Compact modeling of metal-oxide TFTs based on artificial neural network and improved particle swarm optimization


The application of artificial neural network (ANN) can give a very accurate and fast model for semiconductor devices used in circuit simulations. In this paper, we have applied multi-layer perceptron (MLP) neural network based on limited memory Broyden–Fletcher–Goldfarb–Shanno (L-BFGS) method to model the flexible metal-oxide thin-film transistors (TFTs). An improved particle swarm optimization (PSO) is employed to find suitable initial parameters for the ANN model, which consists of a centroid opposition-based learning algorithm and a mutation strategy based on Euclidean distance to enhance the searching ability further. This hybrid modeling routine can improve the accuracy of predictions of both the I–V and small signal parameters (\(g_d\), \(g_m\), etc.) characteristics, which are in good agreement with experimental data and fully demonstrate the validity of the proposed model. Furthermore, the model is implemented into a simulator with Verilog-A. The circuit-level tests of TFT show that the ANN compact model with PSO enables accurate performance estimation of metal-oxide TFT circuits.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8


  1. 1.

    Zhang, L., Huang, C., Li, G., Zhou, L., Wu, W., Xu, M., Wang, L., Ning, H., Yao, R., Peng, J.: A low-power high-stability flexible scan driver integrated by IZO TFTs. IEEE Trans. Electron. Devices 63(4), 1779–1782 (2016)

    Article  Google Scholar 

  2. 2.

    Jeong, J.K.: The status and perspectives of metal oxide thin-film transistors for active matrix flexible displays. Semicond. Sci. Technol. 26(3), 034008 (2011)

    Article  Google Scholar 

  3. 3.

    Fang, J., Deng, W., Ma, X., Huang, J., Wu, W.: A surface-potential-based DC model of amorphous oxide semiconductor TFTs including degeneration. IEEE Electron Device Lett. 38(2), 183–186 (2017)

    Article  Google Scholar 

  4. 4.

    He, H., He, J., Deng, W., Wang, H., Liu, Y., Zheng, X.: Trapped-charge-effect-based above-threshold current expressions for amorphous silicon TFTs consistent with Pao-Sah model. IEEE Trans. Electron Devices 61(11), 3744–3750 (2014)

    Article  Google Scholar 

  5. 5.

    Tsormpatzoglou, A., Hastas, N.A., Choi, N., Mahmoudabadi, F., Hatalis, M.K., Dimitrialdis, C.A.: Analytical surface potential-based drain current model for amorphous InGaZno thin film transistors. J. Appl. Phys. 114(18), 184502–1845026 (2013)

    Article  Google Scholar 

  6. 6.

    Garcia, R., Mejia, I., Tinoco, J., et al.: A compact drain current model for thin-film transistor under bias stress condition. IEEE Trans. Electron Devices 65(5), 1803–1809 (2018)

    Article  Google Scholar 

  7. 7.

    Bahubalindrun, P., Tavares, V., Barquinha, P., Oliveira, P., Martins, R., Fortunato, E.: InGaZnO TFT behavioral model for IC design. Analog Integr. Circuits Signal Process. 87(1), 73–80 (2016)

    Article  Google Scholar 

  8. 8.

    Hayati, M., Rezaei, A., Seifi, M.: CNT-MOSFET modeling based on artificial neural network: application to simulation of nanoscale circuits. Solid-State Electron. 54(1), 52–57 (2010)

    Article  Google Scholar 

  9. 9.

    Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2(5), 359–366 (1989)

    Article  Google Scholar 

  10. 10.

    Tavares, V., Candido, D., Barquinha, P.: a-GIZO TFT neural modeling, circuit simulation and validation. Solid State Electron. 105, 30–36 (2015)

    Article  Google Scholar 

  11. 11.

    Liu, D., Nocedal, J.: On the limited memory BFGS method for large scale optimization. Math. Program. 45(1), 503–528 (1989)

    MathSciNet  Article  Google Scholar 

  12. 12.

    Eberhart, R., Kennedy, J.: A new optimizer using particle swarm theory. In: Proceedings of the Sixth International Symposium on Micro Machine and Human Science, pp. 39–43 (1995)

  13. 13.

    Ismail, A., Jeng, D.S., Zhang, L.: An optimised product-unit neural network with a novel PSO-BP hybrid training algorithm: applications to load-deformation analysis of axially loaded piles. Eng. Appl. Artif. Intell. 26(10), 2305–2314 (2013)

    Article  Google Scholar 

  14. 14.

    Hou, C., Yu, X., Cao, Y., Lai, C., Cao, Y.: Prediction of synchronous closing time of permanent magnetic actuator for vacuum circuit breaker based on PSO-BP. IEEE Trans. Dielectr. Electr. Insul. 24(6), 3321–3326 (2017)

    Article  Google Scholar 

  15. 15.

    Wang, H., Li, H., Liu, Y., Li, C., Zeng, S.: Opposition-based particle swarm algorithm with Cauchy mutation. In: IEEE Congress on Evolutionary Computation, pp. 25–28 (2007)

  16. 16.

    Peng, Y., Deng, W., Wu, W., Luo, Z., Huang, J.: Hybrid modeling routine for metal-oxide TFTs based on particle swarm optimization and artificial neural network. Electron. Lett. 56(9), 453–456 (2020)

    Article  Google Scholar 

  17. 17.

    Zhang, L., Chan, M.: Artificial neural network design for compact modeling of generic transistors. J. Comput. Electron. 16(3), 825–832 (2017)

    Article  Google Scholar 

  18. 18.

    Tizhoosh, H.: Opposition-based learning: a new scheme for machine intelligence. In: Conference on Intelligent Agents, Web Technologies and Internet Commerce. 1, pp. 695–701 (2005)

  19. 19.

    Xu, Q., Wang, L., Hei, X., Zhao, L.: A review of opposition-based learning from 2005 to 2012. Eng. Appl. Artif. Intell. 29(3), 1–12 (2014)

    Article  Google Scholar 

  20. 20.

    Rahnamayan, S., Jesuthasan, J., Bourennani, F., Salehinejad, H.: Computing opposition by involving entire population. In: IEEE Congress on Evolutionary Computation, pp. 6–11 (2014)

  21. 21.

    Wei, T., Yu, F., Huang, G., Xu, C.: A particle-swarm-optimization-based parameter extraction routine for three-diode lumped parameter model of organic solar cells. IEEE Electron Devices Lett. 40(9), 1511–1514 (2019)

    Article  Google Scholar 

  22. 22.

    Chen, Z., Xu, W., Wu, J., Zhou, L., Wu, W., Zhao, J.: A new high gain operational amplifier using transconductance-enhancement topology integrated with metal oxide TFTs. IEEE J. Electron Devices Soc. 7(1), 111–117 (2018)

    Google Scholar 

  23. 23.

    Huang, T., Fukuda, K., Lo, C., Yeh, Y., Sekitani, T., Someya, T., Cheng, L.: Pseudo-CMOS: a design style for low-cost and robust flexible electronics. IEEE Trans. Electron. Devices 58(1), 141–150 (2011)

    Article  Google Scholar 

  24. 24.

    Wu, W., Li, G., Xia, X., Zhang, L., Zhou, L., Xu, M., Wang, L.: Low-power bi-side scan driver integrated by IZO TFTs including a clock-controlled inverter. J. Disp. Technol. 10(7), 523–525 (2014)

    Article  Google Scholar 

  25. 25.

    Iñiguez, B., Xu, Z., Fjeldly, T.A., Shur, M.S.: Unified model for short-channel poly-Si TFTs. Solid-State Electron. 43(10), 1821–1831 (1999)

    Article  Google Scholar 

Download references


The authors would like to thank New Vision Opto-Electronic Technology Co., Ltd., China, for data support of IZO-TFT devices and circuits. This work was supported by the Guangdong Natural Science Foundation under Grants 2018A030313018 and 2020A1515010567.

Author information



Corresponding author

Correspondence to Zhi Luo.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Deng, W., Zhang, W., Peng, Y. et al. Compact modeling of metal-oxide TFTs based on artificial neural network and improved particle swarm optimization. J Comput Electron (2021).

Download citation


  • Particle swarm optimization (PSO)
  • Limited memory Broyden–Fletcher–Goldfarb–Shanno (L-BFGS)
  • Metal-oxide thin-film transistors