Recently,machine learning-based technologies have been developed to automate the classification of wafer map defect patterns during semiconductormanufacturing.The existing approaches used in the wafer map pattern clas...Recently,machine learning-based technologies have been developed to automate the classification of wafer map defect patterns during semiconductormanufacturing.The existing approaches used in the wafer map pattern classification include directly learning the image through a convolution neural network and applying the ensemble method after extracting image features.This study aims to classify wafer map defects more effectively and derive robust algorithms even for datasets with insufficient defect patterns.First,the number of defects during the actual process may be limited.Therefore,insufficient data are generated using convolutional auto-encoder(CAE),and the expanded data are verified using the evaluation technique of structural similarity index measure(SSIM).After extracting handcrafted features,a boosted stacking ensemble model that integrates the four base-level classifiers with the extreme gradient boosting classifier as a meta-level classifier is designed and built for training the model based on the expanded data for final prediction.Since the proposed algorithm shows better performance than those of existing ensemble classifiers even for insufficient defect patterns,the results of this study will contribute to improving the product quality and yield of the actual semiconductor manufacturing process.展开更多
In this work, the wafer bowing during growth can be in-situ measured by a reflectivity mapping method in the 3×2 Thomas Swan close coupled showerhead metal organic chemical vapor deposition（MOCVD） system. The r...In this work, the wafer bowing during growth can be in-situ measured by a reflectivity mapping method in the 3×2 Thomas Swan close coupled showerhead metal organic chemical vapor deposition（MOCVD） system. The reflectivity mapping method is usually used to measure the film thickness and growth rate. The wafer bowing caused by stresses（tensile and compressive） during the epitaxial growth leads to a temperature variation at different positions on the wafer, and the lower growth temperature leads to a faster growth rate and vice versa. Therefore, the wafer bowing can be measured by analyzing the discrepancy of growth rates at different positions on the wafer. Furthermore, the wafer bowings were confirmed by the ex-situ wafer bowing measurement. High-resistivity and low-resistivity Si substrates were used for epitaxial growth. In comparison with low-resistivity Si substrate, Ga N grown on high-resistivity substrate shows a larger wafer bowing caused by the highly compressive stress introduced by compositionally graded Al Ga N buffer layer. This transition of wafer bowing can be clearly in-situ measured by using the reflectivity mapping method.展开更多
The defect detection of wafers is an important part of semiconductor manufacturing.The wafer defect map formed from the defects can be used to trace back the problems in the production process and make improvements in...The defect detection of wafers is an important part of semiconductor manufacturing.The wafer defect map formed from the defects can be used to trace back the problems in the production process and make improvements in the yield of wafer manufacturing.Therefore,for the pattern recognition of wafer defects,this paper uses an improved ResNet convolutional neural network for automatic pattern recognition of seven common wafer defects.On the basis of the original ResNet,the squeeze-and-excitation(SE)attention mechanism is embedded into the network,through which the feature extraction ability of the network can be improved,key features can be found,and useless features can be suppressed.In addition,the residual structure is improved,and the depth separable convolution is added to replace the traditional convolution to reduce the computational and parametric quantities of the network.In addition,the network structure is improved and the activation function is changed.Comprehensive experiments show that the precision of the improved ResNet in this paper reaches 98.5%,while the number of parameters is greatly reduced compared with the original model,and has well results compared with the common convolutional neural network.Comprehensively,the method in this paper can be very good for pattern recognition of common wafer defect types,and has certain application value.展开更多
基金the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.NRF-2021R1A5A8033165)the“Human Resources Program in Energy Technology”of the Korea Institute of Energy Technology Evaluation and Planning(KETEP)and was granted financial resources from the Ministry of Trade,Industry&Energy,Republic of Korea(No.20214000000200).
文摘Recently,machine learning-based technologies have been developed to automate the classification of wafer map defect patterns during semiconductormanufacturing.The existing approaches used in the wafer map pattern classification include directly learning the image through a convolution neural network and applying the ensemble method after extracting image features.This study aims to classify wafer map defects more effectively and derive robust algorithms even for datasets with insufficient defect patterns.First,the number of defects during the actual process may be limited.Therefore,insufficient data are generated using convolutional auto-encoder(CAE),and the expanded data are verified using the evaluation technique of structural similarity index measure(SSIM).After extracting handcrafted features,a boosted stacking ensemble model that integrates the four base-level classifiers with the extreme gradient boosting classifier as a meta-level classifier is designed and built for training the model based on the expanded data for final prediction.Since the proposed algorithm shows better performance than those of existing ensemble classifiers even for insufficient defect patterns,the results of this study will contribute to improving the product quality and yield of the actual semiconductor manufacturing process.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.61274039 and 51177175)the National Basic Research Program of China(Grant No.2011CB301903)+5 种基金the Ph.D.Programs Foundation of Ministry of Education of China(Grant No.20110171110021)the International Science and Technology Collaboration Program of China(Grant No.2012DFG52260)the International Science and Technology Collaboration Program of Guangdong Province,China(Grant No.2013B051000041)the Science and Technology Plan of Guangdong Province,China(Grant No.2013B010401013)the National High Technology Research and Development Program of China(Grant No.2014AA032606)the Opened Fund of the State Key Laboratory on Integrated Optoelectronics,China(Grant No.IOSKL2014KF17)
文摘In this work, the wafer bowing during growth can be in-situ measured by a reflectivity mapping method in the 3×2 Thomas Swan close coupled showerhead metal organic chemical vapor deposition（MOCVD） system. The reflectivity mapping method is usually used to measure the film thickness and growth rate. The wafer bowing caused by stresses（tensile and compressive） during the epitaxial growth leads to a temperature variation at different positions on the wafer, and the lower growth temperature leads to a faster growth rate and vice versa. Therefore, the wafer bowing can be measured by analyzing the discrepancy of growth rates at different positions on the wafer. Furthermore, the wafer bowings were confirmed by the ex-situ wafer bowing measurement. High-resistivity and low-resistivity Si substrates were used for epitaxial growth. In comparison with low-resistivity Si substrate, Ga N grown on high-resistivity substrate shows a larger wafer bowing caused by the highly compressive stress introduced by compositionally graded Al Ga N buffer layer. This transition of wafer bowing can be clearly in-situ measured by using the reflectivity mapping method.
基金supported by the 2021 Annual Scientific Research Funding Project of Liaoning Pro-vincial Department of Education(Nos.LJKZ0535,LJKZ0526)the Natural Science Foundation of Liaoning Province(No.2021-MS-300)。
文摘The defect detection of wafers is an important part of semiconductor manufacturing.The wafer defect map formed from the defects can be used to trace back the problems in the production process and make improvements in the yield of wafer manufacturing.Therefore,for the pattern recognition of wafer defects,this paper uses an improved ResNet convolutional neural network for automatic pattern recognition of seven common wafer defects.On the basis of the original ResNet,the squeeze-and-excitation(SE)attention mechanism is embedded into the network,through which the feature extraction ability of the network can be improved,key features can be found,and useless features can be suppressed.In addition,the residual structure is improved,and the depth separable convolution is added to replace the traditional convolution to reduce the computational and parametric quantities of the network.In addition,the network structure is improved and the activation function is changed.Comprehensive experiments show that the precision of the improved ResNet in this paper reaches 98.5%,while the number of parameters is greatly reduced compared with the original model,and has well results compared with the common convolutional neural network.Comprehensively,the method in this paper can be very good for pattern recognition of common wafer defect types,and has certain application value.
