Abnormal current conditions such as overload, harmonics, non-periodic disturbances, and direct current (DC) components frequently occur in low-voltage electrical lines. These anomalies are the primary causes of temperature rise in conductors, significantly increasing the risk of electrical fires. To achieve accurate identification of overheating causes in low-voltage lines, a method integrating parameter-optimized variational mode decomposition (VMD) with a bidirectional long short-term memory (BiLSTM) enhanced by the convolutional block attention module (CBAM) was proposed. The golden jackal optimization (GJO) algorithm was employed to jointly optimize the key parameters of VMD for multi-modal decomposition of current signals. Multi-dimensional entropy features were subsequently extracted from the most relevant intrinsic mode functions (IMFs) to construct a time-series feature dataset. The CBAM module was incorporated to enhance the model’s sensitivity to relevant abnormal features, improving the BiLSTM’s capability to model time-series patterns under complex disturbances. Experimental results demonstrate that the proposed method achieves an identification accuracy of 95.87%, significantly outperforming four mainstream models: LSTM, BiLSTM, CNN-LSTM, and extreme gradient boosting (XGBoost). This confirms the superior classification performance and robustness of the method. It is concluded that the study provides an effective technical path for early warning of electrical fire hazards and shows promising potential for practical applications.
PAN Hong-guang, ZHANG Jing-he, LI Li, LI Fang-wei.
Parameter-optimized VMD-CBAM-BiLSTM Based Identification Method for Overheating Anomaly Causes in Low-voltage Electrical Lines[J].
Science Technology and Engineering, 2026, 26(13): 5531-5540 DOI:10.12404/j.issn.1671-1815.2505814
(1)通道注意力模块:通过最大池化与平均池化并行提取通道统计特征,引导模型关注与目标任务相关的重要通道。通道注意力模块首先对输入特征图进行全局平均池化(global average pooling, GAP)和全局最大池化(global max pooling, GMP),分别获取每个通道的全局平均值和最大值,这两个池化操作的结果通过共享的全连接层(fully connected layer, FC)进行处理,生成通道注意力权重。
TangDan, WuHao, CaiYuan, et al. Early fault identification of cables based on improved deep residual shrinkage network[J]. Science Technology and Engineering, 2024, 24(28): 12159-12168.
[3]
DengJ, LinQ, LiY, et al. Effect of overload current values on the fire characteristics of polyethylene (PE) copper wires[J]. Journal of Thermal Analysis and Calorimetry, 2023, 148(21): 11695-11705.
[4]
AmariyaD, ThakkarA. A comprehensive survey of anomaly detection algorithms[J]. Annals of Data Science, 2023, 10(3): 829-850.
[5]
WangF J, LiR, WangH, et al. TS-PADM: anomaly detection model of wireless sensors based on spatial-temporal feature points[J]. Wireless Communications and Mobile Computing, 2021, 2021(1): 6656498.
DingQian, ZhaoXiaodong, WuXinjun, et al. Landslide susceptibility assessment model based on multi-class SVM with RBF kernel[J]. China Safety Science Journal, 2022, 32(3): 194-200.
ZhouPing, XuZiyuan, ZhouNan, et al. Research on partial discharge recognition of insulated overhead conductors based on CNN-LSTM model[J]. Power and Energy, 2024, 45(4): 460-464.
LiuWei, LiuHui. High voltage direct current transmission lines fault identification method based on improved VMD-MPE and general regression neural network[J]. Science Technology and Engineering, 2022, 22(1): 211-219.
WanJiacheng, ZengXianwen, LiJingchao. Fault diagnosis for gearbox based on parameter optimization VMD combined with wide convolutional neural network[J]. Electronic Measurement Technology, 2025, 48(10): 25-32.
[14]
ZhouZ, ChenW, YangC. Adaptive range selection for parameter optimization of VMD algorithm in rolling bearing fault diagnosis under strong background noise[J]. Journal of Mechanical Science and Technology, 2023, 37: 5759-5773.
KangYonghong, HeXiaoxing. A new model for long-term mixed prediction of marine environmental parameters using SNR optimized VMD-LSTM[J]. Science of Surveying and Mapping, 2025, 50(10): 1-8.
WuZhongdong, WangPengbo, TangChunyang, et al. Denoising method for partial discharge signals based on optimized VMD-DTCWT[J]. Journal of Lanzhou Jiaotong University, 2025, 44(5): 42-49.
ZhouZhaoxiang, ZhanChunlian. Feature extraction method for target radiated noise based on optimized VMD and slope entropy[J]. Science Technology and Engineering, 2024, 24(28): 12188-12199.
JiJingsheng, ZhouLi, MaXiangyang. VMD combined with wavelet packet information entropy and GJO-SVM for motor bearing fault diagnosis[J]. Modern Manufacturing Engineering, 2024(2): 128-136.
[23]
LiS, ZhuX, ZhouD. Power quality disturbance signal denoising and detection based on improved DBO-VMD combined with wavelet thresholding[J]. Electric Power Systems Research, 2025, 238: 111193.
[24]
WuN, PengM, WangJ, et al. Research on voltage-current type series arc fault detection method based on composite multi-scale entropy[J]. Electric Power Systems Research, 2025, 242: 111445.
[25]
LiY, LiJ, ChenS. A new multi-domain entropy signal classification method[J]. Applied Acoustics, 2025, 231: 110521.
[26]
LiuS, LiX. New fuzzy entropy via class-consistent technology with applications to attribute reduction for heterogeneous data[J]. Journal of Supercomputing, 2025, 81(1): 167.
WangHongwei, SunWenlei, ZhangXiaodong, et al. Fault diagnosis method of wind turbine’s gearbox based on composite multiscale dispersion entropy of optimised VMD and LSTM[J]. Acta Energiae Solaris Sinica, 2022, 43(4): 288-295.
DongShaojiang, LiYang, LiangTian, et al. Fault diagnosis method of rolling bearing based on CNN-BiLSTM under variable working conditions[J]. Journal of Vibration, Measurement and Diagnosis, 2022, 42(5): 1009-1016.
GongXuanlin, TaoQing, SuNa, et al. A recognition method for steady-state visual evoked potential EEG signals based on CNN-CBAM-LSTM[J]. Science Technology and Engineering, 2025, 25(10): 4175-4182.