• Energy Research
• Open Access close

The present work discusses the development and application of a machine-learning-based model to predict the enthalpy of combustion of various oxygenated fuels of interest. A detailed dataset containing 207 pure compounds and 38 surrogate fuels has been prepared, representing various chemical classes, namely paraffins, olefins, naphthenes, aromatics, alcohols, ethers, ketones, and aldehydes. The dataset was subsequently used for constructing an artificial neural network (ANN) model with 14 input layers, 26 hidden layers, and 1 output layer for predicting the enthalpy of combustion for various oxygenated fuels. The ANN model was trained using the collected dataset, validated, and finally tested to verify its accuracy in predicting the enthalpy of combustion. The results for various oxygenated fuels are discussed, especially in terms of the influence of different functional groups in shaping the enthalpy of combustion values. In predicting the enthalpy of combustion, 96.3% accuracy was achieved using the ANN model. The developed model can be successfully employed to predict the enthalpies of neat compounds and mixtures as the obtained percentage error of 4.2 is within the vicinity of experimental uncertainty.

The present work discusses the development and application of a machine-learning-based model to predict the enthalpy of combustion of various oxygenated fuels of interest. A detailed dataset containing 207 pure compounds and 38 surrogate fuels has been prepared, representing various chemical classes, namely paraffins, olefins, naphthenes, aromatics, alcohols, ethers, ketones, and aldehydes. The dataset was subsequently used for constructing an artificial neural network (ANN) model with 14 input layers, 26 hidden layers, and 1 output layer for predicting the enthalpy of combustion for various oxygenated fuels. The ANN model was trained using the collected dataset, validated, and finally tested to verify its accuracy in predicting the enthalpy of combustion. The results for various oxygenated fuels are discussed, especially in terms of the influence of different functional groups in shaping the enthalpy of combustion values. In predicting the enthalpy of combustion, 96.3% accuracy was achieved using the ANN model. The developed model can be successfully employed to predict the enthalpies of neat compounds and mixtures as the obtained percentage error of 4.2 is within the vicinity of experimental uncertainty.

This study has been dedicated towards the conversion of plastics to methanol and hydrogen. The base design (case 1) represents the conventional design for producing syngas via steam gasification of waste plastics followed by CO2 and H₂S removal. The syngas then processed in the methanol synthesis reactor to produce methanol, whereas, the remaining unconverted gases are processed in water gas shift reactors to produce hydrogen. On the other hand, an alternative design (case 2) has been also developed with an aim to increase the H2 and methanol production, which integrates the plastic gasification and the methane reforming units to utilize the high energy stream from gasification unit to heat up the feed stream of reforming unit. Both the cases have been techno-economically compared to evaluate the process feasibility. The comparative analysis revealed that case 2 outperforms the case 1 in terms of both process efficiency and economics.

This study has been dedicated towards the conversion of plastics to methanol and hydrogen. The base design (case 1) represents the conventional design for producing syngas via steam gasification of waste plastics followed by CO2 and H₂S removal. The syngas then processed in the methanol synthesis reactor to produce methanol, whereas, the remaining unconverted gases are processed in water gas shift reactors to produce hydrogen. On the other hand, an alternative design (case 2) has been also developed with an aim to increase the H2 and methanol production, which integrates the plastic gasification and the methane reforming units to utilize the high energy stream from gasification unit to heat up the feed stream of reforming unit. Both the cases have been techno-economically compared to evaluate the process feasibility. The comparative analysis revealed that case 2 outperforms the case 1 in terms of both process efficiency and economics.

Natural rubber is a tropical plantation crop that mainly consists of polyisoprene (cis-1,4-polyisoprene). It can be converted into fuels and other useful chemical commodities by depolymerization processes, with the hydrous pyrolysis being the most cost-effective.

Natural rubber is a tropical plantation crop that mainly consists of polyisoprene (cis-1,4-polyisoprene). It can be converted into fuels and other useful chemical commodities by depolymerization processes, with the hydrous pyrolysis being the most cost-effective.

Environmental concerns surrounding the use of high-sulfur fuel oil (HFO), a marine fuel derived from refinery vacuum residue, motivate the exploration of alternative solutions. Burning high-sulfur fuel oil (HFO) is a major source of air pollution, acid rain, ocean acidification, and climate change. When HFO is burned, it releases sulfur dioxide (SO2) into the air, a harmful gas that can cause respiratory problems, heart disease, and cancer. SO2 emissions can also contribute to acid rain, which can damage forests and lakes. Several countries and international organizations have taken steps to reduce HFO emissions from ships. For example, the International Maritime Organization (IMO) has implemented a global sulfur cap for marine fuels, which limits the sulfur content of fuel to 0.5% by mass. In addition, there is a worldwide effort to encourage the use of low-carbon gases to help reduce greenhouse gas (GHG) emissions. There are several alternative fuels that can be used in ships instead of HFO, such as liquefied natural gas (LNG), methanol, and hydrogen. These fuels are cleaner and more environmentally friendly than HFO. The aim of this study is to develop a process integration framework to co-produce methanol and hydrogen from vacuum residue while minimizing the sulfur and carbon emissions. Two process models have been developed in this study to produce methanol and hydrogen from vacuum residue. In case 1, vacuum residue is gasified using oxygen—steam and the syngas leaving the gasifier is processed to produce both methanol and hydrogen. Case 2 shares the same process model as case 1 except it is concentrated on mainly methanol production from vacuum residue. Both models are techno-economically compared in terms of methanol and H2 production rates, specific energy requirements, carbon conversion, CO2 specific emissions, overall process efficiencies, and project feasibility while considering the fluctuation of vacuum residue feed price from 0.022 $/kg to 0.11 $/kg. The comparative analysis showed that case 2 offers an 86.01% lower specific energy requirement (GJ) for each kilogram (kg) of fuel produced. The CO2 specific emission also decreased in case 2 by 69.76% compared to case 1. In addition, the calculated total net fuel production cost is 0.453 $/kg and 0.223 $/kg at 0.066 $/kg for case 1 and 2, respectively. Overall, case 2 exhibits better project feasibility compared to case 1 with higher process performance and lower production costs.