A data driven deep neural network model for predicting boiling heat transfer in helical coils under high gravity

نویسندگان

چکیده

In this article, a deep artificial neural network (ANN) model has been proposed to predict the boiling heat transfer in helical coils under high gravity conditions, which is compared with experimental data. A test rig set up provide 11 g flux 15100 W/m2 and mass velocity range from 40 2000 kg m−2 s−1. current work, total 531 data samples have used ANN model. The was developed Python Keras environment Feed-forward Back-propagation (FFBP) Multi-layer Perceptron (MLP) using eight features (mass flow rate, thermal power, inlet temperature, pressure, direction, acceleration, tube inner surface area, coil diameter) as inputs two (wall coefficient) outputs. composed of three hidden layers number 1098 neurons 300,266 trainable parameters found optimal according statistical error analysis. Performance evaluation conducted based on six verification statistic metrics (R2, MSE, MAE, MAPE, RMSE cosine proximity) between predicted values. results demonstrate that 8-512-512-64-2 best performance predicting characteristics (R2=0.853, MSE=0.018, MAE=0.074, MAPE=1.110, RMSE=0.136, proximity=1.000) testing stage. It indicated utilisation learning, able successfully coils, especially achieved excellent outputs very large value differences.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Recurrent Neural Network Model for solving CCR Model in Data Envelopment Analysis

In this paper, we present a recurrent neural network model for solving CCR Model in Data Envelopment Analysis (DEA). The proposed neural network model is derived from an unconstrained minimization problem. In the theoretical aspect, it is shown that the proposed neural network is stable in the sense of Lyapunov and globally convergent to the optimal solution of CCR model. The proposed model has...

متن کامل

Review of Reduced Gravity Boiling Heat Transfer: European Research

The ˆrst section of this paper (overview on boiling heat transfer characteristics) is directed to those who are not specialists in the ˆeld of boiling heat transfer, in order to make them aware of the fundamental physical mechanisms, the advantages and the main problems of this technique. Next, some of the basic knowledge achieved on terrestrial boiling heat transfer is outlined, along with the...

متن کامل

Review of Reduced Gravity Boiling Heat Transfer: Japanese Research

To introduce the advance in the researches on boiling and two-phase ‰ow in reduced gravity ˆelds and the change in the situation surrounding them in Japan, a short review is focused on the individual research subjects, i.e., pool boiling, ‰ow boiling, and unheated two-phase ‰ow including their major topics. Representative results obtained so far are introduced. Future direction of researches on...

متن کامل

Highly subcooled pool boiling heat transfer at various gravity levels

A microscale heater array 2:7 mm 2:7 mm in size along with a video camera was used to provide subcooled pool boiling heat transfer measurements at gravity levels ranging from 1.8g to 10 g. The fluid was FC-72 at 1 atm and subcooled by nominally 36 C for all cases. A Terrier–Orion sounding rocket and the KC-135 aircraft were used to provide the microgravity and low-g environments, respectively. ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: International Journal of Heat and Mass Transfer

سال: 2021

ISSN: ['1879-2189', '0017-9310']

DOI: https://doi.org/10.1016/j.ijheatmasstransfer.2020.120743