A Hybrid Metaheuristic–Deterministic Optimization Strategy for Waste Heat Recovery in Industrial Plants

Abstract

This work presents a novel approach to recover industrial waste heat and to integrate it into utilities, refrigeration, and electricity production through the incorporation of heat exchanger networks and thermal engines (steam Rankine cycle, organic Rankine cycle, and absorption refrigeration cycle). The solution approach is based on the iteration between metaheuristic–deterministic optimization strategies. Metaheuristic optimization is established through the MS Excel-VBA-Aspen Plus link to obtain accurate modeling results. Deterministic optimization is implemented in the GAMS platform, where the mathematical formulation is based on a superstructure that considers all of the energy interconnections between the heat exchanger network, utilities, and thermal engines. Furthermore, economic, environmental, and social targets are evaluated. A case study is presented to show the applicability of the proposed methodology. The operating conditions obtained are presented (working fluid flow rate, temperatures, pressures, and efficiencies) for each thermal engine. Furthermore, the results show an increase in the total annual profit by 148%.

Electrospinning Technology, Machine Learning, and Control Approaches: A Review

“…They concluded that inspection-v3 with more than 96% accuracy has the best performance among three models. [271] Recently, researchers have also explored the combination of a variety of ML methods (e.g., MLP, CNN, random forest) for the identification of manufacturing anomalies in electrospun nanofibers [297,298] (see Figure 16).…”

“…Examples of the use of ML with electrospun wearable membranes for application in a) prediction of characteristics of electrospun nanofibers (Reproduced with permission. [ 297 ] Copyright 2024, ACS Publications) and b) hybrid method to detect anomalies in nanomaterials (Reproduced with permission. [ 298 ] Copyright 2021, IEEE).…”

Electrospinning Technology, Machine Learning, and Control Approaches: A Review

“…They concluded that inspection-v3 with more than 96% accuracy has the best performance among three models. [271] Recently, researchers have also explored the combination of a variety of ML methods (e.g., MLP, CNN, random forest) for the identification of manufacturing anomalies in electrospun nanofibers [297,298] (see Figure 16).…”

“…Examples of the use of ML with electrospun wearable membranes for application in a) prediction of characteristics of electrospun nanofibers (Reproduced with permission. [ 297 ] Copyright 2024, ACS Publications) and b) hybrid method to detect anomalies in nanomaterials (Reproduced with permission. [ 298 ] Copyright 2021, IEEE).…”

Electrospinning Technology, Machine Learning, and Control Approaches: A Review

“…They concluded that inspection-v3 with more than 96% accuracy has the best performance among three models. [271] Recently, researchers have also explored the combination of a variety of ML methods (e.g., MLP, CNN, random forest) for the identification of manufacturing anomalies in electrospun nanofibers [297,298] (see Figure 16).…”

“…Examples of the use of ML with electrospun wearable membranes for application in a) prediction of characteristics of electrospun nanofibers (Reproduced with permission. [ 297 ] Copyright 2024, ACS Publications) and b) hybrid method to detect anomalies in nanomaterials (Reproduced with permission. [ 298 ] Copyright 2021, IEEE).…”

Electrospinning Technology, Machine Learning, and Control Approaches: A Review

“…They concluded that inspection-v3 with more than 96% accuracy has the best performance among three models. [271] Recently, researchers have also explored the combination of a variety of ML methods (e.g., MLP, CNN, random forest) for the identification of manufacturing anomalies in electrospun nanofibers [297,298] (see Figure 16).…”

“…Examples of the use of ML with electrospun wearable membranes for application in a) prediction of characteristics of electrospun nanofibers (Reproduced with permission. [ 297 ] Copyright 2024, ACS Publications) and b) hybrid method to detect anomalies in nanomaterials (Reproduced with permission. [ 298 ] Copyright 2021, IEEE).…”