| 屈慧妍,李娟,戴洪德,王希彬,张依.t-SNE降维融合SAPSO-BP的飞机电弧故障识别[J].电子测量与仪器学报,2025,39(9):266-276 |
| t-SNE降维融合SAPSO-BP的飞机电弧故障识别 |
| Aircraft arc fault identification based on t-SNE dimensionalityreduction fusion with SAPSO-BP |
| |
| DOI： |
| 中文关键词: 电弧故障识别 特征提取 改进的变异系数特征 t-SNE算法 模拟退火粒子群算法 |
| 英文关键词:arc fault identification feature extraction the improved coefficient of variation feature t-SNE algorithm simulates annealing particle swarm algorithm |
| 基金项目:鲁东大学研究生创新项目(IPGS2024-045)、工信部民机专项(MJ-2018-J-75)资助 |
|
|
| Author | Institution |
| Qu Huiyan | School of Mathematics and Statistical Science, Ludong University, Yantai 264025, China |
| Li Juan | School of Mathematics and Statistical Science, Ludong University, Yantai 264025, China |
| Dai Hongde | School of Aeronautical Foundation, Naval Aeronautical University, Yantai 264001, China |
| Wang Xibin | School of Aeronautical Foundation, Naval Aeronautical University, Yantai 264001, China |
| Zhang Yi | School of Mathematics and Statistical Science, Ludong University, Yantai 264025, China |
|
| 摘要点击次数: 496 |
| 全文下载次数: 465 |
| 中文摘要: |
| 针对单个特征识别故障电弧时特征的阈值难以确定、且难以设置适用于不同负载的统一阈值等问题，为更准确高效地检测不同负载下的串联电弧故障，提出基于t-分布随机邻域嵌入（t-SNE）和模拟退火粒子群算法优化BP神经网络（SAPSO-BP）结合的多特征故障电弧识别方法。首先，针对故障电弧电流高频分量丰富的特点，通过提取电流频率的变异系数改进传统的变异系数特征，构造时频域特征检测故障电弧，结果表明改进后的变异系数（CV）对不同负载的平均识别准确率达到96%。其次，继续提取小波包细节分量以及能量熵等时频域特征与CV进行多特征融合，共同识别故障电弧。在融合过程中使用多种非线性降维算法对多维特征进行降维，并进行聚类可视化对比，发现使用t-SNE降维将多维特征降至三维空间对故障电弧的区分度最高。最后，将降维后的特征输入SAPSO-BP进行训练，并设计消融实验验证了提出方法的识别性能与鲁棒性。结果表明，融合算法tSNE-SAPSO-BP在不同负载上的识别性能较单个特征的识别准确率分别提升了3.2%、16.8%、27.66%、33.5%。t-SNE降维与聚类很好地处理了各特征间的非线性相关性，为融合机器学习方法识别故障电弧提供了关键特征信息。 |
| 英文摘要: |
| To more accurately and efficiently detect series arc faults under different loads and address the difficulty of setting a unified threshold for different loads when using a single feature, a multi-feature fault arc recognition method based on t-distributed stochastic neighbor embedding (t-SNE) and simulated annealing particle swarm optimization algorithm-optimized BP neural network (SAPSO-BP) is proposed. Firstly, considering the rich high-frequency components in arc fault currents, the traditional coefficient of variation (CV) feature is improved by extracting the CV of current frequency. The improved CV achieves an average recognition accuracy of 96% across different loads. Secondly, wavelet packet detail components and energy entropy, which are time-frequency domain features, are further extracted and fused with CV for the identification of arc faults. During the fusion process, various nonlinear dimensionality reduction algorithms are used, and clustering visualization comparisons are carried out. It is found that reducing the multidimensional features to a three-dimensional space using t-SNE dimensionality reduction provides the highest distinction for fault arcs. Finally, the reduced features are input into SAPSO-BP for training, and ablation experiments are designed to verify the recognition performance and robustness of the proposed method. The results show that the recognition performance of the fusion algorithm tSNE-SAPSO-BP is improved by 3.2%, 16.8%, 27.66%, and 33.5% respectively compared with the recognition accuracy of single features on different loads. t-SNE dimensionality reduction and clustering effectively deal with the nonlinear correlations between features, providing key feature information for the identification of fault arcs by the fusion machine learning method. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
