Vibration Modeling And Simulation Analysis Of Wind Turbine Flexible Tower Based On ChOA Algorithm Optimization

The vibration of flexible towers of wind turbines can cause accidents or even the shutdown of wind turbines from time to time. Establishing a tower vibration prediction model can effectively predict the occurrence of accidents. Aiming at the problems of low prediction accuracy of the BP neural network and easy to fall into the local optimal solution, the BP neural network is optimized using the chimp optimization algorithm (ChOA). To confirm the algorithm's feasibility, the 120m flexible tower data of a 2 MW wind turbine in a wind farm is simulated and analyzed, and the tower vibration prediction model is used to establish by optimizing the heterogeneous data from multiple sources through correlation analysis under different operating conditions of the wind turbine to find out the correlation variables affecting the vibration of the flexible tower. The results show that the ChOABP neural network has the best prediction effect under the rated wind speed, the root mean square error (RMSE) decreases by 12.1267, and the mean absolute error (MAE) decreases by 9.688, and the error-index decreases by more than the rated wind speed, which proves that the algorithm is better than the optimized BP neural network in rated wind speed.