Predicting the Capacitance of Parallel Plate 
Capacitors Using Adaptive Neuro-Fuzzy 
Inference System (ANFIS)

Zvikomborero Hweju; Varaidzo Sostina Dandira

doi:https://doi.org/10.14445/23497157/IJRES-V7I5P105

Research Article | Open Access | Download PDF

Volume 7 | Issue 5 | Year 2020 | Article Id. IJRES-V7I5P105 | DOI : https://doi.org/10.14445/23497157/IJRES-V7I5P105

Predicting the Capacitance of Parallel Plate Capacitors Using Adaptive Neuro-Fuzzy Inference System (ANFIS)

Zvikomborero Hweju, Varaidzo Sostina Dandira

Citation :

Zvikomborero Hweju, Varaidzo Sostina Dandira, "Predicting the Capacitance of Parallel Plate Capacitors Using Adaptive Neuro-Fuzzy Inference System (ANFIS)," International Journal of Recent Engineering Science (IJRES), vol. 7, no. 5, pp. 28-30, 2020. Crossref, https://doi.org/10.14445/23497157/IJRES-V7I5P105

Abstract

Parallel plate capacitors are indispensable passive devices with diverse applications in the field of electronics. The accurate prediction of capacitance value at full charge is of paramount importance during this valuable device's design stage. This work presents a parallel plate capacitance prediction using the Adaptive Neuro-Fuzzy Inference System (ANFIS). The design of the experiment has been achieved using the Taguchi experimental design method. This study's control variables are dielectric absolute permittivity, plate surface area, and plate separation, while capacitance is the single response variable considered. The ANFIS model has a 100% prediction accuracy on training datasets and 83.63% prediction accuracy on testing datasets. The results indicate the reliability of the ANFIS model in parallel plate capacitance prediction during the design stage.

Keywords

ANFIS, Parallel Plate Capacitance, Absolute Permittivity, Plate Surface Area, and Plate Separation.

References

[1] H. Nishiyama and M. Nakamura, Form and Capacitance of ParallelPlate Capacitors, IEEE Transactions On Components, Packaging, And Manufacturing Technology-Part A, (17) (1994) 477-484.
[2] D. K. Reitan, Accurate Determination of the Capacitance of Rectangular Parallel-Plate Capacitors, Journal of Applied Physics, (30) (1959) 172-176.
[3] A. T. Adams and J. R. Mautz, Computer solution of Electrostatic Problems by Matrix Inversion, Proceedings of the 1969 National Electronics Conference.(1969) 198-201.
[4] J. S. R. Jang, ANFIS: Adaptive-network-based fuzzy inference system, IEEE Transactions on Systems, Man and Cybernetics, (23) (1993) 665-685.
[5] A. M. Abdulshahed, A. P.Longstaff, and S. Fletcher, The application of ANFIS prediction models for thermal error compensation on CNC machine tools, Applied Soft Computing, (27) (2015) 158-168.
[6] O Anil Kumar, Ch Rami Reddy, Hybrid Neuro-Fuzzy controller based Adaptive Neuro-Fuzzy Inference System Approach for MultiArea Load Frequency Control of Interconnected Power System, SSRG International Journal of Electrical and Electronics Engineering 3(1) (2016) 17-25.