Estimation of Higher Heating Value for MSW Using DSVM and BSOA

Abstract

In recent decades, the generation of Municipal Solid Waste (MSW) is steadily increasing due to urbanization and technological advancement. The collection and disposal of municipal solid waste cause considerable environmental degradation, making MSW management a global priority. Waste-to-energy (WTE) using thermochemical process has been identified as the key solution in this area. After evaluating many automated Higher Heating Value (HHV) prediction approaches, an Optimal Deep Learning-based HHV Prediction (ODL-HHVP) model for MSW management has been developed. The objective of the ODL-HHVP model is to forecast the HHV of municipal solid waste, based on its oxygen, water, hydrogen, carbon, nitrogen, sulphur and ash constituents. In addition, the ODL-HHVP model contains a Deep Support Vector Machine (DSVM) regression component that can accurately predict the HHV. In addition, the Beetle Swarm Optimization (BSO) method is utilised as a hyperparameter optimizer in conjunction with the DSVM model, resulting in the highest HHV prediction accuracy. A comprehensive simulation study is conducted to validate the performance of the ODL-HHVP method. The Multiple Linear Regression (MLR), Genetic Programming (GP), Resilient backpropagation (RP), Levenberg Marquardt (LM) and DSVM approaches have attained an ineffective result with RMSEs of 4.360, 2.870, 3.590, 3.100 and 3.050, respectively. The experimental findings demonstrate that the ODL-HHVP technique outperforms existing state-of-art technologies in a variety of respects.

Comparative Analysis of Machine Learning Methods for Predicting Energy Recovery from Waste

“…The output data were energy recovery from waste. Energy recovery is a waste management method that converts the energy contained in waste into useful energy in the form of heat, electricity or fuel through various processes such as combustion, pyrolysis, gassing or methane fermentation [15].…”

“…Several studies have developed models to estimate HHV accurately for various types of MSW. Jose and Sasipraba (2023) compared various models for HHV forecasting, including multiple linear regression (MLR), genetic programming (GP), elastic reverse propagation (RP), Levenberg Marquardt (LM), and Deep Support Vector Machine (DSVM), as well as Optimal Deep Learning-Based HHV Prediction (ODL-HHVP), to identify the most accurate method [15]. The input data consisted of the content of oxygen, water, hydrogen, carbon, nitrogen, sulfur, and ash in waste.…”

“…The input data consisted of the content of oxygen, water, hydrogen, carbon, nitrogen, sulfur, and ash in waste. The study found that ODL-HHVP was the most accurate method for HHV forecasting [15]. Bagheri et al (2019) conducted a study to compare the accuracy of three models-programming of gene expression (GEP), support vector machine (SVM), and the Feed-Forward neural network (FFNN)-in predicting HHV.…”