Research On Preventive Maintenance Strategy Of Wind Turbine Equipment Based On Condition Deterioration Model

With the total installed capacity of wind power continues to increase,the maintenance of wind turbine equipment has attracted more and more attention.In order to ensure the safe and reliable operation of wind turbines,preventive maintenance is widely used in the maintenance of wind turbine equipment.Preventive maintenance can be divided into time-based maintenance and condition-based maintenance.Existing research usually considers the two separately,which are prone to problems such as "over-maintenance","under-maintenance",and inaccurate timing of state maintenance.Based on this,this thesis starts from the spatio-temporal evolution relationship of the equipment’s own state,and constructs the state transformation model of the equipment based on stochastic differential equations.The preventive maintenance research of wind turbine equipment starts from three aspects: time maintenance cycle decision,state maintenance threshold decision,and time and state joint maintenance.The main research contents are as follows:(1)The main equipment of the wind turbine is introduced,and the monitoring methods and monitoring indicators used in the condition monitoring of each equipment are analyzed.In view of the situation that multiple monitoring indicators collectively reflect the status of the equipment,this thesis uses the entropy method to assign weights to each monitoring indicator to make the analysis of the equipment status more accurate.(2)Considering that the equipment will be affected by small disturbances such as weather changes and daily inspections during operation,a model of equipment state changes based on stochastic differential equations is established.The equipment state is composed of selfregression and external random interference.The Weibull distribution and polynomial approximation is used to construct the self-regession model of the equipment.The external random interference is simulated by Brownian motion.At the same time,the Numerical iteration method is used to solve the parameters of the equipment state model.The simulation results verify the accuracy of the model.With equipment reliability as the decision-making goal,equipment maintenance time is predicted,and the effectiveness of the model is verified through case analysis.(3)The state deterioration model is used to approximate the state change of the equipment during operation,and the preventive maintenance strategy research is carried out on the equipment based on this.Firstly,the cost model of equipment condition maintenance is constructed based on the reliability,and the optimal reliability threshold is found under the objective of the lowest maintenance cost.Secondly,the cost model of equipment time maintenance is constructed based on the failure rate,and the best maintenance period is found under the goal of the lowest maintenance cost.Then consider that the current maintenance method in wind farms is the combined application of time-based maintenance and conditionbased maintenance,but the existing joint application strategy has a large over-maintenance phenomenon.Therefore,the maintenance strategy of the combined application of Time-based maintenance(TBM)and Condition-based maintenance(CBM)is improved based on the P-F curve.The equipment state deterioration model is used to predict the change trend of the equipment state,referring to the state repair threshold and time repair period when the maintenance cost is the lowest,determines the maintenance method of the equipment by compare the failure time predicted by the state threshold with the periodic maintenance time.Finally,simulation analysis verifies that the improved maintenance strategy has better economic efficiency.