Digital Chemical Engineering最新文献

Hydrogen plays a crucial role in improving sustainability and offering a clean and efficient energy carrier that significantly reduces greenhouse gas emissions. However, the primary method of industrial hydrogen production, steam methane reforming (SMR), relies on the combustion of hydrocarbons as the heating source for the reforming reactions, resulting in significant carbon emissions. To address this issue, an experimental setup of an electrically-heated steam methane reformer (e-SMR) has been constructed at UCLA, and a lumped first-principle dynamic process model was built based on parameters estimated from the experimental data in a previous study. Subsequently, the first-principle dynamic process model was implemented into the computational model predictive control (MPC) scheme, successfully driving the hydrogen production rate to the desired setpoint. While these works are important and pave the way for developing MPC for large-scale e-SMR processes, the first-principle process model may not accurately reflect the actual process behavior, particularly as the process behavior changes with time. Therefore, the development and establishment of an adaptive data-driven approach for implementing model predictive control in the e-SMR process is necessary. To address this need, the present work investigates the construction of recurrent neural network (RNN) models for an e-SMR process in-depth, utilizing data from an experimentally-validated first-principle model. Specifically, a long short-term memory (LSTM) layer was utilized in the RNN model to effectively capture the complex correlations present in long-term sequential data. Subsequently, this LSTM-based RNN process model was employed to design an MPC, and its performance was evaluated through comparison with proportional–integral (PI) control. To address potential disturbances and variability in a typical e-SMR process, three distinct approaches were developed: MPC with an integrator, MPC with real-time online retraining (transfer learning), and offset-free MPC. These approaches effectively eliminated the offset caused by disturbances. Overall, this study underscores the effectiveness of utilizing RNN models to capture process dynamics in an experimental e-SMR process. It also outlines strategies for employing RNN-based control and multiple approaches to address disturbances in general processes with partially infrequent and delayed measurement feedback. This approach is particularly valuable in scenarios where developing first-principle models for a new process may be challenging.

Emission and performance parameters of a 4-stroke CI engine operated on a blend of catalytic co-pyrolysis oil with pure diesel, produced through Azadirachta indica seed, waste LDPE (low-density polyethylene), and aluminium oxide (Al₂O₃) as a catalyst, are modelled in the current work using an Artificial Neural Network (ANN). At 500°C temperature, the highest oil output obtained was 93.91 wt%. The produced liquid fuel possessed similar physical features to that of pure diesel, including density (794 kg/m³) and heating value (44.42 MJ/kg), but lower flash and fire points that would assist in a better and complete combustion of the fuel blend resulting in a better performance and combustion characteristics. Using inputs including brake mean effective pressure, load, brake power, and torque, a developed ANN model was applied to forecast the performance (Brake Thermal Efficiency and Brake Specific Fuel Consumption) along with emission characteristics (Smoke and NO_x). The Levenberg-Marquardt back-propagation training technique was applied for emissions and performance characteristics prediction having the best accuracy. Regression coefficients (R²) for predicting BTE, BSFC, NOx, and smoke were all very near to 1: 0.99801, 0.9983, 0.95753, and 0.97467. The study determines that the proposed alternative fuel could be utilized in blend with the pure diesel to in an unmodified diesel engine. It has also been found that artificial neural networks (ANN) could prove to be useful to model and forecast the performance or emissions of renewable fuels in diesel engines, with the potential for these fuels to be employed in transportation.

This study addresses the challenge of efficiently determining the higher heating value (HHV) of biomass, a crucial parameter in large-scale biomass-based energy systems. The conventional method of measuring HHV using an oxygen bomb calorimeter is time-consuming, expensive, and less accessible to researchers, particularly in developing nations. To overcome these limitations, we employed four machine learning (ML) models, namely Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost). These models were developed by using proximate and ultimate analysis parameters as input features. Up to 200 datasets were compiled from literature and used for the ML models. Our results demonstrate the effectiveness of all ML models in accurately predicting the HHV of biomass materials. Notably, the XGBoost model exhibited superior performance with the highest R-squared (R²) values for both training (0.9683) and test datasets (0.7309), along with the lowest root mean squared error (RSME) of 0.3558. Key influential input features identified for HHV prediction include carbon (C), volatile matter (Vm), ash, and hydrogen (H). Consequently, this research provides a reliable alternative for predicting HHV without the need for costly and time-intensive experimental measurements, facilitating broader accessibility in biomass energy research.

Nanofluids possess enhanced viscous and thermal features that can be utilized to improve the heat transfer performance of several applications involving sustainable manufacturing and industrial ecology, such as in heating/cooling systems, electronics, transportation etc. Therefore, it is important to understand and optimize the flow pattern of these fluids. This research emphasizes the predictions of viscosity of water/ethylene-glycol (EG) based non-Newtonian nanofluids. Four experiment-based data sets are used to predict and validate the effective viscosity, i.e., Fe₃O₄-Ag/EG, MWCNT-alumina/water-EG, Fe₃O₄-Ag/water-EG, and MWCNT-SiO₂/EG-water, via existing correlations and artificial neural network (ANN). The modeling is based on three input parameters, i.e., particle concentrations, temperatures, and shear rates, and one output parameter, i.e., viscosity. The predicted outcomes are compared to the three existing correlation structures. The error matrix consists of the coefficient of determination (R²), average absolute deviation (AAD %), the sum of squared error (SSE), that are employed to evaluate the performance of the model. Results from ANN are found to be more precise, with R² values greater than 0.99 for all datasets, compared to data fitting into existing correlations, in which Fe₃O₄-Ag/water-EG resulted in an R² value as low as 0.72, to determine the nanofluids’ effective viscosity.

The water-gas shift (WGS) reaction is pivotal in industries aiming to convert carbon monoxide, a byproduct of steam reforming of methane and other hydrocarbons, into carbon dioxide and hydrogen. Selecting an effective catalyst for this transformation poses a substantial challenge, as it requires a delicate balance between conversion, stability, and cost. We combine machine learning-driven prediction models with Bayesian optimization to explore and identify novel catalyst compositions. The proposed method efficiently explores the catalysis composition space for a predefined set of active metals, supports, and promoters to identify the most promising catalyst formulations. We assign weights to different performance metrics of catalysts, enabling tailored optimization according to specific industry needs. Our screening system streamlines catalyst discovery and facilitates the screening and selection of catalysts that balance conversion performance, stability, and cost-effectiveness. This approach holds significant promise for advancement in heterogeneous catalysis to meet the growing demands of efficient industrial processes.

This paper investigates the relationship between Responsible Research and Innovation (RRI) and chemistry / chemical engineering education at university level. It does so by describing the genealogy of the RRI concept as well as outlining three different interpretations of what RRI refers to and combining them into the hexagon model of RRI. This model constitutes the theoretical framework for this work. The second part of the paper addresses how the science and engineering education research literature has embraced insights from RRI. The hexagon model of RRI explicitly includes a dimension on (science and engineering) education, and this paper will contribute to this dimension by investigating and discussing how research literature can link RRI and tertiary chemistry and chemical engineering education. The paper shows that very limited work has been done to liaise chemistry higher education and chemical engineering education with the RRI framework. In the concluding section of the paper, we discuss how the reported educational experiences on RRI in STEM can be translated into higher education in chemical engineering and chemistry. Hereby a proposal to fill the identified knowledge gap is made. The core of the paper is conceptual, and its central purpose is to introduce RRI to a chemical engineering and chemistry ethics education audience. As mentioned, the RRI approach has gone largely unnoticed within engineering ethics education, and only received limited attention within ethics of chemistry education. We hope that these research communities will find it inspirational to get involved in the RRI framework and to actively enact RRI insights.

Generative Artificial Intelligence is a rapidly developing area being used to create powerful tools which have the potential to change a wide range of professional practices in chemical engineering. As this area develops, new principles on responsible use of Generative AI in chemical engineering are required to ensure that traditional engineering ethics are able to accommodate the new landscape. In this perspective, we assess the current state of engineering ethics, responsible AI principles and suggest how they can combine to ensure that Generative AI can be used responsibly within the chemical engineering sector. Whilst there are many aspect to engineering ethics and responsible AI use, the core principles which include transparency, integrity, and accountability are omnipresent and provide a shared foundation of good practice on which new regulations may be built as the need arises. Future breakthrough will require development on the AI technology itself, the people-centre approach and regulation changes.

This study demonstrates the successful integration of process simulation using CHEMCAD into Sunway University's Chemical Engineering Thermodynamics curriculum, replacing the traditional lab sessions. This approach has two main benefits, i.e., it provides early exposure to process simulation software, bridging theory and practice, and it supports new chemical engineering programs where labs may not be fully operational. Aligned with Sunway University's commitment to innovative educational approaches, the impact of this integration on the students’ learning experiences is evident through feedback collected from a comprehensive survey conducted with a group of seven students enrolled in Chemical Engineering Thermodynamics in April 2023. The survey's three sections gathered the students’ perceptions, enjoyed aspects, challenges faced, and suggestions. Findings highlight the students’ positive views on the integration, enhancing comprehension of thermodynamics concepts and real-world applications. They also recognized the value of hands-on simulation experience for essential process simulation skills. The students appreciated the practical relevance in highlighting thermodynamics’ real-world importance. Challenges related to software access and technical issues were addressed, with planned improvements. The students expressed interest in deeper learning, including complex simulations, graphical representation use, and external resource access. While many found the integration effective, suggestions for more hands-on engagement and research resource access were noted.

Concerns in relation to consequences of global warming and climate change have activated worldwide attempts for mitigating the concentration of carbon dioxide (CO₂) produced by the industrial sector. Decarbonizing the oil and gas refining (OGR) industries is a challenging problem for policy-makers owing to its potential to prevent economic, environmental, and health risks. In this regard, CO₂ capture, utilization, and storage (CCUS) technologies are the most encouraging options to decarbonize. The technologies related to the part of CO₂ capture can play a vital role in solving the mentioned problem. Various technologies have been employed for CO₂ capture, and choosing the appropriate technology is a complex multi-criteria decision-making (MCDM) issue. This work develops a novel and robust decision support system (DSS). The DSS integrates MCDM techniques of the Delphi and Entropy integration method (DAEIM) and complex proportional assessment of alternatives (COPRAS) method with the interval type-2 trapezoidal fuzzy (IT2TF) environment. The proposed DSS is used to evaluate, prioritize, and choose technologies for CO₂ capture. A hybrid criteria system, which involves elements of socio-technical systems perspective has been used for evaluating the candidate technologies. For implementing the DSS of this work, five capture technologies of post-combustion (A_cc₁), pre-combustion (A_cc₂), oxy-fuel combustion (A_cc₃), direct air capture (A_cc₄), and indirect air capture (A_cc₅) have been chosen for evaluation. The final value of each technology is A_cc₁ (0. 2907), A_cc₂ (0.2602), A_cc₃ (0.1005), A_cc₄ (0.2304), and A_cc₅ (0.1181) and the preferences of the technologies are A_cc₁> A_cc₂> A_cc₄> A_cc₅> A_cc₃. The evaluation findings reveal that post-combustion technology with the value of 0.2907 is the most suitable scenario for the capture of CO₂ emissions from Iran's OGR systems. The computation results demonstrate that the suggested DSS is feasible and applicable and give reliable and robust findings for acquiring the optimal CO₂ capture technology.

In this paper, we provide an overview of the technologies that enable digitalization in the chemical process industry and describe their applications to solve problems in industrial settings. This is done through the identification and categorization of these technologies, thereby providing structure to an otherwise loosely connected basket of technologies and casting a spotlight on state-of-the-art technologies that offer great potential but are still underutilized in industrial applications. Furthermore, we identify the problem domains that characterize the chemical process industry and connect them to development aspects in the industry that lend themselves to digital solutions. For each of these connections, we select the technologies most essential to bridging the gap between problem and solution. This allows practitioners to better understand the relevancy of digitalization to their problems and provides a starting point for further investigation of potential solutions. The connections are substantiated by reference to successful industrial applications, highlighting previous works that have been published in the field. They are further verified by industry experts through brainstorm sessions, interviews, and a workshop.