The field of printed electronics has been extensively researched for its versatility and scalability in flexible and large-area applications.Impedance is of great importance for the performance and reliability of elec...The field of printed electronics has been extensively researched for its versatility and scalability in flexible and large-area applications.Impedance is of great importance for the performance and reliability of electronics.However,its measurement requires electrical contacts,which makes it difficult on complex or bio-interfaces.Although the printing process is accessible,impedance characterization may be cumbersome,which can create a bottleneck during the manufacturing process.This paper reports the first effort at developing a convolutional neural network(CNN)based image regression model to replace impedance spectroscopy(IS).In our study,the CNN model learned the features of inkjet-printed electrode images that are dependent on the printing and sintering of nanomaterials and quantitatively predicted the resistance and capacitance of the equivalent circuit of the inkjet-printed lines.The image-based impedance spectroscopy(IIS)is expected to be the cornerstone as a revolutionary approach to electronics research and development enabled by deep neural networks.展开更多
This paper reviews various inverse analysis models used in steel material design,with a focus on integrating process,microstructure,and properties through advanced machine learning techniques.The study underscores the...This paper reviews various inverse analysis models used in steel material design,with a focus on integrating process,microstructure,and properties through advanced machine learning techniques.The study underscores the importance of establishing comprehensive models that effectively link these elements for enhanced materials engineering.Key models discussed include the convolutional neural network–artificial neural network-coupled model,which employs convolutional neural networks for feature extraction;the Bayesian-optimized generative adversarial network–conditional generative adversarial network model,which generates diverse virtual microstructures;the multi-objective optimization model,which concentrates on process–property relationships;and the microstructure–process parallelization model,which correlates microstructural features with process conditions.Each model is assessed for its strengths and limitations,influencing its practical applicability in material design.The paper concludes by advocating for continued improvements in model accuracy and versatility,with the ultimate goal of enhancing steel properties and expanding the scope of data-driven material development.展开更多
基金supported by the Ministry of Education through the Basic Science Research Program through the National Research Foundation of Korea(NRF-2021R1I1A3059714)by the Korea Institute of Industrial Technology as"Development of root technology for multi-product flexible production(KITECH EO-24-0009)+1 种基金supported by project for Collabo R&Dbetween Industry,University,and Research Institute funded by Korea Ministry of SMEs and Startups in 2023(RS-2023-00224114)supported by the faculty research fund of Sejong University in 2024。
文摘The field of printed electronics has been extensively researched for its versatility and scalability in flexible and large-area applications.Impedance is of great importance for the performance and reliability of electronics.However,its measurement requires electrical contacts,which makes it difficult on complex or bio-interfaces.Although the printing process is accessible,impedance characterization may be cumbersome,which can create a bottleneck during the manufacturing process.This paper reports the first effort at developing a convolutional neural network(CNN)based image regression model to replace impedance spectroscopy(IS).In our study,the CNN model learned the features of inkjet-printed electrode images that are dependent on the printing and sintering of nanomaterials and quantitatively predicted the resistance and capacitance of the equivalent circuit of the inkjet-printed lines.The image-based impedance spectroscopy(IIS)is expected to be the cornerstone as a revolutionary approach to electronics research and development enabled by deep neural networks.
基金funded by a Grant-in-Aid for Transformative Research Areas 21H05194“Material Creation in Super Field”and 22H01807 from the Japanese Grants-in-Aid for Scientific Research.
文摘This paper reviews various inverse analysis models used in steel material design,with a focus on integrating process,microstructure,and properties through advanced machine learning techniques.The study underscores the importance of establishing comprehensive models that effectively link these elements for enhanced materials engineering.Key models discussed include the convolutional neural network–artificial neural network-coupled model,which employs convolutional neural networks for feature extraction;the Bayesian-optimized generative adversarial network–conditional generative adversarial network model,which generates diverse virtual microstructures;the multi-objective optimization model,which concentrates on process–property relationships;and the microstructure–process parallelization model,which correlates microstructural features with process conditions.Each model is assessed for its strengths and limitations,influencing its practical applicability in material design.The paper concludes by advocating for continued improvements in model accuracy and versatility,with the ultimate goal of enhancing steel properties and expanding the scope of data-driven material development.
