Deep Kernel Learning (DKL) has emerged as a powerful framework for Bayesian Optimization (BO), via combining expressive representation learning models with typical Gaussian Processes (GPs) surrogate models. However, conventional DKL typically relies on weight-based feature extractors (e.g., multilayer perceptrons (MLPs)), which often lack interpretability and may suffer from overfitting under data scarcity or training instability, potentially leading to a degraded uncertainty quantification in GP models. Grounded in the Kolmogorov-Arnold representation theorem, this paper proposes a novel DKL-KAN framework that employs Kolmogorov-Arnold Networks (KANs) as adaptive feature extractors, formulating a DKL-KAN surrogate model. Unlike MLPs, the KANs learn data-driven univariate functions, yielding more sample-efficient and stable representations for regression under limited data regimes. Followed by the GP, the DKL-KAN facilitates end-to-end learning of expressive latent representations whil... [more]

Cryogenic air separation units (ASUs) are the primary industrial technology for producing high purity oxygen, nitrogen, and argon gases at commercial scale. Cryogenic ASUs are large consumers of electricity, making them ideal candidates for market-driven operation research in today's volatile and uncertain manufacturing environments. To maximize profitability, ASU operation must dynamically adapt to changing market conditions as they evolve. This work explores the implementation of a rolling-horizon scheduling (RHS) strategy for the real-time market-driven operation of a high-dimensional ASU model with inventory, responding to uncertainty in future plant demand and electricity price forecasts by periodically rescheduling in response to updated market information. A dynamic latent variable-based surrogate model (LV-SM) is used within the scheduling framework as a computationally efficient substitute for an existing first-principles-based ASU model. Results show that RHS and plant invent... [more]

Simulated Moving Bed (SMB) chromatography is widely used for a variety of separations, yet, when applicable, these systems are typically operated using offline optimization strategies. Over time, process degradation and unforeseen disturbances may cause SMB units to deviate from the calculated optimal conditions, reducing overall performance. Real-Time Optimization (RTO) offers a promising solution by continuously monitoring and adjusting operating conditions to maintain optimal performance, despite such perturbations. However, experimental implementation of RTO in industrial SMB processes is costly and requires significant interdisciplinary coordination.To address this challenge, a virtual framework is proposed for the preliminary development of a model-based RTO system. The methodology employs a virtual plant-model pair, in which a representative plant model generates in silico experimental data, while a structurally distinct predictive model reproduces these results. Structural mism... [more]

Efficient deployment of carbon capture, utilisation, and storage (CCUS) within industrial clusters requires coordinated CO2 allocation under economic, technical, and environmental constraints, particularly when CO2 availability is limited. This paper presents a centralised optimisation framework for allocating captured CO2 from nine industrial sources to six utilisation and storage sinks within an industrial park in Qatar. A multi-objective mixed-integer linear programming (MILP) model is developed to minimise total system cost while accounting for capture, purification, transport, and utilisation processes, and enforcing an environmental feasibility constraint to ensure net CO2 reduction. The model is evaluated under four scenarios: a baseline case with sufficient CO2 to satisfy all sink demands, and three scarcity scenarios in which 15%, 25%, and 35% of total source emissions are available. Results show that under scarcity, allocations prioritise large EOR sinks supplied by high-volu... [more]

In this work, the synthesis, design and optimization of a quaternary double dividing wall distillation column (QDDWC) is presented. The effect of the feed composition over the performance of this intensified configuration is studied. The synthesis and design of the QDDWC takes place using as basis a conventional direct sequence for the separation of a n-butane/n-pentane/n-hexane/n-heptane mixture. The column is tested for three molar feed compositions: 40/10/10/40, 25/25/25/25, and 10/40/40/10. The configurations are optimized through a multiobjective genetic algorithm to simultaneously minimize the total heat duty and the number of stages. According to the results, the proposed structure allows savings in heat duty up to 59% but requiring up to 28% more stages than the conventional sequences.

Machine learning (ML) reduces reliance on computationally expensive first-principles simulation while capturing complex nonlinear behaviors. However, poor extrapolation, overfitting, limited interpretability, and lack of strict consistency with governing laws limit the use of ML models in process applications. Current methods for learning optimization policies also struggle with constraint satisfaction and optimality guarantees. Approaches such as physics-informed neural networks (PINNs) incorporate constraints "softly" and do not ensure strict constraint enforcement-an issue that can be particularly detrimental in safety-critical applications, where even minor violations may lead to unsafe or infeasible decisions. To resolve these issues, we develop an ML framework with a differential projection layer that allows computationally efficient process modeling, parameter estimation, and nonlinear optimization with feasibility and optimality guarantees. The framework is general in a sense t... [more]

Distributed deployment of process systems can benefit from modularity and shared components across multiple variants, reducing both manufacturing costs and engineering effort. Process family design formalizes this idea by simultaneously optimizing a family of process variants while determining a shared platform of common components. This results in a large-scale mixed-integer nonlinear program (MINLP) that couples nonlinear process models with discrete platform-allocation decisions. In this work, we solve the process family design MINLP using a progressive hedging (PH)-based decomposition strategy that exploits its block-angular structure. To improve convergence for this nonconvex problem, we introduce dynamic gradient-based penalty updates, a decoupled primal-dual strategy via separate PH runs, and parallel optimization-based bounds tightening of first-stage variables. Computational results on a water desalination case study demonstrate that the proposed approach improves solution qua... [more]

Dimethyl ether (DME) is a promising clean fuel and chemical intermediate, yet its synthesis from synthesis gas remains highly sensitive to both catalyst formulation and operating conditions. In this work, a data-driven framework is developed that combines machine learning surrogate modeling with multi-objective optimization to support systematic decision-making in DME synthesis. The novelty lies in the systematic comparison of different optimization approaches applied to an identical machine learning surrogate model for DME synthesis, thereby highlighting their respective strengths and limitations as decision-support tools under limited-data conditions. A dataset compiled from published literature includes catalyst composition, preparation methods, physicochemical descriptors, and operating conditions, with CO conversion and DME selectivity as performance indicators. After data preprocessing, feature analysis using correlation analysis and principal component analysis (PCA) is applied... [more]

The increasing adoption of modular plant concepts in process engineering requires new strategies for design and safety evaluation. Conventional hazard analysis methods, such as HAZOP are time-consuming and must be repeated whenever a configuration changes, which contradicts the flexibility that modularization aims to achieve. This work combines concepts from the modular HAZOP method and the preHAZOP method to enable an automated, early-stage safety assessment for modular plants based on P&IDs. A workflow is developed that generates a combined P&ID for a modular plant from individual module (PEA) P&IDs provided in DEXPI format and performs an adapted preHAZOP analysis on the resulting plant representation.A key motivation is that P&IDs are always created during plant or module design and already contain relevant piping information, which can be reused for automated module interconnection and plausibility checks. In the proposed workflow, standardized interfaces enable automatic connecti... [more]

Nonlinear model predictive control (NMPC) can substantially improve performance and constraint handling for (bio)chemical processes, but its adoption is still limited by the effort required to build maintainable first-principles models and to implement efficient dynamic optimization-based controllers. This paper presents GlycoPy, an open-source, equation-oriented and object-oriented Python framework that supports hierarchical model construction and integrated workflows for simulation, parameter estimation, dynamic optimization, and NMPC. The case study of the monoclonal antibody glycosylation process based on a multiscale model demonstrates the capability of GlycoPy.

Predicting solvent effects on reaction activation barriers is central to understanding chemical reactivity and reaction kinetics, and guiding solvent selection. The solvent-induced change in activation free energy (DDG_solv‡) provides a quantitative descriptor of this effect, but remains costly to evaluate across vast reaction-solvent spaces, using quantum mechanical methods. Recent data-driven models have enabled prediction of solvent effects. However, most typically rely on two-dimensional representation of reactions and do not explicitly encode sufficient reaction context, such as transition-state information, or three-dimensional structural changes along the reaction, resulting in limited generalizability and predictive accuracy. In this study, systematic evaluation is presented of modelling strategies for predicting DDG_solv‡, with a focus on the role of reaction-state representation, input-geometry fidelity, and input modality. Using a large reaction-solvent dataset, models based... [more]

We investigate ultrasound-assisted transesterification for biodiesel production. We use inline Raman spectroscopy to quantify its impact on reaction kinetics, catalyst reduction, and temperature sensitivity. We perform a systematic experimental study at different temperatures (50, 55, and 60 °C), different catalyst loadings, with and without ultrasound. The results show that ultrasound significantly accelerates early reaction kinetics at all temperatures, with the strongest effect observed at 55 °C, where both Fatty Acid Methyl Ester (FAME) formation rate and final conversion increase by up to 7 wt%. Under reduced catalyst conditions, ultrasound restores high conversion levels, leading to up to 20 wt% higher final FAME compared to operation without ultrasound and achieving performances comparable to, or exceeding, those obtained with (normal) catalyst without ultrasound. This is mainly because ultrasound primarily enhances mass transfer and phase contact, thereby reducing the system's... [more]

Reliable multimodal monitoring in crystallization processes remains challenging due to heterogeneous PAT signal quality, sensor drift, asynchronous sampling and nonstationary noise. This work presents a machine-learning-assisted fusion framework that integrates multimodal PAT alignment, estimation and physics-guided regularisation to generate coherent concentration and particle-size trajectories. A mechanistically informed simulation platform is developed to produce synthetic Raman, FTIR, FBRM and image-based crystal size data with realistically simulated drift, heteroscedastic noise, dropouts and distortion patterns. Sensor reliability is inferred through a Random Forest model trained on variance-normalised discrepancies and quality metrics, which allows the dynamic adjustment of channel contributions. Across modalities, the Random Forest achieves MAE values of 0.03-0.20 for probability-type indicators and shows stable explanatory power for variance-inflation factors on particle-size... [more]

Environmental sustainability is increasingly recognized as a critical consideration in pharmaceutical development, yet it is rarely incorporated at the scale of molecular-level design. This study introduces a strategy to predict cradle-to-gate indicators that can be flexibly incorporated into multiple early-stage molecular prioritization scenarios. A dataset of 150 pharmaceutical-relevant molecules was compiled, with each molecule described by structural descriptors, thermophysical properties, and ReCiPe endpoint indicators representing human health, ecosystem quality, and resource scarcity. A dual-branch multi-task model combining graph-based and descriptor-based representations was trained to predict these three endpoint indicators. Model performance was evaluated through validation metrics, local sensitivity analysis, and SHAP-based interpretability. A case study with solubility-based feasibility constraints was then used to illustrate how different sustainability weighting schemes... [more]

Microstructure segmentation is essential for quantitative materials analysis; however, supervised deep learning demands substantial annotation, whereas general-purpose foundation models such as the Segment Anything Model (SAM) offer limited domain-specific semantic control. This paper presents MatStudio, a human-in-the-loop framework for microstructure segmentation that is proposed and implemented end to end in this work. MatStudio couples an interactive workflow for batchwise micrograph annotation and model adaptation with a dual-head convolutional architecture and SAM-guided boundary refinement. The loop combines sparse supervision with SAM-assisted labeling, task-specific training, and iterative batch-level correction, typically converging within two to three cycles.. The network comprises a shared encoder initialized from a pretrained backbone and two decoders: a UNet-style segmentation head that jointly predicts class labels and pixelwise uncertainty, and a prototype branch that m... [more]

In this paper, PhoSim V.0, a physics-based digital twin core of a wet-process phosphoric acid (WPPA) digestion reactor, is presented as an initial step toward a high-fidelity virtual representation of industrial WPPA plants. The simulator integrates dissolution, reaction, and crystallization phenomena under strongly non-ideal electrolyte conditions. The reactor is modeled as a batch reactor, where the dissolution of tricalcium phosphate is described using a shrinking-core approach, while gypsum precipitation is represented by a one-dimensional population balance equation capturing particle size distribution evolution. Supersaturation ratios governing nucleation and crystal growth are computed from non-ideal activities using a Pitzer-based thermodynamic model, ensuring consistent coupling between dissolution, reaction stoichiometry, and crystallization kinetics. The resulting stiff system of equations is solved to predict key process indicators such as speciation, supersaturation ratio,... [more]

A flexible start-stop operating policy that involves full shut-down and start-up may be beneficial for electrified plants under certain grid conditions, such as dispatchable demand response. This paper introduces a multi-period Hamilton-Jacobi reachability framework to explore the space of state trajectories for plant shut-down and start-up. Shut-down is defined in terms of operations leading to a stand-by state with no material flows or energy inputs, and variables within safety constraints. Candidate stand-by states are identified by constructing backwards reachability tubes from the desired steady-state operating point. The candidate shut-down/stand-by state is partitioned in fast and slow regions. Admissible control input trajectories are determined for the fast region, from which the minimum time trajectory is selected as optimal for fast start-up. A proof-of-concept simulation using a reaction/separation/recycle plant is presented.

Pharmaceutical and fine chemical industries face strong pressure to shorten time-to-market while maintaining compliance with complex regulatory frameworks. These conflicting demands require rapid process design, validation, and scale-up. Modular production plants standardized in VDI 2776 and VDI/VDE/NAMUR 2658 have emerged as a promising strategy to shorten engineering and validation efforts. The Product-Process-Resource (PPR) philosophy represents a key approach to efficient data management in modular plant engineering. It enables the separation of different flexibility dimensions into distinct, relevant aspects that can ideally be exchanged or modified independently. To realize this principle in practical applications, formalized information models and ontologies serve as a key enabler for structuring and managing semantic data. This work investigates several information models and ontologies for the process engineering domain regarding their suitability to support separation accordi... [more]

The increasing demand for energy, water, and chemical products signals the need for more sustainable and efficient process design methodologies. Traditional methods for conceptual process design constrains the exploration of novel and intensified process alternatives, as they rely on prior knowledge in defining the design space. Previous studies employing bottom-up approaches, such as phenomena building blocks (PBBs), suggest that the synthesis of complex bottom-up flowsheets remains computationally challenging and is thus limited to the synthesis of individual units of operation. This work proposes a bottom-up, data-driven framework for process synthesis and intensification based on phenomena building blocks (PBBs), in which process flowsheets are constructed from their underlying physical and chemical phenomena rather than conventional units of operation. The proposed framework introduces a phenomena-based text representation and data collection module. Furthermore, a sequence traini... [more]

Real-time monitoring of metabolite concentrations is critical for optimising bioprocess performance. While Raman spectroscopy offers a non-invasive solution, translating spectra into metabolite concentration estimates requires robust machine learning models. Foundation models such as TabPFN demonstrate exceptional predictive performance but suffer from high inference complexity when trained on large calibration datasets, hindering their use in real-time laboratory settings. This study proposes a batch Active Learning (AL) strategy to efficiently calibrate TabPFN using a minimal subset of data. We employ a weighted K-means clustering strategy that balances model uncertainty and dataset diversity to select the most informative calibration samples. We evaluated this method on a dataset of nearly 7, 000 Raman spectra covering eight substances. Our AL strategy achieved a mean R² score greater than 0.95 with approximately 1, 000 samples, significantly outperforming random sampling. Notably,... [more]

Artificial neural networks (ANNs) have emerged as powerful surrogate models in process design and optimisation, capable of capturing complex nonlinear process behaviour while significantly reducing computational cost compared to detailed first-principles simulations. However, ANN prediction errors in safety-critical applications can lead to suboptimal or vulnerable designs, necessitating rigorous treatment of approximation uncertainties. While probabilistic approaches exist for surrogate-based decision making, risk-averse contexts that require formal robustness guarantees face a fundamental challenge: the nonconvex nature of ANN-embedded models hinders the employment of standard robust optimisation methods. To this end, in this work we explore the global robust optimisation of process design problems with embedded ANNs. A robust spatial branch-and-bound (RsBB) algorithm to achieve global optimality is proposed while enforcing constraint satisfaction across all uncertainty realisations.... [more]

The use of equipment digital twins of standardized, multi-purpose units can accelerate process development and reduce experimental effort. Experimental data are essential not only for identifying critical process parameters and enabling model-based methods within a Quality by Design framework, but also for constructing and validating the simulation models that describe digital twin behavior. To achieve high-fidelity and robust predictive models, structured concepts are required to manage metadata and process-, product-, and resource-specific information exchanged between physical and digital twins. Electronic lab notebooks (ELNs), which contextualize experimental data, must therefore be structured and standardized to ensure interoperability and seamless data exchange. For integration into digital twin workflows and process transfer between equipment instances of the same category, ELNs must comply with FAIR (Findable, Accessible, Interoperable, Reusable) data principles. This work prop... [more]

Dynamic simulation of distillation columns and chemical reactors remains essential for plant design, controllability analysis, and economic optimization. High-purity separations of close-boiling mixtures present significant computational challenges due to nonlinear thermodynamic behavior and stiff differential-algebraic equation (DAE) systems. This work presents a unified Python/JAX framework integrating four computational modules: (1) Peng-Robinson thermodynamics with complex-step differentiation, (2) nonlinear solvers (Newton, Broyden, Newton-Krylov) with automatic Curtis-Reid scaling, (3) DAE solver with Radau IIA collocation and intelligent auto-selection, and (4) constrained optimization using the Augmented Lagrangian Method with JAX automatic differentiation. The framework leverages JAX's just-in-time compilation (JIT), vectorization (vmap), and automatic differentiation (AD) to achieve near-compiled-language performance. Validation includes: nonlinear solver benchmarks with Newt... [more]

Fault diagnosis is essential for ensuring safety and efficiency in chemical process industries. Conventional diagnostic systems often generate raw numerical outputs that require extensive human interpretation, increasing the operator's workload and slowing decision-making during abnormal events. To overcome these limitations, this work introduces a model context protocol (MCP)-integrated fault diagnosis framework, where a Large Language Model (LLM) functions as the MCP client, coordinating multiple diagnostic tools through a unified protocol. Within the proposed framework, the LLM interacts with specialized diagnostic tools, including a convolutional neural network-based fault diagnosis model and an ensemble-based variant for uncertainty-aware analysis. The LLM synthesizes the outputs of these tools and generates operator-oriented natural-language reports that summarize diagnostic results and explicitly communicate uncertainty, thereby supporting more transparent and efficient decision... [more]

Large-scale mixed-integer programs (MIPs) typically cannot be solved by standard solvers with reasonable computational cost. MIP-heuristics decompose large-scale monolithic mixed-integer programs into polylithic programs such that they can be solved with reasonable computational cost at the price of loosing their optimality certificate. The decomposition is steered by hyperparameters that impact the solution quality and the computational cost diametrically. The proper selection of the hyperparameter values is a black-box optimization problem which is mostly solved by grid search or random search. In previous publications the authors proposed a novel hyperparameter optimization method based on Bayesian optimization and studied a use case from the PSE domain. Computational studies showed that the BO-based algorithm is superior for objective functions with few optimal solutions.This contribution generalizes the description of the MIP-Heuristic Optimization Problem (MIP-HOP) and the comput... [more]