{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T20:23:59Z","timestamp":1791923039194,"version":"4.3.4"},"reference-count":23,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T00:00:00Z","timestamp":1754524800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Micromachines"],"abstract":"<jats:p>The switching characteristics of GaN HEMT devices exhibit a very complex dynamic nonlinear behavior and multi-physics coupling characteristics, and traditional switching current models based on physical mechanisms have significant limitations. This article adopts a hybrid architecture of convolutional neural network and long short-term memory network (CNN-LSTM). In the 1D-CNN layer, the one-dimensional convolutional neural network can automatically learn and extract local transient features of time series data by sliding convolution operations on time series data through its convolution kernel, making these local transient features present a specific form in the local time window. In the double-layer LSTM layer, the neural network model captures the transient characteristics of switch current through the gating mechanism and state transfer. The hybrid architecture of the constructed model has significant advantages in accuracy, with metrics such as root mean square error (RMSE) and mean absolute error (MAE) significantly reduced, compared to traditional switch current models, solving the problem of insufficient accuracy in traditional models. The neural network model has good fitting performance at both room and high temperatures, with an average coefficient close to 1. The new neural network hybrid architecture has short running time and low computational resource consumption, meeting the needs of practical applications.<\/jats:p>","DOI":"10.3390\/mi16080915","type":"journal-article","created":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T12:15:40Z","timestamp":1754568940000},"page":"915","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Research on Switching Current Model of GaN HEMT Based on Neural Network"],"prefix":"10.3390","volume":"16","author":[{"given":"Xiang","family":"Wang","sequence":"first","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Guangdong University of Technology, Guangzhou 510006, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihui","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Xidian University, Xi\u2019an 710071, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huikai","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Xidian University, Xi\u2019an 710071, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueqi","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Xidian University, Xi\u2019an 710071, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8560-2478","authenticated-orcid":false,"given":"Shulong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Xidian University, Xi\u2019an 710071, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guohao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Guangdong University of Technology, Guangzhou 510006, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Arias-Purdue, A., Lam, E., Tao, J., O\u2019Malley, E., and Buckwalter, J.F. (2023, January 11\u201313). Artificial neural networks for GaN HEMT model extraction in D-band using sparse data. Proceedings of the 2023 IEEE Radio Frequency Integrated Circuits Symposium (RFIC), San Diego, CA, USA.","DOI":"10.1109\/RFIC54547.2023.10186179"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2707","DOI":"10.1109\/JESTPE.2022.3232265","article-title":"A review of high-speed GaN power modules: State of the art, challenges, and solutions","volume":"11","author":"Emon","year":"2022","journal-title":"IEEE J. Emerg. Sel. Top. Power Electron."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1581","DOI":"10.3390\/cryst12111581","article-title":"Reliability, applications and challenges of GaN HEMT technology for modern power devices: A review","volume":"12","author":"Islam","year":"2022","journal-title":"Crystals"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1109\/JEDS.2020.3013656","article-title":"Comparative Study on Dynamic Characteristics of GaN HEMT at 300K and 150K","volume":"8","author":"Wang","year":"2020","journal-title":"IEEE J. Electron. Devices Soc."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"5795","DOI":"10.1109\/JESTPE.2021.3051207","article-title":"99% Efficient 2.5 kW Four-Level Flying Capacitor Multilevel GaN Totem-Pole PFC","volume":"9","author":"Huang","year":"2021","journal-title":"IEEE J. Emerg. Sel. Top. Power Electron."},{"key":"ref_6","first-page":"631","article-title":"Improvement in the crystalline quality of GaN and defects analysis using cathodoluminescence","volume":"36","author":"Khan","year":"2021","journal-title":"Mater. Proc."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Baker, M., Fard, A.Y., Jain, S., and Shadmand, M.B. (2021, January 1\u20132). Gate Drive Optimization Framework with Electro-thermal Model of GaN HEMTs for High-Frequency DC-DC Converters. Proceedings of the 2021 IEEE Power and Energy Conference at Illinois (PECI), Urbana, IL, USA.","DOI":"10.1109\/PECI51586.2021.9435260"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Gazda, C., Ginste, V.D., Rogier, H., Couckuyt, I., Dhaene, T., Stijnen, K., and Pues, H. (2013, January 12\u201315). Efficient optimization of the integrity behavior of analog nonlinear devices using surrogate models. Proceedings of the Signal and Power Integrity (SPI) workshop, Paris, France.","DOI":"10.1109\/SaPIW.2013.6558316"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Avolio, G., Raffo, A., Angelov, I., Crupi, G., Vannini, G., and Schreurs, D. (2013, January 2\u20137). A novel technique for the extraction of nonlinear model for microwave transistors under dynamic-bias operation. Proceedings of the Microwave Symposium Digest (IMS), Seattle, WA, USA.","DOI":"10.1109\/MWSYM.2013.6697394"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1109\/LED.2014.2324619","article-title":"Performance Enhancement of Flip-Chip Packaged AlGaN\/GaN HEMTs Using Active-Region Bumps-Induced Piezoelectric Effect","volume":"35","author":"Tsai","year":"2014","journal-title":"IEEE Electron. Device Lett."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1393","DOI":"10.1109\/TED.2012.2188634","article-title":"The Study of Self-Heating and Hot-Electron Effects for AlGaN\/GaN Double-Channel HEMTs","volume":"59","author":"Wang","year":"2012","journal-title":"IEEE Trans. Electron. Devices"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1109\/JEDS.2021.3076305","article-title":"Improved Low-Frequency Noise in Recessed-Gate E-mode AlGaN\/GaN MOS-HEMTs Under Electrical and Thermal Stress","volume":"9","author":"Hu","year":"2021","journal-title":"IEEE J. Electron. Devices Soc."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2519","DOI":"10.1109\/TMTT.2016.2586055","article-title":"An artificial neural network-based electrothermal model for GaN HEMTs with dynamic trapping effects consideration","volume":"64","author":"Huang","year":"2016","journal-title":"IEEE Trans. Microw. Theory Tech."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"3415","DOI":"10.3390\/en15093415","article-title":"Circuit models of power MOSFETs leading the way of GaN HEMT modelling\u2014A review","volume":"15","author":"Bottaro","year":"2022","journal-title":"Energies"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"27267","DOI":"10.1109\/ACCESS.2023.3258691","article-title":"Accurate and effective nonlinear behavioral modeling of a 10-W GaN HEMT based on LSTM neural networks","volume":"11","author":"Geng","year":"2023","journal-title":"IEEE Access"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"5661","DOI":"10.1109\/JESTPE.2024.3455999","article-title":"Accurate Modeling of GaN HEMTs and MMICs for Cryogenic Electronics Applications Utilizing Artificial Neural Network","volume":"12","author":"Xiang","year":"2024","journal-title":"IEEE J. Emerg. Sel. Top. Power Electron."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"106","DOI":"10.3390\/mi13010106","article-title":"Study of self-heating and high-power microwave effects for enhancement-mode p-gate GaN HEMT","volume":"13","author":"Qin","year":"2022","journal-title":"Micromachines"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"21759","DOI":"10.1109\/ACCESS.2021.3139443","article-title":"An overview on analyses and suppression methods of trapping effects in AlGaN\/GaN HEMTs","volume":"10","author":"Ye","year":"2021","journal-title":"IEEE Access"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1109\/TDMR.2020.2987394","article-title":"Study of charge trapping effects on AlGaN\/GaN HEMTs under UV illumination with pulsed IV measurement","volume":"20","author":"Nagarajan","year":"2020","journal-title":"IEEE Trans. Device Mater. Reliab."},{"key":"ref_20","first-page":"517","article-title":"A Review of GaN HEMT Dynamic ON-Resistance and Dynamic Stress Effects on Field Distribution","volume":"1","author":"Gill","year":"2023","journal-title":"IEEE Trans. Power Electron."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"5581","DOI":"10.1109\/TPEL.2019.2955656","article-title":"Dynamic on-Resistance in GaN-on-Si HEMTs: Origins, Dependencies, and Future Characterization Frameworks","volume":"35","author":"Zulauf","year":"2019","journal-title":"IEEE Trans. Power Electron."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1063\/1.168556","article-title":"Daubechies wavelets and Mathematica","volume":"9","author":"Rowe","year":"1995","journal-title":"Comput. Phys."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"41539","DOI":"10.1007\/s11042-023-15127-0","article-title":"Review of wavelet denoising algorithms","volume":"82","author":"Halidou","year":"2023","journal-title":"Multimed. Tools Appl."}],"container-title":["Micromachines"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-666X\/16\/8\/915\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:25:35Z","timestamp":1760034335000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-666X\/16\/8\/915"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,7]]},"references-count":23,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["mi16080915"],"URL":"https:\/\/doi.org\/10.3390\/mi16080915","relation":{},"ISSN":["2072-666X"],"issn-type":[{"value":"2072-666X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,7]]}}}