GA-BP Neural Network-Based Strain Prediction in Full-Scale Static Testing of Wind Turbine Blades
AbstractThis paper proposes a strain prediction method for wind turbine blades using genetic algorithm back propagation neural networks (GA-BPNNs) with applied loads, loading positions, and displacement as inputs, and the study can be used to provide more data for the wind turbine blades’ health assessment and life prediction. Among all parameters to be tested in full-scale static testing of wind turbine blades, strain is very important. The correlation between the blade strain and the applied loads, loading position, displacement, etc., is non-linear, and the number of input variables is too much, thus the calculation and prediction of the blade strain are very complex and difficult. Moreover, the number of measuring points on the blade is limited, so the full-scale blade static test cannot usually provide enough data and information for the improvement of the blade design. As a result of these concerns, this paper studies strain prediction methods for full-scale blade static testing by introducing GA-BPNN. The accuracy and usability of the GA-BPNN prediction model was verified by the comparison with BPNN model and the FEA results. The results show that BPNN can be effectively used to predict the strain of unmeasured points of wind turbine blades.
Share & Cite This Article
Liu, Z.; Liu, X.; Wang, K.; Liang, Z.; Correia, J.A.; De Jesus, A.M. GA-BP Neural Network-Based Strain Prediction in Full-Scale Static Testing of Wind Turbine Blades. Energies 2019, 12, 1026.
Liu Z, Liu X, Wang K, Liang Z, Correia JA, De Jesus AM. GA-BP Neural Network-Based Strain Prediction in Full-Scale Static Testing of Wind Turbine Blades. Energies. 2019; 12(6):1026.Chicago/Turabian Style
Liu, Zheng; Liu, Xin; Wang, Kan; Liang, Zhongwei; Correia, José A.F.O.; De Jesus, Abílio M. 2019. "GA-BP Neural Network-Based Strain Prediction in Full-Scale Static Testing of Wind Turbine Blades." Energies 12, no. 6: 1026.
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.