Logo

Surface tension of binary mixtures containing environmentally friendly ionic liquids: Insights from artifcial intelligence

Setiawan, Roy and Daneshfar, Reza and Rezvanjou, Omid and Ashoor, Siavash and Naseri, Maryam (2021) Surface tension of binary mixtures containing environmentally friendly ionic liquids: Insights from artifcial intelligence. [UNSPECIFIED]

[img] PDF
Download (1770Kb)
    [img] PDF
    Download (4Mb)
      [img]
      Preview
      PDF (Paper - Roy S)
      Download (4Mb) | Preview

        Abstract

        The surface tension (ST) of ionic liquids (ILs) and their accompanying mixtures allows engineers to accurately arrange new processes on the industrial scale. Without any doubt, experimental methods for the specification of the ST of every supposable IL and its mixtures with other compounds would be an arduous job. Also, experimental measurements are effortful and prohibitive; thus, a precise estimation of the property via a dependable method would be greatly desirable. For doing this task, a new modeling method according to artificial neural network (ANN) disciplined by four optimization algorithms, namely teaching�learning-based optimization (TLBO), particle swarm optimization (PSO), genetic algorithm (GA) and imperialist competitive algorithm (ICA), has been suggested to estimate ST of the binary ILs mixtures. For training and testing the applied network, a set of 748 data points of binary ST of IL systems within the temperature range of 283.1�348.15 K was utilized. Furthermore, an outlier analysis was used to discover doubtful data points. Gained values of MSE & R2 were 0.0000007 and 0.993, 0.0000002 and 0.998, 0.0000004 and 0.996 and 0.0000006 and 0.994 for the ICA-ANN, TLBO-ANN, PSO-ANN and GA-ANN, respectively. Results demonstrated that the experimental data and predicted values of the TLBO-ANN model for such target are wholly matched.

        Item Type: UNSPECIFIED
        Uncontrolled Keywords: Surface tension � Ionic liquid � Artifcial neural network � Genetic algorithm � Teaching�learning-based optimization � Imperialist competitive algorithm � Particle swarm optimization
        Subjects: H Social Sciences > HD Industries. Land use. Labor > HD28 Management. Industrial Management
        Divisions: Faculty of Economic > Business Management Program
        Depositing User: Admin
        Date Deposited: 12 Apr 2021 18:00
        Last Modified: 11 Aug 2023 11:29
        URI: https://repository.petra.ac.id/id/eprint/19056

        Actions (login required)

        View Item