1 Department of Mechanical Engineering, North China Electric Power University, Baoding 071000, China
2 Hebei Provincial Engineering Research Center for Advanced Manufacturing and Intelligent Operation & Maintenance of Electric Power Machinery and Equipment, Baoding 071003, China
In order to solve the problems of the inability to comprehensively consider the impact of equipment aging and operation environment on the performance of wind turbine system and their components, the severe imbalance in comprehensive weighting, and the lack of effective method to identify the operational states of wind turbine and its components, a wind turbine comprehensive operation state evaluation and sensitivity analysis based on optimal weighting and improved cloud model was proposed. Firstly, comprehensive state evaluation indicator system for wind turbine with multi-level and multi-performance index was created. Secondly, based on the maximization of deviation and the maximum entropy criterion, a multi-objective and multi-attribute optimal weighting model for wind turbine was established. Next, a comprehensive operation state evaluation model for wind turbine was established based on the optimal weighting model and the improved cloud model. And wind turbine and its components operation states of the wind turbine was identified and determined based on the improved ideal curve method. Finally, the effectiveness of the proposed model was verified by taking a wind turbine in wind farm as the research object, and sensitivity analysis was conducted on the wind turbine and its components. The results show that this method not only effectively solves the problem of the severe imbalance in comprehensive weighting and identifies the operational states of wind turbine and its components, but also reveals the impact of changes in operation states indicators on wind turbine system and its components. And it provides theoretical support for the high reliability and stable operation of wind turbine.
WANG Hai-peng, LIU Zi-xuan, NIU Yu-hang, HE Yu-ling, LI Yuan-chao.
Comprehensive Operation State Evaluation and Sensitivity Analysis of Wind Turbine Based on Optimal Weighting and Improved Cloud Model[J].
Science Technology and Engineering, 2026, 26(9): 3806-3816 DOI:10.12404/j.issn.1671-1815.2504461
LiuJun, AnBairen, ZhangWeibo, et al. Review of health status evaluation of large wind turbines[J]. Power System Protection and Control, 2023, 51(1): 176-187.
WeiTai, HeShaoxiong, HuZiwu, et al. Wind turbine abnormal data cleaning based on an improved isolation forest algorithm[J]. Science Technology and Engineering, 2024, 24(9): 3691-3699.
LiuJie, CaoJing. Gearbox condition assessment of wind turbine units based on Vine-Copula-BiLSTM model[J]. Acta Energiae Solaris Sinica, 2025, 46(4): 494-503.
[7]
MenakaS R, BhoiS K, WarisS F, et al. State estimation for DFIG-based wind turbines under voltage dips using multiresolution sinusoidal neural network-Tasmanian Devil optimization in Internet of Things enabled systems[J]. Energy, 2025, 326: 136344.
[8]
YaoQ T, ChenB H, HuA J, et al. A novel diffusion model with Shapley value analysis for anomaly detection and identification of wind turbine[J]. Expert Systems with Applications, 2025, 284: 127925.
[9]
YeH X, ZhuW J, LiH, et al. Failure warning for offshore wind turbines based on autoregressive models[J]. Ocean Engineering, 2025, 332: 121448.
Liu ZhichaoTusongjiang·Kari, MaXiaojing, et al. Condition assessment method for power transformers based on cloud similarity and evidence fusion[J]. Power System Protection and Control, 2023, 51(20): 79-90.
[12]
WangH, GramstadO, SchaerS, et al. Comparison of probabilistic structural reliability methods for ultimate limit state assessment of wind turbines[J]. Structural Safety, 2024, 111: 102502.
[13]
TianZ, XuZ Q, GaoJ S, et al. Damage evaluation of monopile offshore wind turbine subjected to ship collision based on fuzzy theory[J]. Ocean Engineering, 2025, 333: 121460.
[14]
ZhuD P, DingZ, HuangX G. Active learning model for probabilistic estimation of fatigue damage in wind turbines with latent variable uncertainty[J]. Ocean Engineering, 2025, 335: 121724.
YangWeixin, ZhangYangfan, ShenXinyan, et al. Data-driven modeling and evaluation method for wind turbine units power generation performance profiling[J]. Renewable Energy Resources, 2025, 43(5): 646-653.
JinXiaohang, QinZhiwei, GuoYuanjing, et al. Daily operational status assessment of wind turbine units based on an improved degradation degree model[J]. Acta Energiae Solaris Sinica, 2023, 44(1): 239-246.
[19]
LiW B, LiY J, LiJ P, et al. Variable droop gain frequency supporting control with maximum rotor kinetic energy utilization for wind-storage system[J]. International Journal of Electrical Power & Energy Systems, 2024, 163: 110289.
[20]
CuiY F, ZhangY H, HeW D, et al. Temperature prediction for 3 MW wind-turbine gearbox based on thermal network model[J]. Machines, 2024, 12(3): 175.
[21]
Al-BedhanyJ H, MankhiT A, LegutkoS L A. A surface study of failed planetary wind turbine gearbox bearings to investigate the causes of the bearing premature failure issue[J]. Heliyon, 2024, 10(4): e25860.
[22]
ZhangS K, LangZ Q. SCADA-data-based wind turbine fault detection: a dynamic model sensor method[J]. Control Engineering Practice, 2020, 102: 104546.
[23]
KhanW, RenhaiF, AzizA, et al. Numerical case study on thermal efficiency and predictive thermal management in type-4 wind turbines[J]. Case Studies in Thermal Engineering, 2025, 74: 106827.
[24]
HuangS, YangY, WeiJ, et al. Hierarchical service quality regulation method in wind farms based on optimal generating strategy[J]. IEEE Transactions on Sustainable Energy, 2025, 15(3): 1450-1461.
[25]
YinL F, LiuY C, WangZ X, et al. Fast supplementary voltage control strategy to mitigate catastrophic trip-off risk of wind turbines[J]. Journal of Electrical Engineering & Technology, 2022, 17(6): 3183-3194.
[26]
HeX, ZhouC, ZhangY S, et al. Seismic 3D full-horizon tracking based on a knowledge graph to represent the stratigraphic sequence relationship[J]. Geophysics, 2024, 89(2): 15-30.
[27]
YadavS K, MisraS, GuptaS. Improved family of estimators of population coefficient of variation under simple random sampling[J]. Communications in Statistics-Theory and Methods, 2024, 53(2): 727-747.
LuHuishan, WangNing, WeiHongmei, et al. Structure optimization of rectangular microchannel based on multi-objective particle swarm optimization[J]. Science Technology and Engineering, 2022, 22(3): 1085-1090.
[30]
StoyanovM J, TaglianiA, InverardiN L P. Maximum entropy criterion for moment indeterminacy of probability densities[J]. Entropy, 2024, 26(2): 121.
[31]
SchweighoferM, VargasF L. Sum-of-squares certificates for copositivity via test states SIAM[J]. Journal on Applied Algebra and Geometry, 2024, 8(4): 797-820.
[32]
TangD, ZhengZ, GuerreroM J. A hybrid multi-criteria dynamic sustainability assessment framework for integrated multi-energy systems incorporating hydrogen at ports[J]. International Journal of Hydrogen Energy, 2025, 99: 540-552.
[33]
LiuX, TangL, LuY, et al. Energy-saving evaluation and comprehensive benefit analysis of power transmission/distribution system based on cloud model[J]. Energies, 2024, 17(14): 3522.
[34]
DaiJ, GuoQ Y, WangG Y, et al. An optimized method for variational autoencoders based on Gaussian cloud model[J]. Information Sciences, 2023, 645: 119358.
[35]
ZhengX, LiuQ, LiY, et al. Safety risk assessment for connected and automated vehicles: integrating FTA and CM-improved AHP[J]. Reliability Engineering and System Safety, 2025, 257: 110822.
[36]
MakhloufiS, KhennasS, BouchaibS, et al. Multi-objective cuckoo search algorithm for optimized pathways for 75% renewable electricity mix by 2050 in Algeria[J]. Renewable Energy, 2022, 185(4): 1410-1424.
[37]
WuX, FengZ, YangS, et al. Safety risk perception and control of water inrush during tunnel excavation in karst areas: an improved uncertain information fusion method[J]. Automation in Construction, 2024, 163: 105421.