Hybrid modelling routine for metal-oxide TFTs based on particle swarm optimisation and artificial neural network

• Published in: Electronics letters Vol. 56; no. 9; pp. 453 - 456
• Main Authors: Peng, You, Deng, Wanling, Wu, Weijing, Luo, Zhi, Huang, Junkai
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 30.04.2020
• Subjects: ANN model; artificial neural network; curve fitting; effective hybrid algorithm; flexible metal‐oxide thin‐film transistors; great global searching ability; hybrid modelling routine; L‐BFGS algorithm; L‐BFGS method; metal‐oxide TFTs; neural nets; optimisation; optimiser; particle swarm optimisation; PSO; robust hybrid algorithm; Semiconductor technology; thin film transistors; training process; universal searching ability; universal searching ability; artificial neural network; great global searching ability; particle swarm optimisation; L-BFGS method; metal-oxide TFTs; training process; thin film transistors; L-BFGS algorithm; PSO; optimiser; hybrid modelling routine; optimisation; effective hybrid algorithm; flexible metal-oxide thin-film transistors; curve fitting; robust hybrid algorithm; ANN model; neural nets
• ISSN: 0013-5194; 1350-911X; 1350-911X
• DOI: 10.1049/el.2019.4001

An effective and robust hybrid algorithm consisting of particle swarm optimisation (PSO) and limited memory Broyden–Fletcher–Goldfarb–Shanno (L-BFGS) method based on artificial neural network (ANN) is proposed for modelling flexible metal-oxide thin-film transistors (TFTs). The L-BFGS method as an optimiser is exploited to update the parameters of ANN and speed up the training process. A mutation strategy for PSO is derived to enhance the searching ability further. With the great global searching ability, PSO is implemented to find a hopeful initial position in solution space for the next ANN model. The simulation result shows a high accuracy not only in I–V curve fitting but also in small-signal parameter ($g_m$gm, $g_d$gd, etc.) predictions, which have not been exposed in the training process. The measured DC characteristics of In–Zn–O TFTs are used to verify the proposed ANN model, which has the benefits of rapid fitting from the L-BFGS algorithm and universal searching ability from PSO.