In order to improve the accuracy and speed of monitoring,a calibration method based on digital twin is proposed.The finite element model of the motor is constructed and reduced,the thermal twin model based on deep learning and singular value decomposition is built,and the offline and online calibration,the mapping and interaction of the virtual and real space are completed,which ensures the update and accuracy of the digital twin after the actual state of the physical entity changes.
关键词
数字孪生模型/降阶模型/卷积神经网络/长短时记忆网络/在线标定/永磁同步电机
Key words
digital twin model/reduced order model/convolutional neural network/online calibration/permanent magnet synchronous motor
万方数据