Abstract
Low-temperature co-fired ceramics (LTCCs) have been attracting attention due to rapid advances in wireless telecommunications. Low-dielectric-constant (Dk) and low-dissipation-factor (Df) LTCCs enable a low propagation delay and high signal quality. However, the wide ranges of glass, ceramic filler compositions, and processing features in fabricating LTCC make property modulating difficult via experimental trial-and-error approaches. In this study, we explored Dk and Df values of LTCCs using a machine learning method with a Gaussian kernel ridge regression model. A principal component analysis and k-means methods were initially performed to visually analyze data clustering and to reduce the dimension complexity. Model assessments, by using a five-fold cross-validation, residual analysis, and randomized test, suggest that the proposed Dk and Df models had some predictive ability, that the model selection was appropriate, and that the fittings were not just numerical due to a rather small data set. A cross-plot analysis and property contour plot were performed for the purpose of exploring potential LTCCs for real applications with Dk and Df values less than 10 and 2 × 10−3, respectively, at an operating frequency of 1 GHz. The proposed machine learning models can potentially be utilized to accelerate the design of technology-related LTCC systems.
Highlights
Low-temperature co-fired ceramics (LTCCs) have been attracting attention over recent decades due to rapid advances in wireless telecommunications, including the 5th generation (5G) tactile internet and the Internet of Things (IoT) [1]
LTCCs have characteristics that require sintering at temperatures of less than 1000 ◦ C in order to be co-fired with electrode materials, such as Cu, Ag, or
The database is focused on exploring potential LTCC systems with low Dk and dissipation factor (Df) values that can be applied in real 5G applications using various GC, glass/ceramic composite (GCC), and fabrication methods
Summary
Low-temperature co-fired ceramics (LTCCs) have been attracting attention over recent decades due to rapid advances in wireless telecommunications, including the 5th generation (5G) tactile internet and the Internet of Things (IoT) [1]. Ohsato et al recently reviewed the current status and prospects of LTCC applications in microwave and mmWave telecommunications [6] These low Dk and Df values enable a low propagation delay and high signal quality in 5G systems. The review suggests that LTCC fabrications involve modulating a wide range of glass, ceramic composition, and sintering conditions to meet the desired physical properties. Machine learning methods are considered powerful tools to predict material properties which do not have existing physical models, e.g., effective charges in electromigration [15], permittivity of microwave dielectric ceramics [16], and dielectric constants of crystals [17]. We used the glass phase content, ceramic filler content, and GC content as well as the processing features (e.g., calcination temperature and time) to fit the experimentally-determined Dk and Df data. To the best of the author’s knowledge, this is the first paper to use a machine learning method to explore Dk and Df of LTCC systems
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
