Machine Learning and Hybrid Fuzzy Logic for Prediction and Optimization of Flexible Supercapacitor Performance for Smart Textiles

Abstract

In this study, a hybrid decision support system combining Fuzzy AHP, Type-2 Fuzzy TOPSIS, and XGBoost+SHAP methods has been developed for performance optimization of smart textile-based flexible supercapacitor electrodes. Experimental data were collected under over 250 different synthesis conditions to investigate the effects of synthesis parameters; surface area, pore size, conductivity, film thickness, synthesis temperature, flexibility on performance outputs; specific capacitance, energy density, cyclic stability. The highest value for specific capacitance (912 F/g) was obtained at surface area 2450 m²/g, pore size 22 nm, conductivity 8500 S/cm and synthesis temperature 1050°C. According to Fuzzy AHP, the weight of surface area was 0.68, while XGBoost+SHAP showed that this parameter provides an average positive contribution of +47 F/g. The maximum energy density (72.4 Wh/kg) was measured at synthesis temperature 1200°C, conductivity 9800 S/cm, surface area 2300 m²/g. In Type-2 TOPSIS, this point was classified as "excellent" (closeness coefficient 0.94). The highest cyclic stability (92.3%) was observed at pore size 35 nm, film thickness 125 µm, synthesis temperature 700°C. SHAP analysis showed that stability decreases by 12% when pore size falls below 25 nm. High agreement was found between the prediction accuracy of the hybrid model (R² = 0.94) and experimental results.

Keywords

• Smart textile
• Type-2 fuzzy logic
• Machine learning
• Energy density
• Cyclic stability
• Specific capacitance.

Makine Öğrenmesi ve Hibrit Bulanık Mantık ile Akıllı Tekstiller için Esnek Süperkapasitör Performansının Tahmini ve Optimizasyonu

Abstract

Bu çalışmada, akıllı tekstil tabanlı esnek süperkapasitör elektrotlarının performans optimizasyonu için Hibrit Bulanık AHP, Tip-2 Bulanık TOPSIS ve XGBoost+SHAP yöntemlerini birleştiren hibrit bir karar destek sistemi geliştirilmiştir. Deneysel veriler, 6 farklı sentez parametresi olan; yüzey alanı, gözenek boyutu, iletkenlik, film kalınlığı, sentez sıcaklığı, esneklik ile 3 farklı performans çıktısı olan özgül kapasitans, enerji yoğunluğu, döngüsel kararlılık üzerindeki etkilerini incelemek üzere 250’den fazla farklı sentez koşulunda toplanmıştır. Özgül kapasitans için en yüksek değer (912 F/g), yüzey alanı 2450 m²/g, gözenek boyutu 22 nm, iletkenlik 8500 S/cm ve sentez sıcaklığı 1050°C’de elde edilmiştir. Hibrit Fuzzy AHP’ye göre yüzey alanı ağırlığı 0.68 iken, XGBoost+SHAP bu parametrenin ortalama +47 F/g pozitif katkı sağladığını göstermiştir. Enerji yoğunluğu maksimumu (72.4 Wh/kg), sentez sıcaklığı 1200°C, iletkenlik 9800 S/cm, yüzey alanı 2300 m²/g’de ölçülmüştür. Tip-2 TOPSIS’te bu nokta “mükemmel” (yakınlık katsayısı 0.94) olarak sınıflandırılmıştır. Döngüsel kararlılık en yüksek (%92.3), gözenek boyutu 35 nm, film kalınlığı 125 µm, sentez sıcaklığı 700°C’de gözlenmiştir. SHAP analizi, gözenek boyutunun 25 nm altına düşmesi durumunda kararlılığın %12 oranında azaldığını göstermiştir. Hibrit modelin tahmin doğruluğu (R² = 0.94) ile deneysel sonuçlar arasında yüksek uyum bulunmuştur.

Keywords

• Akıllı tekstil
• Tip-2 bulanık mantık
• Makine öğrenmesi
• Enerji yoğunluğu
• Döngüsel kararlılık
• Özgül kapasitans.

References

1. Adriyani, T. R., Ensafi, A. A., & Rezaei, B. (2023). Flexible and sewable electrode based on Ni-Co@ PANI-salphen composite-coated on textiles for wearable supercapacitor. Scientific Reports, 13(1), 19772. https://doi.org/10.1038/s41598-023-47067-y
2. Azari, A., Nabizadeh, R., Mahvi, A. H., & Nasseri, S. (2022). Integrated Fuzzy AHP-TOPSIS for selecting the best color removal process using carbon-based adsorbent materials: multi-criteria decision making vs. systematic review approaches and modeling of textile wastewater treatment in real conditions. International Journal of Environmental Analytical Chemistry, 102(18), 7329-7344. https://doi.org/10.1080/03067319.2020.1828395
3. Chen, Y., Wang, H., Wang, C., Yang, J., Liu, X., Ma, Y., ... & Pan, L. (2025). Machine learning-guided prediction of energy storage performance of carbon cathode materials for zinc-ion hybrid capacitors. Journal of Colloid and Interface Science, 699, 138139. https://doi.org/10.1016/j.jcis.2025.138139
4. Cheng, W., Hu, M., & Wu, C. (2025). Enhancing green building decision-making with a hybrid fuzzy AHP-TOPSIS model for material selection. Applied Water Science, 15(6), 129. https://doi.org/10.1007/s13201-025-02481-7
5. Deshsorn, K., Payakkachon, K., Chaisrithong, T., Jitapunkul, K., Lawtrakul, L., & Iamprasertkun, P. (2023). Unlocking the full potential of heteroatom-doped graphene-based supercapacitors through stacking models and SHAP-guided optimization. Journal of Chemical Information and Modeling, 63(16), 5077-5088. https://doi.org/10.1021/acs.jcim.3c00670
6. Dong, L., Liang, G., Xu, C., Liu, W., Pan, Z., Zhou, E., Kang, F., & Yang, Q.-H. (2017). Multi hierarchical construction-induced superior capacitive performances of flexible electrodes for wearable energy storage. Nano Energy, 34, 242-248. https://doi.org/10.1016/j.nanoen.2017.02.031
7. Emad-Eldeen, A., Azim, M. A., Abdelsattar, M., & AbdelMoety, A. (2024). Utilizing machine learning and deep learning for enhanced supercapacitor performance prediction. Journal of Energy Storage, 100, 113556. https://doi.org/10.1016/j.est.2024.113556
8. Fuse, K., Dalsaniya, A., Modi, D., Vora, J., Pimenov, D. Y., Giasin, K., ... & Wojciechowski, S. (2021). Integration of fuzzy AHP and fuzzy TOPSIS methods for wire electric discharge machining of titanium (Ti6Al4V) alloy using RSM. Materials, 14(23), 7408. https://doi.org/10.3390/ma14237408

9. Gong, T., Yu, W., & Wang, X. (2026). Prediction of composite supercapacitor performance through combining machine learning with novel binder-related features. Nanomaterials, 16(8), 478. https://doi.org/10.3390/nano16080478
10. Ishak, A., & Wanli. (2020). Analysis of fuzzy AHP-TOPSIS methods in multi criteria decision making: Literature review. IOP Conference series: materials science and engineering, 1003(1), 012147. https://doi.org/10.1088/1757-899x/1003/1/012147
11. Khan, A., Grabher, G., & Hossain, G. (2023). Smart-textile supercapacitor for wearable energy storage system. Journal of Energy Storage, 73(1), 108963. https://doi.org/10.1016/j.est.2023.108963
12. Kitila, L. G., Duc, E., Durieux, S., & Taddese, G. A. (2026). An integrated fuzzy AHP-fuzzy TOPSIS approach for multi-criteria decision-making framework in sustainable manufacturing process selection. The International Journal of Advanced Manufacturing Technology, 142(1), 559-583. https://doi.org/10.1007/s00170-025-16881-1
13. Kushwaha, R., Singh, M. K., Krishnan, S., & Rai, D. K. (2023). Machine learning enabled property prediction of carbon-based electrodes for supercapacitors. Journal of Materials Science, 58(39), 15448-15458. https://doi.org/10.1007/s10853-023-08981-8
14. Li, D., Gu, J., Zhang, X., Wang, H., Zhan, W., Wu, P., ... & Liang, J. (2026). Highly flexible fiber supercapacitors with ultra-high energy density for energy storage electronic textiles. Nano Letters, 26(7), 2484-2492. https://doi.org/10.1021/acs.nanolett.5c05637
15. Liu, P., Wen, Y., Huang, L., Zhu, X., Wu, R., Ai, S., ... & Ge, Y. (2021). An emerging machine learning strategy for the assisted‐design of high-performance supercapacitor materials by mining the relationship between capacitance and structural features of porous carbon. Journal of Electroanalytical Chemistry, 899, 115684. https://doi.org/10.1016/j.jelechem.2021.115684
16. Luo, X., Liang, Y., Weng, W., Hu, Z., Zhang, Y., Yang, J., Yang, L., & Zhu, M. (2020). Polypyrrole-coated carbon nanotube/cotton hybrid fabric with high areal capacitance for flexible quasi-solid-state supercapacitors. Energy Storage Materials, 33, 11-17. https://doi.org/10.1016/j.ensm.2020.07.036
17. Manjakkal, L., Pullanchiyodan, A., Yogeswaran, N., Hosseini, E. S., & Dahiya, R. (2020). A wearable supercapacitor based on conductive PEDOT: PSS‐coated cloth and a sweat electrolyte. Advanced Materials, 32(24), 1907254. https://doi.org/10.1002/adma.201907254
18. Song, P., He, X., Xie, M., Tao, J., Shen, X., Ji, Z., Yan, Z., Zhai, L., & Yuan, A. (2020). Polyaniline wrapped graphene functionalized textile with ultrahigh areal capacitance and energy density for high-performance all-solid-state supercapacitors for wearable electronics. Composites Science and Technology, 198, 108305. https://doi.org/10.1016/j.compscitech.2020.108305
19. Tang, M., Ding, Y., Hu, T., Zhu, X., Zheng, G., & Tian, Y. (2024). Machine learning‐based prediction of supercapacitor capacitance for MgCo2O4 electrodes. ChemPhysChem, 25(21), e202400629. https://doi.org/10.1002/cphc.202400629
20. Tamtam, F., & Tourabi, A. (2025). Integrating Fuzzy AHP-TOPSIS for material selection in green hydrogen and ammonia production. Revue des Composites et des Materiaux Avances, 35(2), 355. https://doi.org/10.18280/rcma.350217
21. Zhang, Y., Zhang, S., Qi, K., Wang, Y., Chen, W., Xu, J., ... & Lu, W. (2025). Scalable assembly of polyaniline/Ti3C2Tx MXene modified cotton yarn flexible electrode for high-performance wearable energy storage. Chemical Engineering Science, 305, 121206. https://doi.org/10.1016/j.ces.2025.121206
22. Zhao, C., Lu, X., Tu, H., Yang, Y., Wang, S., Chen, A., & Zhang, H. (2024). Research on specific capacitance prediction of biomass carbon-based supercapacitors based on machine learning. Journal of Energy Storage, 97, 112974. https://doi.org/10.1016/j.est.2024.112974