Graph neural networks (GNNs) have proven state-of-the-art performance in molecular property prediction tasks. However, a significant challenge with GNNs is the reliability of their predictions, particularly in critical domains where quantifying model confidence is essential. Therefore, assessing uncertainty in GNN predictions is crucial to improving their robustness. Existing uncertainty quantification methods, such as Deep ensembles and Monte Carlo Dropout, have been applied to GNNs with some success, but these methods are limited to approximate the full posterior distribution. In this work, we propose a novel approach for scalable uncertainty quantification in molecular property prediction using Stochastic Gradient Hamiltonian Monte Carlo (SGHMC). Additionally, we utilize a cyclical learning rate to facilitate sampling from multiple posterior modes which improves posterior exploration within a single training round. Moreover, we compare the proposed methods with Monte Carlo Dropout a... [more]

The Fourth Industrial Revolution (Industry 4.0) brings a new chapter at dairy sector. Dairy 4.0 technologies are based on Big Data Analysis, Internet of Things, Robotics and Machine Learning. The usage of smart technologies to processing and analyzing complicated massive data has a significant impact in automation, optimization, functional costs and innovation. Artificial Intelligence tools are applied from dairy farms and production lines – including packaging- to supply chain. The aim of this paper is to demonstrate the most used applications of Machine Learning in dairy production so as to enhance the sustainability and the quality of dairy products. The most significant Machine Learning applications integrate machine vision, smart environmental sensors, activity collars, thermal imaging cameras, and digitized supply chain systems to facilitate inventory management. Challenges like milk adulteration, animal diseases, mastitis, traceability and supply chain losses are also addressed... [more]

Precision modeling and forecasting of soil moisture are essential for implementing smart irrigation systems and mitigating agricultural drought. Most agro-hydrological models are based on the standard Richards equation, a highly nonlinear, degenerate elliptic-parabolic partial differential equation (PDE) with first order time derivative. However, research has shown that standard Richards equation is unable to model preferential flow in soil with fractal structure. In such a scenario, the soil exhibits anomalous non-Boltzmann scaling behavior. Incorporating the anomalous non-Boltzmann scaling behavior into the Richards equation leads to a generalized, time-fractional Richards equation based on fractional time derivatives. As expected, solving the time-fractional Richards equation for accurate modeling of water flow dynamics in soil faces extensive computational challenges. To target these challenges, we propose a novel numerical method that integrates finite volume method (FVM), adaptiv... [more]

In this paper, we present a systematic approach to quantify the safe operating window of a proton exchange membrane water electrolysis (PEMWE) system considering energy intermittency and varying hydrogen demand. The PEMWE model has been developed based on first principles, with the polarization curve validated against a lab-scale experimental setup. The impact of key operational variables is investigated which include voltage, inlet temperature, and water flowrate (utilized for both feed and system cooling). Emphasis is given on operating temperature, a safety-critical variable, as its elevation can pose significant hydrogen safety risks within both the electrolyzer cells and the storage system. The impact of temperature on process safety is quantified via a risk index considering the fault probability and consequence severity. Process operability analysis is employed to assess the achievability of a safe and feasible region for design and operations. This analysis provides a comprehen... [more]

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]

Modeling process systems by use of partial differential equations is often complex and computationally expensive, especially for inverse problems such as optimization, state identification, or parameter estimation. Data-driven methods typically provide efficient alternatives with lower computational cost. One such method is Graph Neural Networks (GNNs), which can be used to model dynamical systems as graphs. However, dynamic GNNs often face challenges with extrapolation and representability. Integrating mechanistic insights in surrogate models can improve both prediction accuracy and interpretability. This study compares different strategies for embedding physics-based insights into GNNs to model the dynamic behavior of a catalytic CO2 methanation reactor. The hybrid integration of physics-informed GNNs aims to improve the predictive ability and interpretability while reducing the model development time, thereby facilitating faster deployment. Results show that penalizing the predicted... [more]

The industrialization of catalytic processes requires reliable kinetic models for design, optimization, and control. While white box models are preferred for their interpretability, they demand considerable time and expertise for their construction. This research enhances the ADoK-S framework by embedding prior expert knowledge using mathematical constraints and integrating uncertainty quantification. The improved methodology consists of: (I) a genetic programming algorithm with constraints to produce physically coherent candidate models, (II) a sequential optimization algorithm for parameter estimation, (III) model selection based on the Akaike information criterion (AIC), and (IV) uncertainty quantification of the chosen model’s predictions. The refined approach not only requires less data for discovering kinetic models but also ensures physically sound proposals. With the inclusion of uncertainty quantification, the method bolsters prediction reliability, and aids in safer system de... [more]

Neural networks (NNs) are widely used as surrogate models but they do not guarantee physically consistent predictions thereby preventing adoption in various applications. We propose a method that can enforce NNs to satisfy physical laws that are nonlinear in nature such as enthalpy balances. Our approach, inspired by Picard’s successive approximations method, aims to enforce multiplicatively separable constraints by sequentially freezing and projecting a set of the participating variables. We demonstrate our Picard-KKT-hPINN for surrogate modeling of a catalytic packed bed reactor for methanol synthesis. Our results show that the method efficiently enforces nonlinear enthalpy and linear atomic balances at machine-level precision. Additionally, we show that enforcing conservation laws can improve accuracy in data-scarce conditions compared to vanilla multilayer perceptron.

In an era defined by economic competitiveness and environmental awareness, engineering solutions must maximize profitability, efficiency and sustainability, underscoring the relevance of process optimization and the societal impact any contribution in this research field would bring. In chemical reactor engineering, optimization tasks pose significant challenges due to the highly non-linear and non-convex nature of reactor models, often involving differential equations. While conventional approaches have proven to be reliable strategies for solving these complex problems, their application becomes impractical as problem size and complexity increase. This work introduces a novel application of Physics-Informed Neural Networks (PINNs) to address constrained optimization problems in reactor engineering and demonstrates the proposed methodology through two illustrative case studies in chemical reactor design and control. In doing so, we highlight the capability of PINNs to efficiently lear... [more]

Phase transition enthalpies, such as those for fusion, vaporization, and sublimation, are vital for understanding thermodynamic properties and aiding early-stage process design. However, measuring these properties is often time-consuming and costly, leading to increased interest in computational methods for fast and accurate predictions. Graph neural networks (GNNs), known for their ability to learn complex molecular representations, have emerged as state-of-the-art tools for predicting various thermophysical properties. Despite their success, GNNs do not inherently obey thermodynamic laws. In this study, we present a multitask GNN designed to predict vaporization, fusion, and sublimation enthalpies of organic compounds. We modified the loss function of the GNN, accounting for the thermodynamic cycle of the three phase transition enthalpies. To train the model, we digitized the extensive Chickos and Acree compendium, which encompasses 32,023 experimental measurements. Two approaches we... [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]

Artificial neural networks (ANNs) have gained popularity in the last years as tools to develop data-driven models of chemical process units. However, representing a system only with such artificial intelligence models may lead to a loss in the comprehension of the occurring phenomena. Hybrid models allow combining the predictive capabilities of ANNs with the foundational knowledge of rigorous models. This study explores the impact of hybridization in designing and optimizing shell-and-tube heat exchangers, comparing a full ANN-based model with a hybrid model. The hybrid model incorporates ANN predictions for highly nonlinear components, such as heat transfer coefficients, while other calculations are performed using the rigorous Bell-Delaware model. To generate the necessary data, the rigorous model is solved under randomly selected conditions. Using Python, one ANN predicts the exchanger's cost, while another predicts the heat transfer coefficients. Both models are optimized using the... [more]

Pressure swing adsorption (PSA) is an energy-efficient technology for gas separation, while the multi-objective optimization of PSA is a challenging task. To tackle this, we propose a hybrid optimization framework, which integrates three steps. In the first step, we establish surrogate models for the constraints using Gaussian processes (GPs) and employ multi-objective Bayesian optimization to search for feasible points that satisfy the constraints. In the second step, we establish surrogate models for the objective function and constraints using GPs and utilize constrained multi-objective Bayesian optimization to search for an approximate Pareto front. In the third step, we perform a local search based on the approximate Pareto front. By employing the trust region filter method, we construct quadratic models for each constraint and objective function and refine the Pareto front to achieve local optimality. This framework demonstrates the efficiency of Bayesian optimization and the loc... [more]

Rubber mixing (RM) is a vital batch process producing high-quality composites, which serve as input material for manufacturing different types of final products, such as tires. Due to its complexity, this process faces two main challenges regarding the final quality: i) lack of online measurement and ii) limited comprehension of the influence of the different factors involved in the process. While data-driven and machine learning (ML) based soft-sensing methods have been widely applied to address the first challenge, the second challenge, to the best of the author's knowledge, has not yet been addressed in the rubber industry. This work presents a data-driven method for extracting knowledge and providing explainability in the quality prediction in RM processes. The method centers on an XGBoost model while leveraging high-dimensional data collected over extended time periods from one of Michelin’s complex mixing processes. First, a recursive feature elimination-based procedure is used f... [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]

Waste lubricant oil (WLO) is a hazardous residual that requires proper management, being WLO regeneration the preferred approach. However, regeneration is only viable if the WLO does not coagulate in the equipment. Otherwise, the process needs to be shut down for cleaning and maintenance. To mitigate this risk, a laboratory test is currently used to assess the WLO coagulation potential before it enters the process. This laboratory test is, however, time-consuming, presents several safety risks, and is subjective. To expedite decision-making, process analytics technology (PAT) and machine learning were used to develop a model to classify WLOs according to their coagulation potential. Three approaches were followed, spanning linear and non-linear models. The first approach (benchmark) uses partial least squares for discriminant analysis (PLS-DA) and interval PLS combined with standard chemometric preprocessing techniques (27 model variants). The second approach uses wavelet transforms to... [more]

New research on complex intensified distillation schemes has popularized the use of several commercial process simulation software. The interfaces between process simulation and optimization-oriented software have allowed the use of rigorous and robust models. This type of optimization is mentioned in the literature as "Black Box Optimization", since successive evaluations exploits the information from the simulator without altering the model that represents the given process. Among process simulation software, Aspen Plus® has become popular due to their rigorous calculations, model customization, and results reliability. This work proposes a comparative study for Aspen Plus software and Microsoft Excel VBA®, Python® and MATLAB® interfaces. Five distillation schemes were analyzed: conventional column, reactive column, extractive column, column with side rectifier and a Petlyuk column. The optimization of the ?????? (Total Annual Cost) was carried out by a modified Simulated Annealing A... [more]

A key step in developing high-performance industrial products lies in the design of their constituent molecules. Computer-aided molecular design (CAMD) has garnered significant attention for its potential to accelerate and improve the design process. The mainstream method involves using property prediction models to predict the properties of potential molecules and selecting the best candidates based on these predictions. However, prediction errors are inevitable, introducing unreliability into the design. To address this issue, this paper proposes a novel component property modeling framework based on a molecular similarity coefficient. By calculating the similarity between a target molecule and those in an existing database, the framework selects the most similar molecules to form a tailored training dataset. The similarity coefficient also quantifies the reliability of the property predictions. In tests across various properties, this framework not only provides a quantifiable evalu... [more]

Enhanced weathering (EW) of alkaline minerals in chemical reactors with a controlled environment is recognized as a promising approach for gigaton-level carbon dioxide removal. However, reactor configuration and operating conditions must be optimized to balance the interfacial areas between gas, liquid and solid phases prior to industrial application. We developed a physics-based and data-driven hybrid modelling approach, coupled with multi-objective optimization, to study and compare three typical chemical reactors, i.e., trickle bed, packed bubbling columns, and stirred slurry reactors, and the optimal design to improve CO2 capture rate and reduce energy and water consumptions. Then an adaptive optimization is proposed to dynamically adjust the operating of the reactors in response to intermittent CO2 emission and renewable energy supply. Results indicated that forced stirring enhances CO2 capture rates by accelerating mass transport but increases energy consumption. Trickle bed reac... [more]

Predicting the critical micelle concentration (CMC) of surfactants is essential for optimizing their applications in various industries, including pharmaceuticals, detergents, and emulsions. In this study, we investigate the performance of graph-based machine learning models, specifically Graph Convolutional Networks (GCN), Graph Attention Networks (GAT), and a graph-transformer model, PharmHGT, for predicting CMC values. We aim to determine the most effective model for capturing the structural and physicochemical properties of surfactants. Our results provide insights into the relative strengths of each approach, highlighting the potential advantages of transformer-based architectures like PharmHGT in handling molecular graph representations compared to traditional graph neural networks. This comparative study serves as a step towards enhancing the accuracy of CMC predictions, contributing to the efficient design of surfactants for targeted applications.

In the present paper, we come up with application of machine learning using data for flow visualization as a method for predicting unsteady flow patterns in oscillatory baffled reactors (OBRs). Application of the proper orthogonal decomposition (POD) is investigated for dynamic analysis of spatio-temporal data acquired by particle image velocimetry (PIV) to determine inputs and outputs for neural network model. It has demonstrated that three sets of modes and time-varying mode coefficients extracted by the POD could be useful for dynamic analysis and prediction of time-variant flow patterns in OBR. Also it is shown that decomposition of the time-series data for the mode coefficients by Fourier series expansion was effective for deriving reduced order model.

Dynamic process modeling in process industries has been extensively studied, especially with the development of deep learning techniques. Recurrent neural networks (RNN) and stacked autoencoders (SAE) are two powerful tools for dynamic modeling and data processing. However, most existing research primarily focuses on extracting features from process input data, often neglecting the temporal autocorrelation of output variables. In this work, a hierarchical model based on time-series RNN structure is proposed. The upper layer employs a long short-term memory (LSTM) network to extract temporal features from process input data. The lower layer uses a gated recurrent unit (GRU) to model the temporal dependencies of output variables across samples. These two parts are concatenated to form the model. Additionally, SAE is utilized to perform dimensionality reduction and reconstruction of process input, seamlessly integrating the reconstruction process with the RNN into a unified framework, ter... [more]

Fluid catalytic cracking is a crucial process in the refining industry, capable of converting lower-quality feedstocks into higher-value products. Due to the variability in feedstock properties and fluctuations in product market prices, timely adjustment and optimization of the FCC unit are essential. In this context, data-driven models have garnered increasing attention for their capacity to handle the complex, nonlinear reactions involved in the FCC process. However, on account of the limited operating range of the plants and the black-box nature of data-driven models, relying solely on these models for optimization may lead to contradictory decisions in optimization processes. To address these challenges, we integrate gradient information of product yields with respect to key variables derived from the mechanistic model Petro-SIM, into the training process of data-driven models. To mitigate the high computational demands of the Petro-SIM model, we propose the use of active learning... [more]

The mathematical modeling of enzymatic reactors for esterification of fatty acids with sugars in the production of biosurfactants has been a useful tool for studying and optimizing the process. In particular, artificial neural networks and fuzzy systems emerge as promising methods for developing models for those processes. In this work, regarding artificial neural networks application, coupling of networks to reactor mass balances was considered in hybrid models to infer reactant concentrations over time. Computationally, an algorithm was constructed incorporating material balances, neural reaction rates, and step-by-step numerical integration (employing the classical Runge-Kutta method). Besides, based on an available set of experimental data, fuzzy logic was applied for modeling and optimization of the conversion of esterification as a function of operational process parameters (such as time, temperature and molar ratio of substrates). All computational development was carried out us... [more]

The erosive wear encountered in some industrial processes results in economic loss and even disastrous consequences. Hitherto, the mechanism of the erosive wear is not clear, especially when the erosive wear is caused by large particles (>3.0 mm) carried by a flowing liquid. Current approaches of predicting erosive wear need improvement, and the optimization of relevant equipment and systems lacks a sound guidance. It is of significance to further explore such a subject based on the relevant literature. The present review commences with a theoretical analysis of the dynamics of large particles and the fundamental mechanism of erosion. Then the characteristics of the erosion of various equipment are explicated. Effects of influential factors such as particle size and properties of the target material are analyzed. Subsequently, commonly used erosion models, measurement techniques, and numerical methods are described and discussed. Based on established knowledge and the studies reported,... [more]