Pyrolysis of Low Density Polyethylene: Kinetic Study Using TGA Data and ANN Prediction

Abstract

Pyrolysis of waste low-density polyethylene (LDPE) is considered to be a highly efficient, promising treatment method. This work aims to investigate the kinetics of LDPE pyrolysis using three model-free methods (Friedman, Flynn-Wall-Qzawa (FWO), and Kissinger-Akahira-Sunose (KAS)), two model-fitting methods (Arrhenius and Coats-Redfern), as well as to develop, for the first time, a highly efficient artificial neural network (ANN) model to predict the kinetic parameters of LDPE pyrolysis. Thermogravimetric (TG) and derivative thermogravimetric (DTG) thermograms at 5, 10, 20 and 40 K min−1 showed only a single pyrolysis zone, implying a single reaction. The values of the kinetic parameters (E and A) of LDPE pyrolysis have been calculated at different conversions by three model-free methods and the average values of the obtained activation energies are in good agreement and ranging between 193 and 195 kJ mol−1. In addition, these kinetic parameters at different heating rates have been calculated using Arrhenius and Coats-Redfern methods. Moreover, a feed-forward ANN with backpropagation model, with 10 neurons in two hidden layers and logsig-logsig transfer functions, has been employed to predict the thermogravimetric analysis (TGA) kinetic data. Results showed good agreement between the ANN-predicted and experimental data (R > 0.9999). Then, the selected network topology was tested for extra new input data with a highly efficient performance.

Application of Artificial Neural Networks to Predict the Catalytic Pyrolysis of HDPE Using Non-Isothermal TGA Data

“…Table 9 lists the values of these parameters. The high value of R 2 along with very low values of MAE, RMSE, and MBE indicates a high-efficient performance of the selected model [14]. After that, new 45 datasets were tested by the selected model (NN-3-10-10-1) as shown in Table 10 and Figure 7 clearly shows the high performance of the selected network (See Table 11 as well).…”

“…The best network architecture depends on the type of the represented problem. For high performance of ANN-prediction, a genetic algorithm is applied to optimize the ANN parameters such as the number of hidden layers, the number of neurons in each hidden layer, and the momentum and learning rates [14,16].…”

“…Recently, some researchers have developed ANN models to predict the pyrolytic behavior of the thermal decompositions of some materials using TGA data [14,[17][18][19][20][21][22]. However, in this work, a highly-efficient ANN model is aimed to be developed to predict, for the first time, the catalytic pyrolysis of HDPE.…”

“…However, in this work, a highly-efficient ANN model is aimed to be developed to predict, for the first time, the catalytic pyrolysis of HDPE. The following statistical parameters are used to evaluate the performance of the developed ANN-model [14,16,23]:…”

Pyrolysis of Mixed Plastic Waste: I. Kinetic Study

“…Extensive research on the pyrolysis of a single type of plastic waste such as high-density polyethylene (HDPE) [8,9], low-density polyethylene (LDPE) [9,10], polyvinyl chloride (PVC) [9,[11][12][13], polypropylene (PP) [9,12,14], polycarbonate (PC) [15], and polystyrene (PS) [9,16,17] has been conducted. Although mixed plastic waste is the representative type of plastic waste worldwide, a limited number of works on the pyrolysis of mixed plastic waste plastic has been performed.…”