The Data-driven Optimization of bi-level Mixed-Integer NOnlinear problems (DOMINO) framework is presented for addressing the optimization of bi-level mixed-integer nonlinear programming problems. In ...this framework, bi-level optimization problems are approximated as single-level optimization problems by collecting samples of the upper-level objective and solving the lower-level problem to global optimality at those sampling points. This process is done through the integration of the DOMINO framework with a grey-box optimization solver to perform design of experiments on the upper-level objective, and to consecutively approximate and optimize bi-level mixed-integer nonlinear programming problems that are challenging to solve using exact methods. The performance of DOMINO is assessed through solving numerous bi-level benchmark problems, a land allocation problem in Food-Energy-Water Nexus, and through employing different data-driven optimization methodologies, including both local and global methods. Although this data-driven approach cannot provide a theoretical guarantee to global optimality, we present an algorithmic advancement that can guarantee feasibility to large-scale bi-level optimization problems when the lower-level problem is solved to global optimality at convergence.
•We present B-POP, a toolbox featuring:− bi-level programming solvers for linear and quadratic programming problems, and their mixed-integer counter-parts, − a versatile problem generator capable of ...creating random bi-level problems of arbitrary size, − a library of bi-level programming test problems.•We also present applications of the toolbox for a supply chain planning problem and a hierarchical model predictive control.
In this manuscript we present B-POP, a MATLAB toolbox for bi-level optimization through multi-parametric programming. It features i) bi-level programming solvers for linear and quadratic programming problems, and their mixed-integer counter-parts, ii) a versatile problem generator capable of creating random bi-level problems of arbitrary size, and iii) a library of bi-level programming test problems. The features of B-POP are demonstrated through detailed computational studies showing the capabilities and the scalability of the embedded algorithms. Moreover, two applications, i) a supply chain planning problem, and ii) a hierarchical model predictive control of a reactor system are chosen to show the applicability of bi-level programming and B-POP.
In this contribution, we present a high-fidelity dynamic model of an industrial dividing wall column and the application of explicit model predictive control for its regulation. Our study involves ...the separation of methyl methacrylate from a quaternary mixture. The process includes a dividing wall column coupled with a decanter, which results in highly concentrated methyl methacrylate and water streams from the middle side draw of the column and the decanter, respectively. An equation-oriented mathematical model of the process is developed and presented in detail, where non-ideal thermodynamic calculations are adopted to describe the complex nature of the component interactions. The operability of the process is enhanced by the synthesis and application of an explicit model predictive controller, which is used to track the purity specifications of the product. Our results demonstrate that the proposed modeling and control approach can be utilized for the optimal online operation of the studied system.
This book is based on the Modelling, Control and Optimization of Biomedical Systems (MOBILE) project, which was created to derive intelligent computer model-based systems for optimization of ...biomedical drug delivery systems in the cases of diabetes, anaesthesia, and blood cancer. These systems can ensure reliable and fast calculation of the optimal drug dosage without the need for an online computer - while taking into account the specifics and constraints of the patient model, flexibility to adapt to changing patient characteristics and incorporation of the physician's performance criteria, and maintaining the safety of the patients.
This book covers: mathematical modelling of drug delivery systems; model analysis, parameter estimation, and approximation; optimization and control; sensitivity analysis & model reduction; multi-parametric programming and model predictive control; estimation techniques; physiologically-based patient model; control design for volatile anaesthesia; multiparametric model based approach to intravenous anaesthesia; hybrid model predictive control strategies; and more.
Support vector machines (SVMs) based optimization framework is presented for the data‐driven optimization of numerically infeasible differential algebraic equations (DAEs) without the full ...discretization of the underlying first‐principles model. By formulating the stability constraint of the numerical integration of a DAE system as a supervised classification problem, we are able to demonstrate that SVMs can accurately map the boundary of numerical infeasibility. The necessity of this data‐driven approach is demonstrated on a two‐dimensional motivating example, where highly accurate SVM models are trained, validated, and tested using the data collected from the numerical integration of DAEs. Furthermore, this methodology is extended and tested for a multidimensional case study from reaction engineering (i.e., thermal cracking of natural gas liquids). The data‐driven optimization of this complex case study is explored through integrating the SVM models with a constrained global grey‐box optimization algorithm, namely the ARGONAUT framework.
This article provides a systematic review of recent progress in optimization-based process synthesis. First, we discuss multiscale modeling frameworks featuring targeting approaches, phenomena-based ...modeling, unit operation-based modeling, and hybrid modeling. Next, we present the expanded scope of process synthesis objectives, highlighting the considerations of sustainability and operability to assure cost-competitive production in an increasingly dynamic market with growing environmental awareness. Then, we review advances in optimization algorithms and tools, including emerging machine learning-and quantum computing-assisted approaches. We conclude by summarizing the advances in and perspectives for process synthesis strategies.
The construction and expansion of steam cracking plants and feedstock diversification have resulted in a significant demand for the numerical simulation and optimization of models to achieve ...molecular refining and intelligent manufacturing. However, the existing models cannot be widely applied in industrial practice because of the high computational expense, time consumption, and data size requirements. In this paper, a high-performance optimization process, which integrates transfer learning and a heuristic algorithm, is proposed for the optimization of furnaces for various feedstocks. An effective transfer learning structure based on a motif feature of the reaction network is designed, and a subsequent product distribution prediction program is compiled. Then, a hybrid genetic algorithm and particle swarm optimization method are applied for the coil outlet temperature curve optimization using the derived prediction model, and the results are obtained for different pricing policies of products. The results are determined based on the weight coefficients of prices for different products and could be further explained by the yield distribution pattern and reaction mechanism.
Maintenance can improve the availability of aging production systems and prevent process safety incidents. However, because of system complexity, resource allocation is nontrivial. This research ...developed and applied a framework to obtain optimal future-failure aware and safety-conscious production and maintenance schedules. Ensembles of nonlinear support vector machine classification models were leveraged to predict the time and probability of future equipment failure from equipment condition data. Multiobjective optimization of expected profit and a safety metric was then used to determine optimal process and maintenance schedules. The results of this research were that the ensemble models had an average accuracy and an F1-score of 0.987, that the ensemble models were more accurate and sensitive than the individual classifiers by 3 percentage points, and that the Pareto-optimal process and maintenance schedules were obtained, providing alternative solutions to the decision maker. This research described optimal resource allocation to help improve safety and system effectiveness.
•A mathematical model for the drug distribution and drug effect of intravenous anaesthesia was discussed.•Different estimation techniques have been designed, implemented and tested: Kalman filter, ...offline MHE and online MHE.•The state estimators have been implemented simultaneously with mp-MPC and simulated comparatively.•The developed strategies were tested both with and without noise influencing the output.•Two main challenges in the control of DOA: nonlinearity and inter-and intra- patient variability are successfully addressed.
In this work we present different design strategies towards model based simultaneous multiparametric model predictive control and state estimation for intravenous anaesthesia. We first present a detailed compartmental mathematical model featuring a pharmacokinetic and a pharmacodynamics part. Due to unavailability of data and information, different estimation techniques are formulated and implemented. Furthermore these estimation techniques are implemented simultaneously with multiparametric model predictive controllers and tested for real patient data under the assumption that the output is either noise free or corrupted by noise. The derived control schemes are able to deal with two of the main challenges in controlling the depth of anaesthesia: (i) model nonlinearity and (ii) inter- and intra- patient variability.