| 引用本文: | 刘 伟,王 澜,易冠群.基于多模态三支路异构融合的逆变器开路故障诊断研究[J].电力系统保护与控制,2026,54(01):71-82.[点击复制] |
| LIU Wei,WANG Lan,YI Guanqun.Research on open-circuit fault diagnosis of inverters based on multi-modal three-branch heterogeneous fusion[J].Power System Protection and Control,2026,54(01):71-82[点击复制] |
|
| 摘要: |
| 针对逆变器开路故障，提出了一种基于GAF-RP-LSTM-Transformer的三支路异构融合的诊断方法。首先，采用互补集合经验模态分解与相位随机技术(complementary ensemble empirical mode decomposition with phase randomization technique, CEEMD-PRT)算法处理逆变器输出电流信号，提取局部故障特征。并通过格拉姆角场(Gramian angular field, GAF)和递归图(recurrence plot, RP)变换将一维时序信号转换为二维图像，充分利用时序信号中的全局趋势特征(GAF)和非线性动力学特征(RP)。为弥补传统一维特征提取在空间相关性表征上的不足，利用长短期记忆(long short-term memory, LSTM)网络提取时序数据的动态特征，利用GAF-RP-Transformer双支路模型提取二维图片的空间特征。为实现一维时序特征与二维空间特征间多维信息的融合，提出了全新的异构特征融合模块，通过多模态图像的互补性，增强模型对故障细微差异的捕捉能力。实验结果表明，所提模型在测试集上的分类准确率达到99.3%，显著优于其他对比模型，并能在不同噪声干扰下保持较高的诊断准确性。特别是在30 dB和20 dB噪声下，准确率下降幅度较小，表明该方法具有较强的鲁棒性。仿真验证了GAF-RP-LSTM-Transformer三支路异构融合模型在逆变器故障诊断中的有效性与优越性。 |
| 关键词: 逆变器开路故障诊断 多模态三支路异构融合模型 CEEMD-PRT算法 异构特征融合 |
| DOI：10.19783/j.cnki.pspc.250250 |
| 投稿时间：2025-03-11修订日期：2025-05-15 |
| 基金项目:国家自然科学基金项目资助(62473096) |
|
| Research on open-circuit fault diagnosis of inverters based on multi-modal three-branch heterogeneous fusion |
| LIU Wei1,WANG Lan1,YI Guanqun2 |
| (1. School of Electrical and Information Engineering, Northeast Petroleum University, Daqing 163318, China;
2. State Grid Information & Telecommunication Group Co., Ltd., Beijing 102211, China) |
| Abstract: |
| A three-branch heterogeneous fusion diagnostic method based on GAF-RP-LSTM-Transformer is proposed for inverter open-circuit faults. First, the output current signals are processed to extract localized fault characteristics through complementary ensemble empirical mode decomposition and phase randomization techniques (CEEMD-PRT). Then, the one-dimensional temporal signals are converted into two-dimensional images via Gramian angular field (GAF) and recurrence plot (RP) transformations, effectively leveraging global trend features (GAF) and nonlinear dynamic characteristics (RP) embedded in the temporal sequences. To overcome the limitations of conventional one-dimensional feature extraction in spatial correlation representation, a long short-term memory (LSTM) network is employed to capture dynamic temporal features, while a dual-branch GAF-RP-Transformer model extracts spatial features from the two-dimensional images. To enable multidimensional fusion of temporal and spatial characteristics, a novel heterogeneous feature fusion module is proposed, leveraging the complementarity of multi-modal images to enhance the model’s ability to capture subtle fault differences. Experimental results demonstrate that the proposed model achieves a classification accuracy of 99.3% on the test sets, significantly outperforming comparative models while maintaining high diagnostic accuracy under varying noise conditions. In particular, under 30 dB and 20 dB noise levels, the accuracy degradation remains small, indicating strong robustness. Simulation results validate the effectiveness and superiority of the GAF-RP- LSTM-Transformer three-branch heterogeneous fusion framework in inverter fault diagnosis. |
| Key words: inverter open-circuit fault diagnosis multi-modal three-branch heterogeneous fusion model CEEMD-PRT algorithm heterogeneous feature fusion |
