arXiv subjects

Maria M. Papathanasiou

Publications and source records attributed to Maria M. Papathanasiou.

5 recordsLinked to original sources

arXiv2026

Reduced-Space Multi-Fidelity Bayesian Optimization of Process Simulation Models

Optimizing industrial process flowsheets is often computationally prohibitive due to the high cost of rigorous simulations and the curse of dimensionality inherent in complex design spaces. To address these challenges, we present a reduced-space multi-fidelity Bayesian optimization (RS-MFBO) framework designed for high-dimensional, expensive black-box functions. The approach integrates Global Sensitivity Analysis (GSA) for dimensionality reduction with a fidelity-augmented Gaussian process that captures correlations between low-cost approximations and expensive high-fidelity evaluations. A cost-aware acquisition strategy, augmented with cooldown and promotion mechanisms, adaptively guides the allocation of samples across fidelities. The framework is validated on two distinct industrial process simulators: a plasmid DNA bioprocess in SuperPro Designer and a green fuel synthesis plant in Aspen HYSYS. Results across diverse economic and physical objectives demonstrate that the proposed method substantially reduces the number of high-fidelity simulator evaluations while maintaining competitive optimization performance compared to single-fidelity baselines. These results highlight RS-MFBO as a scalable, simulator-agnostic approach for cost-constrained black-box optimization.

cs.LG↗

arXiv2026

Accelerating Simulation and Optimisation of Cyclic Adsorption Processes with Differentiable Programming

The design of cyclic adsorption processes is computationally demanding, requiring repeated convergence to cyclic steady state within an iterative optimisation loop. Conventional workflows treat the process simulator as a black box and rely on derivative-free optimisation, resulting in design campaigns that can require hundreds to thousands of CPU hours. This work presents an end-to-end differentiable model of a pressure vacuum swing adsorption process, developed using the JAX differentiable programming framework and applied here to a benchmark post-combustion carbon capture problem. Automatic differentiation provides exact gradients throughout the entire computational workflow. The differentiation of a single process cycle provides the Jacobian for a Newton iteration to decrease both the number of iterations and the simulation time required to reach cyclic steady state by a factor of 20 relative to a representative MATLAB implementation. Exact gradients of the performance metrics with respect to the design variables further enable gradient-based multi-objective optimisation using the IPOPT algorithm. Applied to a six-variable design problem, the latter produces a superior Pareto front with improved coverage of the trade-off space and closer convergence to the optimal front than the genetic algorithm NSGA-II. Notably, the full front is obtained over two orders of magnitude faster than the conventional approach. By retaining the full mechanistic model while making it differentiable, this framework transforms cyclic adsorption process design from slow black-box simulation with derivative-free optimisation to efficient gradient-enhanced modelling and optimisation, enabling rapid and systematic exploration of complex design spaces.

cs.CE↗

arXiv2024

Deep learning enhanced mixed integer optimization: Learning to reduce model dimensionality

This work introduces a framework to address the computational complexity inherent in Mixed-Integer Programming (MIP) models by harnessing the potential of deep learning. By employing deep learning, we construct problem-specific heuristics that identify and exploit common structures across MIP instances. We train deep learning models to estimate complicating binary variables for target MIP problem instances. The resulting reduced MIP models are solved using standard off-the-shelf solvers. We present an algorithm for generating synthetic data enhancing the robustness and generalizability of our models across diverse MIP instances. We compare the effectiveness of (a) feed-forward neural networks (ANN) and (b) convolutional neural networks (CNN). To enhance the framework's performance, we employ Bayesian optimization for hyperparameter tuning, aiming to maximize the occurrence of global optimum solutions. We apply this framework to a flow-based facility location allocation MIP formulation that describes long-term investment planning and medium-term tactical scheduling in a personalized medicine supply chain.

math.OC↗

arXiv2023

A model-based approach towards accelerated process development: A case study on chromatography

Process development is typically associated with lengthy wet-lab experiments for the identification of good candidate setups and operating conditions. In this paper, we present the key features of a model-based approach for the identification and assessment of process design space (DSp), integrating the analysis of process performance and flexibility. The presented approach comprises three main steps: (1) model development & problem formulation, (2) DSp identification, and (3) DSp analysis. We demonstrate how such an approach can be used for the identification of acceptable operating spaces that enable the assessment of different operating points and quantification of process flexibility. The above steps are demonstrated on Protein A chromatographic purification of antibody-based therapeutics used in biopharmaceutical manufacturing.

cs.CE↗

arXiv2023

Operability-economics trade-offs in adsorption-based CO$_2$ capture process

Low-carbon dispatchable power underpins a sustainable energy system, providing load balancing complementing wide-scale deployment of intermittent renewable power. In this new context, fossil fuel-fired power plants must be coupled with a post-combustion carbon capture (PCC) process capable of highly transient operation. To tackle design and operational challenges simultaneously, we have developed a computational framework that integrates process design with techno-economic assessment. The backbone of this is a high-fidelity PCC mathematical model of a pressure-vacuum swing adsorption process. We demonstrate that the cost-optimal design has limited process flexibility, challenging reactiveness to disturbances, such as those in the flue gas feed conditions. The results illustrate that flexibility can be introduced by relaxing the CO$_2$ recovery constraint on the operation, albeit at the expense of the capture efficiency of the process. We discover that adsorption-based processes can accommodate for significant flexibility and improved performance with respect to the operational constraints on CO$_2$ recovery and purity. The results herein demonstrate a trade-off between process economics and process operability, which must be effectively rationalised to integrate CO$_2$ capture units in the design of low-carbon energy systems.

eess.SY↗