Distillation is an energy‐consuming process in the chemical industry. Optimizing operating conditions can reduce the amount of energy consumed and improve the efficiency of chemical processes. Herein, we developed a machine learning‐based prediction model for a distillation process and applied the developed model to process optimization. The energy consumed in the distillation process is mainly used to control the temperature of the distillation column. We developed a model that predicted temperature according to the following procedure: (1) data collection; (2) characteristic extraction from the collected data to reduce learning time; (3) min–max normalization to improve prediction performance; and (4) a case study conducted to select the artificial neural network algorithm, optimization method, and batch size, which are the most appropriate elements for predicting production stage temperature. The result of the case study revealed that the most appropriate model was observed with a root mean squared error of 0.0791 and a coefficient of determination of 0.924 when the long short‐term memory algorithm, Adam optimization method, and batch size of 128 were applied. We calculated the amount of steam consumption required to consistently maintain the production stage temperature by utilizing the developed model. The calculation result indicated that the amount of steam consumption was expected to be reduced by approximately 14%, from an average flow rate of 2763–2374 kg/h. This study proposed a control method applying a machine learning‐based prediction model in the distillation process and confirmed that operation energy could be reduced through efficient operation.
An empty fruit bunch (EFB) is a byproduct of the palm oil production process with an undried moisture content of 60−70%, which is too high for use as direct combustion fuel. Drying processes are generally considered essential for the recent use of EFBs as power plant fuels because their high moisture content decreases the boiler efficiency. The lower moisture content of dried EFBs increases the heating value and boiler efficiency but creates a trade-off with the energy required for the drying process. This study developed an EFB-based 10 MW power plant model by integrating economic evaluations in order to obtain optimal drying conditions. A hot air dryer was used in the drying process. The EFB evaporation behavior was predicted by reflecting the drying kinetics of EFBs in Aspen Plus. The optimum drying conditions were found to be a steam recirculation ratio of 0.25 and drying time of 23 min, creating dried EFBs with a 9.91% moisture content, which reduced costs by 5.48% relative to the undried base scenario. In addition, the developed model was compared to the drying process of a real power plant currently under construction in Indonesia. This drying process reduces the EFB moisture content from 48 to 20%.
Gas splitting is an energy-intensive process that is widely used in the chemical industry. Consequently, the cost effectiveness of this process can be maximized through energy optimization. This study focuses on the energy optimization of the commercial mixed butane gas-splitting technique via process modification. Because the previous process is impeded by the instability of the n-butane content in the feedstock, it consumes excessive energy and results in a product that is inferior in purity. Therefore, we initially simulated the previously used process model and then modified this process to achieve the target purity of the product and minimize energy consumption. The energy optimization model was designed in accordance with the standards of the commercial-grade product. After achieving energy optimization, we conducted economic analyses for the two modified processes by considering their capital and operating costs. Each modified process exhibited an approximate reduction of 19.67−21.85% in its energy consumption; however, only one of the two modified processes managed to enhance the product yield (by 1.00%). The net present value of the previous process model was 126.98 M$, whereas those of the modified processes were calculated to be 134.71 and 133.78 M$.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.