Studim krahasues i përçueshmërisë elektrike të komponimeve me bazë polimeri duke përdorur Matlab
DOI:
https://doi.org/10.55312/op.vi1.5891Abstrakti
Ky punim paraqet një studim krahasues të algoritmeve të machine-learning (ML) dhe deep-learning (DL) për analizimin e përçueshmërisë elektrike të kompozitëve me bazë polimerike. Përçueshmëria elektrike është një veti thelbësore në përbërjet e polimerit, duke ndikuar në performancën e tyre në aplikime të ndryshme, duke përfshirë elektronikën, sensorët dhe veshjet përçuese. Duke përdorur MATLAB, një bazë të dhënash me faktorë të tillë si lloji i mbushësit, përqendrimi, parametrat e përpunimit, morfologjia e mbushësit, matrica e polimerit, temperatura, lagështia dhe ekspozimi kimik gjenerohet në mënyrë sintetike. Të dhënat janë krijuar për të përmbledhur gamën e larmishme të faktorëve që ndikojnë në përçueshmërinë elektrike në përbërjet e polimerit. Në këtë studim, algoritmet ML të tilla si Support Vector Machines dhe Random Forests krahasohen me algoritmin DL, Convolutional Neural Networks (CNN). Çdo algoritëm është trajnuar në bazën e të dhënave për të parashikuar përçueshmërinë elektrike të përbërjeve të polimerit bazuar në faktorët e dhënë. Metrika të performancës përdoren për të vlerësuar saktësinë parashikuese dhe aftësinë e përgjithësimit të modeleve. Për më tepër, studimi heton interpretueshmërinë dhe efikasitetin llogaritës të modeleve ML krahasuar me aftësitë e të mësuarit të veçorive dhe përfaqësimit kompleks të modeleve DL. Rezultatet ofrojnë njohuri mbi pikat e forta dhe të dobëta të qasjeve të ndryshme algoritmike për analizimin e përçueshmërisë elektrike në përbërjet me bazë polimerike.
Fjalët kyçe:
Përbërjet polimerike, përçueshmëria elektrike, Machine Learning, Deep Learning, MATLABShkarkimet
References
-
Oladele, I. O., Omotosho, T. F., & Adediran, A. A. (2020, October 19). Polymer-Based Composites: An Indispensable Material for Present and Future Applications. International Journal of Polymer Science, 2020, 1–12. https://doi.org/10.1155/2020/8834518
-
2. Burger, N., Laachachi, A., Ferriol, M., Lutz, M., Toniazzo, V., & Ruch, D. (2016, October). Review of thermal conductivity in composites: Mechanisms, parameters and theory. Progress in Polymer Science, 61, 1–28. https://doi.org/10.1016/j.progpolymsci.2016.05.001
-
Huang, C., Qian, X., & Yang, R. (2018, October). Thermal conductivity of polymers and polymer nanocomposites. Materials Science and Engineering: R: Reports, 132, 1–22. https://doi.org/10.1016/j.mser.2018.06.002
-
Li, Z., & Du, B. (2018, November). Polymeric insulation for high-voltage dc extruded cables: challenges and development directions. IEEE Electrical Insulation Magazine, 34(6), 30–43. https://doi.org/10.1109/mei.2018.8507715
-
Montanari, G. C., Seri, P., Lei, X., Ye, H., Zhuang, Q., Morshuis, P., Stevens, G., & Vaughan,
-
A. (2018, March). Next generation polymeric high voltage direct current cables—A quantum leap needed? IEEE Electrical Insulation Magazine, 34(2), 24–31. https://doi.org/10.1109/mei.2018.8300441
-
Dang, Z., Yuan, J., Yao, S., & Liao, R. (2013, September 6). Flexible Nanodielectric Materials with High Permittivity for Power Energy Storage. Advanced Materials, 25(44), 6334–6365. https://doi.org/10.1002/adma.201301752
-
Yuan, C., Zhou, Y., Zhu, Y., Liang, J., Wang, S., Peng, S., Li, Y., Cheng, S., Yang, M., Hu, J.,
-
Zhang, B., Zeng, R., He, J., & Li, Q. (2020, August 6). Polymer/molecular semiconductor all-organic composites for high-temperature dielectric energy storage. Nature Communications, 11(1). https://doi.org/10.1038/s41467-020-17760-x
-
Andraju, N., Curtzwiler, G. W., Ji, Y., Kozliak, E., & Ranganathan, P. (2022, September 14). Machine-Learning-Based Predictions of Polymer and Postconsumer Recycled Polymer Properties: A Comprehensive Review. ACS Applied Materials & Interfaces, 14(38), 42771–42790. https://doi.
-
org/10.1021/acsami.2c08301
-
Wang, S., Sadowski, G., & Ji, Y. (2024, March 6). Strategy of Coupling Artificial Intelligence with Thermodynamic Mechanism for Predicting Complex Polymer Viscosities. ACS Sustainable Chemistry & Engineering, 12(11), 4631–4643. https://doi.org/10.1021/acssuschemeng.3c08185
-
Wang, S., Huang, Y., Chang, E., Zhao, C., Ameli, A., Naguib, H. E., & Park, C. B. (2021, May). Evaluation and modeling of electrical conductivity in conductive polymer nanocomposite foams with multiwalled carbon nanotube networks. Chemical Engineering Journal, 411, 128382. https://doi.org/10.1016/j.cej.2020.128382
-
Guo, Z., Poot, A. A., & Grijpma, D. W. (2021, April). Advanced polymer-based composites and structures for biomedical applications. European Polymer Journal, 149, 110388. https://doi.org/10.1016/j.eurpolymj.2021.110388
-
Pooja, Kumar, A., Prasher, P., & Mudila, H. (2022, December 19). Factors affecting the electrical conductivity of conducting polymers. Carbon Letters, 33(2), 307–324. https://doi.org/10.1007/s42823-022-00443-6
-
Wan, Y. J., Li, G., Yao, Y. M., Zeng, X. L., Zhu, P. L., & Sun, R. (2020, June). Recent advances in polymer-based electronic packaging materials. Composites Communications, 19, 154–167.https://doi.org/10.1016/j.coco.2020.03.011
-
Zhang, F., & O’Donnell, L. J. (2020). Support vector regression. Machine Learning, 123–140. https://doi.org/10.1016/b978-0-12-815739-8.00007-9
-
Aria, M., Cuccurullo, C., & Gnasso, A. (2021, December). A comparison among interpretative proposals for Random Forests. Machine Learning With Applications, 6, 100094. https://doi.org/10.1016/j.mlwa.2021.100094
-
Zhou, J., Huang, S., Wang, M., & Qiu, Y. (2021, May 29). Performance evaluation of hybrid GA–SVM and GWO–SVM models to predict earthquake-induced liquefaction potential of soil: a multi-dataset investigation. Engineering With Computers, 38(S5), 4197–4215. https://doi.
-
org/10.1007/s00366-021-01418-3
-
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021, March 31). Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data, 8(1).
-
Ejaz, F., Hwang, L. K., Son, J., Kim, J. S., Lee, D. S., & Kwon, B. (2022, August 10). Convolutional neural networks for approximating electrical and thermal conductivities of Cu-CNT composites. Scientific Reports, 12(1). https://doi.org/10.1038/s41598-022-16867-z
-
Ali, L., Alnajjar, F., Jassmi, H. A., Gocho, M., Khan, W., & Serhani, M. A. (2021, March 1). Performance Evaluation of Deep CNN-Based Crack Detection and Localization Techniques for Concrete Structures. Sensors, 21(5), 1688. https://doi.org/10.3390/s21051688
References
Oladele, I. O., Omotosho, T. F., & Adediran, A. A. (2020, October 19). Polymer-Based Composites: An Indispensable Material for Present and Future Applications. International Journal of Polymer Science, 2020, 1–12. https://doi.org/10.1155/2020/8834518
2. Burger, N., Laachachi, A., Ferriol, M., Lutz, M., Toniazzo, V., & Ruch, D. (2016, October). Review of thermal conductivity in composites: Mechanisms, parameters and theory. Progress in Polymer Science, 61, 1–28. https://doi.org/10.1016/j.progpolymsci.2016.05.001
Huang, C., Qian, X., & Yang, R. (2018, October). Thermal conductivity of polymers and polymer nanocomposites. Materials Science and Engineering: R: Reports, 132, 1–22. https://doi.org/10.1016/j.mser.2018.06.002
Li, Z., & Du, B. (2018, November). Polymeric insulation for high-voltage dc extruded cables: challenges and development directions. IEEE Electrical Insulation Magazine, 34(6), 30–43. https://doi.org/10.1109/mei.2018.8507715
Montanari, G. C., Seri, P., Lei, X., Ye, H., Zhuang, Q., Morshuis, P., Stevens, G., & Vaughan,
A. (2018, March). Next generation polymeric high voltage direct current cables—A quantum leap needed? IEEE Electrical Insulation Magazine, 34(2), 24–31. https://doi.org/10.1109/mei.2018.8300441
Dang, Z., Yuan, J., Yao, S., & Liao, R. (2013, September 6). Flexible Nanodielectric Materials with High Permittivity for Power Energy Storage. Advanced Materials, 25(44), 6334–6365. https://doi.org/10.1002/adma.201301752
Yuan, C., Zhou, Y., Zhu, Y., Liang, J., Wang, S., Peng, S., Li, Y., Cheng, S., Yang, M., Hu, J.,
Zhang, B., Zeng, R., He, J., & Li, Q. (2020, August 6). Polymer/molecular semiconductor all-organic composites for high-temperature dielectric energy storage. Nature Communications, 11(1). https://doi.org/10.1038/s41467-020-17760-x
Andraju, N., Curtzwiler, G. W., Ji, Y., Kozliak, E., & Ranganathan, P. (2022, September 14). Machine-Learning-Based Predictions of Polymer and Postconsumer Recycled Polymer Properties: A Comprehensive Review. ACS Applied Materials & Interfaces, 14(38), 42771–42790. https://doi.
org/10.1021/acsami.2c08301
Wang, S., Sadowski, G., & Ji, Y. (2024, March 6). Strategy of Coupling Artificial Intelligence with Thermodynamic Mechanism for Predicting Complex Polymer Viscosities. ACS Sustainable Chemistry & Engineering, 12(11), 4631–4643. https://doi.org/10.1021/acssuschemeng.3c08185
Wang, S., Huang, Y., Chang, E., Zhao, C., Ameli, A., Naguib, H. E., & Park, C. B. (2021, May). Evaluation and modeling of electrical conductivity in conductive polymer nanocomposite foams with multiwalled carbon nanotube networks. Chemical Engineering Journal, 411, 128382. https://doi.org/10.1016/j.cej.2020.128382
Guo, Z., Poot, A. A., & Grijpma, D. W. (2021, April). Advanced polymer-based composites and structures for biomedical applications. European Polymer Journal, 149, 110388. https://doi.org/10.1016/j.eurpolymj.2021.110388
Pooja, Kumar, A., Prasher, P., & Mudila, H. (2022, December 19). Factors affecting the electrical conductivity of conducting polymers. Carbon Letters, 33(2), 307–324. https://doi.org/10.1007/s42823-022-00443-6
Wan, Y. J., Li, G., Yao, Y. M., Zeng, X. L., Zhu, P. L., & Sun, R. (2020, June). Recent advances in polymer-based electronic packaging materials. Composites Communications, 19, 154–167.https://doi.org/10.1016/j.coco.2020.03.011
Zhang, F., & O’Donnell, L. J. (2020). Support vector regression. Machine Learning, 123–140. https://doi.org/10.1016/b978-0-12-815739-8.00007-9
Aria, M., Cuccurullo, C., & Gnasso, A. (2021, December). A comparison among interpretative proposals for Random Forests. Machine Learning With Applications, 6, 100094. https://doi.org/10.1016/j.mlwa.2021.100094
Zhou, J., Huang, S., Wang, M., & Qiu, Y. (2021, May 29). Performance evaluation of hybrid GA–SVM and GWO–SVM models to predict earthquake-induced liquefaction potential of soil: a multi-dataset investigation. Engineering With Computers, 38(S5), 4197–4215. https://doi.
org/10.1007/s00366-021-01418-3
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021, March 31). Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data, 8(1).
https://doi.org/10.1186/s40537-021-00444-8
Ejaz, F., Hwang, L. K., Son, J., Kim, J. S., Lee, D. S., & Kwon, B. (2022, August 10). Convolutional neural networks for approximating electrical and thermal conductivities of Cu-CNT composites. Scientific Reports, 12(1). https://doi.org/10.1038/s41598-022-16867-z
Ali, L., Alnajjar, F., Jassmi, H. A., Gocho, M., Khan, W., & Serhani, M. A. (2021, March 1). Performance Evaluation of Deep CNN-Based Crack Detection and Localization Techniques for Concrete Structures. Sensors, 21(5), 1688. https://doi.org/10.3390/s21051688