Neural network prediction of bioleaching of metals from waste computer printed circuit boards using Levenberg‐Marquardt algorithm

Annamalai, Mohan; Gurumurthy, Kalaichelvan

doi:10.1111/coin.12288

Cited by 8 publications

(3 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, and considering that metal recycling has been booming in recent years [ 121 ], some recent works have used bioleaching for recovering metals from e-waste, such as printed circuit boards (PCB) [ 122 , 123 , 124 , 125 ]. In order to predict the bioleaching dynamics of spent catalysts, Vyas et al [ 123 ] used artificial neural networks to model the efficiency of Mo bioleaching from spent catalysts using microorganisms.…”

Section: Modeling Of Mineral Bioleachingmentioning

confidence: 99%

“…The variation in the extraction of this metal was modeled considering the size of the particles, the density of the pulp, the temperature, and the residence time as independent variables. Annamalai et al [ 125 ] studied the applicability of ANNs to predict the bioleaching of metals from PCB, in addition to the impact of parameters such as initial pH, pulp density, and volume as independent variables of the inoculum, while the explained variables were Ag, Cu, and Au extraction.…”

Section: Modeling Of Mineral Bioleachingmentioning

confidence: 99%

See 1 more Smart Citation

Bioleaching Modeling—A Review

et al. 2023

View full text Add to dashboard Cite

The leaching of minerals is one of the main unit operations in the metal dissolution process, and in turn it is a process that generates fewer environmental liabilities compared to pyrometallurgical processes. As an alternative to conventional leaching methods, the use of microorganisms in mineral treatment processes has become widespread in recent decades, due to advantages such as the non-production of emissions or pollution, energy savings, low process costs, products compatible with the environment, and increases in the benefit of low-grade mining deposits. The purpose of this work is to introduce the theoretical foundations associated with modeling the process of bioleaching, mainly the modeling of mineral recovery rates. The different models are collected from models based on conventional leaching dynamics modeling, based on the shrinking core model, where the oxidation process is controlled by diffusion, chemically, or by film diffusion until bioleaching models based on statistical analysis are presented, such as the surface response methodology or the application of machine learning algorithms. Although bioleaching modeling (independent of modeling techniques) of industrial (or large-scale mined) minerals is a fairly developed area, bioleaching modeling applied to rare earth elements is a field with great growth potential in the coming years, as in general bioleaching has the potential to be a more sustainable and environmentally friendly mining method than traditional mining methods.

show abstract

Section: Modeling Of Mineral Bioleachingmentioning

confidence: 99%

Section: Modeling Of Mineral Bioleachingmentioning

confidence: 99%

Bioleaching Modeling—A Review

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Cu recovery from WPCBs by complex suspension electrolysis process is analyzed by surrogate and ML modelling and simulated annealing technique was utilized to maximize the metal recovery [7]. Annamalai and Gurumurthy [8] applied bioleaching technique for Cu, Au and Ag recovery from WPCBs and used artificial neural network (ANN) and genetic algorithm framework to estimate the optimized conditions for the metal recovery. In few other research studies, ML is used for the modelling of metal recovery process [9,10].…”

Section: Introductionmentioning

confidence: 99%

Machine learning based metal recovery from the waste printed circuit boards of mobile phones for circular economy and sustainable environment

Ashraf,

Panda,

Jadhao

et al. 2023

Preprint

View full text Add to dashboard Cite

The metal recovery from the waste printed circuit boards (WPCBs) of mobile phones presents reduced reliance on natural resources, savings in energy and emissions discharge complemented with economic incentives as well. Herein, we present a machine learning (ML) based model for Cu, Ni and Pb recovery from the WPCBs of mobile phones using low temperature roasting process. The ML model for the metal recovery is built using Artificial Neural Network (ANN) where three variables (roasting temperature, roasting time, NH4Cl dose) are used as inputs for the model. The model-based significance order of the input variables is obtained by computing partial derivatives of outputs with respect to the inputs. Temperature is the most significant input variable for Cu while time is the most significant variable for Ni and Pb recovery, contributing the percentage significance of 42%, 41.3% and 48.4% respectively. The proposed ML based analysis framework can be deployed for enhancing the insights about the metal recovery process contributing to the smart operation and operational excellence.

show abstract