Digital Chemical Engineering最新文献

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.

This study aims to predict the solubility of salicylic acid in 13 different solvents, such as methanol, water, ethanol, ethyl acetate, PEG 300, 1,4-dioxane, 1-propanol, and others, given the significance of salicylic acid in the pharmaceutical industry. based on machine learning has been studied. In this study, 6 machine learning algorithms including neural network, linear regression, logistic regression, decision tree, random forest and kNN (k- Nearest Neighbors) were used. The comparison between the predictions of these algorithms and experimental data highlights the accuracy of predicting the solubility of salicylic acid for 217 samples based on 15 variables (13 solvents, temperature, and pressure). Based on the results of this study, the lowest total error (difference between experimental and predicted values) was 0.00016835 related to the random forest algorithm, and the highest value was 0.024768 related to k-Nearest Neighbors.

The demand for engineering graduates with technical skills in data science, machine learning (ML), and artificial intelligence (AI) is now growing. Chemical engineering (ChemE) departments around the world are currently addressing this skills gap by instituting AI or ML elective courses in their program. However, designing such a course is difficult since the issue of which ML models to teach and the depth of theory to be discussed remains unclear. In this paper, we present a graduate-level ML course particularly designed such that students will be able to apply ML for research in ChemE. To achieve this, the course intends to cover a wide selection of ML models with emphasis on their motivations, derivations, and training algorithms, followed by their applications to ChemE-related data sets. We argue that this algorithmic approach to teaching ML can help broaden the capabilities of students since they can judge for themselves which tool to use when, even for problems outside the process industries, or they can modify the methods to test novel ideas. We found that students remain engaged in the mathematical details as long as every topic is properly motivated and the gaps in the required statistical and computer science concepts are filled. Hence, this paper also presents a roadmap of ML topics, their motivations, and bridging topics that can be followed by instructors. Lastly, we report anonymized student feedback on this course which is being offered at the Department of Chemical Engineering, University of the Philippines, Diliman.

A powerful fault detection and diagnosis (FDD) system plays a pivotal role in achieving operational excellence by maximizing system performance, optimizing maintenance strategies, and ensuring the longevity and resilience of process plants. In the context of FDD for multivariate sensor data, this study presents an improved FDD approach using graph-based neural networks. This graph neural network uses an adjacency matrix developed by extracting the expert domain knowledge and topological information of the multi-sensor system. This additional graph representation of the system is incorporated along with multivariate sensor data to capture the spatial and temporal information in neural networks efficiently. In this regard, we propose and evaluate: 1) A Graph Auto Encoder (GAE) based fault detection strategy and 2) An Attention-based Spatial Temporal Graph Convolution Network (ASTGCN) based fault diagnosis methodology. By leveraging the additional knowledge in the form of graphs, the GAE captures the complex relationships and dependencies among sensors, enabling effective anomaly detection, which identifies abnormal patterns and deviations from normal behavior, thus indicating potential faults in the system. The ASTGCN incorporates attention mechanisms to selectively focus on relevant sensor nodes and capture their spatial and temporal dependencies for fault diagnosis. The effectiveness of the proposed FDD approach is demonstrated using the benchmark Tennessee Eastman Process (TEP) problem. The results show that the proposed approaches outperform traditional methods and highlight the importance of leveraging graph-based knowledge for FDD in complex systems.

The oxidative coupling of methane (OCM) to produce ethane and ethylene (C2 compounds) as platform chemicals involves complex chemistry with reactions both in the gas phase and on the catalyst surface, resulting in a distribution of products at the expense of C2 selectivity. This work uses experimental data from a variety of mixed metal oxides on supports at different reaction conditions (temperature, contact time, and reactant flow rates) to train a random forest regressor that predicts methane conversion and C2 selectivity (key performance indicators (KPIs)). The kinetically validated random forest models are deployed to locate optimal conditions that maximize C2 yield for each of the catalysts. Investigating the regressor interpretability via feature importance reveals that the choice of metals and support are crucial to C2 selectivity predictions in addition to the reaction conditions, while the predictions of methane conversion are largely governed by the reaction conditions. The machine learning (ML) regressor is used as a kinetic surrogate to find a locus of optimal reaction conditions that maximize both selectivity-conversion for each of the catalysts via a multi-objective optimization routine. The maximum C2 yields for catalysts are projected to be improved by 15% on average. Analyzing the catalysts with respect to a popular OCM catalyst, Mn-Na${}_2$WO${}_4$/SiO${}_2$, using the optimal locus eliminates variability in the process conditions to reveal distinct patterns based on intrinsic properties of metals and supports. Further, the decision space with catalyst descriptors and reaction conditions is optimized for high C2 yields using the ML surrogate, in a static multi-objective optimization routine, and an adaptive Bayesian routine, where the latter was found to have a wider field focus in proposing catalyst formulations and reaction conditions. Transition metal oxides on a variety of supports were proposed but not their lanthanide oxide counterparts. The framework has the potential to lend itself to materials acceleration platforms where it is crucial to consider multi-scale phenomena that impact downstream KPIs.

Fault detection constitutes a fundamental task for predictive maintenance, requiring mathematical models that can be conveniently provided by data-driven techniques. Autoencoders are a particular type of unsupervised Artificial Neural Networks that can be suitable for fault detection applications. Diverse architectures might be used for autoencoders, resulting in different fault detection performances, which are usually compared by means of Fault Detection Rates for a fixed threshold of the False Alarm Rate, limiting the conclusions to particular cases. To improve the comparability, the present work uses the area under the receiver operating characteristic curve to compare autoencoder architectures for a range of false alarm rates using the Tennessee Eastman Process benchmark. Performances obtained for shallow and deep autoencoders were compared with those of the denoising and variational autoencoders for undercomplete and sparse structures. Overall, the results indicate better performances for sparse structures, especially for the variational autoencoder and the deep denoising autoencoder, with area under the curve of 98.35%.

Unexpected accidents and events in industrial chemical processes have resulted in a considerable number of causalities and property damage. Safety process management in industrial chemical processes is critical to avoid and ensure casualties and property damage. However, due to the immense scope and high complexity of current industrial chemical processes, the traditional safety process management approaches cannot address these challenges to attain adequate fault detection accuracy. To address this issue, an innovative machine learning-based distributed canonical correlation analysis-dynamic independent component analysis (DICA-DCCA) approach is needed to improve the fault detection effectiveness of complicated systems. The (DICA-DCCA) model could potentially detect anomalies and faults in industrial chemical data by utilizing three essential statistics:$I_d^2$,$I_e^2$and squared prediction error (SPE). The practical effectiveness of the proposed frameworks is evaluated and compared using a continuous stirred tank reactor (CSTR) framework as a standard benchmark study. The research findings present that the suggested (DICA-DCCA) approach is more resilient and effective in detecting abnormalities and faults than the ICA and DICA approaches with FDR 100 % and FAR 0 %. The implied research approach is robust, operational, and productive.