Fault Detection Method of Wind Turbine Gearbox Based on IBOA-ERF
Considering the difficulty of parameter optimization of wind turbine gearbox fault detection model,this paper proposes an extreme random forest fault detection model based on improved butterfly optimization algorithm(IBOA-ERF)optimization.The algebraic sum of the false alarm rate and the missed alarm rate of the fault detection model is constructed as the fitness function,and the individual initial position and position update strategy are improved.The chaotic mapping strategy is introduced to replace the original population initialization method to enhance the randomness of the initial population distribution.An adaptive inertia weight factor is proposed,which combines the landmark operator of the pigeon swarm optimization algorithm to update the population position iteration equation,accelerates the convergence speed,and improves the diversity and robustness of the butterfly optimization algorithm.The dynamic switching method of local search stage and global search stage is adopted to realize the dynamic balance between global exploration and local search and avoid falling into local optimum.The ERF fault detection model is established,and the improved butterfly optimization algorithm is used to obtain the optimal parametersto realize the fast response of the proposed model with good robustness and generalization under high-dimensional data.Compared with other optimization algorithms,the proposed wind turbine gearbox fault detection method has lower false alarm rate and false negative rate.
Fault detectionButterfly optimization algorithmExtreme random forestWind turbineGear box
NETL
NSTL
万方数据
