Artificial Neural Network Modeling Approach For

Abstract

circulating Fluidized Bed (CFB) gasifiers are used to convert solid fuel into liquid fuel. Artificial Neural Network (ANN) and Neuro-fuzzy controllers have immense potential to improve the efficiency of the gasifier because Circulating Fluidized Bed gasifiers exhibit complex computational behavior and nonlinear process, based on their thermodynamic and electrochemistry. The focus of this report is to discuss Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) modeling approach to estimate solid circulation rate at high pressure in the Circulating Fluidized Bed gasifier. The data obtained on laboratory scale prototype in chemical engineering laboratory which is already published in the literature review to observe the flow rate of biomass solid fuel. Both, ANN and ANFIS model worked on 217 samples of experimental data, in which pressure (𝑏𝑎𝑟 − 𝑎𝑏𝑠), single mean diameter (SMD), total valve opening (𝑐𝑚/𝑠), mass flow rate (𝑔/𝑠) and riser dp (𝑚𝑚 − 𝐻20) have been included as the major focus of the study. Moreover, Neural Network toolbox and Neuro fuzzy toolbox are used in MATLAB 2019a. These two different architectures of neural network i.e. Artificial Neural Network (ANN) and Adaptive Neuro Fuzzy Inference System (ANFIS) use four input features and one output feature with multiple neurons in the hidden layers, to estimate the flow of solid particles in the riser. The output results are compared based on their Mean Square Error (MSE), Regression analysis(𝑅2), Mean Average Error (MAE) and Mean Absolute Percentage Error (MAPE). This report discusses in detail about the superiority of Neuro-Fuzzy controller over Artificial Neural Network. Each input is important variable for Artificial Neural Network (ANN) and Adaptive Neuro Fuzzy Inference System (ANFIS) model for the improvement of Circulating Fluidized Bed performance in terms of syngas and input feedstock to boiler.