Publications
49 results found
Basha N, Savage T, McDonough J, et al., 2023, Discovery of mixing characteristics for enhancing coiled reactor performance through a Bayesian optimisation-CFD approach, Chemical Engineering Journal, Vol: 473, ISSN: 1385-8947
Plug flow characteristics are advantageous in various manufacturing processes for fine/bulk chemicals, pharmaceuticals, biofuels, and waste treatment as they contribute to maximising product yield. One such versatile flow chemistry platform is the coiled tube reactor subjected to oscillatory motion, producing excellent plug flow qualities equivalent to well-mixed tanks-in-series ‘N’. In this study, we discover the critical features of these flows that result in high plug flow performance using a data-driven approach. This is done by integrating Bayesian optimisation, a surrogate model approach, with Computational fluid dynamics that we treat as a black-box function to explore the parameter space of the operating conditions, oscillation amplitude and frequency, and net flow rate. Here, we correlate the flow characteristics as a function of the dimensionless Strouhal, oscillatory Dean, and Reynolds numbers to the reactor plug flow performance value ‘N’. Under conditions of optimal performance (specific examples are provided herein), the oscillatory flow is just sufficient to limit axial dispersion through flow reversal and redirection, and to promote Dean vortices. This automated, open-source, integrated method can be easily adapted to identify the flow characteristics that produce an optimised performance for other chemical reactors and processes.
van de Berg D, Petsagkourakis P, Shah N, et al., 2023, Data-driven coordination of subproblems in enterprise-wide optimization under organizational considerations, AIChE Journal, Vol: 69, Pages: 1-24, ISSN: 0001-1541
While decomposition techniques in mathematical programming are usually designed for numerical efficiency, coordination problems within enterprise-wide optimization are often limited by organizational rather than numerical considerations. We propose a “data-driven” coordination framework which manages to recover the same optimum as the equivalent centralized formulation while allowing coordinating agents to retain autonomy, privacy, and flexibility over their own objectives, constraints, and variables. This approach updates the coordinated, or shared, variables based on derivative-free optimization (DFO) using only coordinated variables to agent-level optimal subproblem evaluation “data.” We compare the performance of our framework using different DFO solvers (CUATRO, Py-BOBYQA, DIRECT-L, GPyOpt) against conventional distributed optimization (ADMM) on three case studies: collaborative learning, facility location, and multiobjective blending. We show that in low-dimensional and nonconvex subproblems, the exploration-exploitation trade-offs of DFO solvers can be leveraged to converge faster and to a better solution than in distributed optimization.
Mowbray M, Vallerio M, Perez-Galvan C, et al., 2022, Industrial data science - a review of machine learning applications for chemical and process industries, REACTION CHEMISTRY & ENGINEERING, Vol: 7, Pages: 1471-1509, ISSN: 2058-9883
- Author Web Link
- Cite
- Citations: 18
Savage TR, Almeida-Trasvina F, Chanona EAD-R, et al., 2021, An integrated dimensionality reduction and surrogate optimization approach for plant-wide chemical process operation, AICHE JOURNAL, Vol: 67, ISSN: 0001-1541
- Author Web Link
- Cite
- Citations: 3
Anye Cho B, de Carvalho Servia MA, del Rio Chanona EA, et al., 2021, Synergising biomass growth kinetics and transport mechanisms to simulate light/dark cycle effects on photo-production systems, BIOTECHNOLOGY AND BIOENGINEERING, Vol: 118, Pages: 1932-1942, ISSN: 0006-3592
- Author Web Link
- Cite
- Citations: 6
Méndez-Lucio O, Ahmad M, del Rio-Chanona EA, et al., 2021, A Geometric Deep Learning Approach to Predict Binding Conformations of Bioactive Molecules
<jats:p>Understanding the interactions formed between a ligand and its molecular target is key to guide the optimization of molecules. Different experimental and computational methods have been key to understand better these intermolecular interactions. Herein, we report a method based on geometric deep learning that is capable of predicting the binding conformations of ligands to protein targets. Concretely, the model learns a statistical potential based on distance likelihood which is tailor-made for each ligand-target pair. This potential can be coupled with global optimization algorithms to reproduce experimental binding conformations of ligands. We show that the potential based on distance likelihood described in this paper performs similar or better than well-established scoring functions for docking and screening tasks. Overall, this method represents an example of how artificial intelligence can be used to improve structure-based drug design.</jats:p>
Méndez-Lucio O, Ahmad M, del Rio-Chanona EA, et al., 2021, A Geometric Deep Learning Approach to Predict Binding Conformations of Bioactive Molecules
<jats:p>Understanding the interactions formed between a ligand and its molecular target is key to guide the optimization of molecules. Different experimental and computational methods have been key to understand better these intermolecular interactions. Herein, we report a method based on geometric deep learning that is capable of predicting the binding conformations of ligands to protein targets. Concretely, the model learns a statistical potential based on distance likelihood which is tailor-made for each ligand-target pair. This potential can be coupled with global optimization algorithms to reproduce experimental binding conformations of ligands. We show that the potential based on distance likelihood described in this paper performs similar or better than well-established scoring functions for docking and screening tasks. Overall, this method represents an example of how artificial intelligence can be used to improve structure-based drug design.</jats:p>
Bradford E, Imsland L, Reble M, et al., 2021, Hybrid Gaussian Process Modeling Applied to Economic Stochastic Model Predictive Control of Batch Processes, Lecture Notes in Control and Information Sciences, Pages: 191-218
Nonlinear model predictive control (NMPC) is an effective approach for the control of nonlinear multivariable dynamic systems with constraints. However, NMPC requires an accurate plant model. Plant models can often be determined from first principles, parts of the model are, however, difficult to derive using physical laws alone. In this paper, a new hybrid modeling scheme is proposed to overcome this issue, which combines physical models with Gaussian process (GP) modeling. The GPs are employed to model the parts of the physical model that are difficult to describe using first principles. GPs not only give predictions, but also quantify the residual uncertainty of this model. It is vital to account for this uncertainty in the control algorithm, to prevent constraint violations and performance deterioration. Monte Carlo samples of the GPs are generated offline to tighten constraints of the NMPC and thus ensure joint probabilistic constraint satisfaction online. Advantages of our method include fast online evaluation times, and exploiting the flexibility of GPs and the data efficiency of first principle models. The algorithm is verified on a case study involving a challenging semi-batch bioreactor.
Bradford E, Imsland L, Zhang D, et al., 2020, Stochastic data-driven model predictive control using gaussian processes, Computers and Chemical Engineering, Vol: 139, ISSN: 0098-1354
Nonlinear model predictive control (NMPC) is one of the few control methods that can handle multivariable nonlinear control systems with constraints. Gaussian processes (GPs) present a powerful tool to identify the required plant model and quantify the residual uncertainty of the plant-model mismatch. It is crucial to consider this uncertainty, since it may lead to worse control performance and constraint violations. In this paper we propose a new method to design a GP-based NMPC algorithm for finite horizon control problems. The method generates Monte Carlo samples of the GP offline for constraint tightening using back-offs. The tightened constraints then guarantee the satisfaction of chance constraints online. Advantages of our proposed approach over existing methods include fast online evaluation, consideration of closed-loop behaviour, and the possibility to alleviate conservativeness by considering both online learning and state dependency of the uncertainty. The algorithm is verified on a challenging semi-batch bioprocess case study.
Petsagkourakis P, Sandoval IO, Bradford E, et al., 2020, Reinforcement learning for batch bioprocess optimization, Computers and Chemical Engineering, Vol: 133, ISSN: 0098-1354
Bioprocesses have received a lot of attention to produce clean and sustainable alternatives to fossil-based materials. However, they are generally difficult to optimize due to their unsteady-state operation modes and stochastic behaviours. Furthermore, biological systems are highly complex, therefore plant-model mismatch is often present. To address the aforementioned challenges we propose a Reinforcement learning based optimization strategy for batch processes. In this work we applied the Policy Gradient method from batch-to-batch to update a control policy parametrized by a recurrent neural network. We assume that a preliminary process model is available, which is exploited to obtain a preliminary optimal control policy. Subsequently, this policy is updated based on measurements from the true plant. The capabilities of our proposed approach were tested on three case studies (one of which is nonsmooth) using a more complex process model for the true system embedded with adequate process disturbance. Lastly, we discussed advantages and disadvantages of this strategy compared against current existing approaches such as nonlinear model predictive control.
Savage T, Almeida-Trasvina HF, Del Rio-Chanona EA, et al., 2020, An adaptive data-driven modelling and optimization framework for complex chemical process design, Editors: Pierucci, Manenti, Bozzano, Manca, Publisher: ELSEVIER SCIENCE BV, Pages: 73-78
- Author Web Link
- Cite
- Citations: 1
Bradford E, Imsland L, Del Rio-Chanona EA, 2019, Nonlinear model predictive control with explicit back-offs for Gaussian process state space models, Pages: 4747-4754, ISSN: 0743-1546
Nonlinear model predictive control (NMPC) is an efficient control approach for multivariate nonlinear dynamic systems with process constraints. NMPC does however require a plant model to be available. A powerful tool to identify such a model is given by Gaussian process (GP) regression. Due to data sparsity this model may have considerable uncertainty though, which can lead to worse control performance and constraint violations. A major advantage of GPs in this context is its probabilistic nature, which allows to account for plant-model mismatch. In this paper we propose to sample possible plant models according to the GP and calculate explicit back-offs for constraint tightening using closed-loop simulations offline. These then in turn guarantee satisfaction of chance constraints online despite the uncertainty present. Important advantages of the proposed method over existing approaches include the cheap online computational time and the consideration of closed-loop behaviour to prevent open-loop growth of uncertainties. In addition we show how the method can account for updating the GP plant model using available online measurements. The proposed algorithm is illustrated on a batch reactor case study.
Del Rio-Chanona EA, Ahmed NR, Wagner J, et al., 2019, Comparison of physics-based and data-driven modelling techniques for dynamic optimisation of fed-batch bioprocesses, BIOTECHNOLOGY AND BIOENGINEERING, Vol: 116, Pages: 2971-2982, ISSN: 0006-3592
- Author Web Link
- Cite
- Citations: 17
Zhang D, Del Rio-Chanona EA, Petsagkourakis P, et al., 2019, Hybrid physics-based and data-driven modeling for bioprocess online simulation and optimization, BIOTECHNOLOGY AND BIOENGINEERING, Vol: 116, Pages: 2919-2930, ISSN: 0006-3592
- Author Web Link
- Cite
- Citations: 53
del Rio Chanona EA, Wagner JL, Ali H, et al., 2019, Deep learning-based surrogate modeling and optimization for microalgal biofuel production and photobioreactor design, AIChE Journal, Vol: 65, Pages: 915-923, ISSN: 0001-1541
Identifying optimal photobioreactor configurations and process operating conditions is critical to industrialize microalgae‐derived biorenewables. Traditionally, this was addressed by testing numerous design scenarios from integrated physical models coupling computational fluid dynamics and kinetic modeling. However, this approach presents computational intractability and numerical instabilities when simulating large‐scale systems, causing time‐intensive computing efforts and infeasibility in mathematical optimization. Therefore, we propose an innovative data‐driven surrogate modeling framework, which considerably reduces computing time from months to days by exploiting state‐of‐the‐art deep learning technology. The framework built upon a few simulated results from the physical model to learn the sophisticated hydrodynamic and biochemical kinetic mechanisms; then adopts a hybrid stochastic optimization algorithm to explore untested processes and find optimal solutions. Through verification, this framework was demonstrated to have comparable accuracy to the physical model. Moreover, multi‐objective optimization was incorporated to generate a Pareto‐frontier for decision‐making, advancing its applications in complex biosystems modeling and optimization.
Del Rio-Chanona EA, Cong X, Bradford E, et al., 2019, Review of advanced physical and data-driven models for dynamic bioprocess simulation: Case study of algae-bacteria consortium wastewater treatment, BIOTECHNOLOGY AND BIOENGINEERING, Vol: 116, Pages: 342-353, ISSN: 0006-3592
- Author Web Link
- Cite
- Citations: 24
Petsagkourakis P, Sandoval IO, Bradford E, et al., 2019, Reinforcement Learning for Batch-to-Batch Bioprocess Optimisation, Computer Aided Chemical Engineering, Pages: 919-924
Bioprocesses have received great attention from the scientific community as an alternative to fossil-based products by microorganisms-synthesised counterparts. However, bioprocesses are generally operated at unsteady-state conditions and are stochastic from a macro-scale perspective, making their optimisation a challenging task. Furthermore, as biological systems are highly complex, plant-model mismatch is usually present. To address the aforementioned challenges, in this work, we propose a reinforcement learning based online optimisation strategy. We first use reinforcement learning to learn an optimal policy given a preliminary process model. This means that we compute diverse trajectories and feed them into a recurrent neural network, resulting in a policy network which takes the states as input and gives the next optimal control action as output. Through this procedure, we are able to capture the previously believed behaviour of the biosystem. Subsequently, we adopted this network as an initial policy for the “real” system (the plant) and apply a batch-to-batch reinforcement learning strategy to update the network's accuracy. This is computed by using a more complex process model (representing the real plant) embedded with adequate stochasticity to account for the perturbations in a real dynamic bioprocess. We demonstrate the effectiveness and advantages of the proposed approach in a case study by computing the optimal policy in a realistic number of batch runs.
Chanona EADR, Alves Graciano JE, Bradford E, et al., 2019, Modifier-Adaptation Schemes Employing Gaussian Processes and Trust Regions for Real-Time Optimization, 12th International-Federation-of-Automatic-Control (IFAC) Symposium on Dynamics and Control of Process Systems including Biosystems (DYCOPS), Publisher: ELSEVIER, Pages: 52-57, ISSN: 2405-8963
- Author Web Link
- Cite
- Citations: 18
del Rio-Chanona EA, Zhang D, 2018, A Bilevel Programming Approach to Optimize C-phycocyanin Bio-production under Uncertainty, 10th IFAC Symposium on Advanced Control of Chemical Processes (ADCHEM), Publisher: ELSEVIER SCIENCE BV, Pages: 209-214, ISSN: 2405-8963
Bradford E, Schweidtmann AM, Zhang D, et al., 2018, Dynamic modeling and optimization of sustainable algal production with uncertainty using multivariate Gaussian processes, COMPUTERS & CHEMICAL ENGINEERING, Vol: 118, Pages: 143-158, ISSN: 0098-1354
Harun I, Del Rio-Chanona EA, Wagner JL, et al., 2018, Photocatalytic Production of Bisabolene from Green Microalgae Mutant: Process Analysis and Kinetic Modeling, INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, Vol: 57, Pages: 10336-10344, ISSN: 0888-5885
Iruretagoyena Ferrer D, Sunny N, Chadwick D, et al., 2018, Towards a low carbon economy via sorption enhanced water gas shift and alcohol reforming
Zhang D, del Rio-Chanona EA, Shah N, 2018, Life cycle assessments for biomass derived sustainable biopolymer & energy co-generation, Sustainable Production and Consumption, Vol: 15, Pages: 109-118, ISSN: 2352-5509
Sustainable polymers derived from biomass have been considered as promising candidates to reduce the dependency on fossil based polymers. In this study, a conceptual process design was conducted for citrus waste derived biopolymer production with energy co-generation, and its eco-friendliness was evaluated through life cycle assessment by comparison against a petroleum derived polymer production process. Based on the current research, two original conclusions were proposed. The first one is that energy-efficient separation techniques are of critical importance for the design of eco-friendly chemical processes. Only focusing on the use of sustainable feedstocks with high conversion reactions cannot guarantee an environmentally-friendly final product. The second one is that biomass should be considered not only as a raw material, but more importantly, as an energy source for the sustainable synthesis of biochemicals. In other words, a sustainable process should be designed such that a portion of biomass is used to provide clean energy for process operation, with the rest converted for product generation.
Palamae S, Choorit W, Dechatiwongse P, et al., 2018, Production of renewable biohydrogen by Rhodobacter sphaeroides S10: A comparison of photobioreactors, JOURNAL OF CLEANER PRODUCTION, Vol: 181, Pages: 318-328, ISSN: 0959-6526
Zhang D, del Rio-Chanona EA, Wagner JL, et al., 2018, Life cycle assessments of bio-based sustainable polylimonene carbonate production processes, Sustainable Production and Consumption, Vol: 14, Pages: 152-160, ISSN: 2352-5509
Biomass is a promising feedstock for the production of sustainable biopolymers, which could offer a significant reduction of the adverse environmental impacts associated with conventional petroleum-based polymers. To further evaluate their potential, this study investigated the environmental impacts associated with the production of the newly proposed biopolymer polylimonene carbonate. Different feedstocks (citrus waste and microalgae) were selected and a conceptual process design from limonene oxidation to polymer synthesis was completed. Using life cycle assessment, the potential for energy integration and the contributions of individual process sections on the overall process environmental impacts were thoroughly analysed. The results showed, that sustainable polylimonene carbonate synthesis was limited by the use of tert-butyl hydroperoxide as the limonene oxidation agent and consequently, a more environmentally-friendly and energy-efficient limonene oxidation method should be developed. Based on the economic analysis, the polymer cost was estimated to range from $1.36 to $1.51 kg −1 , comparable to the costs of petrol-based polystyrene ($1.2 to $1.6 kg −1 ). Moreover, this study found that both feedstock selection and the biowaste treatment method have significant effects on the process environmental impacts, and a carbon negative process was achieved when applying the waste biomass for electricity generation. Therefore, it was concluded that future process designs should combine polymer production with the co-generation of energy from waste biomass.
del Rio-Chanona EA, Liu J, Wagner JL, et al., 2018, Dynamic modeling of green algae cultivation in a photobioreactor for sustainable biodiesel production, Biotechnology and Bioengineering, Vol: 115, Pages: 359-370, ISSN: 1097-0290
Biodiesel produced from microalgae has been extensively studied due to its potentially outstanding advantages over traditional transportation fuels. In order to facilitate its industrialization and improve the process profitability, it is vital to construct highly accurate models capable of predicting the complex behavior of the investigated biosystem for process optimization and control, which forms the current research goal. Three original contributions are described in this paper. Firstly, a dynamic model is constructed to simulate the complicated effect of light intensity, nutrient supply and light attenuation on both biomass growth and biolipid production. Secondly, chlorophyll fluorescence, an instantly measurable variable and indicator of photosynthetic activity, is embedded into the model to monitor and update model accuracy especially for the purpose of future process optimal control, and its correlation between intracellular nitrogen content is quantified, which to the best of our knowledge has never been addressed so far. Thirdly, a thorough experimental verification is conducted under different scenarios including both continuous illumination and light/dark cycle conditions to testify the model predictive capability particularly for long-term operation, and it is concluded that the current model is characterized by a high level of predictive capability. Based on the model, the optimal light intensity for algal biomass growth and lipid synthesis is estimated. This work, therefore, paves the way to forward future process design and real-time optimization.
Jing K, Tang Y, Yao C, et al., 2018, Overproduction of L-tryptophan via simultaneous feed of glucose and anthranilic acid from recombinant <i>Escherichia coli</i> W3110: Kinetic modeling and process scale-up, BIOTECHNOLOGY AND BIOENGINEERING, Vol: 115, Pages: 371-381, ISSN: 0006-3592
- Author Web Link
- Cite
- Citations: 26
Estrada-Wiese D, del Rio-Chanona EA, del Rio JA, 2018, Stochastic optimization of broadband reflecting photonic structures, SCIENTIFIC REPORTS, Vol: 8, ISSN: 2045-2322
- Author Web Link
- Cite
- Citations: 15
Zhang D, del Rio-Chanona EA, 2018, A Bilevel Programming Approach for the Dynamic Optimization of Cyanobacterial C-phycocyanin Production under Uncertainty, Computer Aided Chemical Engineering, Pages: 535-540
C-phycocyanin is a high-value bioproduct synthesized by cyanobacterium Arthrospira platensis with a significant global market demand given its applications in the pharmaceutical, food and colorant industries. Unfortunately, its biosynthesis is currently characterized by low productivity and large uncertainty during the production process. High variability and unreliable expectations on product yields substantially hinder the industrialization of microorganism derived biochemicals as they present a risk to the profitability and safety of the underlying systems. Therefore, in this work, we propose a robust optimization approach to determine the lower and upper product yield expectations for the sustainable production of C-phycocyanin. Kinetic modeling is adopted in this study as a tool for fast prototyping, prediction and optimization of chemical and biochemical processes. On the upside, parameters in bioprocess kinetic models are used as a simplification of the complex metabolic networks to enable the simulation, design and control of the process. On the downside, this conglomeration of parameters may result in significant model uncertainty. To address this challenge, we formulate a bilevel max-min optimization problem to obtain the worst-case scenario of our system given the uncertainty on the model parameters. By constructing parameter confidence ellipsoids, we determined the feasible region along which the parameters can minimize the system's performance, while nutrient and light controls are used to maximize the biorenewable production. The inner minimization problem is embedded by means of the optimality conditions into the upper maximization problem and hence both are solved simultaneously. Through this approach, we determined pessimistic and optimistic scenarios for the bioproduction of C-phycocyanin and hence compute reliable expectations on the yield and profit of the process.
Zhang D, del Rio-Chanona EA, Shah N, 2018, Life cycle assessment of bio-based sustainable polylimonene carbonate production processes, Computer Aided Chemical Engineering, Pages: 1693-1698
Biomass derived polymers are considered as promising candidates to replace petroleum based polymers due to their potential environmental friendliness. To facilitate their application, in this study, a newly proposed biopolymer, polylimonene carbonate, was chosen as the representative to investigate the environmental impacts of the biopolymer production process. Different feedstocks (citrus waste and microalgae) were selected and a comprehensive process design from limonene oxidation to polymer synthesis was completed. Through life cycle assessment, effects of biomass treatment methods, energy integration, and use of solvents on the process environmental impacts were thoroughly discussed. It was found that for sustainable polylimonene carbonate synthesis, a more environmentally-friendly and energy-efficient limonene oxidation method should be developed. Based on the economic analysis, the polymer's cost was estimated to be around 1.36 to 1.51 $/kg, indicating its great potential as a substitute for petrol-based polystyrene. Moreover, this study found that both feedstock selection and biowaste treatment method significantly affect the process environmental impacts, and a carbon negative biopolymer can be achieved when the remaining waste is used for energy generation. Therefore, a new concept that considers CO2 as an efficient solar energy carrier for future sustainable process design is proposed in this study.
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.