Hikmet Esen

Artificial neural network and wavelet neural network approaches for modelling of a solar air heater

This paper reports on a modelling study of new solar air heater (SAH) system by using artificial neural network (ANN) and wavelet neural network (WNN) models. In this study, a device for inserting an absorbing plate made of aluminium cans into the double-pass channel in a flat-plate SAH. A SAH system is a multi-variable system that is hard to model by conventional methods. As regards the ANN and WNN methods, it has a superior capability for generalization, and this capability is independent on the dimensionality of the input datas. In this study, an ANN and WNN based methods were intended to adopt SAH system for efficient modelling. To evaluate prediction capabilities of different types of neural network models (ANN and WNN), their best architecture and effective training parameters should be found. The performance of the proposed methodology was evaluated by using several statistical validation parameters. Comparison between predicted and experimental results indicates that the proposed WNN model can be used for estimating the some parameters of SAHs with reasonable accuracy.

Modelling of a new solar air heater through least-squares support vector machines

This paper reports on a modelling study of new solar air heater (SAH) system efficiency by using least-squares support vector machine (LS-SVM) method. In this study, a device for inserting an absorbing plate made of aluminium cans into the double-pass channel in a flat-plate SAH. A SAH system is a multi-variable system that is hard to model by conventional methods. As regards the LS-SVM, it has a superior capability for generalization, and this capability is independent on the dimensionality of the input data. In this study, a LS-SVM based method was intended to adopt SAH system for efficient modelling. For modelling, different mass flow rates in flow duct and collector types are used and then for obtaining the optimum LS-SVM parameters, such as regularization parameter, and optimum kernel function and parameters, several tests have been carried out. The performance of the proposed methodology was evaluated by using several statistical validation parameters. It is found that root mean squared error (RMSE) value is 0.0024, the coefficient of multiple determinations (R^2) value is 0.9997 and coefficient of variation (cov) value is 2.1194 for the proposed radial basis function (RBF)-kernel LS-SVM method at 0.03kg/s air mass flow rate. It is found that RMSE value is 0.0135, R^2 value is 0.9991 and cov value is 2.9868 for the proposed RBF-kernel LS-SVM method at 0.05kg/s air mass flow rate. Comparison between predicted and experimental results indicates that the proposed LS-SVM model can be used for estimating the efficiency of SAHs with reasonable accuracy.

Performance prediction of a ground-coupled heat pump system using artificial neural networks

This paper describes the applicability of artificial neural networks (ANNs) to predict performance of a horizontal ground-coupled heat pump (GCHP) system. Performance forecasting is the precondition for the optimal control and energy saving operation of heat pump systems. ANNs have been used in varied applications and they have been shown to be particularly useful in system modelling and system identification. In order to train the ANN, limited experimental measurements were used as training data and test data. In this study, in input layer, there are air temperature entering condenser unit and air temperature leaving condenser unit, and ground temperatures (1 and 2m); coefficient of performance of system (COPS) is in output layer. The back propagation learning algorithm with three different variants, namely Levenberg-Marguardt (LM), Pola-Ribiere conjugate gradient (CGP), and scaled conjugate gradient (SCG), and tangent sigmoid transfer function were used in the network so that the best approach can find. The most suitable algorithm and neuron number in the hidden layer are found as LM with seven neurons. For this number level, after the training, it is found that Root-mean squared (RMS) value is 1%, and absolute fraction of variance (R^2) value is 99.999% and coefficient of variation in percent (COV) value is 28.62%. It is concluded that, ANNs can be used for prediction of COPS as an accurate method in the systems.

Modelling and experimental performance analysis of solar-assisted ground source heat pump system

Abstract In this study, slinky (the slinky-loop configuration is also known as the coiled loop or spiral loop of flexible plastic pipe)type ground heat exchanger (GHE) was established for a solar-assisted ground source heat pump system. System modelling is performed with the data obtained from the experiment. Artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) are used in modelling. The slinky pipes have been laid horizontally and vertically in a ditch. The system coefficient of performance (COPsys) and the heat pump coefficient of performance (COPhp) have been calculated as 2.88 and 3.55, respectively, at horizontal slinky-type GHE, while COPsys and COPhp were calculated as 2.34 and 2.91, respectively, at vertical slinky-type GHE. The obtained results showed that the ANFIS is more successful than that of ANN for forecasting performance of a solar ground source heat pump system.

Modelling of a vertical ground coupled heat pump system by using artificial neural networks

This paper describes the applicability of artificial neural networks (ANNs) to estimate of performance of a vertical ground coupled heat pump (VGCHP) system used for cooling and heating purposes experimentally. The system involved three heat exchangers in the different depths at 30 (VB1), 60 (VB2) and 90 (VB3)m. The experimental results were obtained in cooling and heating seasons of 2006-2007. ANNs have been used in varied applications and they have been shown to be particularly useful in system modeling and system identification. In this study, the back-propagation learning algorithm with three different variants, namely Levenberg-Marguardt (LM), Pola-Ribiere conjugate gradient (CGP), and scaled conjugate gradient (SCG), and tangent sigmoid transfer function were used in the network so that the best approach could be found. The most suitable algorithm and neuron number in the hidden layer were found as LM with 8 neurons for both cooling and heating modes.

ANN and ANFIS models for performance evaluation of a vertical ground source heat pump system

The aim of this study is to demonstrate the comparison of an artificial neural network (ANN) and an adaptive neuro-fuzzy inference system (ANFIS) for the prediction performance of a vertical ground source heat pump (VGSHP) system. The VGSHP system using R-22 as refrigerant has a three single U-tube ground heat exchanger (GHE) made of polyethylene pipe with a 40mm outside diameter. The GHEs were placed in a vertical boreholes (VBs) with 30 (VB1), 60 (VB2) and 90 (VB3)m depths and 150mm diameters. The monthly mean values of COP for VB1, VB2 and VB3 are obtained to be 3.37/1.93, 3.85/2.37, and 4.33/3.03, respectively, in cooling/heating seasons. Experimental performances were performed to verify the results from the ANN and ANFIS approaches. ANN model, Multi-layered Perceptron/Back-propagation with three different learning algorithms (the Levenberg-Marquardt (LM), Scaled Conjugate Gradient (SCG) and Pola-Ribiere Conjugate Gradient (CGP) algorithms and the ANFIS model were developed using the same input variables. Finally, the statistical values are given in as tables. This paper shows the appropriateness of ANFIS for the quantitative modeling of GSHP systems.

Investigation of Photovoltaic Assisted Misting System Application for Arbor Refreshment

In this study, for the first time in the literature, solar assisted cooler with misting system established on an arbor with an area of 24 m2 and georeferenced in Elazig (38.6775° N, 39.1707° E), Turkey, is presented. Here, we present a system that reduces interior temperature of the arbor while increasing humidity. Also, the system generates required electricity with a solar photovoltaic module to power pressurized water pump through an inverter and stores it in a battery for use when there is no sunlight. The model of the photovoltaic module was implemented using a Matlab program. As a result of being an uncomplicated system, return on investment for the system is 3.7 years.

Design and Implementation of Automatic Wheat Mower Based on Smart Sensor Fed by a Photovoltaic

The biggest problems of our time are environmental pollution and the reduction of fossil fuel resources. In recent years, photovoltaic (PV) has started to be used efficiently in order to produce electrical energy from solar energy throughout the world. In this study, a wheat mover machine taking its energy with PV technology transformation from the sun was designed supported by smart sensors. The designed vehicle was tested in two wheat fields in Sivas in Turkey. It was seen that daily average sunshine rates were not lower than 700 Watt/m2 during the testing dates and time. The amounts of electrical charge used to mow 5 m2 and 50 m2 areas are obtained as 500 mAh and 3395 mAh, respectively. Also maximum power is calculated from used PV panel as 26.15 Watt during the day of the experiments. The range of solar radiation intensity is found 4.5 kWh/m2/day at the studied kWh which was 0.140 USD on the date of November 2015. This system is 94.5% more economic than conventional mowers over an area of 1000 m2.