Effects of PCPDTBT:PCBM Ratio on the Electrical Analysis and the Prediction Of I-V Data Using Machine Learning Algorithms for Au/PCPDTBT:PCBM/n-Si MPS SBDs

Authors : Ömer Berkan ÇELİK, Burak TAŞ, Özgün UZ, Hüseyin Muzaffer ŞAĞBAN, Özge TÜZÜN ÖZMEN

Pages : 36-44

View : 13 | Download : 7

Publication Date : 2023-05-01

Article Type : Research Paper

Abstract :In this study, Au/Poly[2,6-insert ignore into journalissuearticles values(4,4-bis-insert ignore into journalissuearticles values(2-ethylhexyl);-4H-cyclopenta[2,1-b;3,4-b′]dithiophene);-alt-4,7insert ignore into journalissuearticles values(2,1,3-benzothiadiazole);] insert ignore into journalissuearticles values(PCPDTBT); : [6,6]-phenyl C61 butyric acid methyl ester insert ignore into journalissuearticles values(PCBM); /n-Si heterojunction Schottky barrier diodes insert ignore into journalissuearticles values(SBDs); with 1:1 and 2:1 PCPDTBT:PCBM doping ratios were produced, and the electrical analysis of metal-polimer-semiconductor insert ignore into journalissuearticles values(MPS); SBDs with different concentrations was investigated. Ideality factor insert ignore into journalissuearticles values(n);, saturation current values insert ignore into journalissuearticles values(I0); and barrier heights insert ignore into journalissuearticles values(F0); of the materials were obtained based on the current-voltage insert ignore into journalissuearticles values(I-V); measurements performed. According to the results obtained, the PCBM concentration has significant effects on the electrical properties of the Au/PCPDTBT:PCBM/n-Si MPS SBD. To predict the electrical characterization of a system in detail, based on its doping concentration, the I-V data set consisting of 2 samples is typically split into a 70% training set and a 30% test set, which is used to train machine learning algorithms. Various methods, including Fine Tree, Cubic SVM, Fine KNN, Boosted Trees, Bagged Trees, Subspace KNN, RUSBoosted Trees, Wide Neural Network, Trilayered Neural Network, and Logistic Regression Kernel, have been analyzed. The obtained results indicate that certain algorithms can predict the I-V data of Au/PCPDTBT:PCBM/n-Si MPS SBD with full accuracy, i.e., 100%.
Keywords : Schottky barrier diode, PCPDTBT PCBM ratio, electrical analysis, I V data, machine learning