arXiv subjects

Klaus Hellgardt

Publications and source records attributed to Klaus Hellgardt.

6 recordsLinked to original sources

arXiv2026

An LLM-Driven Workflow for Automated Process Control Strategy Generation and Tuning from Dynamic Process Models

We present a structured large-language-model-driven workflow for automated multi-variable control design from dynamic process models. The workflow decomposes the design task into constrained code-generation steps: plant-interface construction, normalization, manipulated-variable controlled-variable (MV-CV) pairing, controller specification, closed loop simulation, scenario generation, performance evaluation and Bayesian-optimization (BO) based tuning. Generated artifacts are executed and validated before downstream tasks proceed, and failed artifacts are repaired using validation feedback. The proposed approach is demonstrated on a nonlinear gas-preheater benchmark with coupled pressure and temperature dynamics. The generated workflow produces a physically consistent decentralized PI (proportional-integral) feedback-feedforward control structure and an executable tuning environment. Bayesian optimization reduces the closed loop performance objective, which aggregates set-point tracking and disturbance-rejection errors for the controlled variables, by approximately 26.5% relative to the initial controller generated by the workflow, mainly through improved pressure-loop transient performance. This figure quantifies the automated tuning stage rather than a comparison against a manually designed controller. The results demonstrate the feasibility of using structured large-language-model-based code generation to construct executable control-design workflows, while also highlighting the need for broader validation on larger plantwide-control benchmarks.

cs.AI↗

arXiv2025

CarAT: Carbon Atom Tracing across Industrial Chemical Value Chains via Chemistry Language Models

The chemical industry is increasingly prioritising sustainability, with a focus on reducing carbon footprints to achieve net zero. By 2026, the Together for Sustainability (TfS) consortium will require reporting of biogenic carbon content (BCC) in chemical products, posing a challenge as BCC depends on feedstocks, value chain configuration, and process-specific variables. While carbon-14 isotope analysis can measure BCC, it is impractical for continuous industrial monitoring. This work presents CarAT (Carbon Atom Tracker), an automated methodology for calculating BCC across industrial value chains, enabling dynamic and accurate sustainability reporting. The approach leverages existing Enterprise Resource Planning data in three stages: (1) preparing value chain data, (2) performing atom mapping in chemical reactions using chemistry language models, and (3) applying a linear program to calculate BCC given known inlet compositions. The methodology is validated on a 27-node industrial toluene diisocyanate value chain. Three scenarios are analysed: a base case with fossil feedstocks, a case incorporating a renewable feedstock, and a butanediol value chain with a recycle stream. Results are visualised with Sankey diagrams showing the flow of carbon attributes across the value chain. The key contribution is a scalable, automated method for real-time BCC calculation under changing industrial conditions. CarAT supports compliance with upcoming reporting mandates and advances carbon neutrality goals by enabling systematic fossil-to-biogenic substitution. Through transparent, auditable tracking of carbon sources in production networks, it empowers data-driven decisions to accelerate the transition to sustainable manufacturing.

cs.CE↗

arXiv2025

Constraint-Guided Symbolic Regression for Data-Efficient Kinetic Model Discovery

The industrialization of catalytic processes hinges on the availability of reliable kinetic models for design, optimization, and control. Traditional mechanistic models demand extensive domain expertise, while many data-driven approaches often lack interpretability and fail to enforce physical consistency. To overcome these limitations, we propose the Physics-Informed Automated Discovery of Kinetics (PI-ADoK) framework. By integrating physical constraints directly into a symbolic regression approach, PI-ADoK narrows the search space and substantially reduces the number of experiments required for model convergence. Additionally, the framework incorporates a robust uncertainty quantification strategy via the Metropolis-Hastings algorithm, which propagates parameter uncertainty to yield credible prediction intervals. Benchmarking our method against conventional approaches across several catalytic case studies demonstrates that PI-ADoK not only enhances model fidelity but also lowers the experimental burden, highlighting its potential for efficient and reliable kinetic model discovery in chemical reaction engineering.

cs.CE↗

arXiv2025

Simplest Mechanism Builder Algorithm (SiMBA): An Automated Microkinetic Model Discovery Tool

Microkinetic models are key for evaluating industrial processes' efficiency and chemicals' environmental impact. Manual construction of these models is difficult and time-consuming, prompting a shift to automated methods. This study introduces SiMBA (Simplest Mechanism Builder Algorithm), a novel approach for generating microkinetic models from kinetic data. SiMBA operates through four phases: mechanism generation, mechanism translation, parameter estimation, and model comparison. Our approach systematically proposes reaction mechanisms, using matrix representations and a parallelized backtracking algorithm to manage complexity. These mechanisms are then translated into microkinetic models represented by ordinary differential equations, and optimized to fit available data. Models are compared using information criteria to balance accuracy and complexity, iterating until convergence to an optimal model is reached. Case studies on an aldol condensation reaction, and the dehydration of fructose demonstrate SiMBA's effectiveness in distilling complex kinetic behaviors into simple yet accurate models. While SiMBA predicts intermediates correctly for all case studies, it does not chemically identify intermediates, requiring expert input for complex systems. Despite this, SiMBA significantly enhances mechanistic exploration, offering a robust initial mechanism that accelerates the development and modeling of chemical processes.

cs.CE↗

arXiv2023

The Automated Discovery of Kinetic Rate Models -- Methodological Frameworks

The industrialization of catalytic processes requires reliable kinetic models for their design, optimization and control. Mechanistic models require significant domain knowledge, while data-driven and hybrid models lack interpretability. Automated knowledge discovery methods, such as ALAMO (Automated Learning of Algebraic Models for Optimization), SINDy (Sparse Identification of Nonlinear Dynamics), and genetic programming, have gained popularity but suffer from limitations such as needing model structure assumptions, exhibiting poor scalability, and displaying sensitivity to noise. To overcome these challenges, we propose two methodological frameworks, ADoK-S and ADoK-W (Automated Discovery of Kinetic rate models using a Strong/Weak formulation of symbolic regression), for the automated generation of catalytic kinetic models using a robust criterion for model selection. We leverage genetic programming for model generation and a sequential optimization routine for model refinement. The frameworks are tested against three case studies of increasing complexity, demonstrating their ability to retrieve the underlying kinetic rate model with limited noisy data from the catalytic systems, showcasing their potential for chemical reaction engineering applications.

cs.SC↗

arXiv2021

Enhancing microalgal cell wall permeability by microbubble streaming flow

We demonstrate that the permeability of the cell wall of microalga $\textit{C. reinhardtii}$ can be enhanced in controlled microstreaming flow conditions using single bubbles adherent to a wall and driven by ultrasound near their resonance frequency. We find that microstreaming flow is effective at acoustic pressures as low as tens of kPa, at least one order of magnitude lower than those used in bulk ultrasonication. We quantify the increase in number of fluorescent cells for different acoustic pressure amplitudes and ultrasound exposure times. We interpret the increase in dye uptake after microstreaming flow as an indication of enhanced permeability of the cell wall. We perform microscopic visualizations to verify the occurrence of non-spherical shape oscillations of the bubbles, and to identify the optimal conditions for dye uptake. In our experimental conditions, with acoustic pressures in the range 20-40 kPa and frequencies in the range 25-70 kHz, we obtained spherical oscillations of bare microbubbles and non-spherical shape oscillations in microbubbles with algae attached to their surface. Only the latter were able to generate a non-linear microstreaming flow with sufficiently large viscous stresses to induce algae permeabilization. The results demonstrate that controlled microbubble streaming flow can enhance cell wall permeability in energy-efficient conditions.

q-bio.QM↗