Heat transfer optimization using genetic algorithm and artificial neural network in a heat exchanger with partially filled different high porosity metal foam

Abstract An experimental work is conducted on counter flow plate fin compact heat exchanger using offset strip fin under different mass flow rates. The training, testing, and validation set of data has been collected by conducting experiments. Next, artificial neural network merged with Genetic Algorithm (GA) utilized to measure the performance of plate-fin compact heat exchanger. The main aim of present research is to measure the performance of plate-fin compact heat exchanger and to provide full explanations. An artificial neural network predicted simulated data, which verified with experimental data under 10–20% error. Then, the authors examined two well-known global search techniques, simulated annealing and the genetic algorithm. The proposed genetic algorithm and Simulated Annealing (SA) results have been summarized. The parameters are impartially important for good results. With the emergence of a new data-driven modeling technique, Neuro-fuzzy based systems are established in academic and practical applications. The neuro-fuzzy interference system (ANFIS) has also been examined to undertake the problem related to plate-fin heat exchanger performance measurement under various parameters. Moreover, Parallel with ANFIS model and Artificial Neural Network (ANN) model has been created with emphasizing the accuracy of the different techniques. A wide range of statistical indicators used to assess the performance of the models. Based on the comparison, it was revealed that technical ANFIS improve the accuracy of estimates in the small pool and tropical ANN. Highlights Performance of compact plate fin heat exchanger has been measured. Predicted data given by ANN has been verified by simulation data and the experimental data. Depicted the applications of optimization methods upon fin heat exchanger.

Download Full-text

Modeling of overall heat transfer coefficient of a concentric double pipe heat exchanger with limited experimental data by using curve fitting and ANN combination

Thermal Science ◽

10.2298/tsci171206111k ◽

2019 ◽

Vol 23 (6 Part A) ◽

pp. 3579-3590 ◽

Cited By ~ 3

Author(s):

Necati Kocyigit ◽

Huseyin Bulgurcu

Keyword(s):

Neural Network ◽

Heat Transfer ◽

Experimental Data ◽

Artificial Neural Network ◽

Heat Transfer Coefficient ◽

Heat Exchanger ◽

Transfer Coefficient ◽

Curve Fitting ◽

Overall Heat Transfer Coefficient ◽

Artificial Neural

The modeling accuracy of artificial neural networks (ANN) was evaluated by using limited heat exchanger data acquired experimentally. The artificial neural networks were used for predicting the overall heat transfer coefficient of a concentric double pipe heat exchanger where oil flowed inside the inner tube while the water flowed in the outer tube. In the cases of parallel and counter flows, the experimental data were collected by testing heat exchanger in wide range of operating conditions. Curve fitting and artificial neural network combination was used for the estimation of the overall heat transfer coefficient to compensate the experimental errors in the data. The curve fitting was used to detect the trend and generate data points between the experimentally collected points. The artificial neural network was trained better from the generated data set. The feed forward type artificial neural network was trained by using the Levenberg-Marquardt algorithm. Two backpropagation network type artificial neural network algorithms were also used, and their performance were compared with the estimation of the Levenberg-Marquardt algorithm. The average estimation error between the predictions and the experimental data were in the range of 1.31e?4 to 4.35e?2%. The study confirmed that curve fitting and artificial neural network combination could be used effectively to estimate the overall heat transfer coefficient of heat exchanger.

Download Full-text