{"title":"基于宽温度范围实验数据的肖特基二极管特性机器学习建模","authors":"Yunis Torun , Hülya Doğan","doi":"10.1016/j.spmi.2021.107062","DOIUrl":null,"url":null,"abstract":"<div><p><span>In this study, 4 common machine learning methods have been used to model the I–V characteristic of the Au/Ni/n-GaN/undoped GaN Schottky diode. The current values of previously produced Au/Ni/n-GaN/undoped GaN Schottky diode against the voltages applied to the diode terminal starting from the temperature of 40K up to 400K with 20K steps were measured. Models were created using Adaptive Neuro Fuzzy System, </span>Artificial Neural Network, Support Vector Regression, and Gaussian Process Regression techniques using experimental data containing 5192 samples in total. After determining the combinations and specifications for each one that provide the lowest model error of each model, the performances of the obtained models were compared with each other concerning the various performance indices. The performance of the ANFIS model was found to be much better than the others in both the learning and test phases with RMSE model errors as 6.231e-06 and 6.806e-06, respectively. Therefore, it was proposed as a powerful tool for modeling I–V characteristics at all temperature values between 40K and 400K.</p></div>","PeriodicalId":22044,"journal":{"name":"Superlattices and Microstructures","volume":null,"pages":null},"PeriodicalIF":3.3000,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":"{\"title\":\"Modeling of Schottky diode characteristic by machine learning techniques based on experimental data with wide temperature range\",\"authors\":\"Yunis Torun , Hülya Doğan\",\"doi\":\"10.1016/j.spmi.2021.107062\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p><span>In this study, 4 common machine learning methods have been used to model the I–V characteristic of the Au/Ni/n-GaN/undoped GaN Schottky diode. The current values of previously produced Au/Ni/n-GaN/undoped GaN Schottky diode against the voltages applied to the diode terminal starting from the temperature of 40K up to 400K with 20K steps were measured. Models were created using Adaptive Neuro Fuzzy System, </span>Artificial Neural Network, Support Vector Regression, and Gaussian Process Regression techniques using experimental data containing 5192 samples in total. After determining the combinations and specifications for each one that provide the lowest model error of each model, the performances of the obtained models were compared with each other concerning the various performance indices. The performance of the ANFIS model was found to be much better than the others in both the learning and test phases with RMSE model errors as 6.231e-06 and 6.806e-06, respectively. Therefore, it was proposed as a powerful tool for modeling I–V characteristics at all temperature values between 40K and 400K.</p></div>\",\"PeriodicalId\":22044,\"journal\":{\"name\":\"Superlattices and Microstructures\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.3000,\"publicationDate\":\"2021-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"7\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Superlattices and Microstructures\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0749603621002603\",\"RegionNum\":3,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"PHYSICS, CONDENSED MATTER\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Superlattices and Microstructures","FirstCategoryId":"101","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0749603621002603","RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PHYSICS, CONDENSED MATTER","Score":null,"Total":0}
Modeling of Schottky diode characteristic by machine learning techniques based on experimental data with wide temperature range
In this study, 4 common machine learning methods have been used to model the I–V characteristic of the Au/Ni/n-GaN/undoped GaN Schottky diode. The current values of previously produced Au/Ni/n-GaN/undoped GaN Schottky diode against the voltages applied to the diode terminal starting from the temperature of 40K up to 400K with 20K steps were measured. Models were created using Adaptive Neuro Fuzzy System, Artificial Neural Network, Support Vector Regression, and Gaussian Process Regression techniques using experimental data containing 5192 samples in total. After determining the combinations and specifications for each one that provide the lowest model error of each model, the performances of the obtained models were compared with each other concerning the various performance indices. The performance of the ANFIS model was found to be much better than the others in both the learning and test phases with RMSE model errors as 6.231e-06 and 6.806e-06, respectively. Therefore, it was proposed as a powerful tool for modeling I–V characteristics at all temperature values between 40K and 400K.
期刊介绍:
Micro and Nanostructures is a journal disseminating the science and technology of micro-structures and nano-structures in materials and their devices, including individual and collective use of semiconductors, metals and insulators for the exploitation of their unique properties. The journal hosts papers dealing with fundamental and applied experimental research as well as theoretical studies. Fields of interest, including emerging ones, cover:
• Novel micro and nanostructures
• Nanomaterials (nanowires, nanodots, 2D materials ) and devices
• Synthetic heterostructures
• Plasmonics
• Micro and nano-defects in materials (semiconductor, metal and insulators)
• Surfaces and interfaces of thin films
In addition to Research Papers, the journal aims at publishing Topical Reviews providing insights into rapidly evolving or more mature fields. Written by leading researchers in their respective fields, those articles are commissioned by the Editorial Board.
Formerly known as Superlattices and Microstructures, with a 2021 IF of 3.22 and 2021 CiteScore of 5.4