| 引用本文: | 赵 鑫,王东丽,彭 泓,等.基于多策略改进蜣螂算法优化的变压器故障诊断[J].电力系统保护与控制,2024,52(6):120-130.[点击复制] |
| ZHAO Xin,WANG Dongli,PENG Hong,et al.Transformer fault diagnosis based on a multi-strategy improved dung beetle optimizer[J].Power System Protection and Control,2024,52(6):120-130[点击复制] |
|
| 摘要: |
| 为了保证油浸式变压器故障诊断的可靠性，提出了一种基于多策略改进蜣螂算法(multi-strategy improved dung beetle optimizer, MIDBO)优化双向长短时记忆网络(bi-directional long short-term memory, BiLSTM)的变压器故障诊断方法。由于蜣螂算法存在全局搜索能力较差、容易陷入局部最优解的缺点，首先通过Bernoulli混沌映射、引入自适应因子和Levy飞行策略融合动态权重系数进行改进，并对其性能进行评估。然后针对BiLSTM的诸多超参数利用MIDBO进行优化，形成MIDBO-BiLSTM故障诊断模型。通过核主成分分析(kernel principal component analysis, KPCA)提取特征值，进而深入分析特征值与故障类型之间的关联性，提高模型的收敛速度。最终实验结果表明所提出的MIDBO-BiLSTM变压器故障诊断方法准确率高、泛化能力强。其准确率高达94.67%，适用于变压器的故障诊断。 |
| 关键词: 变压器 故障诊断 改进蜣螂算法 双向长短时记忆网络 KPCA |
| DOI：10.19783/j.cnki.pspc.230783 |
| 投稿时间：2023-06-28修订日期：2023-10-10 |
| 基金项目:国家自然科学基金项目资助(51974151)；辽宁省教育厅重点实验室项目资助(LJZS003) |
|
| Transformer fault diagnosis based on a multi-strategy improved dung beetle optimizer |
| ZHAO Xin1,WANG Dongli1,PENG Hong2,YU Hongxia1,LI Shilin2 |
| (1. Shenyang Institute of Technology, Shenyang 113122, China; 2. Liaoning Technical University, Huludao 123000, China) |
| Abstract: |
| To ensure reliable oil-immersed transformer fault diagnosis, a transformer fault diagnosis method based on a multi-strategy improved dung beetle optimizer (MIDBO) optimized bi-directional long short-term memory network (BiLSTM) is proposed. There are shortcomings of the dung beetle algorithm, such as poor global search ability and it is easy for it to fall into a local optimum. First, through the Bernoulli chaotic map, the introduction of adaptive factors and the Levy flight strategy, the dynamic weight coefficient is improved and its performance is evaluated. Then, MIDBO is used to optimize many hyperparameters of BiLSTM to form the MIDBO-BiLSTM fault diagnosis model. Kernel principal component analysis (KPCA) is used to extract the eigenvalues, and the correlation between the eigenvalues and the fault types is analyzed in depth to improve the convergence speed of the model. The final experimental results show that the proposed MIDBO-BiLSTM transformer fault diagnosis method has high accuracy and strong generalizability. Its accuracy rate is as high as 94.67%. This is suitable for transformer fault diagnosis. |
| Key words: transformer fault diagnosis improved dung beetle optimizer bidirectional long short-term memory network KPCA |
