Investigation on Kinetic Parameters of Combustion and Oxy-Combustion of Calcined Pet Coke Employing Thermogravimetric Analysis Coupled to Artificial Neural Network Modeling

Abstract

The objective of the present study is to understand the combustion behavior and to estimate kinetic parameters for combustion and oxy-combustion of calcined pet coke (CPC) employing thermogravimetric analysis (TGA), which is crucial for subsequent design and modeling of the combustion systems. In order to estimate the kinetics, the onset reaction temperature (ORT) is estimated using TGA for both the systems, and all subsequent experiments are conducted at temperatures higher than the ORT. The kinetic parameters viz., activation energy (E a ) and pre-exponential factor (A), are estimated using the shrinking particle model (SPM) and weight fraction model (WFM). While SPM assumes uniform particle size and first-order intrinsic kinetics, WFM is used to estimate even order of reaction besides E a and A. Prediction from SPM fits better to the data obtained from TGA, albeit with WFM estimating the order of the reaction as 0.6 in this case. The present study will be useful in employing the predicted kinetic data to design an industrial scale pet coke combustor. Artificial neural network (ANN) modeling is applied to isothermal TGA data to predict the TG curves of combustion and oxy-combustion of CPC. The ANN model predicted the TG curve with a high degree of accuracy, i.e., with a coefficient of determination in the order of 0.99999. The agreement between the experimental and predicted data substantiates the accuracy of the ANN model.

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

“…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 ]: where (W %) est , (W %) exp , and are the ANN model-estimated, experimental, and average values of mass left %, respectively.…”

“…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].…”

“…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 Low Density Polyethylene: Kinetic Study Using TGA Data and ANN Prediction

“…For better performance of ANNs, genetic algorithm should be implemented for optimizing parameters of the ANN such as number of neurons in hidden layers, number of hidden layers, the learning rate and the momentum rate [15]. The performance of an ANN model in predicting an output variable can be evaluated based on the following statistical correlations [28][29][30][31] :…”

Harnessing the power of machine learning for carbon capture, utilisation, and storage (CCUS) – a state-of-the-art review

“…The results indicated that BPNNs gave a better prediction than that of RBF neural networks 141 . Govindan et al 142 used trained ANNs, using TGA to predict the sample mass loss percentage of oxy-fuel combustion of calcined pet coke, with the predictions obtained from the model showing a high degree of accuracy, with a coefficient of determination (R 2 ) of 0.99. Qiao and Zeng 143 also applied the ANN framework to predict the gas products of heavy oil gasification under oxy-fuel conditions but the authors have not clarified how they trained and validated their ANN models.…”