| 引用本文: | 陈豪钰,李振华,张绍哲,等.基于MHA-CNN-SLSTM和误差补偿的短期互感器误差预测[J].电力系统保护与控制,2024,52(24):74-84.[点击复制] |
| CHEN Haoyu,LI Zhenhua,ZHANG Shaozhe,et al.Short-term transformer error prediction based on MHA-CNN-SLSTM and error compensation[J].Power System Protection and Control,2024,52(24):74-84[点击复制] |
|
| 摘要: |
| 为提高互感器误差预测准确度，首先引入对立搜索算子策略、非线性收敛控制因子对传统海鸥算法进行改进，提出一种基于改进海鸥优化算法(improved seagull optimization algorithm, ISOA)优化变分模态分解(variational mode decomposition, VMD)关键参数的方法，实现误差数据自适应分解。然后，基于多头注意力机制(multi-head attention, MHA)对误差影响特征交叉处理，挖掘各特征间关联性，通过强相关性特征与误差间关系建立弱相关特征与误差间深层联系，避免因数据浪费造成预测精度降低。并考虑训练集与测试集间关系，提出考虑样本相似性的长短期记忆神经网络(similar long short-term memory, SLSTM)，动态调整网络权重和偏置。最终构建MHA-CNN- SLSTM预测模型，并将预测值与实际值误差作为训练集再次输入预测模型，生成补偿数据补偿初步预测值，进一步提高预测精度。最后，以某实测互感器数据进行验证，结果表明所提模型具有更高的预测精度和更好的效果。 |
| 关键词: 超短期预测 变分模态分解 多头注意力机制 LSTM 误差补偿 |
| DOI：10.19783/j.cnki.pspc.240256 |
| 投稿时间：2024-03-05修订日期：2024-04-02 |
| 基金项目:国家自然科学基金项目资助(52277012)；武汉强磁场学科交叉基金项目资助(WHMFC202202) |
|
| Short-term transformer error prediction based on MHA-CNN-SLSTM and error compensation |
| CHEN Haoyu1,2,LI Zhenhua1,2,ZHANG Shaozhe3,CHENG Jiangzhou1,2,LI Zhenxing2,QIU Li2 |
| (1. Hubei Provincial Key Laboratory for Operation and Control of Cascaded Hydropower Station, China Three Gorges University,
Yichang 443002, China; 2. College of Electrical Engineering & New Energy, China Three Gorges University, Yichang 443002,
China; 3. National High Magnetic Field Center, Huazhong University of Science and Technology, Wuhan 430074, China) |
| Abstract: |
| To improve the accuracy of instrument transformer error prediction, first, an antagonistic search operator strategy and nonlinear convergence control factor are introduced to improve the traditional seagull algorithm. A method based on the improved Seagull optimization algorithm (ISOA) to optimize the key parameters of variational mode decomposition (VMD) is proposed to realize the adaptive decomposition of error data. Then, based on the multi-head attention (MHA) mechanism, the cross-processing of error-influencing features is used to mine the correlation between each feature, and the deep relationship between the weakly correlated features and errors is established through the relationship between the strongly correlated features and the errors, so as to avoid the reduction of prediction accuracy caused by data waste. Considering the relationship between the training set and the test set, a long short-term memory (SLSTM) neural network considering the similarity of samples is proposed to dynamically adjust the network weights and biases. Based on this, the MHA-CNN-SLSTM prediction model is constructed, and the error between the predicted value and the actual value is re-input into the prediction model as the training set, and the compensation data is generated to compensate for the preliminary predicted value and further improve the predicted value. Finally, the measured data of a transformer is used to verify the results, and the results show that the proposed model has higher prediction accuracy and effect. |
| Key words: ultra-short-term forecasting VMD multi-head attention mechanism LSTM error compensation |
