Application of Generalized Regression Neural Network in Predicting the Thermal Performance of Solar Flat Plate Collector Systems

2020 ◽  
Vol 13 (2) ◽  
Author(s):  
M. Sridharan ◽  
Shribalaji Shenbagaraj
Keyword(s):  
Neural Network ◽  
Flat Plate ◽  
Thermal Performance ◽  
Experimental Studies ◽  
Generalized Regression Neural Network ◽  
Fluid Temperature ◽  
Transient Nature ◽  
Collector System ◽  
Generalized Regression ◽  
Flat Plate Collector

Abstract This study presents a smart neural network (NN) model for estimating the thermal performance of a transient nature solar flat plate collector system (SFPCS). For this purpose, a series of experimental studies are conducted through four successive days with three different arrangements of SFPCS (standalone, series, and parallel). Experimental results of such arrangements are then used for designing a generalized regression neural network (GRNN) model. The GRNN architecture proposed in this study consists of four inputs (mass flowrate, solar irradiance, fluid temperature difference, and collector area) and two dependent outputs (power output and efficiency of SFPCS). Such GRNN architecture is trained, tested, and validated with real-time experimental transient datasets for each arrangement individually. The results of the GRNN model are in good agreement with experimental datasets. The overall accuracy of the developed GRNN model in predicting the performance of standalone, series, and parallel connected SFPCS is 98%.

Application of Generalized Regression Neural Network in Predicting the Performance of Natural Convection Solar Dryer

2019 ◽  
Vol 142 (3) ◽  
Author(s):  
M. Sridharan
Keyword(s):  
Neural Network ◽  
Natural Convection ◽  
Network Architecture ◽  
Experimental Studies ◽  
Generalized Regression Neural Network ◽  
Atmospheric Conditions ◽  
Time Duration ◽  
Transient Nature ◽  
Solar Dryer ◽  
Generalized Regression

Abstract The performance evaluation of a natural convection solar dryer is a complex one because of the transient and non-linear nature of atmospheric conditions. In this comparative study, a smart neural network -based tool was developed for estimating the performance of such a transient nature solar dryer. For this purpose, a series of experimental studies are conducted through four successive days and compared with the generalized regression neural network (GRNN) modeling. GRNN architecture proposed in this study consists of three inputs (time duration, irradiance, and ambient temperature) and four outputs (drying chamber temperature, the mass of moisture removed, drying rate, and dryer efficiency). Such generalized regression neural network architecture was trained, tested, and validated with real-time experimental variable data sets. The results of the GRNN model are in good agreement with experimental results. The overall accuracy of the proposed GRNN model in predicting the performance is 96.29%.

scholarly journals Using a Generalized Regression Neural Network Prediction Tool to Estimate Thermal Performance in A Heat Exchanger By using Triple Elliptical Leaf Angle Strips with Opposite Orientation and Same Direction

2019 ◽  
Vol 8 (11) ◽  
pp. 528-535
Keyword(s):  
Neural Network ◽  
Heat Transfer ◽  
Heat Exchanger ◽  
Thermal Performance ◽  
Leaf Angle ◽  
Generalized Regression Neural Network ◽  
Opposite Orientation ◽  
Statistical Tool ◽  
Pressure Drops ◽  
Generalized Regression

In our day to day hectic schedule humans have got so adaptive to technology that tremendous pressure is built on researchers to produce better equipment with greater output & easier way of human usage. One among these is Heat exchanger which is a device for trading heat and providing comfortable environment either for humans or the equipment .This paper aims at finding a solution in improvement of the thermal performance of the heat exchanger by implementing a statistical tool derived from Artificial Neural Network. The name of the tool is GRNN. (Generalized Regression Neural Network) From a sparse data of inputs (Temperatures, Angle orientation & mass flow rates) the outputs of (outlet temperatures & drop in pressure) are found out using this tool. An experiment is also conducted to find the heat transfer rates and pressure drops. To enhance the heat transfer rate three elliptical shaped leaf strips are introduced in the tube with opposite orientation and same direction. The results obtained from both the sources are compared and the percentage of error is calculated.

scholarly journals Thermal Performance Improvement Study of a Solar Collector with Compound Parabolic Concentrator

2018 ◽  
Vol 3 (11) ◽  
pp. 78-82
Author(s):  
Md. Forhad Ibne Al Imam ◽  
Rafiqul Alam Beg ◽  
Shamimur Rahman
Keyword(s):  
Water Temperature ◽  
Flat Plate ◽  
Thermal Performance ◽  
Thermal Efficiency ◽  
Solar Collector ◽  
Compound Parabolic Concentrator ◽  
Collector System ◽  
Solar Intensity ◽  
Flat Plate Collector ◽  
Parabolic Collector

Heating water with solar energy is easy and effective in both domestic and industrial areas. The initial implementation cost of a solar-water-heating system is high but long term use of it makes it cost effective. For geographical location, Bangladesh is very suitable for using it. In a solar collector system, collector area is an important design factor. To achieve better thermal performance, 0.81m2 solar collector was used in this study. Commonly used flat plate collector takes more space to be installed. In Bangladesh, space on the roofs of houses and industries are limited and so there is a little scope to use flat plate collector system. Compound parabolic collector can solve this problem. Solar collector with compound parabolic collector needs less space than flat plate collector with reflector. When compound parabolic concentrator was attached with the solar collector, thermal performance improves. Compare with other alternatives that improve thermal efficiency, compound parabolic concentrator shows better thermal performance. Compare thermal efficiency of the consecutive three months. In this system, when water flow rate increase, outlet water temperature decrease but thermal efficiency increases. It is also observed that when solar intensity increases, thermal efficiency also increases likewise when solar intensity decreases, thermal efficiency also decreases. In this research, outputs of different similar researches are compared to show the effectiveness of the compound parabolic concentrator based solar collector. The compound parabolic concentrator reflects more solar radiation, eventually directs it to the collector and increased the difference between the inlet and outlet water temperature.

ENHANCEMENT OF THERMAL PERFORMANCE OF SOLAR FLAT PLATE COLLECTOR USING SiO2 NANOFLUID

2017 ◽  
Vol 12 (4) ◽  
pp. 33 ◽  
Author(s):  
DALWADI M.D. ◽  
NAIK H.K. ◽  
PADHIAR R.D. ◽  
RANA S.S. ◽  
CHAVDA N.K. ◽  
...  
Keyword(s):  
Flat Plate ◽  
Thermal Performance ◽  
Flat Plate Collector

Risk of Voltage Collapse Using Multi-Layer Feed-Forward Neural Network and Generalized Regression Neural Network

2015 ◽  
Vol 793 ◽  
pp. 483-488
Author(s):  
N. Aminudin ◽  
Marayati Marsadek ◽  
N.M. Ramli ◽  
T.K.A. Rahman ◽  
N.M.M. Razali ◽  
...  
Keyword(s):  
Neural Network ◽  
System Analysis ◽  
Risk Index ◽  
Weather Condition ◽  
Generalized Regression Neural Network ◽  
Voltage Collapse ◽  
Ann Model ◽  
Feed Forward ◽  
Feed Forward Network ◽  
Generalized Regression

The computation of security risk index in identifying the system’s condition is one of the major concerns in power system analysis. Traditional method of this assessment is highly time consuming and infeasible for direct on-line implementation. Thus, this paper presents the application of Multi-Layer Feed Forward Network (MLFFN) to perform the prediction of voltage collapse risk index due to the line outage occurrence. The proposed ANN model consider load at the load buses as well as weather condition at the transmission lines as the input. In realizing the effectiveness of the proposed method, the results are compared with Generalized Regression Neural Network (GRNN) method. The results revealed that the MLFFN method shows a significant improvement over GRNN performance in terms of least error produced.

Sign in / Sign up

Export Citation Format

Share Document