| 引用本文: | 周 萱,吴伟丽.基于改进SMOTE不均衡样本处理和IHPO-DBN的变压器故障诊断方法研究[J].电力系统保护与控制,2024,52(11):21-30.[点击复制] |
| ZHOU Xuan,WU Weili.Transformer fault diagnosis method based on improved SMOTE unbalancedsample processing and IHPO-DBN[J].Power System Protection and Control,2024,52(11):21-30[点击复制] |
|
| 摘要: |
| 针对由于变压器故障样本不均衡和故障模型陷入局部最优而导致的分类准确率低的问题，提出了基于改进的合成少数类过采样技术和优化深度置信网络(deep belief network, DBN)的变压器故障诊断方法。首先采用聚类融合的K-means算法，通过分簇和匹配的方式筛选出不稳定的少数类样本用以改进中心点合成少数类过采样技术(center point synthetic minority oversampling technique, CP-SMOTE)算法，并对少数类样本进行扩增，解决了变压器故障数据分布不均衡的问题。其次，通过加入随机逆向学习和自适应惯性权重技术对猎食者优化算法进行改进，并用改进后的算法对DBN的内部参数进行优化调整，提高了模型精度。最后，将不同数据预处理情况下以及不同数据规模下的变压器故障模型进行仿真对比。结果表明，经过数据预处理和模型优化后的变压器故障识别准确率能够提高到98%，有效地解决了故障数据不平衡导致的分类精度低的问题。 |
| 关键词: 变压器故障诊断 不均衡样本 K-means聚类 改进合成少数过采样 改进猎食者优化 |
| DOI：10.19783/j.cnki.pspc.231094 |
| 投稿时间：2023-08-24修订日期：2023-12-11 |
| 基金项目:国家电网公司科技项目资助(SGXJCJ00KJJS2100582)；陕西省教育厅自然科学专项资助(17JK0503)；合肥市关键共性技术研发项目资助(2021GJ039) |
|
| Transformer fault diagnosis method based on improved SMOTE unbalancedsample processing and IHPO-DBN |
| ZHOU Xuan1,2,WU Weili1,2 |
| (1. College of Electrical and Control Engineering, Xi’an University of Science and Technology, Xi’an 710054, China;
2. Xi’an Key Laboratory of Electrical Equipment Condition Monitoring and Power Supply Security, Xi’an 710054, China) |
| Abstract: |
| To solve the problem of low classification accuracy due to unbalanced transformer fault samples and a local optimal fault model, a transformer fault diagnosis method based on improved synthetic minority oversampling technique and an optimized deep belief network (DBN) is proposed. First, the K-means algorithm of clustering fusion is used to select the unstable minority class samples by clustering and matching to improve the center point synthetic minority oversampling technique (CP-SMOTE) algorithm and expand the minority class samples to solve the problem of unbalanced distribution of transformer fault data. Secondly, the algorithm of predator optimization is improved by adding stochastic reverse learning and adaptive inertial weight technology, and the internal parameters of deep confidence network are optimized and adjusted by the improved algorithm, which improves the accuracy of the model. Finally, the transformer fault models in different data preprocessing conditions and data scales are simulated and compared. The results show that the transformer fault identification accuracy can be increased to 98% after data preprocessing and model optimization. This effectively solves the problem of low classification accuracy caused by fault data imbalance. |
| Key words: transformer fault diagnosis unbalanced samples K-means clustering improved synthetic minority oversampling improved predator optimization |
