基于退化轨迹和Wiener模型的光伏组件剩余寿命预测方法

REMAINING LIFE PREDICTION METHOD OF PHOTOVOLTAIC MODULES BASED ON DEGRADATION TRAJECTORY AND WIENER MODEL

针对光伏组件退化过程呈现的非单调、随机特性以及对组件剩余寿命自适应预测的需求,建立基于维纳(Wiener)过程的退化模型,在此基础上,提出一种结合退化轨迹自适应更新光伏组件剩余寿命的方法。首先,构建基于Wiener过程的光伏组件功率退化模型,刻画组件退化过程的非单调性以及组件退化过程的时间不确定性和个体差异性;然后,基于光伏组件的退化轨迹,联合贝叶斯更新和期望最大化(EM)算法对模型参数进行实时自适应更新,并在此基础上预测光伏组件的剩余寿命分布。最后,通过比较不同方法下光伏组件剩余寿命预测值的误差,验证所提方法的可行性与优越性。

To address the non-monotonic and stochastic characteristics of the PV module degradation process and the need for adaptive prediction of the remaining life of the module,a degradation model based on the Wiener process is established,on this basis,a method for adaptively updating the remaining life of PV modules in conjunction with the degradation trajectory is proposed.First,the PV module power degradation model based on the Wiener process is constructed to describe the non-monotonicity of the module degradation process,as well as the time uncertainty and individual differences of the module degradation process.Then,based on the degradation trajectory of the PV module,the Bayesian update and expectation maximization(EM)algorithm are combined to perform a real-time adaptive update of the model parameters,on this basis,the remaining life distribution of PV module is predicted.Finally,the feasibility and superiority of the proposed method are verified by comparing the errors of the remaining life prediction values of PV modules under different scenarios.