scholarly journals Development and Application of a Multi-Objective Tool for Thermal Design of Heat Exchangers Using Neural Networks

Mathematics ◽  
2021 ◽  
Vol 9 (10) ◽  
pp. 1120
Author(s):  
José Luis de Andrés Honrubia ◽  
José Gaviria de la Puerta ◽  
Fernando Cortés ◽  
Urko Aguirre-Larracoechea ◽  
Aitor Goti ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Pressure Drop ◽  
Heat Exchangers ◽  
Thermal Design ◽  
Design Parameters ◽  
User Friendliness ◽  
Multi Objective ◽  
Industrial Companies ◽  
Objective Tool

This paper presents the design of a multi-objective tool for sizing shell and tube heat exchangers (STHX), developed under a University/Industry collaboration. This work aims to show the feasibility of implementing artificial intelligence tools during the design of Heat Exchangers in industry. The design of STHX optimisation tools using artificial intelligence algorithms is a visited topic in the literature, nevertheless, the degree of implementation of this concept is uncommon in industrial companies. Thus, the challenge of this research consists of the development of a tool for the design of STHX using artificial intelligence algorithms that can be used by industrial companies. The approach is implemented using a simulated dataset contrasted with ARA TT, the company taking part in the project. The given dataset to develop a theoretical STHX calculator was modeled using MATLAB. This dataset was used to train seven neural networks (NNs). Three of them were mono-objective, one per objective to predict, and four were multi-objective. The last multi-objective NN was used to develop an inverse neural network (INN), which is used to find the optimal configuration of the STHXs. In this specific case, three design parameters, the pressure drop on the shell side, the pressure drop on the tube side and heat transfer rate, were jointly and successfully optimised. As a conclusion, this work proves that the developed tool is valid in both terms of effectiveness and user-friendliness for companies like ARA TT to improve their business activity.

Construction, performance, and thermal design of plate heat exchangers

2009 ◽  
Vol 223 (3) ◽  
pp. 123-131 ◽  
Author(s):  
M A Mehrabian
Keyword(s):  
Heat Exchangers ◽  
Close Agreement ◽  
Thermal Design ◽  
Design Parameters ◽  
Final Decision ◽  
Process Data ◽  
Design Data ◽  
Plate Heat ◽  
Computer Codes

Much of design data for plate heat exchangers remain proprietary. A step by step methodology for determination of the exchanger size and internal geometry from the knowledge of process data is scarce. Commercial computer codes do not give the user accessibility to mathematical modelling. Engineers do not usually understand the terminology and geometry of these exchangers. This article presents a manual method for thermal design of plate heat exchangers based on physically meaningful estimations, calculations, and comparisons. When there is no close agreement, it may be necessary to change one or more of the design parameters, i.e. channel (passage) velocities, wall temperatures, or corrugation inclination angle. Considerable skill and judgment is required by the thermal design engineer at this stage to decide how the tentative design should be changed to provide a rapid solution. The experienced design engineer is often able to judge on the final decision from the first or second trial designs.

Comparison of stationary and rotary matrix heat exchangers using teaching-learning-based optimization algorithm

2017 ◽  
Vol 232 (4) ◽  
pp. 493-502 ◽  
Author(s):  
Hassan Hajabdollahi
Keyword(s):  
Heat Exchanger ◽  
Pressure Drop ◽  
Optimization Algorithm ◽  
Heat Exchangers ◽  
Design Parameters ◽  
Matrix Heat Exchanger ◽  
Teaching Learning Based Optimization ◽  
Mass Flow Rates ◽  
Teaching Learning ◽  
Matrix Heat

In this paper, two kinds of compact heat exchanger including plate fin heat exchanger and rotary regenerator, respectively the stationary and rotary matrix heat exchanger, are compared. For this purpose, both heat exchangers are optimized by considering three simultaneous objective functions including effectiveness, heat exchanger volume, and total pressure drop using multi-objective teaching learning based optimization algorithm. Six different design parameters are considered for the both plate fin heat exchanger and rotary regenerator. Optimization is performed for the same and different hot and cold side mass flow rates. The optimum results reveal 13.26% growth in the effectiveness, 475.17% increase in the volume, and 95.45% reduction in the pressure drop in RR as compared with plate fin heat exchanger and for the final optimum point. As a result, rotary regenerator is more suitable in the case of high effectiveness and low pressure drop while plate fin heat exchanger is more suitable in the case of space limitation (lower heat exchanger volume).

Thermal Design of Heat Exchanger With Fins Inside and Outside Tubes

2006 ◽  
Author(s):  
G. N. Xie ◽  
Q. Y. Chen ◽  
M. Zeng ◽  
Q. W. Wang
Keyword(s):  
Heat Transfer ◽  
Heat Exchanger ◽  
Pressure Drop ◽  
Heat Exchangers ◽  
Total Pressure ◽  
Thermal Design ◽  
Operating Pressure ◽  
Heat Transfer Area ◽  
Tube Heat Exchanger ◽  
Total Pressure Drop

Compact heat exchangers such as tube-fin types and plate-fin types are widely used for gas-liquid or gas-gas applications. Some examples are air-coolers, fan coils, regenerators and recuperators in micro-turbines. In this study, thermal design of fin-and-tube (tube-fin) heat exchanger performance with fins being employed outside and inside tubes was presented, with which designed plate-fin heat exchanger was compared. These designs were performed under identical mass flow rate, inlet temperature and operating pressure on each side for recuperator in 100kW microturbine as well as specified allowable fractions of total pressure drop by means of Log-Mean Temperature Difference (LMTD) method. Heat transfer areas, volumes and weights of designed heat exchangers were evaluated. It is shown that, under identical heat duty, fin-and-tube heat exchanger requires 1.8 times larger heat transfer area outside tubes and volume, 0.6 times smaller heat transfer area inside tubes than plate-fin heat exchanger. Under identical total pressure drop, fin-and-tube heat exchanger requires about 5 times larger volume and heat transfer area in gas-side, 1.6 times larger heat transfer area in air-side than plate-fin heat exchanger. Total weight of fin-and-tube heat exchanger is about 2.7 times higher than plate-fin heat exchanger, however, the heat transfer rate of fin-and-tube heat exchanger is about 1.4 times larger than that of plate-fin heat exchanger. It is indicated that, both-sides finned tube heat exchanger may be used in engineering application where the total pressure drop is severe to a small fraction and the operating pressure is high, and may be adopted for recuperator in microturbine.

Multi-Objective Design Optimization of Multi-Floor, Counterflow Micro Heat Exchangers

2013 ◽  
Author(s):  
Abas Abdoli ◽  
George S. Dulikravich
Keyword(s):  
Pressure Drop ◽  
Heat Exchangers ◽  
Flow Direction ◽  
Heat Removal ◽  
Heat Transfer Analysis ◽  
Multi Objective Optimization ◽  
Multi Objective ◽  
Removal Capacity ◽  
Branching Networks ◽  
Analysis Package

Heat removal capacity, coolant pumping pressure drop and surface temperature non-uniformity are three major challenges facing single-phase flow microchannel compact heat exchangers. In this paper multi-objective optimization has been performed to increase heat removal capacity, and decrease pressure drop and temperature non-uniformity in single-flow microchannels. Three-dimensional (3D) 4-floor branching networks have been applied to increase heat removal capacity of a microchannel from silicon substrate (15×15×2 mm). Each floor has four different branching sub-networks with opposite flow direction with respect to the next one. Each branching network has four inlets and one outlet. However, branching patterns of each of these sub-networks could be different from the others. Conjugate heat transfer analysis has been performed by developing a software package which uses quasi-1D thermo-fluid analysis and a 3D steady heat conduction analysis. These two solvers are coupled through their common boundaries representing surfaces of the cooling microchannels. Using quasi-1D solver significantly decreases computing time and its results are in good agreement with 3D Navier-Stokes equations solver for these types of application. The analysis package is capable of generating 3D branching networks with random topologies. 1341 random cooling networks were simulated using this analysis package. Multi-objective optimization using modeFrontier software was performed using response surface approximation and genetic algorithm. Diameters and branching pattern of each sub-network and coolant flow direction on each floor were design variables of multi-objective optimization. Maximizing heat removal capacity, minimizing pressure drop and temperature non-uniformity on the hot surface were three simultaneous objectives of the optimization. Pareto-optimal solutions demonstrate that thermal loads of up to 500 W/cm2 can be managed with 3D 4-floor microchannel cooling networks.

scholarly journals A General Approach in Optimization of Heat Exchangers by Bio-Inspired Artificial Intelligence Methods

Energies ◽  
2019 ◽  
Vol 12 (23) ◽  
pp. 4441 ◽  
Author(s):  
Jaroslaw Krzywanski
Keyword(s):  
Heat Transfer ◽  
Artificial Intelligence ◽  
Neural Networks ◽  
Genetic Algorithms ◽  
Artificial Neural Networks ◽  
Heat Transfer Rate ◽  
Heat Exchangers ◽  
Transfer Rate ◽  
Artificial Neural ◽  
Bottom To Top

The paper introduces the artificial intelligence (AI) approach as a general method for the design and optimization study of heat exchangers. Genetic Algorithms (GA) and Artificial Neural Networks (ANN) are applied in the paper. An AGENN model, combining Genetic Algorithms with Artificial Neural Networks, was developed and validated against the desired data on a large falling film evaporator. A broad range of operating conditions and geometric configurations are considered in the study. Four kinds of tubes are deliberated, including plain and enhanced tubes. Different tube pass arrangements, i.e., top-to-bottom, bottom-to-top, and side-by-side, are discussed. Finally, the effects of liquid refrigerant mass flow rate, as well as the number of flooded tubes on the performance of the evaporator, are analyzed. The total heat transfer rate of the evaporator, predicted by the model, is in good agreement with the desired data; the maximum error is lower than ±3%. The highest heat transfer rate of the evaporator is 1140.01 kW and corresponds to Turbo EHP tubes, and bottom-to-top tubes pass arrangements, which guarantee the best thermal energy conversion. The presented approach can be referred to as a complementary technique in heat exchanger design procedures, besides the common rating and sizing tasks. It is an effective and alternative method for the existing approaches, considering the complexity of analytical and numerical techniques as well as the high costs of experiments.

New correlations for wavy plate-fin heat exchangers: different working fluids

2014 ◽  
Vol 24 (5) ◽  
pp. 1086-1108 ◽  
Author(s):  
Morteza Khoshvaght Aliabadi ◽  
Faramarz Hormozi ◽  
Elham Hosseini Rad
Keyword(s):  
Heat Transfer ◽  
Experimental Data ◽  
Pressure Drop ◽  
Heat Exchangers ◽  
Cfd Simulation ◽  
Design Parameters ◽  
Geometrical Parameters ◽  
Working Fluids ◽  
Content Type ◽  
Simulation Results

Purpose – The main purpose of this paper is the generation of the heat transfer and pressure drop correlations by considering three working fluids, namely air, water, and ethylene glycol, for the wavy plate-fin heat exchangers (PFHEs). Design/methodology/approach – In order to present the general correlations, various models with different geometrical parameters should be tested. Because of the problems, such as difficult, long time, and costly fabrication of the wavy fins in experimental tests, computational fluid dynamics (CFD) calculations can be a useful method for the generation of the heat transfer and pressure drop correlations with eliminating the experimental problems. Hence, the effective design parameters of the wavy plate-fin, including fin pitch, fin height, wave length, fin thickness, wave amplitude, and fin length, and also their levels were recognized from the literature. The Taguchi method was applied to formulate the CFD simulation work. Findings – The simulation results were compared and validated with an available experimental data. The mean deviations of the Colburn factor, j, and Fanning friction factor, f, values between the simulation results and the experimental data were 3.74 and 9.07 percent, respectively. The presented air correlations and experimental data were in a good agreement, so that approximately 95 percent of the experimental data were correlated within ±12 percent. The j factor values varied for the different working fluids, while the f factor values did not sensibly change. Practical implications – The presented correlations can be used to estimate the thermal-hydraulic characteristics and to design of the compact PFHE with the wavy channels. Originality/value – This manuscript presents the new correlations for the compact PFHEs with the way channels by considering all the geometrical parameters and the working fluids with the different Prandtl numbers, 0.7, 7, and 150.

The Concept of Irreversibility in Heat Exchanger Design: Counterflow Heat Exchangers for Gas-to-Gas Applications

1977 ◽  
Vol 99 (3) ◽  
pp. 374-380 ◽  
Author(s):  
A. Bejan
Keyword(s):  
Heat Exchanger ◽  
Heat Exchangers ◽  
Design Method ◽  
Thermal Design ◽  
Design Parameters ◽  
Regenerative Heat ◽  
Pressure Drops ◽  
Heat Exchanger Design ◽  
Thermodynamic Irreversibility ◽  
Useful Power

The thermal design of counterflow heat exchangers for gas-to-gas applications is based on the thermodynamic irreversibility rate or useful power no longer available as a result of heat exchanger frictional pressure drops and stream-to-stream temperature differences. The irreversibility (entropy production) concept establishes a direct relationship between the heat exchanger design parameters and the useful power wasted due to heat exchanger nonideality. The paper presents a heat exchanger design method for fixed or for minimum irreversibility (number of entropy generation units NS). In contrast with traditional design procedures, the amount of heat transferred between streams and the pumping power for each side become outputs of the NS design approach. To illustrate the use of this method, the paper develops the design of regenerative heat exchangers with minimum heat transfer surface and with fixed irreversibility NS.

scholarly journals An oppositional Salp Swarm: Jaya algorithm for thermal design optimization of an Organic Rankine Cycle

2021 ◽  
Vol 3 (2) ◽  
Author(s):  
Mert Sinan Turgut ◽  
Oguz Emrah Turgut
Keyword(s):  
Optimization Problems ◽  
Organic Rankine Cycle ◽  
Rankine Cycle ◽  
Thermal Design ◽  
Design Parameters ◽  
Nsga Ii ◽  
Multi Objective ◽  
Specific Investment ◽  
Weighted Sum Method ◽  
Pareto Curve

AbstractThis study proposes a hybrid metaheuristic algorithm to tackle both single and multi objective optimization problems that are subjected to hard constraints. Twenty-four single objective optimization benchmark problems comprising unimodal and multi modal test functions have been solved by the proposed hybrid algorithm (OPSSAJ) and numerical results have been compared with those acquired by some of the new emerged metaheuristic optimizers. The proposed OPSSAJ shows a significant accuracy and robustness in most of the cases and proves its efficiency in solving high dimensional problems. As a real-world case study, seventeen operational design parameters of an organic rankine cycle (ORC) operating with a binary mixture of R227EA and R600 refrigerants are optimized by the proposed hybrid OPSSAJ to obtain the optimum values of contradicting dual objectives of second law efficiency and Specific Investment Cost. A Pareto curve composed of non-dominated solutions is constructed through the weighted sum method and the final solution is chosen by the reputed TOPSIS decision-maker. The pareto curve and best-compromising result obtained by utilizing the OPPSAJ are compared with that of acquired by using nondominated sorting genetic algorithm II (NSGA-II) and multiple objective particle swarm optimization (MOPSO) algorithms. The multi-objective ORC design obtained with the OPSSAJ yields a significant improvement in thermal efficiency and cost values compared to designs found by the NSGA-II and MOPSO algorithms. Furthermore, a sensitivity analysis is performed to observe the influences of the selected design variables on problem objectives.

Sign in / Sign up

Export Citation Format

Share Document