US 12,481,879 B2
Virtual metrology method based on convolutional autoencoder and transfer learning and system thereof
Fan-Tien Cheng, Tainan (TW); Yu-Ming Hsieh, Kaohsiung (TW); Yueh-Feng Tsai, Yunlin County (TW); and Chin-Yi Lin, Taipei (TW)
Assigned to NATIONAL CHENG KUNG UNIVERSITY, Tainan (TW)
Filed by NATIONAL CHENG KUNG UNIVERSITY, Tainan (TW)
Filed on Dec. 8, 2022, as Appl. No. 18/063,661.
Claims priority of application No. 111123260 (TW), filed on Jun. 22, 2022.
Prior Publication US 2023/0419107 A1, Dec. 28, 2023
Int. Cl. G06N 3/08 (2023.01)
CPC G06N 3/08 (2013.01) 20 Claims
OG exemplary drawing
 
1. A virtual metrology method based on convolutional autoencoder and transfer learning, comprising:
obtaining a plurality of sets of process data, wherein the sets of process data are used or generated by a production tool when a plurality of workpieces are processed by the production tool, and the sets of process data are one-to-one corresponding to the workpieces, and each of the sets of process data comprises values of a plurality of parameters, and the values of each of the parameters are respectively corresponding to a plurality of sets of time series data of the workpieces, and each of the sets of time series data has a data length;
performing a data alignment operation onto the sets of process data, the data alignment operation comprising:
performing a data-length adjusting operation to repeat adding at least one data point having a value of an end data point of each of the sets of time series data of each of the parameters after the end data point until the data length of each of the sets of time series data of each of the parameters is equal to a longest data length of the sets of process data;
obtaining a plurality of actual measurement values of the workpieces;
performing a modeling operation, the modeling operation comprising:
classifying the sets of process data and the actual measurement values into a plurality of paired data and at least one unpaired process data, wherein each of the paired data comprises one of the sets of process data and one of the actual measurement values corresponding to the one of the sets of process data; and
creating at least one pre-trained model by using the at least one unpaired process data, and then inputting the paired data to the at least one pre-trained model to create a virtual metrology model based on convolutional autoencoder, wherein the virtual metrology model based on convolutional autoencoder comprises at least one convolutional neural network model; and
performing a calculating operation, the calculating operation comprising:
obtaining at least one of another set of process data and another actual measurement value of another workpiece, and executing one of a predicting step and a transfer learning step according to whether the another actual measurement value is obtained, thereby calculating one of a phase-one virtual metrology value and a phase-two virtual metrology value of the another workpiece;
wherein the predicting step comprises calculating the phase-one virtual metrology value by the another set of process data according to the virtual metrology model based on convolutional autoencoder, and the transfer learning step comprises calculating the phase-two virtual metrology value of the another workpiece by the another set of process data and the another actual measurement value according to the virtual metrology model based on convolutional autoencoder.