Predicting the Conversion Ratio for the Leaching of Celestite in Sodium Carbonate Solution Using an Adaptive Neuro-Fuzzy Inference System

Abstract

In this study, an adaptive neuro-fuzzy inference system (ANFIS) was used to predict conversion kinetics as the percent ratio of SrSO 4 to SrCO 3 in sodium carbonate solution. The results of the ANFIS were compared to a previous study of multilayer perceptron (MLP) artificial neural networks (ANNs) that used the same data set. The ANFIS model showed proper fitting to the experimental data according to the mean absolute error (MAE) and determination coefficient (R 2 value). The ANFIS model can easily determine the conversion ratio of SrSO 4 to SrCO 3 . Hence, it is possible to predict the ratio without measuring parameters under different experiments. The Matlab program was used for all coding. Moreover, a user interface program was developed in Simulink to simulate the ANFIS model for entering combinations of input parameters. The ANFIS output showed a satisfactory result in terms of overall performance.

Human brain-inspired chemical artificial intelligence tools for the analysis and prediction of the anion-sensing characteristics of an imidazole-based luminescent Os(ii)-bipyridine complex

“…Obtaining a quantitative insight of a particular observation either through theoretical calculations or by experimentation is always associated with the consumption of time. We employed, in this work, various deep learning and machine learning tools, such as fuzzy logic, 11–16 artificial neural network (assisted by three different training algorithms), 17–22 adaptive neuro-fuzzy inference system, 23–27 as well as decision tree regression analysis, 28–34 on our existing anion-sensing dataset of an Os( ii )-polyheterocyclic complex for proper understanding as well as to fully predict its anion-sensing characteristic within a very short period of time (Chart 1). 35…”

Neuro-Fuzzification Architecture for Modeling of Electrochemical Ion-Sensing Data of Imidazole-Dicarboxylate-Based Ru(II)–Bipyridine Complex

“…Machine learning (ML) and various artificial intelligence (AI) tools are now widely been employed in diverse fields in chemistry, materials sciences, and biology. − One of the most important foci of the present-day research is to design smart materials and to analyze their diverse physicochemical data (such as sensing) for the diagnostic grounds. However, relatively little advancement has been made in other subsidiary domains of AI, such as fuzzy logic system (FLS), ANNs, adaptive neuro–fuzzy inference system (ANFIS), robotics, and evolutionary computation. − Fabrication of reliable and comprehensive database could expand ML to a boarder domain of applications. Significant emphasis is now been put forward to flourish the fertile area of AI with vague and imprecise inputs.…”

Analysis and prediction of anion- and temperature responsive behaviours of luminescent Ru(ii)-terpyridine complexes by using Boolean, fuzzy logic, artificial neural network and adapted neuro fuzzy inference models

“…Comparatively little progress has been accomplished in other supplementary areas of AI, such as FL, ANNs, ANFIS and evolutionary computation. 10–20 Creation of a dependable and exhaustive catalogue might expand ML to a wide range of applications. Hence, tremendous efforts have now been paid to expand the productive domain of AI having vague and imprecise inputs.…”

“…Among the two types of neural networks {recurrent (RNN) and feed-forward (FFN)}, we applied here the ANN-function fitting (ANN-FF) network due to the static nature of our systems and because of its efficiency in understanding and forecasting a complicated system. 17–20…”