M. Benghanem

Least squares support vector machine for short-term prediction of meteorological time series

The prediction of meteorological time series plays very important role in several fields. In this paper, an application of least squares support vector machine (LS-SVM) for short-term prediction of meteorological time series (e.g. solar irradiation, air temperature, relative humidity, wind speed, wind direction and pressure) is presented. In order to check the generalization capability of the LS-SVM approach, a K-fold cross-validation and Kolmogorov–Smirnov test have been carried out. A comparison between LS-SVM and different artificial neural network (ANN) architectures (recurrent neural network, multi-layered perceptron, radial basis function and probabilistic neural network) is presented and discussed. The comparison showed that the LS-SVM produced significantly better results than ANN architectures. It also indicates that LS-SVM provides promising results for short-term prediction of meteorological data.

Data acquisition system for photovoltaic water pumps

In Algeria, there are several photovoltaic water pumping system (PVWPS) which are situated in remote areas. Typical problems are detected as sizing of photovoltaic (PV) generator (over-sizing) and maintenance (underestimate) by many operators. Due to the high cost of setting up and maintaining a large number of data acquisition systems for the PVWPS, we have developed a real time expert system based on central microcomputer used as a micro-server, with a low cost. This paper presents a design of a universal data acquisition system for Algeria with available components and easily accessible with a central server. This data acquisition system analyses the performance of PVWPS. The systems hardware and software architectures and an application to test its performance are described.

Modelling of sizing the photovoltaic system parameters using artificial neural network

The objective of this work is to use an artificial neural network (ANN) to predict the sizing parameters of photovoltaic (PV) system with a minimum of input data. A neural network has been trained by using 54 known sizing parameter data corresponding to 54 locations. In this way the network was trained to accept and even handle a number of unusual cases. Known data were subsequently used to investigate the accuracy of prediction. A prediction with maximum deviation of 6% was obtained. This result indicates that the proposed method can successfully be used for the estimation of sizing parameters data for any locations.

Performance of stand-alone photovoltaic systems using measured meteorological data for Algiers

In order to estimate the performance of photovoltaic (PV) systems, we develop a real time expert system based on central microcomputer used as microserver and easily consultable with different automatic stations. We present in this paper, the principles and specificities of the measurement system and of the automatic data measuring device and its sensors, and also some aspects of the database and expert system developed for this application. We propose a method based on the determination of the loss-of-load probability (LLP), which allows the estimation of the optimum combination of battery capacity (Cs) and photovoltaic array peak power (Pc). The problem consists of determining the combination which corresponds to a minimum total system cost.

Generation of Large Volume Atmospheric Pressure Air Plasma

Atmospheric pressure large volume air plasma was generated by applying 100 ns, 1-kHz high voltage pulse between two parallel electrodes separated by 48-mm gap. The high voltage power electrode has uniformly distributed pens and ground electrode shaped as a flat disc. Glow discharge ignition is initialized at the outer pens to form luminousness circle. By applying higher voltage, the glow expands to ignite the internal pens and to fill the gap between the two electrodes. Each pen forms glow discharge plasma with the ground electrode. The increase in voltage or frequency enhances the plasma intensity and homogeneity. The generated plasma showed efficiency against the fruit borne fungi of grapes.

Solar radiation estimated from measured air temperature: a review and proposed a new model

Estimation of solar radiation from measured air temperature offers an important alternative in the absence of measured solar radiation because of the wide availability of air temperature data. Solar radiation is considered as the most important parameter in meteorology, solar conversion, and renewable energy applications. Many correlation models have been developed to estimate daily solar radiation using air temperature measurement. The main objective of this paper is to present an overview of methods based on air temperature data to predict solar radiation data. Published literature presented in this paper show the importance of air temperature data as a design tool for the simulation of solar radiation data. The models presented in this paper provide good estimation of solar radiation data, especially in isolated areas, where the weather data are not always available. Also, we propose one new model for estimating daily global solar radiation from measured air temperature for Madinah site. A newly developed model that includes the difference between maximum and minimum daily air temperature estimates the global solar radiation with higher accurately.

Artificial intelligence techniques for prediction of solar radiation data: a review

Artificial intelligence (AI) techniques are becoming useful as alternate approaches to conventional techniques. They have been used to solve complicated practical problems in various areas and are able to deal with non-linear problems. AI techniques have been applied for modelling, identification, optimisation, prediction, forecasting, and control of complex systems. Artificial neural networks have been used by the author in the field of solar energy for the estimation of solar radiation data. The main objective of this paper is to present an overview of the AI-techniques for prediction of solar radiation data. Published literature presented in this paper show the potential of AI as a design tool for the simulation of solar radiation data and also forecasting and modelling others meteorological data. The advantage of using an AI-based prediction of solar radiation is that it provides good estimation of data, especially in isolated areas, where the weather data are not available.

Large volume air plasma for fruit sterilization

Summary form only given. Large volume atmospheric pressure air plasmas [1,2] were generated by applying ~ 100 ns high voltage pulse between two parallel electrodes separated by 48 mm gap in air. The generated plasma frequencies can be varied from single pulse to 2000 Hz. A uniformly distributed stainless steel pens were welded to the high voltage electrode while the grounded electrode is a metallic flat disc. The pens have 32 mm length and 0.48 mm radius and separated by 8.7 mm to form a brush-shape. The pin tips are cut to form sharp ends to enhance the applied electric field and reduced the ignition voltage. The atmospheric pressure large volume glow discharges plasma ignite first at the outer pens forming luminousness circle then the internal pens ignited with the increase in the applied voltage. The glowed plasma expanded to cover the gap by increasing the applied voltage. Each pens form glow discharge with the ground electrode. The plasma intensity and homogeneity enhanced with increasing the applied voltage or the plasma frequency. The emission spectra investigations declared the main presence of nitrogen bands, second positive band and first negative band in the investigated range between 200 nm and 800 nm. The generated plasma was successfully proved as an efficacious tool for sterilizing a wide range of fruits from the naturally occurring bacterial and fungal contamination.

Characteristics of cold atmospheric pressure plasma jet and its antimicrobial activity

Cold atmospheric pressure plasma jet (CAPPJ) has been approved by several investigators as anti-microbial agent [1]. In this experiment, CAPPJ in air is generated by applying AC voltage 7-14 kV (peak-to-peak), with frequency of 21-29 kHz to Al2O3 tube. The tube has 150 mm length with a 4 and 6 mm inner and outer diameter, respectively. Argon flow rates ranged from 0.1 to 10 SLM were blown through the tube to form the plasma jet. The addition of oxygen to argon as operating gases enhances the generation of O and OH radicals. The electric and spectroscopic characteristics of the generated plasma jet were investigated. The generated plasma jet length and mode of operation varied as a function of oxygen flow rate percentage, applied voltage and frequency. The plasma jet length increases with argon flow rate to reach its maximum at 5 SLM then ceases to reach saturation at 8 SLM. The energies consumed by the discharge were estimated using the charge-voltage curve (Lissajous figure). The consumed energy increased with increasing the input power. Regarding the decontamination, the data indicate an optimum condition of E. coli sterilization at 0.02% of oxygen.

Double jet atmospheric pressure plasma as a decontaminating agent

Summary form only given. Atmospheric pressure plasmas jet are recently of high interest due to the promising biomedical applications. Double atmospheric pressure plasma jet system was used to disinfect date-palm fruits. The double jet was formed by blowing argon gas though ceramic alumina tube. It has two capillaries of 1 mm inner diameter for each and 31.5 mm outer diameter. The two capillaries are separated by 3.8 mm. The generated double jet plasma was characterized electrically, spectroscopically and photographically. A high voltage ~20 kHz sinusoidal wave was applied to a copper ring electrode surrounding the tube. The two jets were ignited simultaneously and homogeneous plasma is formed as indicated from the current waveform. Photographic investigation shows that the double plasma jet length increases with the increase in argon gas flow rate to reach optimum length at 3.5 l/min. However, the double jet shrinks with higher flow rates. The presence of OH, O radicles, excited nitrogen molecules and argon species were detected in the double jet spectra, at 3 mm from jet nozzle. The presence of reactive species nominated the double jet to be as sterilized tool. Therefore, the double jet plasma was successfully used to inactivate A. niger spores, inoculated onto sterilized date palm discs at different flow rate from 0.5 to 4.5 l/min. with optimum efficacy measured at 3.5 l/min which is probably related to the higher amount of reactive species, OH and O radicals.