刘河生,徐浩,李宁,李林晏,景玮钰,雷航,张瑞刚

• 1:西安热工研究院有限公司
• 2:中车山东风电有限公司

摘要(Abstract)：

齿轮箱健康状态直接影响风电机组的发电量，为了在工程实际中尽早实现齿轮箱故障状态的预警，提出一种基于改进狮群优化的K-means聚类算法。将监督机制及考虑非线性权重的正余弦优化算法引入狮群算法实现算法改进，通过改进狮群优化算法对狮王位置的迭代，选择最优解作为K-means算法聚类中心，以解决传统聚类算法对初始聚类中心依赖性强的问题。选择UCI数据对算法进行对比验证，结果表明，基于改进狮群优化的K-means聚类算法的分类准确度和稳定性有较好的提升。将该算法应用于某风电场内4台同一型号机组齿轮箱振动加速度有效值的对比测试，发现该算法的分类中心分布与齿轮箱实际运行状态相吻合，且与标准规定的齿轮箱不同状态所对应的振动能量分布相一致，证明该算法可实现风电机组齿轮箱早期故障预警。

关键词(KeyWords)： 风电机组;齿轮箱;改进狮群优化;聚类算法;故障预警

Abstract:

Keywords:

基金项目(Foundation): 西安热工研究院有限公司科技项目（TQ-22-TYK27）~~

作者(Author): 刘河生,徐浩,李宁,李林晏,景玮钰,雷航,张瑞刚

DOI: 10.19666/j.rlfd.202310152

参考文献(References)：

• [1]夏云峰.2022年全球风电新增装机77.6 GW[J].风能,2023(5):56-60.XIA Yunfeng.77.6 GW of newly installed wind power globally in 2022[J].Wind Energy,2023(5):56-60.
• [2]2022年中国风电吊装容量统计简报[J].风能,2023(4):40-56.2022 China wind power hoisting capacity statistical briefing[J].Wind Energy,2023(4):40-56.
• [3]SHENG S.Report on wind turbine subsystem reliability:a survey of various databases[R].America:National Renewable Energy Laboratory,2013:5.
• [4]向玲,朱浩伟,丁显,等.基于CAE与Bi LSTM结合的风电机组齿轮箱故障预警方法研究[J].动力工程学报,2022,42(6):514-521.XIANG Ling,ZHU Haowei,DING Xian,et al.Research on fault warning method of wind turbine gearbox based on CAE and Bi LSTM[J].Journal of Chinese Society of Power Engineering,2022,42(6):514-521.
• [5]GRENIER M E,LEFEBVRE D,VAN CUTSEM T.Quasi steady-state models for long-term voltage and frequency dynamics simulation[C].2005 IEEE Russia Power Tech.St.Petersburg:IEEE,2005:1-8.
• [6]任岩,毕亚雄,王德宽,等.风电机组传动链的故障树智能诊断技术[J].排灌机械工程学报,2016,34(4):328-331.REN Yan,BI Yaxiong,WANG Dekuan,et al.Fault tree intelligent diagnosis technology for wind turbine drivetrain[J].Journal of Drainage and Irrigation Machinery Engineering,2016,34(4):328-331.
• [7]孙文卿,邓艾东,邓敏强,等.基于模型融合的风电机组齿轮箱故障诊断[J].太阳能学报,2022,43(1):64-72.SUN Wenqing,DENG Aidong,DENG Minqiang,et al.Fault diagnosis of wind turbine gearbox based on model fusion[J].Acta Energiae Solaris Sinica,2022,43(1):64-72.
• [8]曹梦楠,邱颖宁,冯延晖,等.基于无迹卡尔曼方法的风电机组齿轮箱故障诊断[J].太阳能学报,2017,38(1):32-38.CAO Mengnan,QIU Yingning,FENG Yanhui,et al.Fault diagnosis of wind turbine gearbox with unscented Kalman filter[J].Acta Energiae Solaris Sinica,2017,38(1):32-38.
• [9]赵勇,韩斌,房刚利.风力发电机状态监测与故障诊断技术综述[J].热力发电,2016,45(10):1-5.ZHAO Yong,HAN Bin,FANG Gangli.A survey of condition monitoring and fault diagnosis for wind power generators[J].Thermal Power Generation,2016,45(10):1-5.
• [10]邓巍,韩斌,王建亮,等.风力发电机轴承故障包络谱扫频分析诊断[J].热力发电,2019,48(7):126-130.DENG Wei,HAN Bin,WANG Jianliang,et al.Envelope spectrum sweeping analysis method for bearing fault diagnosis of wind turbine[J].Thermal Power Generation,2019,48(7):126-130.
• [11]谢玉存.基于齿轮箱振动信号的深度学习故障诊断方法研究[D].北京:华北电力大学,2023:1.XIE Yucun.Research on deep learning fault diagnosis method based on gearbox vibration signal[D].Beijing:North China Electric Power University,2023:1.
• [12]王敏.基于聚类异动搜索的风电机组齿轮箱早期故障识别研究[D].保定:华北电力大学(保定),2013:1.WANG Min.Research on early fault identification of wind turbines gear box based on clustering abnormal parameter search[D].Baoding:North China Electric Power University (Baoding),2013:1.
• [13]刘生建,杨艳,周永权.一种群体智能算法--狮群算法[J].模式识别与人工智能,2018,31(5):431-441.LIU Shengjian,YANG YAN,ZHOU Yongquan.A swarm intelligent algorithms-lions swarm algorithm[J].Pattern Recognition and Artificial Intelligence,2018,31(5):431-441.
• [14]虞海燕.基于监督机制的群智能算法的理论研究及应用[D].济南:山东大学,2023:1.YU Haiyan.Theoretical research and application of swarm intelligence algorithm based on supervision mechanism[D].Jinan:Shandong University,2023:1.
• [15]胡啸,王玲燕,张浩宇,等.基于狮群优化的改进K-means聚类算法研究[J].控制工程,2022,29(11):1996-2002.HU Xiao,WANG Lingyan,ZHANG Haoyu,et al.Research on improved K-means clustering algorithm based on lion swarm optimization[J].Control Engineering of China,2022,29(11):1996-2002.
• [16]CHEGINI N S,BAGHERI A,NAJAFI F.PSOSCALF:a new hybrid PSO based on sine cosine algorithm and levy flight for solving optimization problems[J].Applied Soft Computing,2018,73:697-726.
• [17]MIRJALILI S.SCA:a sine cosine algorithm for solving optimization problems[J].Knowledge-Based Systems,2016,96(15):120-133.
• [18]李银通,韩统,赵辉,等.自学习策略和Lévy飞行的正弦余弦优化算法[J].重庆大学学报,2019,42(9):56-66.LI Yintong,HAN Tong,ZHAO Hui,et al.An improved sine cosine optimization algorithm with self-learning strategy and Lévy flight[J].Journal of Chongqing University,2019,42(9):56-66.
• [19]丁飞,江铭炎.基于改进狮群算法和BP神经网络模型的房价预测[J].山东大学学报(工学版),2021,51(4):8-16.DING Fei,JIANG Mingyan.Housing price prediction based on improved lion swarm algorithm and BP neural network model[J].Journal of Shandong University(Engineering Science),2021,51(4):8-16.
• [20]风力发电机组及其组件机械振动测量与评估:GB/T35854-2018[S].北京:中国电力出版社,2018:6.Mechanical vibration measurement and evaluation for the wind turbines and their components:GB/T 35854-2018[S].Beijing:China Electric Power Press,2018:6.