We study a data reconciliation problem in a petrol refinery. The problem is to reconcile inventory and flow measurements to estimate true values of measured and unmeasured flows respecting the mass conservation. The problem is formulated as a mixed-integer quadratic program (MIQP). Upon successful problem resolution, a neural network (NN) is trained to mimic the MIQP solver to study potential improvements in CPU time without compromising the solution quality. The results show a significant improvement in refinery monitoring and feasibility of NN-based reconciliation.

Maintaining mother liquor supersaturation at a setpoint within the metastable range is vital for achieving the best production yield in industrial sugar production. However, precise online measurement and control is challenging. In this work, we develop a model-based soft sensor for supersaturation monitoring, and we propose a new feedforward-feedback control structure for batch sugar crystallization. Supersaturation is estimated using standard process measurements, enabling a soft sensor that can be readily adapted to different production units. The soft sensor continuously estimates supersaturation from standard process signals, and the control strategy ensures it remains within the desired operating range, enabling simple and straightforward application to other sugar production units.

We develop a multi-fidelity soft-sensing framework to reconcile online (low-fidelity) industrial measurements with sparse (high-fidelity) laboratory samples from an alkylation unit in a refinery. A first-principles model is used to generate an additional low-fidelity dataset and train a surrogate that predicts the output variable. We investigate whether incorporating sparse high-fidelity laboratory data with the low-fidelity data improves prediction accuracy. A multi-fidelity predictor forms a corrected output by learning the residual between the high-fidelity observations and the low-fidelity surrogate using Gaussian process regression. The simplest model structure performs best, reducing test prediction error (computed against laboratory samples) by 31.1% relative to the currently deployed industrial analyzer and outperforming a standard high-fidelity-only model trained on laboratory data. Overall, the simplified surrogate model captures the main industrial trends well enough to serv... [more]

The convergence of artificial intelligence (AI) and chemical process systems engineering is creating unprecedented opportunities to transform current refineries from conventionally operated plants into intelligent, automated, and resilient systems. However, the practical deployment of AI in these complex industrial environments faces several critical challenges. First, most existing process datasets contain minimal labeled data, making it difficult to apply supervised learning techniques that require extensive annotations to generate meaningful insights. Furthermore, refinery data typically consists of high-dimensional, multivariate time series, which pose additional complexities in capturing temporal dynamics and system interactions. Traditional Fault Detection and Diagnosis (FDD) frameworks often struggle to address these complexities, lacking adaptability to evolving process conditions, scalability to large plant networks, and explainability in their diagnostic reasoning. To address... [more]

In modern industrial systems, increasing performance requirements and sustainability constraints have intensified the need for advanced optimization methodologies capable of efficiently handling complex process models. The Simulated Moving Bed (SMB) process is a well-established technology for continuous chromatographic separations, offering high productivity and reduced solvent consumption compared to batch operations. However, its optimization is challenging due to the underlying distributed-parameter nature of the process.This work presents the development of a dynamic simulation and parameter optimization framework for the SMB process, implemented in Python using the open-source CasADi framework. The SMB model accounts for axial dispersion and mass transfer using a linear driving force formulation and is discretized in space using the method of lines, resulting in a state-space representation compatible with CasADi's numerical tools. Model accuracy was validated by reproducing a be... [more]

Reinforcement learning (RL) presents a promising alternative to model-based advanced control schemes, such as model predictive control (MPC), whose application can be limited by highly complex system models. However, incorporating constraints in RL remains challenging and formulating a suitable optimization objective is not straightforward. Reinforcement learning from human feedback (RLHF) offers an approach to derive the RL reward function from human expert preferences, enabling the incorporation of process knowledge. In this work, we present the application of RLHF to fine-tune an approximate MPC controller with suboptimal performance. We demonstrate that combining conventional reward formulations with RLHF, along with varying trajectory segment lengths for collecting human feedback, improves the control methodology for a batch bioreactor by enhancing safety and accounting for long-term effects. Furthermore, direct-preference based policy optimization (DPPO) represents a promising al... [more]

Early and reliable prediction of convergence to cyclic steady state (CSS) is increasingly important in periodic downstream bioprocessing, where switching and cut decisions are tuned for a repeatable cyclic regime. This work addresses time-to-CSS (TCSS) forecasting and CSS-existence classification for multicolumn countercurrent solvent gradient purification (MCSGP) systems under run-to-run feed variability. We propose a Multi-Feature k-Nearest Neighbours (MF-kNN) framework that performs long-horizon one-shot trajectory forecasting from an early run segment. CSS outcomes are inferred by reapplying a peak-based convergence rule to the predicted trajectory, while CSS existence is predicted via neighbour-label voting. The approach uses multivariate, standardised features, run-level splits, and a windowed neighbour search to reduce computation. Hyperparameters are tuned with a CSS-oriented objective function that balances trajectory fidelity, TCSS error, and misclassification penalties. On a... [more]

The extensive use of renewable energy to supply hydrogen production for chemical processes is hindered by the uncertainty in power generation and by strict operational limits.These challenges are addressed through a real-time dynamic optimization approach based on a receding-horizon strategy that provides optimal decision variables. The framework explicitly relies on imperfect weather forecasts and dynamically adapts the hydrogen reference production to guarantee the final productivity target. The optimization methodology focuses on minimizing grid electricity imports, limiting excessive equipment stress, and preventing constraint violations, while ensuring that the hydrogen production target is satisfied.The proposed approach yields competitive economic and environmental performance, with a levelized cost of hydrogen of 3.31 USD/kgH2, well within literature values (1.50-7.50 USD/kgH2) and below typical industrial costs (4-12 USD/kgH2). At the same time, carbon dioxide emissions are re... [more]

The Dividing Wall Column (DWC) offers significant potential in saving both energy- and capital cost compared to conventional distillation sequences. However, there are some issues regarding flexibility and control that require attention in reducing the risks or uncertainties in achieving the potential benefits in practical operation. This calls for control and optimization methods that rely on the available measurement data and less on simulation models. The "Perturb and Observe" method is a simple algorithm that seems suitable for this on-line optimisation task. A series of experiments have been carried out at the Kaibel-column pilot at NTNU and some key results are presented. The method is combined with a conventional control structure at the regulatory layer.

A safety-intelligent framework is presented for developing a multiple-input multiple-output (MIMO) risk-based explicit model predictive control (R-eMPC) for metal hydride storage systems (MHSS). These systems are susceptible to thermal runaway during the charging process as a result of the exothermic adsorption reaction within the metal alloy. To address this issue, deterministic and stochastic safety-intelligent control algorithms are designed and implemented by explicitly embedding a dynamic risk index (RI) or risk tolerance (() into the control law and decision-making. In closed-loop analysis, the deterministic R-eMPC regulates both core temperature and hydrogen storage capacity by forecasting fault occurrence, triggering alarms, and reducing the risk index by adjusting the optimal control actions, supply pressure and water flowrate. Meanwhile, the stochastic R-eMPC accounts for uncertainties in core temperature variation by incorporating risk tolerance through chance-constraints. W... [more]

This work demonstrates the application of a pulsed microwave system for single-step co-production of ethylene and ammonia from methane. To mitigate inherent production fluctuations from pulsed microwave reactors, a staggered manifold configuration was utilized to stabilize effluent flow for industrial-scale compatibility. Dynamic validation of the ammonia and ethylene purification columns confirmed that a rigorously tuned control strategy effectively rejects ±10% feed disturbances while maintaining process stability and product purity. Ultimately, this systematic approach establishes a robust foundation for the sustainable, electrified production of foundational chemicals by bridging the gap between laboratory-scale pulsing phenomena and industrial-scale operational reliability.

Centralized monitoring methods experience reduced fault detection sensitivity in large-scale industrial systems due to the masking effect arising from the aggregation of many interconnected variables. Decentralized monitoring, where variables are grouped into subsystems, has been shown to effectively address these limitations. However, the performance of this class of methods critically depends on how the network is partitioned, and the role of its structural factors on fault detection remains poorly understood. This work studies how network topology and causal structure affect decentralized monitoring in high-dimensional systems. Using SimCaNet, a DAG-based data simulator, where large-scale systems with 100-1000 variables were generated, we rigorously compared the performance of centralized and decentralized causal log-likelihood monitoring methods under process perturbations and sensor bias faults. Network partitioning is performed using the Leiden community detection algorithm and c... [more]

For the long-cycle process industry, operational cycles can be severely affected by equipment aging, catalyst deactivation, and safety limitations. As illustrated by the residue hydrotreating process, metal impurities gradually deposit on the catalyst during residue purification, leading to catalyst poisoning and eventual process shutdown. Such long-cycle processes require dynamic adjustments of operating conditions to balance immediate economics with long-term sustainability. While current practice relies on empirical tuning based on historical data, this work focuses on studying how to obtain an optimal operating trajectory to guide the monthly adjustments of operating variables. The long-cycle simulation of the residue hydrotreating process can be performed using the commercial software, PetroSIM. After adjusting the feed conditions, its embedded mechanistic model can calculate the deviation of average bed temperature from the set point and output the remaining operating time. Since... [more]

This study investigates control strategies for the flexible operation of heat pump-assisted distillation processes, focusing on the heat integrated distillation column configuration. The methanol/water separation system was selected as a case study and modelled to achieve 99.9 wt% AA-grade methanol purity. A limiting piece of equipment for flexible operation of heat pump assisted distillation is the compressor. To assess its impact on flexible operation, dynamic simulations in Aspen Dynamics were conducted for two heat integrated distillation column control strategies: one using fixed compressor duty and one using variable compressor duty. The control performance for a 20% throughput disturbance, as well as for a 50% turndown ratio scenario was investigated. Results show that fixed-duty operation maintains robust stability and rapid disturbance recovery even at 50% turndown, while variable-duty operation delivers higher efficiency for moderate load changes but cannot sustain low-load s... [more]

Brazil is the world's largest producer of orange juice, generating significant peel residues that are currently underutilized. This study proposes a mixed-integer linear programming (MILP) framework for optimal supply chain design, utilizing Special Ordered Sets of type 2 (SOS2) to accurately represent non-linear investment costs. The model maximizes Net Present Value (NPV) by integrating production costs with multi-echelon logistics, including inland transport, port handling, and international maritime freight. Applied to a case study in São Paulo, the framework evaluates pathways for the co-production of D-limonene, pectin, and bioenergy. Results indicate a positive NPV of BRL 1.27 billion, with pectin contributing over 65% of total revenue. The optimization favors centralized configurations in Araraquara or Matão to exploit economies of scale while minimizing the transport of high-volume, wet biomass. Notably, total transportation costs represent only 1.13% of expenditures, as the h... [more]

Production scheduling in the process industry is often treated as a static optimization problem, although real plants require frequent rescheduling due to disturbances such as rush orders, equipment breakdowns, and changes in processing times. This paper compares a simulation-optimization approach that couples a discrete-event simulator with an evolutionary algorithm (EA) with a sequence-based mixed-integer linear programming (MILP) formulation for real-time scheduling of multistage batch systems. Both methods are embedded in an event-driven rolling-horizon framework under strict computation time limits.In static experiments for a 3-stage, 2-machine flow-shop setting (10 products, 20 orders, random processing times), the EA achieved lower makespans across all tested time budgets, improving results by about 7-13% on average compared to the MILP approach. In real-time experiments (40 initial orders, maintenance, three rush orders, 10 s and 60 s periodic updates), the solution quality of... [more]

The Heterogeneous Capacitated Vehicle Routing Problem (HCVRP) is a fundamental extension of the classical Vehicle Routing Problem in which customer demands must be satisfied using a fleet of vehicles with varying capacities and costs. In this paper, a novel and intuitive decomposition-based formulation for HCVRP is presented that decomposes the problem into two tractable subproblems: (i) a route generation and an optimal customer sequencing problem and (ii) a vehicle route assignment problem. In the first stage, all feasible customer combinations are constructed as routes, and for each route an optimization problem is solved to identify the optimal customer sequence that results in the minimum distance travelled. In the second stage, the optimal routes are selected, and vehicles are assigned using a mixed integer linear programming (MILP) formulation that minimizes the fixed cost of vehicle utilisation and total transportation costs, ensuring demand satisfaction for all customers while... [more]

Critical metals are essential for clean energy technologies but, due to being mainly sourced through mining, the critical metal supply chain is susceptible to geopolitical risks. Electronic waste (e-waste), however, can serve as an alternative "urban mine", but the recovery at high purities requires complex and resource-intensive processing. This work explores the modeling and optimization-based design for the intensification of liquid-liquid extraction in small channels as a means to recover critical metals from e-waste. Small channels can achieve high mass transfer rates while mitigating the environmental impact. A superstructure-based approach is employed to represent the alternative system configurations, while a plant propagation algorithm is used to optimize the multi-objective problem to recover Neodymium (Nd) and Samarium (Sm). The multi-objective problem aimed to tackle product quality, process economics, and environmental impact. The results demonstrated that optimally design... [more]

Pyrolysis, a key waste-to-X technology, enables converting a wide portfolio of biomass waste into valuable chemicals and fuels. However, raw pyrolysis oils are chemically and physically unstable. A multi-step stabilisation is necessary to reduce acidity and the content of reactive components, mainly carbonyls and carboxylic acids. During stabilisation, which involves deoxygenation and hydrogenation as the main steps, an aqueous phase is generated as a by-product. This stream contains mainly water, but relevant amounts of methanol and ethanol (2-8 wt%) are also present, together with minor concentrations of higher alcohols, C1-C4 carboxylic acids, and light esters. The aim of this work is to design and optimise a process to isolate the methanol and ethanol embodied in the aqueous phase and exploit them as intermediates to generate biofuels, biochemicals, and pharmaceutical products. The process consists of a train of four distillation columns to maximise the recovery rate and purity of... [more]

This work proposes a two-stage optimization framework for the optimal utilization of biogas from pig manure, integrating process-level design with short-term operational planning under dynamic electricity tariff schemes in Mexico. In the first stage, a multi-objective optimization based on 3E (Exergy, Environment, and Energy) analysis was performed. The results demonstrate that increasing the biogas split fraction for upgrading significantly reduces the environmental and exergy indices, enhancing thermodynamic and environmental performance without compromising the energy index. High upgrading flows (split > 0.7) emerged as the most favorable compromise across the evaluated metrics. In the second stage, support vector regression (SVR) surrogate models were developed to approximate nonlinear relationships between the operational split and process outputs. These surrogates were embedded in a Mixed-Integer Linear Programming (MILP) formulation to optimize weekly scheduling under the Mexica... [more]

Self-driving laboratories (SDLs) increasingly use Bayesian optimisation (BO) to navigate expensive design spaces, yet high-fidelity simulations and experiments remain too costly to query at scale. Multi-fidelity Bayesian optimisation (MFBO) alleviates this by combining abundant low-fidelity evaluations with scarce high-fidelity observations. However, Gaussian process (GP) surrogates can become computational bottlenecks as data volume and dimensionality increase, motivating scalable alternatives. Here, we assess transfer learning based deep neural network (DNN) surrogates that pretrain on low-fidelity data and fine-tune on high-fidelity observations. We construct a chemical process benchmark for glacial acetic acid separation and purification with paired low- and high-fidelity flowsheets. The optimisation considers eight decision variables and minimises the minimum selling price (MSP), while enforcing a product purity threshold via a quadratic penalty. To reflect realistic resource cons... [more]

Water supply in the countryside of São Paulo state, Brazil, is based on groundwater resources that can be contaminated with substances such as heavy metals or fluoride, requiring the usage of water treatment technologies such as Reverse Osmosis (RO); however, RO systems create a stream of high-salinity brine, with negative environmental consequences. Besides, regulatory constraints demand that well operations must be interrupted for a daily contiguous period. In this work, a Mixed-Integer Linear program (MILP) was implemented to define water network topologies and well exploitation schedules, under these downtime constraints, aiming the minimization of RO plant capacity (and, therefore, of brine discharges). This model was then applied to the water supply of a small city in the São Paulo countryside, with around 8000 inhabitants, where high fluoride concentrations warranted the implementation of an RO system. Demand variations between weekdays and weekends (with demands 52.7% higher) w... [more]

Membranes provide an efficient method for treating flue gases to capture CO2 from various point sources, achieving high recovery and purity rates. However, the lack of systematic process-level design tools has limited the translation of advanced membrane materials into large-scale technical and economic metrics. Thus, in this study, we present a superstructure model for the design of membrane-based carbon capture, both from highly energy-intensive industries and from power plants. The superstructure model enables the flexible design and global optimization of multi-stage membrane systems. Multiple membranes are compared under technical performance indicators (specific energy and specific area), while the already commercialized polymeric membranes Polaris and PolyActive are taken into consideration for estimating their economic performance. The presented framework establishes a robust link between material innovation and optimal process design, providing a key tool for the large-scale d... [more]

This work presents an integrated geospatial-technoeconomic optimization framework for siting modular blue and green hydrogen production units co-located with hydrogen refueling stations (HRS) along U.S highways, with a case study focused on New England. The workflow identifies geospatial highway networks and natural gas infrastructure intersections, estimates hydrogen demand based on heavy-duty truck flows from U.S. Freight Analysis Framework, and formulates a mixed-integer linear program (MILP) that selects technology candidates and their capacities to minimize total cost, subject to corridor coverage and supply-demand constraints. Two onsite hydrogen production scenarios are evaluated: a green hydrogen-only production case and a mixed configuration combining modular green and blue hydrogen. Results indicate that, under a 5% hydrogen adoption scenario in truck traffic, 29 HRS with onsite hydrogen production are needed in the New England region. These findings highlight the benefits of... [more]

This study presents a techno-economic modeling framework integrating a modular blue H2N2 production unit with a hydrogen refueling station (HRS) across capacities ranging from 0.1 to 4.0 tpd. A model-based approach is used to size key process and refueling components and to estimate the resulting hydrogen retail cost. The analysis indicates that hydrogen retail costs range from 4.6 to 10.8 USD kgH2-1 over the considered capacity range. Relative to alternative on-site hydrogen production pathways, the proposed system demonstrates better cost-effectiveness while meeting clean hydrogen production standards. The approach is particularly suitable for regions with established natural gas infrastructure, as it leverages existing supply chains. Overall, the results provide actionable insights for policymakers and industry stakeholders in planning future hydrogen refueling infrastructure.