Optimizing pretreatment of Leucaena leucocephala using artificial neural networks (ANNs). (September 2019)

• Record Type: Journal Article
• Authors: Kumari, Neeta; Garg, Shruti; Singhal, Anjali; Kumar, Madan; Bhattacharya, Mallika; Jha, Pawan Kumar; Chauhan, Devendra Kumar; Thakur, Indu Shekhar
• Is Part Of: Bioresource technology reports. Volume 7(2019)
• Publication Date: 2019-09
• Subjects: Pretreatment -- Artificial neural network -- Optimization -- Leucaena; Biomass energy -- Periodicals; Biotransformation (Metabolism) -- Periodicals; Agricultural wastes -- Periodicals; Factory and trade waste -- Periodicals; Organic wastes -- Periodicals; Waste products as fuel -- Periodicals; Waste products as fuel; Organic wastes; Factory and trade waste; Biotransformation (Metabolism); Biomass energy; Agricultural wastes; Periodicals; Electronic journals; 662.88
• DOI: 10.1016/j.biteb.2019.100289
• Languages: English
• ISSNs: 2589-014X

Abstract

Abstract: This study deals with optimizing the pretreatment process for Leucaena leucocephala wood. Total 51 experiments were conducted. Three parameters were optimized i.e. catalyst concentration (1–3%), duration (120–300 min) and temperature (100–150 °C). Improvement in saccharification efficiency was evaluated using commercial cellulases. Single response, total reducing sugar yield, was estimated at the end of the experiments. The results of these experiments were analysed by three algorithms of neural networks i.e. Bayesian Regularization Neural Network (BRNN), Scaled Conjugate Gradient Neural Network (SCGNN), and Levenberg Marquardt Neural Network (LMNN). Among the three algorithms of ANN, BRNN gave most accurate predictions for total reducing sugar yield. At some points, BRNN and LMNN are almost equally efficient but BRNN had lower values for all error functions. SCGNN and LMNN are supervised in nature but Bayesian uses probabilistic optimization. Probably that makes this technique better than others. Highlights: Optimization of the chemical pretreatment process for Leucaena leucocephala wood Three algorithms of neural networks, BRNN, SCGNN and LMNN were applied. BRNN gave best predictions; TRS yield 331.36 g/Kg. BRNN had lowest values for Error functions (RMSE, SEP (%), Af, Bf). Better performance of BRNN was due to probabilistic optimization.