期刊论文

中文

变压器

1001-8425

2023

60

06

6-12

国家自然科学基金资助项目(52177015)。

本校为第一机构

针对目前应用人工智能算法对油浸风冷式变压器进行热点温度预测时，预测模型输入特征量的选取不够精准及预测准确率不足的问题，本文作者在变压器内部温升-散热过程的分析基础上，提出以油浸风冷式变压器的箱壁温度作为预测模型输入特征量之一,建立了蚁群算法优化支持向量机（ACO-SVM）预测变压器绕组热点温度的模型。以实测数据作为样本进行模型训练，将文中模型与PSO-SVM模型和SVM模型的预测性能进行比较，文中模型的均方误差和平均相对误差相较于PSO-SVM模型降低了87.74%和40%，相较于SVM模型降低了87%和38.86%，测试结果表明该方法预测精度更高，对预测油浸风冷式变压器的热点温度具有更好的...

At present,when artificial intelligence algorithm is used to predict the hot spot temperature of oil-immersed air-cooled transformer,the selection of the input characteristic quantity of the prediction model is not accurate enough and the prediction accuracy is insuffic...MORE At present,when artificial intelligence algorithm is used to predict the hot spot temperature of oil-immersed air-cooled transformer,the selection of the input characteristic quantity of the prediction model is not accurate enough and the prediction accuracy is insufficient.Based on the analysis of the internal temperatu...