基于自监督预训练与时序注意力机制的变压器顶层油温预测OA北大核心CSTPCD
Transformer Top Oil Temperature Prediction Based on Self-supervised Pre-training and Time-series Attention Mechanism
变压器故障预警依赖于更精确可信的变压器顶层油温预测.应用自监督预训练方法将预测模型训练过程中的油温预测任务转变为油温重建任务,泛化模型训练方式的同时提升模型对历史油温态势信息的抽取能力.该文提出双通道预训练时序注意力网络(dual-channel pre-trained time-series attention network,DPAnet)模型,模型是采用时序注意力机制和趋势周期分支的深度神经网络,分别针对油温数据的趋势规律和周期规律实现单时…查看全部>>
Transformer fault early warning relies on more accurate and reliable prediction of transformer top oil temperature.The self-supervised pre-training method is used to transform the oil temperature prediction task in the forecasting model training process into the oil temperature reconstruction task,which generalizes the model training method and improves the model's ability to extract historical oil temperature situation information.A dual-channel pre-trained…查看全部>>
李启明;李彬;刘浩;甘津瑞;石富岭;卢卫疆;杨春萍
华北电力大学电气与电子工程学院,北京市 昌平区 102206华北电力大学电气与电子工程学院,北京市 昌平区 102206国网智能电网研究院有限公司,北京市 昌平区 102209国网智能电网研究院有限公司,北京市 昌平区 102209华北电力大学电气与电子工程学院,北京市 昌平区 102206国网智能电网研究院有限公司,北京市 昌平区 102209华北电力大学电气与电子工程学院,北京市 昌平区 102206
动力与电气工程
顶层油温自监督预训练时序注意力深度神经网络
top oil temperatureself-supervised pre-trainingtime self-attentiondeep neural network
《中国电机工程学报》 2024 (z1)
318-331,14
评论