摘要： 在新能源发电系统中，数据缺失问题严重制约了设备运行状态评估与故障预警的准确性。由于新能源场景下的数据通常具有高复杂性、长序列依赖性以及强波动性，传统的数据补全方法在准确性与泛化能力方面难以满足实际应用需求。为此，本文提出了一种基于多尺度特征融合的新能源缺失数据补全方法。首先，采用皮尔逊相关系数与最大互信息系数对多变量特征进行筛选，以提升输入数据的相关性与信息质量。随后，设计了一种全新的时序数据补全模型——AFMFormer（Adaptive Frequency-aware Multi-scale Transformer），该模型首先通过自适应频域特征增强模块对输入序列进行频域分解与主频增强，从而实现对复杂长序列中主要特征的突出。接着，模型引入两条并行时间特征提取分支Patch-based Transformer、Standard Transformer，其中，Patch-based Transformer用于捕捉短期时间序列特征，Standard Transformer用于提取长期时间序列特征。最后，通过特征融合模块对两个分支的输出结果进行融合，生成最终的缺失值补全结果。实验结果表明，所提出模型的评价指标均显著优于基线方法，其中，在风电、光伏数据集上的均方误差相较最优基线模型分别降低49.3%和31.5%，显著提升补全效果。

Abstract: In new energy power generation systems, missing data severely constrains the reliability of equipment condition assessment and fault prediction. The data in such scenarios typically exhibit high complexity, long-term dependencies, and strong volatility, making conventional imputation techniques inadequate in terms of both accuracy and generalization. To address these limitations, this paper proposes AFMFormer, an adaptive frequency-aware multi-scale transformer designed for imputation in new energy systems. Initially, Pearson correlation coefficients and maximal information coefficients are employed to select informative multivariate features, thereby enhancing the relevance and quality of the input data. AFMFormer integrates an adaptive frequency-domain feature enhancement module that performs frequency decomposition and dominant frequency amplification, emphasizing critical components within complex long sequences. Furthermore, two parallel temporal branches—a Patch-based Transformer for short-term dynamics and a Standard Transformer for long-term dependencies—jointly capture comprehensive temporal representations. Finally, a feature fusion mechanism combines the outputs of both branches to generate the imputed sequences. The experimental results show that the evaluation metrics of the proposed model are all significantly better than the baseline method, in which the mean square errors on the wind and PV datasets are reduced by 49.3% and 31.5%, respectively, compared with the optimal baseline model, which significantly improves the imputation effect.