Showing papers by "Soteris A. Kalogirou published in 2006"

Artificial neural networks in energy applications in buildings

Abstract: Artificial neural networks (ANNs) are nowadays accepted as an alternative technology offering a way to tackle complex and ill-defined problems. They are not programmed in the traditional way but they are trained using past history data representing the behaviour of a system. They have been used in a number of diverse applications. Results presented in this paper are testimony to the potential of artificial neural networks as a design tool in many areas of building services engineering. Copyright , Manchester University Press.

Thermodynamic analysis of subcooling and superheating effects of alternative refrigerants for vapour compression refrigeration cycles

Abstract: This paper presents a computer-based first law and exergy analysis applied to vapour compression refrigeration systems for determining subcooling and superheating effects of environmentally safe new refrigerants. Three refrigerants are considered: R134a, R407c and R410a. It is found that subcooling and superheating temperatures directly influence the system performance as both condenser and evaporator temperatures are affected. The thermodynamic properties of the refrigerants are formulated using artificial neural network (ANN) methodology. Six ANNs were trained to predict various properties of the three refrigerants. The training and validation of the ANNs were performed with good accuracy. The correlation coefficient obtained when unknown data were used to the networks were found to be equal or very near to 1 which is very satisfactory. Additionally, the present methodology proved to be much better than the linear multiple regression analysis. From the analysis of the results it is found that condenser and evaporator temperatures have strong effects on coefficient of performance (COP) and system irreversibility. Also both subcooling and superheating affect the system performance. This effect is similar for R134a and R407c, and different for R410a. Copyright © 2005 John Wiley & Sons, Ltd.

Neuro-Fuzzy Based Modeling for Photovoltaic Power Supply System

Abstract: Due to the increasing need for intelligent systems, the adaptive neuro-fuzzy inference system (ANFIS) has recently attracted the attention of researchers in various scientific and engineering areas The purpose of this work is to present the modeling of a photovoltaic power supply (PVPS) system using an ANFIS For the modeling of the PVPS system, it is required to find suitable models for its different components (ANFIS PV-generator, ANFIS battery and ANFIS regulator) under variable climatic conditions A database of measured weather data (global radiation, temperature and humidity) and electrical signals (photovoltaic, battery and regulator voltage and current) of a PVPS system installed in Tahifet (south of Algeria) has been recorded for the period from 1992 to 1997 using a data acquisition system These data have been used for the modeling and simulation of the PVPS system The ANFIS for the PV-generator, battery and regulator have been trained by using 10 signals recorded from the different components of the PVPS system Each signal is represented by 365*5 values (complete 5-years) A set of data for 4-years have been used for the training of the ANFIS and data for 1-year has been used for the testing of the ANFIS In this way, the ANFIS was trained to accept and handle a number of unusual cases The comparison between actual and estimated values obtained from the ANFIS gave satisfactory results The correlation coefficient between measured values and those estimated by the ANFIS gave good prediction accuracy of 98% In addition, test results show that the ANFIS performed better than the artificial neural networks (ANN) Predicted electrical signals by the ANFIS can be used for several applications in PV systems

Application of Neural Networks and Genetic Algorithms for Predicting the Optimal Sizing Coefficient of Photovoltaic Supply (PVS) Systems

Abstract: In literature several methodologies based on artificial intelligence techniques (neural networks, genetic algorithms and fuzzy-logic) have been proposed as alternatives to conventional techniques to solve a wide range of problems in various domains. The purpose of this work is to use neural networks and genetic algorithms for the prediction of the optimal sizing coefficient of Photovoltaic Supply (PVS) systems in remote areas when the total solar radiation data are not available. A database of total solar radiation data for 40 sites corresponding to 40 locations in Algeria, have been used to determine the iso-reliability curves of a PVS system (CA, CS) for each site. Initially, the genetic algorithm (GA) is used for determining the optimal coefficient (CAop, CSop) for each site by minimizing the optimal cost (objective function). These coefficients allow the determination of the number of PV modules and the capacity of the battery. Subsequently, a feed-forward neural network (NN) is used for the prediction of the optimal coefficient in remote areas based only on geographical coordinates; for this, 36 couples of CAop and CSop have been used for the training of the network and 4 couples have been used for testing and validation of the model. The simulation results have been analyzed and compared with classical models in order to show the importance of this methodology. The Matlab (R) Ver. 7 has been used for this simulation.

Development of a Neural Network-Based Fault Diagnostic System

Abstract: The objective of this work is to present the development of an automatic solar water heater (SWH) fault diagnosis system (FDS). The FDS system consists of a prediction module, a residual calculator and the diagnosis module. A data acquisition system measures the temperatures at four locations of the SWH system. In the prediction module an artificial neural network (ANN) is used, trained with values obtained from a TRNSYS model of a fault-free system operated with the typical meteorological year (TMY) files of Nicosia, Cyprus and Paris, France. Thus, the neural network is able to predict the fault-free temperatures under different environmental conditions. The input data to the ANN are the time of the year, various weather parameters and one input temperature. The residual calculator receives both the current measurement data from the data acquisition system and the fault-free predictions from the prediction module. The system can predict three types of faults; collector faults and faults in insulation of the pipes connecting the collector with the storage tank and these are indicated with suitable labels. The system was validated by using input values representing various faults of the system.

An ANFIS-based Modeling for a Photovoltaic Power Supply (PVPS) System

Abstract: Due to the increasing need for intelligent systems, the Adaptive Neuro-fuzzy Inference System (ANFIS) has recently attracted the attention of researchers in various scientific and engineering areas. The purpose of this work is to present the modeling of a Photovoltaic Power Supply PVPSsystem using an ANFIS. For the modeling of the PVPS-system, it is required to find suitable models for its different components (ANFIS-PV-array, ANFIS-battery and ANFIS-regulator) under variable climatic conditions. A database of measured weather data (global radiation and temperature) and electrical signals (photovoltaic, battery and regulator voltage and current) of a PVPS system installed in Tahifet (south of Algeria) has been recorded for the period from 1992 to 1997 using a data acquisition system. These data have been used for the modeling and simulation of the PVPS-system. The ANFIS for the PV-array, battery and regulator have been trained by using 8 signals recorded from the different components of the PVPS system. Each signal is represented by 365*5 values (complete 5-years). A set of data for 4-years have been used for the training of the ANFIS, and data for 1-year has been used for the testing of the ANFIS. In this way, the ANFIS was trained to accept and handle a number of unusual cases. The comparison between actual and estimated values obtained from the ANFIS gave satisfactory results. The correlation coefficient between measured values and those estimated by the ANFIS gave good prediction accuracy of 98%. In addition, test results show that the ANFIS performed better than the neural networks. The results obtained from ANFIS can also be used for the prediction of the optimal configuration of PV systems, for the control of PV systems and for the prediction of the performance of the systems.