基于卷积变分自编码和多头自注意力机制的断路器剩余机械寿命预测  

Remaining mechanical useful life prediction for circuit breaker based on convolutional variational autoencoder and multi-head self-attention

作　　者：孙曙光 王泽伟 陈静 黄光临 王景芹[3] Sun Shuguang;Wang Zewei;Chen Jing;Huang Guanglin;Wang Jingqin(School of Artificial Intelligence,Hebei University of Technology,Tianjin 300130,China;Wenzhou Juxing Technology Co.,Ltd.,Wenzhou 325062,China;State Key Lab Reliability and Intelligence of Electrical Equipment,Hebei University of Technology,Tianjin 300130,China)

机构地区：[1]河北工业大学人工智能与数据科学学院,天津300130 [2]温州聚星科技股份有限公司,温州325062 [3]河北工业大学省部共建电工装备可靠性与智能化国家重点实验室,天津300130

出　　处：《仪器仪表学报》2024年第3期106-118,共13页Chinese Journal of Scientific Instrument

基　　金：河北省自然科学基金(E2021202136)项目资助。

摘　　要：针对万能式断路器退化过程的不确定性,考虑到振动信号对机械性能退化的完善表征,提出了一种基于卷积变分自编码(CVAE)和多头自注意力机制(MSA)的断路器分闸机械机构寿命预测方法。首先依据断路器不同的事件区间提取参数特征,再通过CVAE挖掘信号成分中的深度特征,将参数特征与深度特征融合得到完备退化特征,最后建立GRU-MSA的定量寿命预测模型,引入了多头自注意力机制,在多个不同表征子空间中捕捉信号的不同依赖关系,对重要的时间步赋予更大的权重。最后利用3台试品的振动信号测量数据对所提断路器分闸机械机构寿命预测方法进行测试,结果表明,所提出的方法在3个数据集中寿命预测均方根误差(RMSE)分别为141.46、128.75和134.16,平均绝对误差(MAE)分别为112.17、101.52和106.22,预测精度高且稳定性好,相对于其他混合预测模型更具优势。Arming at the uncertainty of the degradation of conventional circuit breakers and the perfect mechanical degradation characterization by vibration signals,an opening mechanical mechanism life prediction method based on CVAE and MSA mechanism is proposed.Firstly,the parametric features are extracted based on the different event intervals of the circuit breaker.Then,the depth features in the signal components are mined by CVAE,and the parametric features are fused with the depth features to obtain the complete degradation features.Finally,the quantitative life prediction model of the GRU-MSA is formulated,which introduces MSA to capture the different dependencies of signals in several different representation subspaces and assign greater weights to the important time steps.Finally,the proposed method is tested by using the vibration signal measurement data of three test samples.The results show that the proposed method has life prediction RMSE of 141.46,128.75,and 134.16,and MAE of 112.17,101.52,and 106.22,respectively.The prediction accuracy is high and the stability is good,which has more advantages compared with other hybrid prediction models.

关 键 词：万能式断路器 卷积变分自编码 多头自注意力机制 剩余寿命预测 

分 类 号：TM561[电气工程—电器] TH165.3[机械工程—机械制造及自动化]