A reinforcement learning framework is developed for the synthesis of distillation trains. The rigorous Naphtali-Sandholm algorithm for equilibrium separation modeling was implemented in JAX and coupled with the benchmarking Jumanji RL library. The vanilla actor-critic agent was successfully trained to build distillation trains for a seven-component hydrocarbon mixture. A transformer encoder structure was used to apply self-attention over the agent’s observation. The agent was trained on minimal data representation containing quantitative component flows and relative volatility parameters between present components. Training sessions involving 5·104 episodes (3·105 column designs) were typically run in under 60 minutes. While training was fast and reliable with appropriate tuning of the hyperparameters, further improvements are needed in the generalizability performance for similar separation problems.

This paper introduces a prototype for constructing an edge AI system utilizing the contemporary Machine Learning Operations (MLOps) concept. By employing microcontrollers such as the Raspberry Pi as hardware, our methodology includes data scrubbing and machine learning model deployment on edge devices. Crucially, the MLOps pipeline is fully developed within the ecoKI platform, a research platform for ML/AI applications. In this study, we thoroughly investigate the performance of our ecoKI platform by comparing it with the established Edge Impulse platform. We deployed the ML model with different weight quantization methods, such as FP32 and INT8, to compare accuracy variations and inference speed between these two platforms and quantization strategies on edge devices. In our experiments, we identified that the average accuracy performance of the ecoKI platform is 3.61% better than the edge impulse. Moreover, real-time AI processing on edge devices enables microcontrollers, even those w... [more]

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]

Compartmental models are widely used to simplify the analysis of complex fluid dynamics systems, yet subjective compartment definitions and computational constraints often limit their applicability. The CompArt algorithm introduces an AI-driven framework that automates compartmentalization in Computational Fluid Dynamics (CFD) simulations, optimizing both accuracy and efficiency. By leveraging unsupervised clustering techniques such as Agglomerative Clustering, CompArt identifies coherent flow regions based on velocity and turbulent kinetic energy dissipation rate, ensuring a data-driven, physically consistent segmentation. The methodology integrates a connectivity-based clustering strategy, where compartments are dynamically optimized using the Silhouette score and adjacency matrix. This approach enables the reduction of high-resolution 3D CFD simulations into a network of interconnected sub-systems, significantly lowering computational costs while preserving system heterogeneity. The... [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]

Maintenance is critical for industrial plants to ensure operational reliability and worker safety. In process industries, fouling, the accumulation of solid residues in equipment, poses a significant challenge, causing inefficiencies and productivity losses. Effective modeling of fouling evolution over time is essential for maintenance planning to prevent equipment from operating under suboptimal conditions. Traditional approaches to fouling prediction include equation-based models, which offer high precision but may struggle with continuously changing process boundaries, and machine learning techniques, which are more adaptable but less effective at capturing rapidly evolving trends driven by complex underlying physics. This study introduces an innovative hybrid machine learning approach for predictive maintenance, combining the strengths of both methods. Pressure differential is modeled using an equation-based approach that links pressure data with fouling thickness, while the foulin... [more]

Process engineers in the Chemical and Oil & Gas industries extensively use process simulation for the design, development, analysis, and optimization of complex systems. This study investigates the integration of Artificial Intelligence (AI) with AVEVATM Process Simulation (APS), a next-generation commercial simulation tool. We propose a framework for a custom chatbot application designed to assist engineers in developing and troubleshooting simulations. This chatbot application utilizes a custom-trained model to transform engineer prompts into standardized queries, facilitating access to essential information from APS. The chatbot extracts critical data regarding solvers and thermodynamic models directly from APS to help engineers develop and troubleshoot process simulations. Furthermore, we compare the performance of our custom model against OpenAI technology. Our findings indicate that this integration significantly enhances the usability of process simulation tools, promoting more... [more]

Accurate mechanistic models provide valuable physical insight and are crucial for efficient process scale-up and optimisation, but their identification requires lengthy experimental data collection, model construction, validation and discrimination. Traditional black-box machine learning transfer methods leverage prior knowledge but lack interpretability and physical insights. To address this, we propose a novel approach using artificial neural network feature attribution to automatically locate corrections and symbolic regression to make structural modifications to an inaccurate or low-fidelity mechanistic model. In a comprehensive in-silico case study, the framework adapted a kinetic model from one biochemical system to a different but related one, enhancing predictive accuracy. Integrated within an iterative model-based design of experiments routine, it minimised the number of new experiments required. The study also discusses the impact of the inductive bias trade-off and alternati... [more]

Fault diagnosis is critical for ensuring the safety and efficiency of chemical processes, as undetected faults can lead to catastrophic consequences. While deep learning-based methods have shown promise in this field, they often require manual hyperparameter tuning, which is not efficient since they heavily rely on expert knowledge and need iterative trial-and-error. This work introduces a novel approach combining a Multiscale Convolutional Neural Network (MSCNN) with Tree-Structured Parzen Estimator (TPE) for automated hyperparameter optimization to enhance the performance of fault diagnosis for chemical processes. The Multi-Scale Module is to capture complex nonlinear features from the fault data, while the TPE efficiently searches for optimal hyperparameters for MSCNN. An experimental study was carried out on the Tennessee Eastman Process (TE Process) dataset, where the proposed method was benchmarked against state-of-the-art models. The results indicate that the MSCNN-TPE method de... [more]

Chemical process models often involve high non-linearity due to thermodynamic and kinetic relationships, with non-convex bilinear terms adding complexity to process optimization. Recently, data-driven models, particularly artificial neural networks (ANNs), have gained traction for representing chemical processing units. The predictive accuracy of ANNs depends on data quality, variable interactions, and network architecture, the latter being an optimization challenge itself. This study proposes and evaluates two strategies to optimize ANN architecture for modeling a propylene glycol production process from glycerol. The process includes a reactor and two distillation columns, with training data generated through simulation in Aspen Plus by varying design and operating variables. Two approaches are compared: random ANN structure generation and architecture optimization using the ant colony algorithm, a method suitable for discrete problems. Decision variables include the number of hidden... [more]

This paper presents a novel fault detection method based on key variable forecasting models. The approach integrates future forecasts of key variables into a time window, allowing for early fault detection without modifying the offline training phase of the existing fault detection model. By incorporating predicted data into the detection process, the proposed method significantly improves fault detection rates and reduces detection delays. Experiments using the Continuous Stirred Tank Heater (CSTH) system demonstrate the superiority of our method over traditional approaches, showing the advantages of forecasting in enhancing detection performance. However, our results also highlight the dependency of the method's effectiveness on the quality of the forecasting model, suggesting the need for more advanced time-series forecasting techniques. Additionally, the current point forecasting method may not be sufficient in real-world applications, where probabilistic modeling of key variables... [more]

Batch chemical processes face significant challenges due to frequent operational shifts and varying conditions, requiring models to be retrained for each new scenario. This high retraining demand limits the scalability of traditional process monitoring systems, making them unsuitable for dynamic batch operations. To address this, we propose a transfer learning-based framework that enhances adaptability by reusing learned features across different batch conditions, reducing the need for extensive retraining. Proposed method integrates Temporal Convolutional Networks (TCNs) for capturing temporal dependencies in batch data and predicting Quality-Indicative Variables (QIVs) to identify deviations. The core innovation lies in transfer learning, enabling the model to adapt to new process variations with minimal updates. This approach ensures robust, accurate monitoring even under evolving conditions. This framework is validated using the IndPenSim penicillin fermentation dataset, which simu... [more]

Solvent selection is a critical decision-making process that balances economic, environmental, and societal factors. The vast chemical space makes evaluating all potential solvents impractical, necessitating pre-selection strategies to identify promising candidates. Predictive thermodynamic models, such as the UNIFAC model, are commonly used for this purpose. Recent advancements in deep learning have led to models like the Gibbs-Helmholtz Graph Neural Network (GH-GNN), which overall offers higher accuracy in predicting infinite dilution activity coefficients over a broader chemical space than UNIFAC. This study presents a systematic comparison of solvent pre-selection using GH-GNN and UNIFAC-IL in the context of liquid-liquid extraction. The original GH-GNN model is extended to simultaneously predict organic and ionic systems. This extended GH-GNN model predicts more than 92 % of the logarithmic IDACs with an absolute error of less than 0.3. By comparison, UNIFAC-based models only achi... [more]

Recently, the focus on increasing process efficiency to reduce energy consumption has driven the adoption of alternative systems, such as Petlyuk distillation columns. It has been proven that, when compared to conventional distillation columns, these systems offer significant energy and cost savings. From an economic standpoint, achieving high-purity products alone does not ensure the feasibility of a process. Instead, balancing the trade-off between product purity and cost necessitates multi-objective optimization. While conventional optimization methods are effective, novel strategies like Bayesian optimization offer distinct advantages for handling complex systems. Bayesian optimization requires no explicit mathematical model and can efficiently optimize even when starting from a single initial point. However, as a black-box method, it demands a detailed analysis of hyperparameters, such as the acquisition function and the number of initial points, to ensure optimal performance. Thi... [more]

An essential problem in precision agriculture is to accurately model and predict root-zone (top 1 m of soil) soil moisture profile given soil properties and precipitation and evapotranspiration information. This is typically achieved by solving agro-hydrological models. Nowadays, most of these models are based on the standard Richards equation (RE), a highly nonlinear, degenerate elliptic-parabolic partial differential equation that describes irrigation, precipitation, evapotranspiration, runoff, and drainage through soils. Recently, the standard RE has been generalized to time-fractional RE with any fractional order between 0 and 2. Such generalization allows the characterization of anomalous soil exhibiting non-Boltzmann behavior due to the presence of preferential flow. In this work, we focus on inverse modeling of time-fractional RE; that is, how to accurately estimate the fractional order and soil property parameters of the fractional RE given soil moisture content measurements. S... [more]

Process monitoring is essential in industrial settings to ensure system functionality, necessitating the identification and understanding of fault causes. While a substantial body of research focuses on fault detection, fault diagnosis has received significantly less attention. Typically, faults originate either from abnormal instrument behavior, indicating the need for calibration or replacement, or from process faults, signaling a malfunction within the system. A primary objective of this study is to apply the proposed fault diagnosis methodology to a benchmark that closely mirrors real-world conditions. Specifically, we introduce a fault diagnosis framework for a wastewater treatment plant (WWTP) that effectively addresses the challenges posed by imbalanced big data commonly encountered in large-scale systems. In our study, four distinct fault scenarios were investigated: fault-free conditions, process faults only, sensor faults only, and simultaneous sensor and process faults. To e... [more]

Contains 423 original peer-reviewed research articles presented at the 35th European Symposium on Computer Aided Process Engineering (ESCAPE 35). Subject categories include Modelling and Simulation, Sustainable Product Development and Process Design, Large Scale Design and Planning/Scheduling, Model Based Optimisation and Advanced Control, Concepts, Methods and Tools, Digitalization and AI, CAPEing with Societal Challenges, CAPE Education and Knowledge, PSE4Food and Biochemical, and PSE4BioMedical and (Bio)Pharma.

Supplementary Material for the contribution "Synthesis of Distillation Flowsheets with Reinforcement Learning using Transformer Blocks" by Niklas Slager and Meik Franke (UTwente) for ESCAPE 35

The transition to renewable energy sources, such as biogas, requires purification processes to separate methane from carbon dioxide, with adsorption-based methods being widely employed. Accurate simulations of these systems, governed by coupled PDEs, ODEs, and algebraic equations, critically depend on precise parameter determination. While traditional approaches often result in significant errors or complex procedures, optimization algorithms provide a more efficient and reliable means of parameter estimation, simplifying the process, improving simulation accuracy, and enhancing the understanding of these systems.
This work introduces an Artificial Intelligence-based methodology for estimating the isotherm parameters of a mathematical phenomenological model for fixed-bed experiments. The separation of CO₂ and CH₄ is used as case study. This work develops an algorithm for parameter estimation for the system's mathematical model. The results show that the validated model has a close fi... [more]

The document is the digital supplementary material for the article titled "Application of Artificial Intelligence in process simulation tool", submitted to the ESCAPE 35 conference. It contains additional information and figures.

Overview presenation by Prof. Alexander Dowling at the Public Affairs & Information Committee (PAIC) Town Hall at AIChE Annual Meeting in 2024.

An important measure to achieve global reduction in CO2 emissions is CO2 capture, transport, and storage. The deployment of CO2 capture requires the development of a shared CO2 transport infrastructure, where CO2 can be transported with different transport modes. Furthermore, the cost of CO2 transport can be subject to significant economies of scale effects with respect to the amount of CO2 transported, also mentioned as clustering effects. Therefore, optimizing the shared infrastructure of multiple CO2 sources can lead to significant reductions in infrastructure costs. This paper presents a novel formulation of the clustered CO2 transport network. The Markov Decision Process formulation defined here allows for more detailed modeling of non-linear, discrete transport costs and increased geographical resolution. The clustering effects are modeled through cooperative multi-agent interactions. A multi-agent, reinforcement learning-based algorithm is proposed to optimize the shared transpo... [more]

This paper proposes an AI-assisted approach aimed at accelerating chemical process design through causal incremental reinforcement learning (CIRL) where an intelligent agent is interacting iteratively with a process simulation environment (e.g., Aspen HYSYS, DWSIM, etc.). The proposed approach is based on an incremental learnable optimizer capable of guiding multi-objective optimization towards optimal design variable configurations, depending on several factors including the problem complexity, selected RL algorithm and hyperparameters tuning. One advantage of this approach is that the agent-simulator interaction significantly reduces the vast search space of design variables, leading to an accelerated and optimized design process. This is a generic causal approach that enables the exploration of new process configurations and provides actionable insights to designers to improve not only the process design but also the design process across various applications. The approach was valid... [more]

Artificial intelligence (AI) and particularly generative AI led to recent breakthroughs, e.g., in generating text and images. There is also a potential of these technologies in chemical engineering, but the lack of structured big domain-relevant data hinders advancements. I envision an open Chemical Engineering Knowledge Graph (ChemEngKG) that provides big open and linked chemical process information. In this article, I present the concept of “flowsheet mining” as the first step towards the ChemEngKG. Flowsheet mining extracts process information from flowsheets and process descriptions found in scientific literature and patents. The proposed technology requires the integration of data mining, computer vision, natural language processing, and semantic web technologies. I present the concept of flowsheet mining, discuss previous literature, and show future potentials. I believe the availability of big data will enable breakthroughs in process design through artificial intelligence.