Abstract :
Muhammad Asyraf Mat Asri1,a,*, Hidayani Jaafar1,b, Haryati Jaafar2,c and Zainal Ariffin Ahmad3,d
1Faculty of Bioengineering and Technology, Universiti Malaysia Kelantan, Jeli Campus, 17600, Jeli, Kelantan, Malaysia
2Universiti Malaysia Perlis, 02600 Arau, Perlis
3Universiti Sains Malaysia Engineering Campus,14300 Nibong Tebal, Pulau Pinang.,
a*j23d007f@siswa.umk.edu.my, bhidayani@umk.edu.my, charyati@unimap.edu.my, dsrzainal@usm.my
Abstract. Power conversion efficiency (PCE) from dye sensitized solar cell(DSSC) is typically in the average range (<0.05–1.7%) and requires a thorough understanding of the role of pigment’s molecular structure, electronic properties, anchoring groups, and conjugated double bonds or free π-electrons for improved PCE from enhanced carriers transport and decreased recombination. Narrowband absorption and poor binding with photoanode are the limitation for band gap using natural dye that need to overcome. Therefore, by built supervised classification models would allow the scientific community to further study the impact of band gap on the performance of natural dyes.We aim to optimize the non-linearity behaviour of band gap using adaptive neural fuzzy inference system (ANFIS) model for natural dye sensitizers performance based on π bonds, anchoring group, and HOMO-LUMO. The ANFIS network, which is the best in data predicting, was trained with back propagation optimum method. In this study, 30 natural dyes will be extracted from different anthocyanin types. Data collection using FTIR, EIS, UV-VIS for number of π-bonds (PI), the number of anchoring groups, HOMO-LUMO, and bandgap energy will be collected. To further interpret the data collection, ANFIS model will design comprised of a five-layered neural network that used fuzzy inference system concepts. Input (π bonds, anchoring group, HOMO-LUMO, bandgap), hidden, and output layers (% of PCE) made up the structure. This work shows the potential of adopting trained classifiers for analyzing natural sensitizer’s abilities to inject and separate generated electron-hole pairs for producing renewable, cost-effective, and sustainable energy.
Keywords: Power conversion efficiency, adaptive neural fuzzy inference system, anthocyanin, bandgap energy, dye sensitized solar cell |
