Computers & Chemical Engineering最新文献

Rapid demand growth would double GHG emissions of fossil-based chemicals and plastics production by 2050. In contrast, recycling, biomass utilization, and electrification enable pathways to net-zero GHG emissions. Such pathways often compare the costs of fossil and renewable technologies based on the next 30 years. However, this assumption contrasts the timeframes of legislative periods and investors desiring fast returns, leading to myopic (i.e., short-term) investment decisions. Therefore, this study compares pathways based on long-term with myopic decision-making. While a 20-year foresight still achieves net zero by 2050, a 10-year foresight fails the net-zero target and increases cumulated GHG emission by 43%. Moreover, the chemical industry would invest +307 bn-USD (+3.2%) in additional fossil and, thus, potentially stranded assets. Therefore, industry and investors should account for the environmental and economic impacts of myopic decision-making and practice long-term decision-making to mitigate carbon lock-ins, stranded assets, and financial risks for investors.

The scheduling of crude oil operations holds critical significance in the petrochemical industry due to its profound influence on downstream unit operations and, consequently, overall business profitability. This work presents a novel multi-operation sequencing formulation considering operations with restricted overlapping constraints. This operation-centric model also distinguishes itself by incorporating constraints posed by refinery practice such as downstream product management, multiparcel unloading, brine settling, and changeover detection. A new symmetry-breaking strategy is applied to remove symmetric solutions properly and expedite problem solving while ensuring solution quality. Case studies of various examples are conducted to validate the efficacy of the proposed model. Comparative analyses are performed with the unit-specific event-based formulation, which enables multiple time grids tailored to different units and is widely used in continuous-time modeling. Results further demonstrate the great potential of the presented formulation in generating tighter bounds and accelerating convergence.

This review article explores how emerging generative artificial intelligence (GenAI) models, such as large language models (LLMs), can enhance solution methodologies within process systems engineering (PSE). These cutting-edge GenAI models, particularly foundation models (FMs), which are pre-trained on extensive, general-purpose datasets, offer versatile adaptability for a broad range of tasks, including responding to queries, image generation, and complex decision-making. Given the close relationship between advancements in PSE and developments in computing and systems technologies, exploring the synergy between GenAI and PSE is essential. We begin our discussion with a compact overview of both classic and emerging GenAI models, including FMs, and then dive into their applications within key PSE domains: synthesis and design, optimization and integration, and process monitoring and control. In each domain, we explore how GenAI models could potentially advance PSE methodologies, providing insights and prospects for each area. Furthermore, the article identifies and discusses potential challenges in fully leveraging GenAI within PSE, including multiscale modeling, data requirements, evaluation metrics and benchmarks, and trust and safety, thereby deepening the discourse on effective GenAI integration into systems analysis, design, optimization, operations, monitoring, and control. This paper provides a guide for future research focused on the applications of emerging GenAI in PSE.

The design space (DS) is defined as the combination of materials and process conditions that guarantees the assurance of quality. This principle ensures that as long as a process operates within DS, it consistently produces a product that meets specifications. It was originally developed for a single unit system. Many industrial processes frequently involve multiple unit operations. Assessing the interaction of Critical Process Parameters (CPPs) with Critical Quality Attributes (CQAs) across stages enables informed decision-making and the capacity to balance different requirements. Analysis and visualization of the complex, multi-dimensional DS is a challenging task. This paper presents a framework for identification such DSs, considering both joint and decoupled strategies using a detailed analysis of a two-stage batch reactor case study. We assess and discuss the practicality and relevance of these methods.

The building sector, primarily through heating, ventilation, and air conditioning (HVAC) systems, accounts for over 30% of global final energy consumption and 26% of energy-related emissions, highlighting the urgency for efficient energy management and effective fault detection. Optimizing HVAC system performance is crucial for energy conservation and sustainability. This study introduces a hybrid modeling methodology to enhance HVAC systems’ fault detection and isolation (FDI). Using feature extraction through principal component analysis (PCA) and autoencoder (AE), the proposed approach integrates first-principles knowledge with data to improve the performance of different clustering algorithms (K-means, density-based spatial clustering of applications with noise (DBSCAN), and ordering points to identify the clustering structure (OPTICS)) to distinguish datasets of different operating conditions (normal and faulty conditions). The proposed approach is applied to detect common faults in HVAC systems, demonstrating superior performance compared to purely data-driven methods.

To foster self-driving experimentation and address the reproducibility crisis in bioprocess development in a collaborative environment, a modular Workflow Management System (WMS) is required. In this work, a WMS based on Directed Acyclic Graphs that offers a modular and flexible design for plug-and-play integration of computational tools is presented. A case study is used to demonstrate that the implementation of a computational WMS in robotic experimental facilities promotes the application of Findable, Accessible, Interoperable and Re-usable principles, allowing researchers to readily share protocols, models, methods and data. As a proof of concept, we integrated three different computational workflows for online re-design of feeding rates in 24 parallel E. coli fed-batch cultivations producing elastin-like proteins. This approach provides a solid foundation for increasing scientific data generation in robotic experimental facilities, fostering open collaboration, and addressing the challenges of reproducibility in research.

This paper presents the development of algorithms for mass-constrained neural network models that can exactly satisfy mass conservation laws of chemical process systems, even if the training data violates the same. As opposed to approximately satisfying mass balance constraints of a system by considering additional penalty terms in the objective function, algorithms have been developed to solve an equality-constrained optimization problem, thus ensuring the exact satisfaction of the overall mass conservation laws. For developing dynamic mass-constrained networks, hybrid series and parallel all-nonlinear static-dynamic neural network models are leveraged. The proposed algorithms for solving both the inverse and forward problems are tested by considering both steady-state and dynamic data in presence of varieties of noise characterizations. The proposed structures and algorithms are applied to the development of data-driven models of two nonlinear dynamic chemical processes, namely the Van de Vusse reactor system as well as a solvent-based post-combustion CO₂ capture process.

This study proposes a stock boundary compensation method to address the uncertainty of gaseous energy in integrated steel plants. The uncertainty disrupts the balance of temporary storage, resulting in energy waste, environmental pollution, and disturbances in steel production. The method accurately compensates for the impact of gaseous energy uncertainty on storage. Firstly, this paper takes oxygen and byproduct gas systems as the examples to describe the gas energy system and its scheduling model. The storage deviation caused by gaseous energy uncertainty is quantitatively analyzed using formulas. Subsequently, this study formulates an optimization problem to determine the optimal margin for compensating the storage boundary using a data-driven approach. Comparative experiments demonstrate that the proposed method not only significantly enhances the safety of gaseous energy storage subject to uncertainty, but also outperforms traditional robust optimization and stock fluctuation optimization methods in terms of system robustness against uncertainty and operating cost optimality.

Minimisation of environmental footprint in line with sustainability goals rests at the top of the agenda of the pharmaceutical industry. Volatile Organic Compounds (VOCs), while essential to primary pharmaceutical manufacturing, are solvents whose emissions pose a risk to human health and ecosystems. Adsorption on activated carbon beds is an established technology for end of pipe emissions control, which, however, faces efficiency limitations by quick and irregular bed saturation due to complex, transient feeds. This study employs a validated nonisothermal, multicomponent adsorption model to quantitatively assess the exact effect and potential value of waste stream feed sequencing towards activated carbon bed utilisation optimisation. Our results indicate that gradual increase of dichloromethane feed concentration in combination with a low, constant inlet concentration of the strongly adsorbing component leads to the latest breakthrough onset for the dichloromethane-acetone, dichloromethane-chloroform and dichloromethane-toluene mixtures. Transient vs. constant feeds usage and their interplay clearly affects bed behaviour, paving the way to industrial VOC emission abatement scheduling and process optimisation.

In this article, we present a novel deep learning-based group contribution framework for the targeted design of ionic liquids (ILs). This computational framework can expedite and improve the process of finding desirable molecular structures of IL via accurate property predictions in a data-driven manner. Our proposed framework consists of two essential steps: establishing a correlation between IL viscosity and CO₂ solubility by merging two deep learning models (DNN-GC and ANN-GC) and utilizing this correlation to identify the optimal IL structure with maximal CO₂ absorption capacity. Our model achieves high accuracy with R² values of 95%, 94.2%, and 96.4% for DNN-GC, ANN-GC, and DNN-ANN-GC, respectively. Correlation results align with the experimental data, affirming the applicability of our framework. Finally, the algorithm is employed in a CO₂ capture case study to generate and select the best-performing novel ILs, which exhibit behavior consistent with established ILs in the literature.