基于贝叶斯参数学习优化的海上风电机组动态可靠性预测

黄玲玲; 王全德; 应飞祥; 苗育植; 符杨; 刘璐洁

doi:10.19912/j.0254-0096.tynxb.2024-1055

PDF(1132 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (10) : 703-713. DOI: 10.19912/j.0254-0096.tynxb.2024-1055

基于贝叶斯参数学习优化的海上风电机组动态可靠性预测

黄玲玲¹, 王全德², 应飞祥², 苗育植³, 符杨¹, 刘璐洁¹

作者信息 +

DYNAMIC RELIABILITY PREDICTION OF OFFSHORE WIND TURBINE BASED ON BAYESIAN PARAMETER LEARNING OPTIMIZATION

Huang Lingling¹, Wang Quande², Ying Feixiang², Miao Yuzhi³, Fu Yang¹, Liu Lujie¹

Author information +

文章历史 +

摘要

为提升风电机组可靠性预测的准确性,构建一种基于贝叶斯参数学习优化的动态可靠性预测模型。首先,提出融合单纯可靠性贝叶斯网络与卷积神经网络的状态信息数据处理方法,以解决“多元异质”状态信息的参数不确定性和提取状态数据特征的问题。其次,提出基于参数学习优化的贝叶斯改进方法处理参数不确定性,提高模型对未来可靠性水平的预测准确性。最终,构建的基于贝叶斯参数学习优化的动态可靠性预测模型能精确预测风电机组在一定时间尺度内的可靠性变化趋势。算例结果表明,与其他基准模型相比,所提的预测模型在预测风电机组可靠性变化趋势方面表现出更高的优越性,进一步验证其有效性。

Abstract

To improve the accuracy of reliability prediction for wind turbines, a dynamic reliability prediction model optimized through Bayesian parameter learning is developed. Firstly, a data processing method that integrates a pure reliability Bayesian network with a convolutional neural network was proposed to address the parameter uncertainty and feature extraction of "multivariate heterogeneous" state information. Secondly, a Bayesian improvement method based on parameter learning optimization was introduced to handle parameter uncertainty, enhancing the model’s accuracy in predicting future reliability levels. Finally, the constructed dynamic reliability prediction model, based on Bayesian parameter learning optimization, can precisely predict the reliability trend of wind turbine units over a certain time scale. Case study results show that, compared to other benchmark models, the proposed prediction model exhibits superior performance in predicting the reliability trend of wind turbine units, further validating its effectiveness.

导出引用

黄玲玲, 王全德, 应飞祥, 苗育植, 符杨, 刘璐洁. 基于贝叶斯参数学习优化的海上风电机组动态可靠性预测[J]. 太阳能学报. 2025, 46(10): 703-713 https://doi.org/10.19912/j.0254-0096.tynxb.2024-1055

Huang Lingling, Wang Quande, Ying Feixiang, Miao Yuzhi, Fu Yang, Liu Lujie. DYNAMIC RELIABILITY PREDICTION OF OFFSHORE WIND TURBINE BASED ON BAYESIAN PARAMETER LEARNING OPTIMIZATION[J]. Acta Energiae Solaris Sinica. 2025, 46(10): 703-713 https://doi.org/10.19912/j.0254-0096.tynxb.2024-1055

中图分类号： TM614

参考文献

[1] 葛畅, 阎洁, 刘永前, 等. 海上风电场运行控制维护关键技术综述[J]. 中国电机工程学报, 2022, 42(12): 4278-4292.
GE C, YAN J, LIU Y Q, et al.Review of key technologies for operation control and maintenance of offshore wind farm[J]. Proceedings of the CSEE, 2022, 42(12): 4278-4292.
[2] 赵琳, 魏澈, 王阳, 等. 海上风电场宏观选址与风能资源储量估算[J]. 太阳能学报, 2024, 45(5): 1-8.
ZHAO L, WEI C, WANG Y, et al.Macroscopical site selection and estimation of wind energy reserves for offshore wind farms[J]. Acta energiae solaris sinica, 2024, 45(5): 1-8.
[3] 符杨, 张耀楠, 刘璐洁, 等. 海上风电场维护任务动态调度策略[J]. 电力系统自动化, 2021, 45(21): 48-56.
FU Y, ZHANG Y N, LIU L J, et al.Dynamic dispatching strategy for maintenance tasks of offshore wind farm[J]. Automation of electric power systems, 2021, 45(21): 48-56.
[4] 黄玲玲, 符杨, 任浩瀚, 等. 基于状态信息的风电机组维护研究综述[J]. 中国电机工程学报, 2020, 40(21): 7065-7078.
HUANG L L, FU Y, REN H H, et al.Review of wind turbine maintenance based on condition monitoring systems[J]. Proceedings of the CESS, 2020, 40(21): 7065-7078.
[5] 张晓红, 张剑飞, 何于港, 等. 基于多状态空间划分的风电机组非完美维修决策[J]. 太阳能学报, 2022, 43(11): 203-214.
ZHANG X H, ZHANG J F, HE Y G, et al.Imperfect maintenance decision of wind turbine based on multi-state space partitioning[J]. Acta energiae solaris sinica, 2022, 43(11): 203-214.
[6] BHARDWAJ U, TEIXEIRA A P, SOARES C G.Reliability prediction of an offshore wind turbine gearbox[J]. Renewable energy, 2019, 141: 693-706.
[7] YAN Y Y.Load characteristic analysis and fatigue reliability prediction of wind turbine gear transmission system[J]. International journal of fatigue, 2020, 130: 105259.
[8] ZHU Y C, ZHU C C, SONG C S, et al.Improvement of reliability and wind power generation based on wind turbine real-time condition assessment[J]. International journal of electrical power & energy systems, 2019, 113: 344-354.
[9] ZHANG J X, SUN H X, SUN Z X, et al.Reliability assessment of wind power converter considering SCADA multistate parameters prediction using FP-growth, WPT, K-means and LSTM network[J]. IEEE access, 2020, 8: 84455-84466.
[10] ZHAO Y Y, LI D S, DONG A, et al.Fault prediction and diagnosis of wind turbine generators using SCADA data[J]. Energies, 2017, 10(8): 1210.
[11] HUANG L B, XIN H H, LI Z Y, et al.Identification of generalized short-circuit ratio for on-line stability monitoring of wind farms[J]. IEEE transactions on power systems, 2020, 35(4): 3282-3285.
[12] QIAN P, MA X D, ZHANG D H, et al.Data-driven condition monitoring approaches to improving power output of wind turbines[J]. IEEE transactions on industrial electronics, 2019, 66(8): 6012-6020.
[13] 符杨, 苗育植, 黄玲玲, 等. 基于改进贝叶斯网络的风电机组动态可靠性评估[J]. 电力自动化设备, 2022, 42(11): 32-39.
FU Y, MIAO Y Z, HUANG L L, et al.Dynamic reliability evaluation of wind turbine based on improved Bayesian network[J]. Electric power automation equipment, 2022, 42(11): 32-39.
[14] 董超跃. 基于动态贝叶斯网络的动车组牵引传动系统可靠性分析[D]. 北京: 北京交通大学, 2020.
DONG C Y.Reliability analysis of EMU traction drive system based on dynamic Bayesian network[D]. Beijing: Beijing Jiaotong University, 2020.
[15] 高立艾, 霍利民, 黄丽华, 等. 基于贝叶斯网络时序模拟的含微网配电系统可靠性评估[J]. 中国电机工程学报, 2019, 39(7): 2033-2041.
GAO L A, HUO L M, HUANG L H, et al.Reliability evaluation based on Bayesian networks time sequence simulation for distribution systems containing microgrid[J]. Proceedings of the CSEE, 2019, 39(7): 2033-2041.
[16] LIU Y, CHEN C J.Dynamic reliability assessment for nonrepairable multistate systems by aggregating multilevel imperfect inspection data[J]. IEEE transactions on reliability, 2017, 66(2): 281-297.
[17] 狄鹏, 倪子纯, 尹东亮. 基于云模型和证据理论的多属性决策优化算法[J]. 系统工程理论与实践, 2021, 41(4): 1061-1070.
DI P, NI Z C, YIN D L.A multi-attribute decision making optimization algorithm based on cloud model and evidence theory[J]. Systems engineering-theory & practice, 2021, 41(4): 1061-1070.
[18] 张哲, 秦博宇, 高鑫, 等. 基于CNN-LSTM网络的电网电压稳定紧急控制策略[J]. 电力系统自动化, 2023, 47(11): 60-68.
ZHANG Z, QIN B Y, GAO X, et al.Emergency control strategy of power grid voltage stability based on convolutional neural network and long short-term memory network[J]. Automation of electric power systems, 2023, 47(11): 60-68.
[19] ZHANG C, MA H X, HUA L, et al.An evolutionary deep learning model based on TVFEMD, improved sine cosine algorithm, CNN and BiLSTM for wind speed prediction[J]. Energy, 2022, 254: 124250.
[20] 白旭, 汤荣铿, 罗小芳, 等. 基于故障树分析和贝叶斯网络方法的半潜式钻井平台系统多状态可靠性分析[J]. 中国造船, 2020, 61(2): 220-228.
BAI X, TANG R K, LUO X F, et al.Multi-state reliability analysis of semi-submersible drilling platform system based on FTA and BN[J]. Shipbuilding of China, 2020, 61(2): 220-228.
[21] 张军舰, 马岱君. 考试成绩的混合正态分布分析[J]. 数理统计与管理, 2021, 40(5): 815-821.
ZHANG J J, MA D J.Score analysis with mixed normal distribution[J]. Journal of applied statistics and management, 2021, 40(5): 815-821.
[22] MALAHINA E A U, IRIANE G R, BELUTOWE Y S, et al. A grid-search method approach for hyperparameter evaluation and optimization on teachable machine accuracy: a case study of sample size variation[J]. Journal of applied data sciences, 2024, 5(3): 1008-1025.
[23] BAI Y, YANG E, HAN B, et al.Understanding and improving early stopping for learning with noisy labels[J]. Advances in neural information processing systems, 2021, 34: 24392-24403.
[24] FU Y, YING F X, HUANG L L, et al.Multi-step-ahead significant wave height prediction using a hybrid model based on an innovative two-layer decomposition framework and LSTM[J]. Renewable energy, 2023, 203: 455-472.
[25] ZHOU F T, HUANG Z H, ZHANG C H.Carbon price forecasting based on CEEMDAN and LSTM[J]. Applied energy, 2022, 311: 118601.
[26] 黄玲玲, 李锁, 符杨, 等. 基于风电机组状态的超短期海上风电功率预测[J]. 太阳能学报, 2022, 43(8): 391-398.
HUANG L L, LI S, FU Y, et al.Ultra-short term offshore wind power prediction based on condition-assessment of wind turbines[J]. Acta energiae solaris sinica, 2022, 43(8): 391-398.