Response surface methods based in artificial intelligence for superstructure thermoeconomic optimization of waste heat recovery systems in a large internal combustion engine

Araújo, Leonardo Rodrigues de; Morawski, Alexandre Persuhn; Barone, Marcelo Aiolfi; Rocha, Helder R. O.; Donatelli, João Luiz Marcon; Santos, José Joaquim Conceição Soares

doi:10.1016/j.enconman.2022.116275

Cited by 8 publications

(3 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This streamlined approach boasts straightforward programming and consistently delivers favorable outcomes, even in scenarios involving complex, multimodal functions. Moreover, the scientific community has exhibited significant interest in the application of this optimization technique, as evidenced by references [20,[24][25][26][27]36,37]. The genetic algorithm method integrated into EES is an adaptation of the publicly available Pikaia optimization program (version 1.2, April 2002), which was originally developed by Paul Charbonneau and Barry Knapp at The National Center for Atmospheric Research (NCAR).…”

Section: Genetic Algorithmmentioning

confidence: 99%

“…This approach offers straightforward programming and consistently yields favorable outcomes, particularly when dealing with complex, multipeaked functions. Moreover, there is a burgeoning interest within the scientific community in employing genetic algorithms for the optimization of thermal systems [20,[23][24][25][26][27]. A novel metaheuristic optimization technique, as introduced by [28], is known as the Gray Wolf Optimizer (GWO).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Gray Wolf Optimizer for the Cogeneration Power Plant Design Within a Framework of Commercial Software and Mathematical Platform

Araújo,

Gasperazzo,

Rocha

2023

Preprint

View full text Add to dashboard Cite

In a realm where finite natural fossil fuel reservoirs coexist with escalating energy requisites and critical ecological contamination thresholds, matters pertaining to the configuration of thermal systems, encompassing energy efficacy, financial assessment, project intricacy, ecological consciousness, and fine-tuned optimization, have progressively piqued the scientific community's curiosity. Hence, thermoeconomic optimization emerges as a promising avenue for enhancing the efficiency of thermal system designs. Nevertheless, the intricacies of thermoeconomic optimization in thermal system design typically involve a multitude of components, interconnected processes, and flows, which collectively give rise to a complex system of nonlinear equations stemming from both thermodynamic and economic modeling. Moreover, the inherent objective functions in these optimization challenges are analytically daunting, characterized by traits like discontinuity, multimodality, and non-differentiability, further compounded by a multitude of decision variables. In this context, metaheuristic methods present themselves as promising and appealing tools for optimizing such intricate systems. In this study, we employ two metaheuristic methods, namely the Genetic Algorithm (GA) and the Gray Wolf Optimizer (GWO), to optimize the regenerative gas turbine cogeneration system, recognized in the literature as the CGAM problem. The thermoeconomic optimization challenge is tackled and resolved through the computational integration of a commercial software package (EES) and a mathematical platform (Matlab). Within this framework, the thermodynamic and economic modeling, as well as the thermoeconomic optimization components, are seamlessly integrated into the Engineering Equation Solver (EES). EES, in turn, calculates the thermodynamic properties for all streams within the cogeneration system while concurrently solving mass and energy balances as necessitated by the evaluation of the objective function. It is worth noting that the GA operates as an optimization tool within EES, whereas the GWO is implemented in Matlab and effectively integrated with EES. This study reveals that, despite GWO's relatively longer computational time attributable to the integration between Matlab and EES, it stands out as notably efficient in addressing the given problem, primarily owing to its reduced demand for objective function evaluations during the optimization process. Moreover, both the decision variables and the objective function tend to converge towards values closely aligned with those found in the reference literature.

show abstract

Section: Genetic Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Gray Wolf Optimizer for the Cogeneration Power Plant Design Within a Framework of Commercial Software and Mathematical Platform

Araújo,

Gasperazzo,

Rocha

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…This analysis involves using advanced techniques such as artificial neural networks and genetic algorithms to optimize the system's performance. In the work in [6] artificial intelligence and response surface methods are used in order to optimize the thermoeconomic performance of waste heat recovery system in a large internal combustion engine. As shown in the literature, the studies are focused on the application of Thermoeconomics and Machine learning methods for optimising industrial systems.…”

Section: Introductionmentioning

confidence: 99%

First Step to Define a Predictive Model of the Behaviour of a Building's Thermal System to Analyse the Climate Change Influence

Godoy

Picallo-Perez

Inza

et al. 2023

36th International Conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy Systems (ECOS 20

View full text Add to dashboard Cite

Buildings account for 40% of the EU's final energy consumption and 36% of its energy-related GHG emissions. Therefore, to reduce the EU's GHG emissions it is needed to reduce the energy consumption and increase energy efficiency. For that, not only the design but also the maintenance of systems is essential to ensure the proper functioning and the energy efficiency. On the other hand, the environmental temperature is rising at a high rate because of the global warming. Therefore, this will undoubtedly influence on the energy efficiency of the buildings thermal systems. However, we can only estimate the effects from predictions based on previous data models. In this work we develop a methodology in order to learn a predictive model of a simple thermal system of a building, consisting of a boiler and the distribution equipment that provides the dynamic DHW demand. The model is learn from databases obtained from a thermal system software to calculate the influence of climate change on the cost formation process. That is, we quantify the effects on costs due to outdoor temperature variation when the demand does not vary, based on thermoeconomic indices. The next step will be to incorporate heating demand that will also vary due to climate change. The reference model of the thermal facility would serve to predict the behaviour when the climate changes, in order to implement it in maintenance tasks and thermoeconomic diagnosis for fault detection.

show abstract

Experimental analysis and multi-objective optimization of flame dynamics and combustion performance in methane-fueled slit-type combustors

Gao,

Tang,

Cai

et al. 2024

Applied Energy

View full text Add to dashboard Cite

Response surface methods based in artificial intelligence for superstructure thermoeconomic optimization of waste heat recovery systems in a large internal combustion engine

Cited by 8 publications

References 68 publications

Gray Wolf Optimizer for the Cogeneration Power Plant Design Within a Framework of Commercial Software and Mathematical Platform

Gray Wolf Optimizer for the Cogeneration Power Plant Design Within a Framework of Commercial Software and Mathematical Platform

First Step to Define a Predictive Model of the Behaviour of a Building's Thermal System to Analyse the Climate Change Influence

Experimental analysis and multi-objective optimization of flame dynamics and combustion performance in methane-fueled slit-type combustors

Contact Info

Product

Resources

About