Intelligent optimization of bioleaching process for waste lithium-ion batteries : an application of support vector regression approach

Recovery of toxic and vital metal from spent Li-ion batteries is a vital problem in the recycling industry. The recycling processes such as bioleaching are much simpler and environment friendly but lack the required efficiency for metal recovery to prove the commercial feasibility of the model. This...

Full description

Saved in:
Bibliographic Details
Main Authors: Ruhatiya, C., Gandra, R., Kondaiah, P., Manivas, K., Samhith, A., Gao, L., Lam, Jasmine Siu Lee, Garg, A.
Other Authors: School of Civil and Environmental Engineering
Format: Article
Language:English
Published: 2021
Subjects:
Online Access:https://hdl.handle.net/10356/154503
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-154503
record_format dspace
spelling sg-ntu-dr.10356-1545032021-12-23T08:15:33Z Intelligent optimization of bioleaching process for waste lithium-ion batteries : an application of support vector regression approach Ruhatiya, C. Gandra, R. Kondaiah, P. Manivas, K. Samhith, A. Gao, L. Lam, Jasmine Siu Lee Garg, A. School of Civil and Environmental Engineering Engineering::Civil engineering Bioleaching Intelligent Optimization Recovery of toxic and vital metal from spent Li-ion batteries is a vital problem in the recycling industry. The recycling processes such as bioleaching are much simpler and environment friendly but lack the required efficiency for metal recovery to prove the commercial feasibility of the model. This work focuses on increasing the efficiency of the bioleaching process by targeting its intermediate processes for maximum vital metal recovery. The intermediate process of biomass generation from Aspergillus niger fungus is targeted. The data from experimental design is modelled using support vector regression with v-fold cross-validation. The bioleaching process is optimized such that maximum biomass concentration is obtained for efficient and commercially viable metal recovery. The results are divided into four sections, each addressing an important issue of the recycling process mechanism. The generated model is found to have good stability and accurate process mechanism predictability. Global sensitivity and interaction analysis is employed for efficient weighted optimization. The model generated trends and optimization results are verified through the profiling curve as well as past literature experimental data. This work reports the maximum biomass concentration of 25 g/L. The model employed is stable and efficient, reaching a stable optimized value under 300 iterations. The optimized input parameters values obtained are 144.39 g/L, 1.29% v/v, 6.70, 1513.05 ppm, 4989.79 ppm, 2094.22 ppm, 347.57 ppm and 2.37 for sucrose concentration, inoculum size, initial pH, oxalic acid, gluconic acid, malic acid, citric acid concentration and final pH, respectively. This research was supported/partially supported byMahindra Ecole Centrale, Hyderabad Telangana, India500043. 2021-12-23T08:15:33Z 2021-12-23T08:15:33Z 2021 Journal Article Ruhatiya, C., Gandra, R., Kondaiah, P., Manivas, K., Samhith, A., Gao, L., Lam, J. S. L. & Garg, A. (2021). Intelligent optimization of bioleaching process for waste lithium-ion batteries : an application of support vector regression approach. International Journal of Energy Research, 45(4), 6152-6162. https://dx.doi.org/10.1002/er.6238 0363-907X https://hdl.handle.net/10356/154503 10.1002/er.6238 2-s2.0-85096766135 4 45 6152 6162 en International Journal of Energy Research © 2020 John Wiley & Sons Ltd. All rights reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Civil engineering
Bioleaching
Intelligent Optimization
spellingShingle Engineering::Civil engineering
Bioleaching
Intelligent Optimization
Ruhatiya, C.
Gandra, R.
Kondaiah, P.
Manivas, K.
Samhith, A.
Gao, L.
Lam, Jasmine Siu Lee
Garg, A.
Intelligent optimization of bioleaching process for waste lithium-ion batteries : an application of support vector regression approach
description Recovery of toxic and vital metal from spent Li-ion batteries is a vital problem in the recycling industry. The recycling processes such as bioleaching are much simpler and environment friendly but lack the required efficiency for metal recovery to prove the commercial feasibility of the model. This work focuses on increasing the efficiency of the bioleaching process by targeting its intermediate processes for maximum vital metal recovery. The intermediate process of biomass generation from Aspergillus niger fungus is targeted. The data from experimental design is modelled using support vector regression with v-fold cross-validation. The bioleaching process is optimized such that maximum biomass concentration is obtained for efficient and commercially viable metal recovery. The results are divided into four sections, each addressing an important issue of the recycling process mechanism. The generated model is found to have good stability and accurate process mechanism predictability. Global sensitivity and interaction analysis is employed for efficient weighted optimization. The model generated trends and optimization results are verified through the profiling curve as well as past literature experimental data. This work reports the maximum biomass concentration of 25 g/L. The model employed is stable and efficient, reaching a stable optimized value under 300 iterations. The optimized input parameters values obtained are 144.39 g/L, 1.29% v/v, 6.70, 1513.05 ppm, 4989.79 ppm, 2094.22 ppm, 347.57 ppm and 2.37 for sucrose concentration, inoculum size, initial pH, oxalic acid, gluconic acid, malic acid, citric acid concentration and final pH, respectively.
author2 School of Civil and Environmental Engineering
author_facet School of Civil and Environmental Engineering
Ruhatiya, C.
Gandra, R.
Kondaiah, P.
Manivas, K.
Samhith, A.
Gao, L.
Lam, Jasmine Siu Lee
Garg, A.
format Article
author Ruhatiya, C.
Gandra, R.
Kondaiah, P.
Manivas, K.
Samhith, A.
Gao, L.
Lam, Jasmine Siu Lee
Garg, A.
author_sort Ruhatiya, C.
title Intelligent optimization of bioleaching process for waste lithium-ion batteries : an application of support vector regression approach
title_short Intelligent optimization of bioleaching process for waste lithium-ion batteries : an application of support vector regression approach
title_full Intelligent optimization of bioleaching process for waste lithium-ion batteries : an application of support vector regression approach
title_fullStr Intelligent optimization of bioleaching process for waste lithium-ion batteries : an application of support vector regression approach
title_full_unstemmed Intelligent optimization of bioleaching process for waste lithium-ion batteries : an application of support vector regression approach
title_sort intelligent optimization of bioleaching process for waste lithium-ion batteries : an application of support vector regression approach
publishDate 2021
url https://hdl.handle.net/10356/154503
_version_ 1720447186629558272