Soft computing evaluation of luffa oil epoxide development using luffa fiber catalyst

Epoxidation of luffa oil was performed using a heterogeneous catalyst developed from calcined luffa fibres. Although luffa oil has previously been epoxidized for biopolymer and polyol production, no study has reported the use of luffa fibre as a catalyst for epoxidation reactions, presenting a clear research gap. Additionally, existing studies lack comprehensive comparative modeling using soft-computing techniques. The fibres were initially washed, dried, pulverized with a ball mill, and sieved to a particle size of 300 μm. They were then treated with 0.5 M sulphuric acid and calcined at 700 °C for four hours to introduce active sites. Characterization using FTIR, SEM, XRD, BET surface analysis, and XRF confirmed that --SO₃H functional groups were successfully incorporated onto the catalyst surface. Process optimization was carried out using catalyst loading, reaction duration, and temperature as the key input factors, while the oxirane value was taken as the output response. Increasing these operational variables led to a notable rise in oxirane yield. Response Surface Methodology (RSM) was used to identify the best reaction conditions, and the resulting quadratic model was validated through ANOVA, which produced R² = 0.9927, adjusted R² = 0.9833, and predicted R² = 0.8828 indicating strong model performance. Three-dimensional surface plots further highlighted the significant effects of the variables on oxirane formation. Model accuracy was assessed using R² and mean square error (MSE). The highest oxirane yield (3.34 mol) was obtained at a catalyst loading of 1.62 wt%, reaction time of 6.81 h, and temperature of 57.34 °C. Additional predictive analyses using Artificial Neural Networks (ANN) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS) showed that ANFIS provided superior predictive reliability, achieving R² = 0.9969 and MSE = 6.7 × 10⁻⁷, compared with ANN results (R² = 0.9378, MSE = 0.060991). FTIR and GC-MS examination of the resulting epoxide confirmed the formation of oxirane functional groups. The dual utilization of the luffa plant—employing its oil as feedstock and its fibre as catalyst—represents a novel, sustainable approach that enhances the industrial value of this non-edible crop. The findings demonstrate that soft-computing techniques, particularly ANFIS, offer robust predictive capabilities for optimizing bioepoxide production, providing a framework for developing cost-effective, environmentally benign catalysts and reducing dependence on petrochemical-derived epoxides.

Authors

Institutions

Publication Details

Journal
Discover Chemistry.
Published
2026-11-14
DOI
https://doi.org/10.1007/s44371-026-01050-4
Primary Topic
Biodiesel Production and Applications
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Soft computing evaluation of luffa oil epoxide development using luffa fiber catalyst

Kenechi Nwosu‐Obieogu, Prince Chinaemeze Iroabueke
Discover Chemistry.
Biodiesel Production and Applications
article

Soft computing evaluation of luffa oil epoxide development using luffa fiber catalyst

Kenechi Nwosu‐Obieogu, Prince Chinaemeze Iroabueke
article en

Abstract

Epoxidation of luffa oil was performed using a heterogeneous catalyst developed from calcined luffa fibres. Although luffa oil has previously been epoxidized for biopolymer and polyol production, no study has reported the use of luffa fibre as a catalyst for epoxidation reactions, presenting a clear research gap. Additionally, existing studies lack comprehensive comparative modeling using soft-computing techniques. The fibres were initially washed, dried, pulverized with a ball mill, and sieved to a particle size of 300 μm. They were then treated with 0.5 M sulphuric acid and calcined at 700 °C for four hours to introduce active sites. Characterization using FTIR, SEM, XRD, BET surface analysis, and XRF confirmed that --SO₃H functional groups were successfully incorporated onto the catalyst surface. Process optimization was carried out using catalyst loading, reaction duration, and temperature as the key input factors, while the oxirane value was taken as the output response. Increasing these operational variables led to a notable rise in oxirane yield. Response Surface Methodology (RSM) was used to identify the best reaction conditions, and the resulting quadratic model was validated through ANOVA, which produced R² = 0.9927, adjusted R² = 0.9833, and predicted R² = 0.8828 indicating strong model performance. Three-dimensional surface plots further highlighted the significant effects of the variables on oxirane formation. Model accuracy was assessed using R² and mean square error (MSE). The highest oxirane yield (3.34 mol) was obtained at a catalyst loading of 1.62 wt%, reaction time of 6.81 h, and temperature of 57.34 °C. Additional predictive analyses using Artificial Neural Networks (ANN) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS) showed that ANFIS provided superior predictive reliability, achieving R² = 0.9969 and MSE = 6.7 × 10⁻⁷, compared with ANN results (R² = 0.9378, MSE = 0.060991). FTIR and GC-MS examination of the resulting epoxide confirmed the formation of oxirane functional groups. The dual utilization of the luffa plant—employing its oil as feedstock and its fibre as catalyst—represents a novel, sustainable approach that enhances the industrial value of this non-edible crop. The findings demonstrate that soft-computing techniques, particularly ANFIS, offer robust predictive capabilities for optimizing bioepoxide production, providing a framework for developing cost-effective, environmentally benign catalysts and reducing dependence on petrochemical-derived epoxides.

Discover Chemistry.Vol. 3(1)
Michael Okpara University of Agriculture (NG)
Biodiesel Production and Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon