Global biomanufacturing is projected to expand rapidly in the coming decade due to advancements in DNA sequencing and manipulation. However, the complexity of cellular behaviour introduces difficulty in modelling and optimizing biomanufacturing processes. Phenomenological models that represent the physics of the system in empirical equations suffer from poor robustness, while their machine learning (ML) counterparts suffer from poor extrapolative capability. On the other hand, hybrid models allow us to leverage both physical constraints and the flexibility of ML. This work describes a new approach for hybrid modeling that integrates the time-variant parameter estimation and ML model training into a singular step. We implement this approach on a proposed scheme for the cell-mediated conversion of a lignin derivative into a bioplastic precursor and show that our integrated hybrid model outperforms the traditional two-step hybrid, phenomenological, and ML model counterparts. Lastly, we de... [more]

Miniaturised stirred bioreactors are crucial in high-throughput bioprocesses for their simplicity and cost-effectiveness. To accelerate process optimisation in chemical and bioprocess industries, models that integrate CFD-predicted flow fields with (bio)reaction kinetics are needed. However, conventional two-step coupling methods, which freeze flow fields after solving hydrodynamics and then address (bio)reaction transport, face numerical challenges in miniaturised systems due to unsteady radial flows, recirculation zones, and secondary vortices. These flow fluctuations prevent steady-state hydrodynamic convergence. This study addresses these challenges by time-averaging the RANS solutions of the transitional SST model to achieve statistical hydrodynamic convergence. This method is particularly effective for internal flow problems at low to midrange Reynolds numbers (100 W/m²) due to light limitation. This model provides a framework for optimising stirring speeds and refining operation... [more]

Effective prediction of nutrient demands is crucial for optimising microalgae growth, maximising productivity and minimising the waste of resources. With the increasing amount of data related to microalgae cultivation systems, data mining and machine learning models to extract additional knowledge have gained popularity. In the development of such models, a data preprocessing stage is necessary due to the poor data quality. At this stage, cleaning and outlier removal techniques are employed to eliminate missing data and outliers, respectively. Afterwards, data splitting and cross-validation strategies are employed to ensure that the models are trained and evaluated with representative subsets of the data. Principal component analysis is also applied to simplify complex environmental datasets by reducing the number of features while retaining as much information as possible. To further improve prediction capabilities, ensemble methods are incorporated, leveraging multiple models to achi... [more]

Understanding the complexity of human digestion is critical for designing models that serve as valuable research tools for process simulation and prediction. Due to the high cost of medical intervention & recent advancements in in vitro digestion protocols, increased demand for inexpensive in silico solutions emerges. This study aims to develop a mathematical model that simulates the in vitro dynamic Food Digestion SIMulator (FooDSIM) functionalities via a digital twin approach. Ordinary Differential Equations (ODEs) simulate the system as a series of Continuously Stirred Tank Reactors (CSTRs) and describe different regions of human organs (stomach, duodenum, ileum, colon) of the human Gastrointestinal Tract (GIT). Various time horizons were used to investigate the effect of periodic feeding on the dynamic stabilisation of the inherently simulated processes (hydraulics, pH, biochemical interactions between enzymes & substrates, and nutrient absorption). A Polynomial Chaos Expansion (P... [more]

Predicting water quality is essential for effective environmental management and pollution control. Dissolved oxygen (DO), one of key water quality parameters, plays a vital role in biological wastewater treatment [1]. This study aims to forecast DO levels in activated sludge tanks of an oil refinery’s wastewater treatment plant (WWTP). Proper oxygen concentration is critical for microbial activity, as inadequate levels can disrupt the biological breakdown of pollutants. The objective is to develop predictive models to identify operational risks early, enhancing treatment efficiency and optimizing resources like chemicals, bacterial cultures, and aeration systems. Additionally, the study aims to provide early warnings to operators, minimizing reliance on laboratory tests and ensuring optimal conditions for bacteria, leading to better operational performance, cost reduction, and improved water quality ultimately promoting sustainable wastewater treatment. Various deep learning models, i... [more]

Water lily (Eichhornia crassipes) has been identified as an invasive exotic plant with high proliferation in Mexico, affecting aquatic bodies, such as lakes. After extraction, the water hyacinth biomass can be used as raw material for the production of bioproducts and bioenergy, however, the majority of them not covered the region's needs, and their economic profitability decreases significantly. Also, few reports present its use as raw material inside a biorefinery scheme. In this work, we propose a local biorefinery scheme to produce power and bioproducts from water lilies, using Aspen Plus V.10.0, per the needs of the Patzcuaro Lake community in Michoacán, Mexico. The scheme has been designed to process the harvested and sun-dried water lily from 197.6 kg/h of total wet harvested biomass, according to the extraction region schedule. The biomass is separated: root (RT) and stems-leaves (SL). The processing scheme involves the RT combustion to produce electric power, and two process... [more]

Pharmacokinetic and pharmacodynamic (PK/PD) models are used to predict drug transport in the body and to assess treatment efficacy and optimal dosage. The kinetic parameters embedded in the models, which define transport across body compartments or drug efficacy, can be linked to patient-specific characteristics; understanding the parameter space-model output relationship is critical towards linking patient population heterogeneity to the therapeutic outcome variability. Global Sensitivity Analysis (GSA) is a well-established tool used to examine parameter-to-parameter interactions, shedding light on underlying interactions towards enhanced system understanding. Despite its potential and usefulness, GSA performance is dependent to the model complexity; large-scale and nonlinear PK/PD models, which often have large sets of parameters, can render GSA challenging to perform, requiring excessive computational effort. Proposed approaches to reduce GSA complexity, such as segmentation in par... [more]

Hybrid modelling utilizes advantageous aspects of both mechanistic (white box) and data-driven (black box) modelling. Combining the physical interpretability of kinetic modelling with the power of a data-driven Artificial Neural Network (ANN) yields a hybrid (grey box) model with superior accuracy when compared to a traditional mechanistic model, while requiring less data than a purely data-driven model. This study demonstrates the construction a hybrid model with transfer learning for the predictive modelling and optimization of a high-cell-density microalgal fermentation process for lutein production. Dynamic optimization was conducted to identify a feeding strategy that maximized final lutein production. The results were then experimentally validated. Overall, this work presents a novel digital twin application that can be easily adapted to general bioprocesses for model predictive control and process optimization.

The growing concern over the environmental impacts of the wine industry has driven the search for sustainable technologies to manage its waste, particularly the residual sludge generated during effluent treatment. This sludge, rich in organic matter, represents a significant source of pollution if not properly treated. However, their energy content allows them to turn this environmental liability into an asset through innovative valorization. Hydrothermal liquefaction (HTL) emerges as a promising technology in this context. This process allows the direct conversion of residual sludge into high-energy-value liquid biofuels. Unlike other treatment methods, HTL can process wet biomass without needing prior drying, making it particularly suitable for managing sludge from wine effluents. Thus, this research aims to evaluate the conversion of residual sludge derived from wine effluent treatment into biofuels through a hydrothermal liquefaction simulation, integrating this process into a sust... [more]

The paradigm shift into an era of Industry 4.0, also referred to as the fourth Industrial Revolution, has emphasized the need for intelligent networking between process equipment and industrial processes themselves. This has brought on an age of research and framework development for smart manufacturing in the name of Industry 4.0 [1]. While the physical and digital advancements towards smart manufacturing integration are substantial the inclusion of engineers themselves amongst this shift is often less considered [2]. There are educational efforts in Europe to create and implement smart manufacturing curriculum for non-traditional or adult learners already integrated in the workforce, but attention is also needed on a next generation smart manufacturing curriculum for pre-career students [3]. We, the teaching team of CHE 554: Smart Manufacturing at Purdue University, developed and implemented a curriculum geared towards the training of undergraduate, graduate, and non-traditional stud... [more]

The field of Process Systems Engineering (PSE) is undergoing a renaissance through the integration of artificial intelligence (AI) and machine learning (ML). This transformation is driven by the vast availability of industrial data and advanced computing power, enabling the practical application of sophisticated ML models. These models enhance PSE capabilities in design, control, optimization, and safety. The progress of ML and ever-present data collection address previously intractable problems, particularly in system integration and life-cycle modeling. ML-powered predictive algorithms are augmenting traditional control systems, showing potential in supply chain optimization and increasing operational resilience. Additionally, ML-driven fault prediction and diagnostics are enhancing process safety systems, allowing for predictive maintenance and minimizing risks of accidents. A case study of the collaboration between the University of West Attica and Helleniq Energy through the MSc p... [more]

Ensuring access to clean water, preserving water reserves, and meeting energy needs are fundamental for sustainability and a priority for global organizations like the UN and EU. The Mediterranean, particularly Greece, faces severe water imbalances due to rising demand, prolonged droughts, and seasonal tourism pressure. This over-exploitation of water resources threatens agriculture, employment, and regional sustainability. Addressing these challenges, this study analyzes the water-energy nexus in high-stress areas and develops an optimization model for sustainable water resource management. The model integrates sectoral demands, energy consumption, and seasonal variability to improve efficiency while balancing economic and environmental constraints. Additionally, it incorporates demand forecasting to align water use with ecosystem sustainability, reducing environmental impacts. By providing a systematic framework for decision-makers, this research supports the development of long-term... [more]

The climate crisis continues to grow as an existential threat. Establishing reliable energy resources that are renewable and zero-carbon emitting is a critical endeavour. Hydrogen has emerged as one such critical resource due to its high gravimetric energy density and near-abundant availability. However, it suffers from low volumetric energy density and is incredibly challenging to store and transport. The metal hydride, a solid-state storage method, provides a viable solution to the current limitations. Storage is achieved through the chemical absorption of hydrogen into a porous metal alloy’s sublattice. But its challenging thermodynamic functionality leaves a gap between the ideal storage capacity that current industry requires and the limited capacity that reusable metal hydrides currently provide. This work used mathematical modelling to determine optimal operating conditions for a metal hydride in order to maximise hydrogen storage capacity. Computational fluid dynamics is used t... [more]

A transition to low-carbon fuels is integral in addressing the challenge of climate change. An essential transformation is underway in the transportation sector, one of the primary sources of global greenhouse gas emissions. The electrofuels that represent methanol synthesis via power-to-fuel technology have the potential to decarbonize the sector. This paper outlines a critical comprehensive life cycle assessment for electrofuels, with this study focusing on the production of synthetic methanol from renewable hydrogen from water electrolysis coupled with carbon from the direct air capture (DAC) process. This study has provided a comparison of the environmental impacts of synthetic methanol produced from grids of five regions (India, the US, China, Switzerland, and the EU) with conventional methanol from coal gasification and natural gas reforming. The results from this impact assessment show a high dependency of environmental scores on the footprint of the grid. Switzerland, with its... [more]

The aluminium industry emits approximately 1.1 billion tonnes of CO2-eq annually, contributing about 2% of global industrial emissions. Decarbonization pathways aim to achieve net-zero emissions by 2050, but this requires making decisions today for technologies having lifetimes of 20 – 25 years, based on uncertain economic assumptions, particularly given the volatility of energy prices. Traditional price forecasting models often fail to anticipate major disruptions, such as the 2022 energy crisis. This work applies Monte-Carlo Analysis (MCA) to evaluate the financial stability of decarbonization pathways under energy crisis scenarios and report on the resilience of the alternative solutions. In the modelled secondary aluminium production facility, direct electrification is assumed for lower temperature furnaces of annealing heat treatments or preheating, while the study defines the decarbonization options based on the melter furnace technology, a key bottleneck in terms of load and via... [more]

The separation of 1,3-butadiene from C4 hydrocarbon mixtures is a crucial step in the production of synthetic rubbers and plastics. Conventional extractive distillation methods using solvents, like N,N-dimethylformamide (DMF), have proven effective but presents significant health and environmental challenges. This study explores the feasibility of using propylene carbonate (PC) as a green solvent alternative for butadiene extractive distillation, leveraging its environmentally friendly properties and industrial compatibility. Simulations were conducted using Aspen Plus®, employing the Non-Random Two-Liquid (NRTL) model coupled with the Redlich-Kwong equation of state to describe phase equilibrium. Results indicate that PC integrates seamlessly into existing processes, achieving comparable operational stability and butadiene separation efficiency with minimal modifications. A significant design improvement was the elimination of the methylacetylene separation column in the PC process, w... [more]

Surface tension is a fundamental property at the liquid/gas interface, influencing phenomena such as capillary action, droplet formation, and interfacial behavior in chemical engineering processes. Despite its significance, experimental determination of surface tension is time-intensive and impractical for in silico-designed compounds. Predictive models are essential for bridging this gap. This study expands on Gaudin's COSMO-RS-based model, which assumes uniform molecular orientation at the surface, by testing its predictive capability across broader temperatures (5-50°C) and developing a hybrid model combining first-principle and machine learning insights to improve Gaudin's model predictions. The HM employs a serial configuration where COSMO-RS predictions serve as inputs alongside molecular descriptors, derived using the Mordred library. SHAP analysis guides feature selection, enhancing model interpretability. An artificial neural network refines predictions, optimized via Bayesian... [more]

Developing ultra- or high-performance liquid chromatography (HPLC) methods for analysis or purification requires significant amounts of material and manpower, and typically involves time-consuming iterative lab-based workflows. This work demonstrates in two case studies that an autonomous HPLC platform coupled with a mechanistic model that self-corrects itself by performing parameter estimation can efficiently develop an optimized HPLC method with minimal experiments (i.e., reduced experimental costs and burden) and manual intervention (i.e., reduced manpower). At the same time, this HPLC platform, referred to as Smart HPLC Robot, can deliver a calibrated mechanistic model that provides valuable insights into method robustness.

Deep learning faces significant challenges in efficiently training large-scale models. These issues are closely linked, as efficient training often depends on precise and computationally feasible gradient calculations. This work introduces innovative methodologies to improve deep learning network (DLN) training in complex systems. A novel approach to DLN training is proposed by adapting the block coordinate descent (BCD) method, which optimizes individual layers sequentially. This is combined with traditional batch-based training to create a hybrid method that harnesses the strengths of both techniques. Additionally, the study explores Iterated Control Random Search (ICRS) for initializing parameters and applies quasi-Newton methods like L-BFGS with restricted iterations to enhance optimization. By tackling DLN training efficiency, this contribution offers a comprehensive framework to address key challenges in modern machine learning. The proposed methods improve scalability and effect... [more]

The efficient separation of carbon dioxide (CO2) and methane (CH4) is crucial for chemical processes, including biogas upgrading and natural gas purification. Metal-organic frameworks (MOFs) have gained significant attention as promising adsorbents for these processes due to their high porosity and tunable structures. Estimating the adsorption capacity of MOFs is essential for screening high performing adsorbents. While molecular simulations are commonly used to estimate the adsorption capacities, their computational intensity acts as a bottleneck in screening MOF adsorbents. In this study, we propose a machine learning (ML)-based framework for the high-throughput prediction of adsorption isotherms for CO2 and CH4 in MOFs. A graph neural network (GNN) model was developed to predict adsorption capacities, effectively replacing the time-consuming molecular simulations. The GNN model processes the structural graphs of MOFs, capturing their spatial configurations, such as surface structure... [more]

Physics-Informed Symbolic Regression (PISR) offers a pathway to discover human-interpretable solutions to partial differential equations (PDEs). This work investigates three fitness metrics within a PISR framework: PDE fitness, Bayesian Information Criterion (BIC), and a fitness metric proportional to the probability of a model given the data. Through experiments with Laplace’s equation, Burgers’ equation, and a nonlinear wave equation, we demonstrate that incorporating information theoretic criteria like BIC can yield higher fidelity models while maintaining interpretability. Our results show that BIC-based PISR achieved the best performance, identifying an exact solution to Laplace’s equation and finding solutions with R2-values of 0.998 for Burgers’ equation and 0.957 for the nonlinear wave equation. The inclusion of the Bayes D-optimality criterion in estimating model probability strongly constrained solution complexity, limiting models to 3-4 parameters and reducing accuracy. Thes... [more]

Balancing economic and environmental goals in industrial applications is critical amid challenges like climate change. Multi-objective optimization (MOO) and multi-criteria decision analysis (MCDA) are key tools for addressing conflicting objectives. MOO generates viable solutions, while MCDA selects the optimal option based on key performance indicators such as profitability, environmental impact, safety, and efficiency. However, large datasets pose a challenge in selecting the preferred solution during the MCDA process This study introduces a novel machine learning-enhanced MCDA framework and applies the method to analyze decarbonization solutions for a European refinery. A stage-wise dimensionality reduction method, combining AutoEncoders and Principal Component Analysis (PCA), is applied to simplify high-dimensional datasets while preserving key spatial features. Geometric analysis techniques, including Intrinsic Shape Signatures (ISS), are employed to refine the identification of... [more]

The accumulation of heavy polynuclear aromatics (HPNAs) in hydrocracking units (HCUs) poses significant challenges to catalyst performance and process efficiency. This study proposes an integrated machine learning framework that combines ridge regression, K-means, and long short-term memory (LSTM) neural networks to predict HPNA formation, enabling proactive process management. For the training phase, weighted average bed temperature (WABT), catalyst deactivation phase—clustered using unsupervised K-means clustering—and hydrocracker feed (HCU feed) parameters obtained from laboratory analyses are utilized to capture the complex nonlinear relationships influencing HPNA formation. In the simulation phase, forecasted WABT values are generated using a ridge regression model, and future HCU feed changes are derived from planned crude oil blend data provided by the planning department. These forecasted WABT values, predicted catalyst deactivation phases, and anticipated HCU feed parameters s... [more]

The rapid advancement of computational drug discovery has enabled the generation of vast virtual libraries of promising drug candidates. However, evaluating the synthetic accessibility (SA) of these compounds remains a critical bottleneck. While computer-aided synthesis planning (CASP) tools can provide synthesis routes to the candidate, their computational demands make them impractical for large-scale screening. Existing rapid SA scoring methods, struggle to generalize to out-of-distribution molecules and do not account for economic viability. To address these challenges, we present MolPrice, an accurate and reliable price prediction tool. By introducing a novel self-supervised learning approach, MolPrice achieves robust generalization to diverse molecular structures of various complexities. Our comprehensive analysis of model architectures and molecular representations reveals that substructure-based features strongly correlate with market prices, supporting the relationship between... [more]

This study tackles the challenge of accurate yield prediction in fluid catalytic cracking (FCC) units by comparing conventional supervised regression with time series forecasting methods using industrial data collected from the distributed control system (DCS) of an FCC plant. We introduce a shifted forecast paradigm that preserves temporal relationships between predictors and targets. Our preprocessing pipeline, which employs trimmed mean smoothing, addresses common industrial data challenges. Results demonstrate that the forecasting approach significantly outperforms supervised regression, achieving a mean absolute percentage error (MAPE) of 1.56% for 3-hour shifted predictions compared to 6.20% for supervised regression. The model maintains robust performance even with extended shifts during predictions, showing an MAPE of 3.55% for 14-day forecasts. This research provides valuable insights for implementing predictive analytics in industrial FCC operations, demonstrating the superio... [more]