Most integrated energy system (IES) optimization frameworks employ the price-taker approximation, which ignores important interactions with the market and can result in overestimated economic values. In this work, we propose a machine learning surrogate-assisted optimization framework to quantify IES/market interactions and thus go beyond price-taker. We use time series clustering to generate representative IES operation profiles for the optimization problem and use machine learning surrogate models to predict the IES/market interaction. We quantify the accuracy of the time series clustering and surrogate models in a case study to optimally retrofit a nuclear power plant with a polymer electrolyte membrane electrolyzer to co-produce electricity and hydrogen.

The chemical industry is actively pursuing energy transition and decarbonization through renewables and other decarbonization initiatives. However, navigating this transition is challenging due to uncertainties in capital investments, electricity costs, and carbon taxes. Adapting to decarbonization standards while preserving existing valuable infrastructure presents a dilemma. Early transitions may lead to inefficiencies, while delays increase the carbon footprint. This research proposes a framework to find an optimal retrofit decarbonization strategy for existing oil refineries. We start with a generic process flowsheet representing the refinery's current configuration and operations, and consider various decarbonization alternatives. Through superstructure optimization, we identify the most cost-effective retrofit strategy over the next three decades to achieve decarbonization goals. We develop a Mixed-Integer Linear Programming (MILP) model, integrating simplified process equations... [more]

The growing electrification of buildings and vehicles, while a natural step towards achieving global decarbonization, poses some challenges for the electric grid in terms of power consumption. One way of addressing them is by deploying onsite, behind-the-meter resources (BTMR), such as battery energy storage and solar PV generation. The optimal design of these systems, however, is a demanding task that depends on the integration of multiple complex subsystems. In this work, the optimal integrated design and dispatch of BTMR systems for retail buildings with electric vehicle fast charging stations is addressed. A framework is proposed, combining high-fidelity simulation (of buildings, electric vehicle fast charging stations, and BTMR), predictive control strategies with closed-loop implementation, and a derivative-free design method that explores parallelization and high-performance computing. Focus is given to the design layer, highlighting the effect of parallelization on the choice o... [more]

Chemical looping ammonia synthesis (CLAS) is a new ammonia synthesis method capable of efficiently synthesizing ammonia at atmospheric pressure. The low-pressure operation of CLAS systems could decrease the capital and operational costs of ammonia synthesis. Despite its early developmental stage, the use of standard process engineering equipment in CLAS makes it possible to reasonably assess its economic potential. In this study, we evaluated the technoeconomic potential of CLAS systems in comparison to a Haber-Bosch (HB) synthesis process in the context of green ammonia production. CLAS is more compatible with the separate nitrogen and hydrogen feedstocks used in green ammonia production, and cost savings from CLAS could improve the economic viability of green ammonia production. Ammonia synthesis loops were modeled in Aspen Plus and the levelized cost of ammonia (LCOA) of each system was calculated. Three CLAS systems; two high temperature and one low-temperature chemical loop, were... [more]

Direct air capture (DAC) of carbon dioxide is a promising technology to enable climate change mitigation. The liquid solvent DAC (LSDAC) process is one of the leading technologies being piloted. However, LSDAC uses a high-temperature regeneration process which requires a lot of thermal energy. Although current LSDAC designs incorporate pre-heat cyclones and a heat recovery steam generator to enable heat recovery, these do not maximize the use of the heat in the products of calcination. In this paper, a linear optimization model is developed to minimize energy cost in a LSDAC that is powered by renewable energy and natural gas. First, the material flow network is modified to include a heat exchanger (HX) and water supply to a proton exchange membrane (PEM) electrolyser. Mass and energy balance constraints are then developed to include the water flow as well as the energy balance at the PEM and the HX. Results show that about 911 tonnes of hydrogen could be produced over 336 hours of ope... [more]

Water-gas shift membrane reactors (WGS-MRs) offer a pathway to affordable blue H2 generation/purification from gasified feedstock or reformed fuels. To exploit their cost benefits for blue hydrogen production, WGS-MRs’ performance needs to be optimized, which includes navigating the multidimensional design space (e.g., temperature, feed pressures, space velocity, membrane permeance and selectivity, catalytic performance). This work describes an equation-oriented modeling framework for WGS-MRs in the Pyomo ecosystem, with an emphasis on model scaling and multi-start initialization strategies to facilitate reliable convergence with nonlinear optimization solvers. We demonstrate, through sensitivity analysis, that our model converges rapidly (< 1 CPU second on a laptop computer) under a wide range of operating parameters (e.g., feed pressures of 1-3 MPa, reactor temperatures of 624-824 K, sweep-to-feed ratios of 0-0.5, and steam/carbon ratios of 1-5). Ongoing work includes (1) validat... [more]

In this work, we present a follow-up work of reinforcement learning (RL)-driven process design using the Institute for Design of Advanced Energy Systems Process Systems Engineering (IDAES-PSE) Framework. Herein, process designs are generated as stream inlet-outlet matrices and optimized using the IDAES platform, the objective function value of which is the reward to RL agent. Deep Q-Network is employed as the RL agent including a series of convolutional neural network layers and fully connected layers to compute the actions of adding or removing any stream connections, thus creating a new process design. The process design is then informed back to the RL agent to refine its learning. The iteration continues until the maximum number of steps is reached with feasible process designs generated. To further expedite the RL search of the design space which can comprise the selection of any candidate unit(s) with arbitrary stream connections, we investigate the role of RL reward function and... [more]

Pharmaceutically elegant tablets are an expectation from pharmacists, health care providers and consumers for solid oral dosage forms. The presence of non-aesthetically pleasing defects in solid oral dosage forms can result in complaints back to the manufacturer and potentially non-compliance with medicines. The purpose of this study was to simulate and analyze the design of a tablet core and the aqueous film-coating process, to gain a better understanding of tablet defect generation, and to help eliminate the defects from the finished product. This evaluation employs Discrete Element Method (DEM) using the software product Altair® EDEM™ to understand the potential mechanisms that are causing the defects, based on the forces tablets experience in the coating operation, along with the number of tablet-to-tablet interactions that occur during the duration of the process. Defects observed during the scale up of the coating process to a commercial production scale confirmed the DEM results... [more]

The integrated design and control (IDC) framework is becoming increasingly important for systematic design of flexible manufacturing and energy systems. Recent advances in computing and derivative-free optimization have enabled more tractable solution methods for complex IDC problems that involve, e.g., multi-period dynamics, the presence of high-variance and non-stationarity probabilistic uncertainties, and mixed-integer control/scheduling decisions. Parallelly, developments in techno-ecological synergy (TES) have allowed co-design of industrial and environmental systems that have been shown to lead to win-win solutions in terms of the economy, ecological, and societal benefits. In this work, we propose to combine the IDC and TES frameworks to more accurately capture the real-time interactions between process systems and the surrounding natural resources (e.g., forests, watersheds). Specifically, we take advantage of (multi-scale) model predictive control to close the loop on a realis... [more]

Copolymers are commonplace in various industries. Nevertheless, fine-tuning their properties bears significant cost and effort. Hence, an ability to predict polymer properties a priori can significantly reduce costs and shorten the need for extensive experimentation. Given that the physical and chemical characteristics of copolymers are correlated with molecular arrangement and chain topology, understanding the reactivity ratios of monomers—which determine the copolymer composition and sequence distribution of monomers in a chain—is important in accelerating research and cutting R&D costs. In this study, the prediction accuracy of two Artificial Neural Network (ANN) approaches, namely, Multi-layer Perceptron (MLP) and Graph Attention Network (GAT), are compared. The results highlight the potency and accuracy of the intrinsically interpretable ML approaches in predicting the molecular structures of copolymers. Our data indicates that even a well-regularized MLP cannot predict the reacti... [more]

Continuous manufacturing in pharmaceutical industries has shown great promise to achieve process intensification. To better understand and justify such changes to the current status quo, a technoeconomic analysis of a continuous production must be conducted to serve as a predictive decision-making tool for manufacturers. This paper uses PharmaPy, a custom-made Python-based library developed for pharmaceutical flowsheet analysis, to simulate an annual production cycle for a given active pharmaceutical ingredient (API) of varying production volumes for a batch crystallization system and a continuous mixed suspension, mixed product removal (MSMPR) crystallizer. After each system is optimized, the generalized cost drivers, categorized as capital expenses (CAPEX) or operational expenses (OPEX), are compared. Then, a technoeconomic and sustainability cost analysis is done with the process mass intensity (PMI) as a green metric. The results indicate that while the batch system does have an ov... [more]

Modeling the non-linear dynamics of a system from measurement data accurately is an open challenge. Over the past few years, various tools such as SINDy and DySMHO have emerged as approaches to distill dynamics from data. However, challenges persist in accurately capturing dynamics of a system especially when the physical knowledge about the system is unknown. A promising solution is to use a hybrid paradigm, that combines mechanistic and black-box models to leverage their respective strengths. In this study, we combine a hybrid modeling paradigm with sparse regression, to develop and identify models simultaneously. Two methods are explored, considering varying complexities, data quality, and availability and by comparing different case studies. In the first approach, we integrate SINDy-discovered models with neural ODE structures, to model unknown physics. In the second approach, we employ Multifidelity Surrogate Models (MFSMs) to construct composite models comprised of SINDy-discover... [more]

Cardiomyocytes (CMs), the contractile heart cells that can be derived from human induced pluripotent stem cells (hiPSCs). These hiPSC derived CMs can be used for cardiovascular disease drug testing and regeneration therapies, and they have therapeutic potential. Currently, hiPSC-CM differentiation cannot yet be controlled to yield specific heart cell subtypes consistently. Designing differentiation processes to consistently direct differentiation to specific heart cells is important to realize the full therapeutic potential of hiPSC-CMs. A model that accurately represents the dynamic changes in cell populations from hiPSCs to CMs over the differentiation timeline is a first step towards designing processes for directing differentiation. This paper introduces a microsimulation model for studying temporal changes in the hiPSC-to-early CM differentiation. The differentiation process for each cell in the microsimulation model is represented by a Markov chain model (MCM). The MCM includes c... [more]

A hybrid model for the fluid bed granulation operation was built. The deterministic component focuses on the mass and energy balances representing the water ingress and egress from the powder bed. The empirical one does on granule growth. Estimability techniques were used to determine which parameters to regress from the available data. A partial least squares approach was used to better understand the impact of the model parameters onto key model responses and sensitivity plots were made to aid operational decisions and support pharmaceutical development.

This paper presents the development of algorithms for mass-energy constrained neural network (MECNN) models that can exactly conserve the overall mass and energy of distributed chemical process systems, even though the noisy steady-state/transient data used for optimal model training violate the same. For developing dynamic mass-energy constrained network models for distributed systems, hybrid series and parallel dynamic-static neural networks are used as candidate architectures. The proposed approaches for solving both the inverse and forward problems are validated considering both steady-state and dynamic data in presence of various noise characteristics. The proposed network structures and algorithms are applied to the development of data-driven models of a nonlinear non-isothermal reactor that involves an exothermic reaction making it significantly challenging to exactly satisfy the mass and energy conservation laws of the system only by using the available input and output boundar... [more]

Modern industrial processes are continuously monitored by a large number of sensors. Despite having access to large volumes of historical and online sensor data, industrial practitioners still face challenges in the era of Industry 4.0 in effectively utilizing them to perform online process monitoring and fast fault detection and diagnosis. To target these challenges, in this work, we present a novel framework named “FARM” for Fast, Accurate, and Robust online process Monitoring. FARM is a holistic monitoring framework that integrates (a) advanced multivariate statistical process control (SPC) for fast anomaly detection of nonparametric, heterogeneous data streams, and (b) modified support vector machine (SVM) for accurate and robust fault classification. Unlike existing general-purpose process monitoring frameworks, FARM’s unique hierarchical architecture decomposes process monitoring into two fault detection and diagnosis, each of which is conducted by targeted algorithms. Here, we t... [more]

Machine learning (ML) has become a powerful tool to analyze complex relationships between multiple variables and to unravel valuable information from big datasets. However, an open research question lies in how ML can accelerate the design and optimization of processes in the early experimental development stages with limited data. In this work, we investigate the ML-aided process design of a microwave reactor for ammonia production with exceedingly little experimental data. We propose an integrated approach of synthetic minority oversampling technique (SMOTE) regression combined with neural networks to quantitatively design and optimize the microwave reactor. To address the limited data challenge, SMOTE is applied to generate synthetic data based on experimental data at different reaction conditions. Neural network has been demonstrated to effectively capture the nonlinear relationships between input features and target outputs. The softplus activation function is used for a smoother... [more]

Adaptive and self-optimizing intelligent systems such as digital twins are increasingly important in science and engineering. Digital twins utilize mathematical models to provide added precision to decision-making. However, physics-informed models are challenging to build, calibrate, and validate with existing data science methods. Model-based design of experiments (MBDoE) is a popular framework for optimizing data collection to maximize parameter precision in mathematical models and digital twins. In this work, we apply MBDoE, facilitated by the open-source package Pyomo.DoE, to train and validate mathematical models for batch crystallization. We quantitatively examined the estimability of the model parameters for experiments with different cooling rates. This analysis provides a quantitative explanation for the heuristic of using multiple experiments at different cooling rates.

We present a string representation for hybrid extraction and distillation using symbols representing phenomena building blocks. Unlike the conventional equipment-based string representation, the proposed representation captures the design details of liquid-liquid extraction and distillation. We generate a set of samples through the procedure of input parameter sampling and superstructure optimization that minimizes separation cost. We convert these generated samples into a set of string representations based on pre-defined rules. We use these string representations as descriptors and connect them with conditional variational encoder. The trained conditional variational encoder shows good prediction accuracy. We further use the trained conditional variational encoder to screen designs of hybrid extraction and distillation with desired cost investment.

Computer-aided Molecular and Process Design (CAMPD) is an equation-oriented multi-scale decision making framework for designing both materials (molecules) and processes for separation, reaction, and reactive separation whenever material choice significantly impacts process performance. The inherent nonlinearity and nonconvexity in CAMPD optimization models, introduced through the property and process models, pose challenges to state-of-the-art solvers. Recently, quantum computing (QC) has shown promise for solving complex optimization problems, especially those involving discrete decisions. This motivates us to explore the potential usage of quantum optimization techniques for solving CAMPD problems. We have developed a technique for directly solving a class of mixed integer nonlinear programs using QC. Our approach represents both continuous and integer design decisions by a set of binary variables through encoding schemes. This transformation allows to reformulate certain types of CA... [more]

Antibody therapies are important in treating life-threatening ailments such as cancer and autoimmune diseases. Purity of the antibody is essential for successful applications and Protein A selective resin extraction is the standard step for antibody recovery. Unfortunately, such resins can cost up to 30% of the total cost of antibody production. Hence, the optimal design of this purification step becomes a critical factor in downstream processing to minimize the size of the column needed. An accurate predictive model, as a digital twin representing the purification process, is necessary where changes in the flow rates and the inlet concentrations are modeled via the Method of Moments. The system uncertainties are captured by including the stochastic Ito process model of Brownian motion with drift. Pontryagin’s Maximum Principle under uncertainty is then applied to predict the flowrate control strategy for optimized resin use, column design, and efficient capturing of the antibodies. In... [more]

Machine learning presents opportunities to improve the scale-specific accuracy of mechanistic models in a data-driven manner. Here we demonstrate the use of a machine learning technique called Sparse Identification of Nonlinear Dynamics (SINDy) to improve a simple mechanistic model of algal growth. Time-series measurements of the microalga Chlorella Vulgaris were generated under controlled photobioreactor conditions at the University of Technology Sydney. A simple mechanistic growth model based on intensity of light and temperature was integrated over time and compared to the time-series data. While the mechanistic model broadly captured the overall growth trend, discrepancies remained between the model and data due to the model's simplicity and non-ideal behavior of real-world measurement. SINDy was applied to model the residual error by identifying an error derivative correction term. Addition of this SINDy-informed error dynamics term shows improvement to model accuracy while maint... [more]

Water chemistry plays a critical role in the design and operation of water treatment processes. Detailed chemistry modeling tools use a combination of advanced thermodynamic models and extensive databases to predict phase equilibria and reaction phenomena. The complexity and formulation of these models preclude their direct integration in equation-oriented modeling platforms, making it difficult to use their capabilities for rigorous water treatment process optimization. Neural networks (NN) can provide a pathway for integrating the predictive capability of chemistry software into equation-oriented models and enable optimization of complex water treatment processes across a broad range of conditions and process designs. Herein, we assess how NN architecture and training data impact their accuracy and use in equation-oriented water treatment models. We generate training data using PhreeqC software and determine how data generation and sample size impact the accuracy of trained NNs. The... [more]

In this paper, a hybrid heuristic rule-based and deterministic optimization-driven process decision framework is presented for the analysis and optimization of process flowsheets for end-to-end optimal (E2E0) pharmaceutical manufacturing. The framework accommodates various operating modes, such as batch, semi-batch and continuous, for the different unit operations that implement each manufacturing step. To address the challenges associated with solving process synthesis problems using a simulation-optimization approach, heuristic-based process synthesis rules are employed to facilitate the reduction of the superstructure into smaller sub-structures that can be more readily optimized. The practical application of the framework is demonstrated through a case study involving the end-to-end continuous manufacturing of an anti-cancer drug, lomustine. Alternative flowsheet structures are evaluated in terms of the sustainability metric, E-factor while ensuring compliance with the required pro... [more]

Explicitly incorporating the effects of chemical phenomena such as chemical pretreatment and mineral scaling during the design of treatment systems is critical; however, the complexity of these phenomena and limitations on data have historically hindered the incorporation of detailed water chemistry into the modeling and optimization of water desalination systems. Thus, while qualitative assessments and experimental studies on chemical pretreatment and scaling are abundant in the literature, very little has been done to assess the technoeconomic implications of different chemical pretreatment alternatives within the context of end-to-end water treatment train optimization. In this work, we begin to address this challenge by exploring the impact of pH control during pretreatment on the cost and operation of a high-recovery desalination train. We compare three pH control methods used in water treatment (H2SO4, HCl, and CO2) and assess their impact on the operation of a desalination plant... [more]