Eng., 9.","DOI":"10.3390\/jmse9060566"},{"key":"ref_35","unstructured":"Syed, T. (2015). Parallelization of Hierarchical Density-Based Clustering using MapReduce. [Master\u2019s Thesis, University of Alberta]."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"101925","DOI":"10.1016\/j.jocs.2022.101925","article-title":"A varied density-based clustering algorithm","volume":"66","author":"Fahim","year":"2023","journal-title":"J. Comput. Sci."},{"key":"ref_37","first-page":"133","article-title":"A comprehensive survey on imputation of missing data in internet of things","volume":"55","author":"Adhikari","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Little, R., and Rubin, D. (2019). Statistical Analysis with Missing Data, John Wiley & Sons.","DOI":"10.1002\/9781119482260"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1016\/j.eswa.2019.04.049","article-title":"Model selection to improve multiple imputation for handling high rate missingness in a water quality dataset","volume":"131","author":"Ratolojanahary","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"ref_40","first-page":"139","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Kim, J., Tae, D., and Seok, J. (2020, January 19\u201321). A survey of missing data imputation using generative adversarial networks. Proceedings of the 2020 International conference on artificial intelligence in information and communication (ICAIIC), Fukuoka, Japan.","DOI":"10.1109\/ICAIIC48513.2020.9065044"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1002\/bimj.202000393","article-title":"Missing data imputation in clinical trials using recurrent neural network facilitated by clustering and oversampling","volume":"64","author":"Haliduola","year":"2022","journal-title":"Biom. J."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"102397","DOI":"10.1109\/ACCESS.2019.2928641","article-title":"Time series imputation via integration of revealed information based on the residual shortcut connection","volume":"7","author":"Zhang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Verma, H., and Kumar, S. (2019, January 4\u20137). An accurate missing data prediction method using LSTM based deep learning for health care. Proceedings of the 20th International Conference on Distributed Computing and Networking, Bangalore, India.","DOI":"10.1145\/3288599.3295580"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1002\/mpr.329","article-title":"Multiple imputation by chained equations: What is it and how does it work?","volume":"20","author":"Azur","year":"2011","journal-title":"Int. J. Methods Psychiatr. Res."},{"key":"ref_46","first-page":"10","article-title":"A comparative study of interpolation methods for missing data","volume":"36","author":"Song","year":"2020","journal-title":"Stat. Decis. Mak."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Mallik, M., Tesfay, A., Allaert, B., Kassi, R., Egea-Lopez, E., Molina-Garcia-Pardo, J., and Clavier, L. (2022). Towards Outdoor Electromagnetic Field Exposure Mapping Generation Using Conditional GANs. Sensors, 22.","DOI":"10.20944\/preprints202211.0040.v1"},{"key":"ref_48","first-page":"228","article-title":"A small-sample rolling bearing fault classification method based on VAE-GAN data enhancement algorithm","volume":"57","author":"Zhang","year":"2023","journal-title":"At. Energy Sci. Technol."},{"key":"ref_49","unstructured":"Lv, Y., Sun, S., Zhao, Q., Tian, J., and Li, C. (2021). International Conference on Big Data and Security, Springer."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"012031","DOI":"10.1088\/1742-6596\/2195\/1\/012031","article-title":"A Method of Integrated Energy Metering Simulation Data Generation Algorithm Based on Variational Autoencoder WGAN","volume":"2195","author":"Zhang","year":"2022","journal-title":"J. Phys. Conf. Ser. (IOP)"},{"key":"ref_51","first-page":"148","article-title":"Optimized WGAN fault diagnosis method for wind turbine gearboxes under unbalanced dataset","volume":"43","author":"Su","year":"2022","journal-title":"J. Sol. Energy"},{"key":"ref_52","first-page":"50","article-title":"Recognition of bad data in power system based on improved Wasserstein generative adversarial network","volume":"42","author":"Zang","year":"2022","journal-title":"Power Autom. Equip."},{"key":"ref_53","first-page":"55","article-title":"A WGAN-GP data enhancement method for local discharge pattern recognition","volume":"16","author":"Lu","year":"2022","journal-title":"South. Power Grid Technol."},{"key":"ref_54","first-page":"109","article-title":"Bearing health diagnosis method based on WGAN-GP","volume":"52","author":"Sun","year":"2023","journal-title":"Mech. Manuf. Autom."},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Qin, J., Gao, F., Wang, Z., Liu, L., and Ji, C. (2022). Arrhythmia Detection Based on WGAN-GP and SE-ResNet1D. Electronics, 11.","DOI":"10.3390\/electronics11213427"},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"101640","DOI":"10.1016\/j.jocs.2022.101640","article-title":"From missing data imputation to data generation","volume":"61","author":"Neves","year":"2022","journal-title":"J. Comput. Sci."},{"key":"ref_57","unstructured":"Yoon, J., Jordon, J., and Schaar, M. (2018, January 10\u201315). Gain: Missing data imputation using generative adversarial nets. Proceedings of the 35th International Conference on Machine Learning, PMLR, Stockholm, Sweden."},{"key":"ref_58","unstructured":"Friedjungov\u00e1, M., Va\u0161ata, D., Balatsko, M., and Ji\u0159ina, M. (2020). International Conference on Computational Science, Springer International Publishing."},{"key":"ref_59","unstructured":"Neves, D., Naik, M., and Proen\u00e7a, A. (2021). International Conference on Computational Science, Springer International Publishing."},{"key":"ref_60","doi-asserted-by":"crossref","unstructured":"McInnes, L., and Healy, J. (2017, January 18\u201321). Accelerated hierarchical density based clustering. Proceedings of the 2017 IEEE International Conference on Data Mining Workshops (ICDMW), New Orleans, LA, USA.","DOI":"10.1109\/ICDMW.2017.12"},{"key":"ref_61","unstructured":"Campello, R., Moulavi, D., and Sander, J. (2013). Pacific-Asia Conference on Knowledge Discovery and Data Mining, Springer."},{"key":"ref_62","doi-asserted-by":"crossref","unstructured":"Van Buuren, S. (2018). Flexible Imputation of Missing Data, CRC Press.","DOI":"10.1201\/9780429492259"},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"112095","DOI":"10.1016\/j.measurement.2022.112095","article-title":"Missing data imputation framework for bridge structural health monitoring based on slim generative adversarial networks","volume":"204","author":"Gao","year":"2022","journal-title":"Measurement"},{"key":"ref_64","first-page":"5767","article-title":"Improved training of wasserstein gans","volume":"30","author":"Gulrajani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_65","first-page":"3","article-title":"Treatment of Turbine Blade Cracks in Unit No. 2 of Fengtan Hydropower Station","volume":"35","author":"Chen","year":"2012","journal-title":"Mech. Electr. Technol. Hydropower Station."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/1\/118\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:41:55Z","timestamp":1760132515000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/1\/118"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,25]]},"references-count":65,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,1]]}},"alternative-id":["s24010118"],"URL":"https:\/\/doi.org\/10.3390\/s24010118","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2023,12,25]]}}}