The Experts below are selected from a list of 3225 Experts worldwide ranked by ideXlab platform
Megan Jobson - One of the best experts on this subject based on the ideXlab platform.
-
optimal design of flexible heat integrated Crude Oil Distillation units using surrogate models
Chemical Engineering Research & Design, 2021Co-Authors: Megan Jobson, Dauda Ibrahim, Gonzalo GuillengosalbezAbstract:Abstract The design of Distillation columns often considers a given fixed feedstock and nominal operating conditions. Here we present an optimization-based approach for the optimal design of these units considering a flexible operation under a range of potential feedstocks. Our method combines an artificial neural network with a support vector machine to model the Crude Oil Distillation unit. The artificial neural network model predicts the performance of the Distillation unit for a given Crude Oil feedstock whilst the support vector machine classifier filters out infeasible design alternatives from the solution space (i.e., designs that are unlikely to converge when simulated using a rigorous model). The inputs to the artificial neural network include the column structural variables and operating conditions, whilst the outputs are process variables linked to the column performance. The artificial neural network models and support vector machines constructed for different Crude Oil feedstocks are integrated into a two-stage optimization framework in order to optimize the column structural variables and operating conditions, where the minimum utility demand is estimated using the pinch analysis. An effective solution strategy that combines stochastic and deterministic optimization algorithms is applied to search for economically viable and flexible design alternatives that can operate over a given range of Crude Oil feedstocks while satisfying the product quality specifications. The capabilities of the proposed approach are illustrated using an industrially-relevant case study, where we clearly show that the proposed approach can identify design alternatives capable of handling various feedstocks effectively.
-
optimization based design of Crude Oil Distillation units using surrogate column models and a support vector machine
Chemical Engineering Research & Design, 2018Co-Authors: Dauda Ibrahim, Megan Jobson, Jie Li, Gonzalo GuillengosalbezAbstract:Abstract This paper presents a novel optimization-based approach for the design of heat-integrated Crude Oil Distillation units, which are widely used in refineries. The methodology presented combines, within a unified framework, surrogate Distillation column models based on artificial neural networks, feasibility constraints constructed using a support vector machine, and pinch analysis to maximize heat recovery, in order to optimize the Distillation column configuration and its operating conditions. The inputs to the surrogate column model are given by the column structure and operating conditions, while the outputs are related to the column performance. The support vector machine classifier filters infeasible design alternatives from the search space, thus reducing computational time, and ultimately improves the quality of the final solution. The overall optimization problem takes the form of a mixed-integer nonlinear program, which is solved by a genetic algorithm that seeks the design and operating variables values that minimize the total annualized cost. The capabilities of the proposed approach are illustrated using an industrially–relevant case study. Numerical results show that promising design alternatives can be obtained using the proposed method. The approach can help engineers to design and operate petroleum refineries optimally, where these are expected to continue to play a major role in the energy mix for some years.
-
simulation optimization based design of Crude Oil Distillation systems with preflash units
Industrial & Engineering Chemistry Research, 2018Co-Authors: Minerva Ledezmamartinez, Megan Jobson, Robin SmithAbstract:In energy-intensive Crude Oil Distillation systems, with their Distillation units and heat recovery systems, preflash units can create opportunities to reduce demand for fired heating and increase heat recovery. As holistic, systematic design methodologies are not available for design of Crude Oil Distillation systems with preflash units, this work proposes a simulation-based design approach, where the objective is to minimize fired heat demand of the system. The approach exploits interactions between the separation and heat recovery systems, considering product quality and yield. Rigorous Distillation models in Aspen HYSYS, pinch analysis, and randomized optimization (a genetic algorithm) are employed, via a MatLab interface, to minimize hot utility demand by optimizing operating variables and one structural variable, namely, the feed location of the preflash vapor. A case study demonstrates the approach, showing that a preflash unit can reduce hot utility demand but that the system is vulnerable to yiel...
-
optimization based design of Crude Oil Distillation units using rigorous simulation models
Industrial & Engineering Chemistry Research, 2017Co-Authors: Dauda Ibrahim, Megan Jobson, Gonzalo GuillengosalbezAbstract:The complex nature of Crude Oil Distillation units, including their interactions with the associated heat recovery network and the large number of degrees of freedom, makes their optimization a very challenging task. We address here the design of a complex Crude Oil Distillation unit by integrating rigorous tray-by-tray column simulation using commercial process simulation software with an optimization algorithm. While several approaches were proposed to tackle this problem, most of them relied on simplified models that are unable to deal with the whole complexity of the problem. The design problem is herein formulated to consider both structural variables (the number of trays in each column section) and operational variables (feed inlet temperature, pump-around duties and temperature drops, stripping steam flow rates and reflux ratio). A simulation-optimization approach for designing such a complex system is applied, which searches for the best design while accounting for heat recovery opportunities usin...
-
surrogate models combined with a support vector machine for the optimized design of a Crude Oil Distillation unit using genetic algorithms
Computer-aided chemical engineering, 2017Co-Authors: Dauda Ibrahim, Megan Jobson, Jie Li, Gonzalo GuillengosalbezAbstract:Abstract This paper introduces a novel optimization-based framework for the design of a Crude Oil Distillation unit. The approach presented integrates surrogate models based on artificial neural networks (ANN) with feasibility constraints generated using a support vector machine (SVM) in order to optimise the column configuration and its operating conditions. The SVM filters infeasible design options from the solution space of the design problem, which reduces the computational effort and ultimately improves the quality of the final solution. Rigorous process simulations are used to build the surrogate model, while pinch analysis is employed to determine the maximum heat recovery and minimum utility costs. The objective is to minimise the total annualized cost, which is optimised by combining a genetic algorithm with the surrogate model. The approach is illustrated in an industrially relevant case study.
Robin Smith - One of the best experts on this subject based on the ideXlab platform.
-
simulation optimization based design of Crude Oil Distillation systems with preflash units
Industrial & Engineering Chemistry Research, 2018Co-Authors: Minerva Ledezmamartinez, Megan Jobson, Robin SmithAbstract:In energy-intensive Crude Oil Distillation systems, with their Distillation units and heat recovery systems, preflash units can create opportunities to reduce demand for fired heating and increase heat recovery. As holistic, systematic design methodologies are not available for design of Crude Oil Distillation systems with preflash units, this work proposes a simulation-based design approach, where the objective is to minimize fired heat demand of the system. The approach exploits interactions between the separation and heat recovery systems, considering product quality and yield. Rigorous Distillation models in Aspen HYSYS, pinch analysis, and randomized optimization (a genetic algorithm) are employed, via a MatLab interface, to minimize hot utility demand by optimizing operating variables and one structural variable, namely, the feed location of the preflash vapor. A case study demonstrates the approach, showing that a preflash unit can reduce hot utility demand but that the system is vulnerable to yiel...
-
retrofit of heat integrated Crude Oil Distillation columns
Chemical Engineering Research & Design, 2015Co-Authors: Victor M Enriquezgutierrez, Megan Jobson, Lluvia M Ochoaestopier, Robin SmithAbstract:Engineering projects to increase the capacity of existing heat-integrated Crude Oil Distillation columns are commonplace. Retrofit projects aim to exploit the processing capacity of existing units by changing operating parameters and/or modifying equipment. Operational modifications can be effective and usually incur little capital expenditure, but equipment changes may also be needed to achieve retrofit objectives. Existing retrofit methodologies for Crude Oil Distillation systems mainly focus on increasing heat recovery, increasing Crude Oil throughput and/or increasing the yield of most valuable products by optimising column operating parameters. However, methodologies that also consider hardware modifications are lacking. The present work proposes a systematic retrofit methodology based on Distillation column and heat exchanger network (HEN) simulation. Hydraulic correlations are used to consider replacing existing Distillation column internals with high-capacity trays and/or structured packings. Industrially relevant case studies illustrate the benefits of the proposed methodology to analyse and assess hardware modifications for the retrofit of Distillation systems when increasing capacity.
-
optimization of heat integrated Crude Oil Distillation systems part ii heat exchanger network retrofit model
Industrial & Engineering Chemistry Research, 2015Co-Authors: Lluvia M Ochoaestopier, Megan Jobson, Lu Chen, Clemente A Rodriguezforero, Robin SmithAbstract:This is the second part of a series that applies optimization to maximize the productivity and minimize operating costs of existing heat-integrated Crude Oil Distillation systems. This paper presents a two-level retrofit approach for heat exchanger networks. In the first level, simulated annealing proposes topology modifications to the existing network (e.g., adding, removing, and relocating heat exchangers; changing the heat loads of heat exchangers, adding and removing stream splitters, and changing the split fraction of stream splitters). In the second level, a repair algorithm addresses the violation of constraints. These constraints consider the minimum temperature approach, stream enthalpy balances, and existing heat transfer areas. The repair algorithm is formulated as a nonlinear least-squares problem. Temperature-dependent thermal properties are considered in this work for the accurate prediction of stream temperatures. Two case studies illustrate the application of the proposed methodology to decrease total annualized costs.
-
the use of reduced models for design and optimisation of heat integrated Crude Oil Distillation systems
Energy, 2014Co-Authors: Lluvia M Ochoaestopier, Megan Jobson, Robin SmithAbstract:The importance of exploiting degrees of freedom within a Crude Oil Distillation process for improving energy performance has been a feature of process integration from the earliest days. Combining process changes with changes to the heat recovery system leads to far better results, compared with changes to the heat recovery system alone. However, in order to obtain the best results, the Distillation process and heat exchanger network need to be optimised simultaneously. Whilst in principle this is straightforward, there are many difficulties. Methods for the optimisation of heat exchanger networks are well developed. In these methods, heat exchanger network models are based on network details, such as stream connections between heat exchangers, heat transfer area of individual units, etc. The consideration of these network details is important to design and optimise Crude Oil Distillation systems. On the other hand, the Distillation process model to be coupled with the heat exchanger network model needs to be simple and robust enough to be included in an optimisation framework. If Distillation models and heat recovery models can be combined effectively, then there are not just opportunities for design and retrofit, but also for operational optimisation. One of the big challenges to progress the application of this approach is the effective generation of reduced Distillation models. Short-cut Distillation models can be used, but many other options are available, such as the use of artificial neural networks. This paper reviews various Crude Oil Distillation modelling approaches and highlights the areas of application of these different approaches. An example illustrates the computational performance of reduced and rigorous Crude Oil Distillation models.
-
a design methodology for retrofit of Crude Oil Distillation systems
Computer-aided chemical engineering, 2014Co-Authors: Victor M Enriquezgutierrez, Megan Jobson, Robin SmithAbstract:Retrofit of Crude Oil Distillation systems is a non-trivial problem with many degrees of freedom and constraints. This work proposes a systematic retrofit methodology for increasing the throughput to Crude Oil Distillation systems, embedded in a computational tool with mass and energy balance results from rigorous simulations, hydraulic correlations for valve trays and structured packings and a retrofit model for heat exchanger networks. The feasibility of retrofit options is assessed against constraints related to product specifications, jet flooding and liquid load per weir length in the main fractionator and side strippers and the required area for heat exchangers in the heat exchanger network (HEN). The methodology is applied to an existing Crude Oil Distillation system; the results show the impact of increasing throughput on column hydraulics and heat transfer area requirements. Retrofit solutions are proposed for relieving hydraulic bottlenecks and minimizing impact on the HEN by varying column operating conditions.
Lluvia M Ochoaestopier - One of the best experts on this subject based on the ideXlab platform.
-
retrofit of heat integrated Crude Oil Distillation columns
Chemical Engineering Research & Design, 2015Co-Authors: Victor M Enriquezgutierrez, Megan Jobson, Lluvia M Ochoaestopier, Robin SmithAbstract:Engineering projects to increase the capacity of existing heat-integrated Crude Oil Distillation columns are commonplace. Retrofit projects aim to exploit the processing capacity of existing units by changing operating parameters and/or modifying equipment. Operational modifications can be effective and usually incur little capital expenditure, but equipment changes may also be needed to achieve retrofit objectives. Existing retrofit methodologies for Crude Oil Distillation systems mainly focus on increasing heat recovery, increasing Crude Oil throughput and/or increasing the yield of most valuable products by optimising column operating parameters. However, methodologies that also consider hardware modifications are lacking. The present work proposes a systematic retrofit methodology based on Distillation column and heat exchanger network (HEN) simulation. Hydraulic correlations are used to consider replacing existing Distillation column internals with high-capacity trays and/or structured packings. Industrially relevant case studies illustrate the benefits of the proposed methodology to analyse and assess hardware modifications for the retrofit of Distillation systems when increasing capacity.
-
optimization of heat integrated Crude Oil Distillation systems part iii optimization framework
Industrial & Engineering Chemistry Research, 2015Co-Authors: Lluvia M Ochoaestopier, Megan JobsonAbstract:This paper is the third of a three-part series that applies optimization to maximize the productivity and minimize operating costs of heat-integrated Crude Oil Distillation systems. The approach presented in this paper implements simulation models for the Distillation process and heat exchanger network (HEN), and HEN retrofit models into the overall optimization framework. The optimization approach is formulated in two levels. In the first level, simulated annealing is used to optimize the operating conditions of the Crude Oil Distillation unit (e.g., Distillation products and stripping steam flow rates, pump-around duties and temperature drops, and furnace exit temperatures) and to propose HEN structural modifications (e.g., adding, removing, relocating heat exchangers; adding, removing stream splitters, etc.). The second level is a nonlinear least-squares problem used to enforce HEN constraints. Three case studies illustrate the application of this approach to increase net profit and reduce annualized c...
-
optimization of heat integrated Crude Oil Distillation systems part i the Distillation model
Industrial & Engineering Chemistry Research, 2015Co-Authors: Lluvia M Ochoaestopier, Megan JobsonAbstract:This work presents a methodology for optimizing heat-integrated Crude Oil Distillation systems. Part I of this three-part series presents a modeling strategy where artificial neural networks are used to represent the Distillation process. Part II presents a new methodology to retrofit heat exchanger networks (HENs) and Part III presents the application of this Distillation model to perform operational optimization of the Crude Oil Distillation unit while proposing retrofit modifications to the associated HEN. Independent variables of the Distillation model include flow rates of products, stripping steam, pump-around specifications, and furnace exit temperature. Dependent variables include those related to product quality, and temperatures, duties, and heat capacities of process streams involved in heat integration. The resulting neural network model is able to overcome convergence problems presented by rigorous or simplified models. Simulation time is significantly improved using neural networks, compared...
-
optimization of heat integrated Crude Oil Distillation systems part ii heat exchanger network retrofit model
Industrial & Engineering Chemistry Research, 2015Co-Authors: Lluvia M Ochoaestopier, Megan Jobson, Lu Chen, Clemente A Rodriguezforero, Robin SmithAbstract:This is the second part of a series that applies optimization to maximize the productivity and minimize operating costs of existing heat-integrated Crude Oil Distillation systems. This paper presents a two-level retrofit approach for heat exchanger networks. In the first level, simulated annealing proposes topology modifications to the existing network (e.g., adding, removing, and relocating heat exchangers; changing the heat loads of heat exchangers, adding and removing stream splitters, and changing the split fraction of stream splitters). In the second level, a repair algorithm addresses the violation of constraints. These constraints consider the minimum temperature approach, stream enthalpy balances, and existing heat transfer areas. The repair algorithm is formulated as a nonlinear least-squares problem. Temperature-dependent thermal properties are considered in this work for the accurate prediction of stream temperatures. Two case studies illustrate the application of the proposed methodology to decrease total annualized costs.
-
the use of reduced models for design and optimisation of heat integrated Crude Oil Distillation systems
Energy, 2014Co-Authors: Lluvia M Ochoaestopier, Megan Jobson, Robin SmithAbstract:The importance of exploiting degrees of freedom within a Crude Oil Distillation process for improving energy performance has been a feature of process integration from the earliest days. Combining process changes with changes to the heat recovery system leads to far better results, compared with changes to the heat recovery system alone. However, in order to obtain the best results, the Distillation process and heat exchanger network need to be optimised simultaneously. Whilst in principle this is straightforward, there are many difficulties. Methods for the optimisation of heat exchanger networks are well developed. In these methods, heat exchanger network models are based on network details, such as stream connections between heat exchangers, heat transfer area of individual units, etc. The consideration of these network details is important to design and optimise Crude Oil Distillation systems. On the other hand, the Distillation process model to be coupled with the heat exchanger network model needs to be simple and robust enough to be included in an optimisation framework. If Distillation models and heat recovery models can be combined effectively, then there are not just opportunities for design and retrofit, but also for operational optimisation. One of the big challenges to progress the application of this approach is the effective generation of reduced Distillation models. Short-cut Distillation models can be used, but many other options are available, such as the use of artificial neural networks. This paper reviews various Crude Oil Distillation modelling approaches and highlights the areas of application of these different approaches. An example illustrates the computational performance of reduced and rigorous Crude Oil Distillation models.
Gonzalo Guillengosalbez - One of the best experts on this subject based on the ideXlab platform.
-
optimal design of flexible heat integrated Crude Oil Distillation units using surrogate models
Chemical Engineering Research & Design, 2021Co-Authors: Megan Jobson, Dauda Ibrahim, Gonzalo GuillengosalbezAbstract:Abstract The design of Distillation columns often considers a given fixed feedstock and nominal operating conditions. Here we present an optimization-based approach for the optimal design of these units considering a flexible operation under a range of potential feedstocks. Our method combines an artificial neural network with a support vector machine to model the Crude Oil Distillation unit. The artificial neural network model predicts the performance of the Distillation unit for a given Crude Oil feedstock whilst the support vector machine classifier filters out infeasible design alternatives from the solution space (i.e., designs that are unlikely to converge when simulated using a rigorous model). The inputs to the artificial neural network include the column structural variables and operating conditions, whilst the outputs are process variables linked to the column performance. The artificial neural network models and support vector machines constructed for different Crude Oil feedstocks are integrated into a two-stage optimization framework in order to optimize the column structural variables and operating conditions, where the minimum utility demand is estimated using the pinch analysis. An effective solution strategy that combines stochastic and deterministic optimization algorithms is applied to search for economically viable and flexible design alternatives that can operate over a given range of Crude Oil feedstocks while satisfying the product quality specifications. The capabilities of the proposed approach are illustrated using an industrially-relevant case study, where we clearly show that the proposed approach can identify design alternatives capable of handling various feedstocks effectively.
-
optimization based design of Crude Oil Distillation units using surrogate column models and a support vector machine
Chemical Engineering Research & Design, 2018Co-Authors: Dauda Ibrahim, Megan Jobson, Jie Li, Gonzalo GuillengosalbezAbstract:Abstract This paper presents a novel optimization-based approach for the design of heat-integrated Crude Oil Distillation units, which are widely used in refineries. The methodology presented combines, within a unified framework, surrogate Distillation column models based on artificial neural networks, feasibility constraints constructed using a support vector machine, and pinch analysis to maximize heat recovery, in order to optimize the Distillation column configuration and its operating conditions. The inputs to the surrogate column model are given by the column structure and operating conditions, while the outputs are related to the column performance. The support vector machine classifier filters infeasible design alternatives from the search space, thus reducing computational time, and ultimately improves the quality of the final solution. The overall optimization problem takes the form of a mixed-integer nonlinear program, which is solved by a genetic algorithm that seeks the design and operating variables values that minimize the total annualized cost. The capabilities of the proposed approach are illustrated using an industrially–relevant case study. Numerical results show that promising design alternatives can be obtained using the proposed method. The approach can help engineers to design and operate petroleum refineries optimally, where these are expected to continue to play a major role in the energy mix for some years.
-
optimization based design of Crude Oil Distillation units using rigorous simulation models
Industrial & Engineering Chemistry Research, 2017Co-Authors: Dauda Ibrahim, Megan Jobson, Gonzalo GuillengosalbezAbstract:The complex nature of Crude Oil Distillation units, including their interactions with the associated heat recovery network and the large number of degrees of freedom, makes their optimization a very challenging task. We address here the design of a complex Crude Oil Distillation unit by integrating rigorous tray-by-tray column simulation using commercial process simulation software with an optimization algorithm. While several approaches were proposed to tackle this problem, most of them relied on simplified models that are unable to deal with the whole complexity of the problem. The design problem is herein formulated to consider both structural variables (the number of trays in each column section) and operational variables (feed inlet temperature, pump-around duties and temperature drops, stripping steam flow rates and reflux ratio). A simulation-optimization approach for designing such a complex system is applied, which searches for the best design while accounting for heat recovery opportunities usin...
-
surrogate models combined with a support vector machine for the optimized design of a Crude Oil Distillation unit using genetic algorithms
Computer-aided chemical engineering, 2017Co-Authors: Dauda Ibrahim, Megan Jobson, Jie Li, Gonzalo GuillengosalbezAbstract:Abstract This paper introduces a novel optimization-based framework for the design of a Crude Oil Distillation unit. The approach presented integrates surrogate models based on artificial neural networks (ANN) with feasibility constraints generated using a support vector machine (SVM) in order to optimise the column configuration and its operating conditions. The SVM filters infeasible design options from the solution space of the design problem, which reduces the computational effort and ultimately improves the quality of the final solution. Rigorous process simulations are used to build the surrogate model, while pinch analysis is employed to determine the maximum heat recovery and minimum utility costs. The objective is to minimise the total annualized cost, which is optimised by combining a genetic algorithm with the surrogate model. The approach is illustrated in an industrially relevant case study.
Dauda Ibrahim - One of the best experts on this subject based on the ideXlab platform.
-
optimal design of flexible heat integrated Crude Oil Distillation units using surrogate models
Chemical Engineering Research & Design, 2021Co-Authors: Megan Jobson, Dauda Ibrahim, Gonzalo GuillengosalbezAbstract:Abstract The design of Distillation columns often considers a given fixed feedstock and nominal operating conditions. Here we present an optimization-based approach for the optimal design of these units considering a flexible operation under a range of potential feedstocks. Our method combines an artificial neural network with a support vector machine to model the Crude Oil Distillation unit. The artificial neural network model predicts the performance of the Distillation unit for a given Crude Oil feedstock whilst the support vector machine classifier filters out infeasible design alternatives from the solution space (i.e., designs that are unlikely to converge when simulated using a rigorous model). The inputs to the artificial neural network include the column structural variables and operating conditions, whilst the outputs are process variables linked to the column performance. The artificial neural network models and support vector machines constructed for different Crude Oil feedstocks are integrated into a two-stage optimization framework in order to optimize the column structural variables and operating conditions, where the minimum utility demand is estimated using the pinch analysis. An effective solution strategy that combines stochastic and deterministic optimization algorithms is applied to search for economically viable and flexible design alternatives that can operate over a given range of Crude Oil feedstocks while satisfying the product quality specifications. The capabilities of the proposed approach are illustrated using an industrially-relevant case study, where we clearly show that the proposed approach can identify design alternatives capable of handling various feedstocks effectively.
-
optimization based design of Crude Oil Distillation units using surrogate column models and a support vector machine
Chemical Engineering Research & Design, 2018Co-Authors: Dauda Ibrahim, Megan Jobson, Jie Li, Gonzalo GuillengosalbezAbstract:Abstract This paper presents a novel optimization-based approach for the design of heat-integrated Crude Oil Distillation units, which are widely used in refineries. The methodology presented combines, within a unified framework, surrogate Distillation column models based on artificial neural networks, feasibility constraints constructed using a support vector machine, and pinch analysis to maximize heat recovery, in order to optimize the Distillation column configuration and its operating conditions. The inputs to the surrogate column model are given by the column structure and operating conditions, while the outputs are related to the column performance. The support vector machine classifier filters infeasible design alternatives from the search space, thus reducing computational time, and ultimately improves the quality of the final solution. The overall optimization problem takes the form of a mixed-integer nonlinear program, which is solved by a genetic algorithm that seeks the design and operating variables values that minimize the total annualized cost. The capabilities of the proposed approach are illustrated using an industrially–relevant case study. Numerical results show that promising design alternatives can be obtained using the proposed method. The approach can help engineers to design and operate petroleum refineries optimally, where these are expected to continue to play a major role in the energy mix for some years.
-
optimization based design of Crude Oil Distillation units using rigorous simulation models
Industrial & Engineering Chemistry Research, 2017Co-Authors: Dauda Ibrahim, Megan Jobson, Gonzalo GuillengosalbezAbstract:The complex nature of Crude Oil Distillation units, including their interactions with the associated heat recovery network and the large number of degrees of freedom, makes their optimization a very challenging task. We address here the design of a complex Crude Oil Distillation unit by integrating rigorous tray-by-tray column simulation using commercial process simulation software with an optimization algorithm. While several approaches were proposed to tackle this problem, most of them relied on simplified models that are unable to deal with the whole complexity of the problem. The design problem is herein formulated to consider both structural variables (the number of trays in each column section) and operational variables (feed inlet temperature, pump-around duties and temperature drops, stripping steam flow rates and reflux ratio). A simulation-optimization approach for designing such a complex system is applied, which searches for the best design while accounting for heat recovery opportunities usin...
-
surrogate models combined with a support vector machine for the optimized design of a Crude Oil Distillation unit using genetic algorithms
Computer-aided chemical engineering, 2017Co-Authors: Dauda Ibrahim, Megan Jobson, Jie Li, Gonzalo GuillengosalbezAbstract:Abstract This paper introduces a novel optimization-based framework for the design of a Crude Oil Distillation unit. The approach presented integrates surrogate models based on artificial neural networks (ANN) with feasibility constraints generated using a support vector machine (SVM) in order to optimise the column configuration and its operating conditions. The SVM filters infeasible design options from the solution space of the design problem, which reduces the computational effort and ultimately improves the quality of the final solution. Rigorous process simulations are used to build the surrogate model, while pinch analysis is employed to determine the maximum heat recovery and minimum utility costs. The objective is to minimise the total annualized cost, which is optimised by combining a genetic algorithm with the surrogate model. The approach is illustrated in an industrially relevant case study.