This paper proposes an artificial neural network (ANN) controller for the maximum power point tracking (MPPT) of a photovoltaic system under rapidly varying temperature and solar radiation conditions. This intelligent control method is applied to a DC/DC Buck-Boost converter. The main difference between the proposed systems to existing MPPT control systems is that it includes an automatic determination of the main switch duty cycle which permits an optimal operation of the control circuit under steady and perturbed environmental conditions. The maximum power point tracking controllers receive solar radiation and photovoltaic cell temperature as inputs, and it estimates the optimum duty cycle corresponding to maximum power as output. The different steps of the design of the intelligent controller are presented hereby with some simulation results using Matlab/Simulink software.

This paper proposes an artificial neural network (ANN) controller for the maximum power point tracking (MPPT) of a photovoltaic system under rapidly varying temperature and solar radiation conditions. This intelligent control method is applied to a DC/DC Buck-Boost converter. The main difference between the proposed systems to existing MPPT control systems is that it includes an automatic determination of the main switch duty cycle which permits an optimal operation of the control circuit under steady and perturbed environmental conditions. The maximum power point tracking controllers receive solar radiation and photovoltaic cell temperature as inputs, and it estimates the optimum duty cycle corresponding to maximum power as output. The different steps of the design of the intelligent controller are presented hereby with some simulation results using Matlab/Simulink software.

During the last years, in industrial process control, requirements for Continuous Emission Monitoring (CEM) have increased significantly. Most plants are investing in CEM systems in order to burn waste, obtain ISO 14000 and 18001 certification to protect operator's life. In this work, our approach describes development of a novel internet and fuzzy-based CEM system (IFCEMS). This system contains operator's stations for the bag filter's automation system and monitored using Internet. The object of the present installation consists of a suction ventilator, a bag filter and a system for collecting and evacuating the dust. To optimize the running of the bag filter workshop and ensure continuous control, the process based on one of the most powerful Artificial Intelligence techniques which is fuzzy logic involves the removal or filtration of smoke from the kiln and/or cement mill with control of temperature and pressure of the fumes.

In this paper, we present a simple new human activity recognition method using discrete cosine transform (DCT). The scheme uses the DCT coefficients extracted from silhouettes as descriptors (features) and performs frame-by-frame recognition, which make it simple and suitable for real time applications. We carried out several tests using radial basis neural network (RBF) for classification, a comparative study against stat-of-the-art methods shows that our technique is faster, simple and gives higher accuracy performance comparing to discrete transform based techniques and other methods proposed in literature.