Dans ce travail nous nous proposons de concevoir un système de diagnostic par reconnaissance de formes immunitaires. La reconnaissance de formes est un vaste champ de recherche, indispensable à tout système intelligent d’aide à la décision. En nous inspirant des systèmes immunitaires nous avons essayé de capturer plusieurs propriétés utiles à la reconnaissance, comme la mémorisation et l’adaptation. L’algorithme développé est inspiré de l’algorithme d’apprentissage bio «CLONCLAS ». Cet algorithme utilise une nouvelle formule pour le calcul d’affinité qui est plus proche du modèle réel. Un logiciel informatique de simulation interactive baptisé DAIS (Diagnosis Artificiel Immun System) est développé sous MATLAB au sein du LAP (Batna), destiné à l’apprentissage et au test d’un système de diagnostic immunitaire de pannes d’un procédé industriel complexe. DAIS utilise les théories immunitaires pour le diagnostic industriel, plus précisément la sélection clonale.

Renewable Energy Sources (RES) are one of the key solutions to handle the world's future energy needs, while decreasing carbon emissions. To produce electricity, large concentrating solar power plants depend on Direct Normal Irradiance (DNI), which is rapidly variable under broken clouds conditions. To work at optimum capacity while maintaining stable grid conditions, such plants require accurate DNI forecasts for various time horizons. The main goal of this study is the forecasting of DNI over two short-term horizons: 15-min and 1-hour. The proposed system is purely based on historical local data and Artificial Neural Networks (ANN). For this aim, 1-min solar irradiance measurements have been obtained from two sites in different climates. According to the forecast results, the coefficient of determination (R 2) ranges between 0.500 and 0.851, the Mean Absolute Percentage Error (MAPE) between 0.500 and 0.851, the Normalized Mean Squared Error (NMSE) between 0.500 and 0.851, and the Root Mean Square Error (RMSE) between 0.065 kWh/m 2 and 0.105 kWh/m 2. The proposed forecasting models show a reasonably good forecasting capability , which is decisive for a good management of solar energy systems.

Renewable Energy Sources (RES) are one of the key solutions to handle the world’s future energy needs, while decreasing carbon emissions. To produce electricity, large concentrating solar power plants depend on Direct Normal Irradiance (DNI), which is rapidly variable under broken clouds conditions. To work at optimum capacity while maintaining stable grid conditions, such plants require accurate DNI forecasts for various time horizons. The main goal of this study is the forecasting of DNI over two short-term horizons: 15-min and 1-h. The proposed system is purely based on historical local data and Artificial Neural Networks (ANN). For this aim, 1-min solar irradiance measurements have been obtained from two sites in different climates. According to the forecast results, the coefficient of determination (R²) ranges between 0.500 and 0.851, the Mean Absolute Percentage Error (MAPE) between 0.500 and 0.851, the Normalized Mean Squared Error (NMSE) between 0.500 and 0.851, and the Root Mean Square Error (RMSE) between 0.065 kWh/m² and 0.105 kWh/m². The proposed forecasting models show a reasonably good forecasting capability, which is decisive for a good management of solar energy systems.

In this paper, we propose a set of times series forecasting techniques based on the combination of Support Vector Regression methods to predict global horizontal solar radiation in Algeria. The models were constructed and tested using different architectures of Support Vector Machine (SVM), namely, (RBF kernel, Polinomial kernel and Linear kernel). We use individual time series models and linear combination techniques to predict global solar radiation indifferent sites in Algeria. For this aim, the recorded data of 4 stations spread over Algeria were used to build different combination schemes for the different times series algorithms. The efficiency of the different models was calculated using a number of statistical indicators: the Mean Absolute Percentage Error (MAPE), the Mean Squared Error (RMSE), Mean Bias Error (MABE) and the Coefficient of Determination (R ²). The results obtained from these models were compared with the measured data.

In this paper, we propose a set of times series forecasting techniques based on the combination of Support Vector Regression methods to predict global horizontal solar radiation in Algeria. The models were constructed and tested using different architectures of Support Vector Machine (SVM), namely, (RBF kernel, Polinomial kernel and Linear kernel). We use individual time series models and linear combination techniques to predict global solar radiation indifferent sites in Algeria. For this aim, the recorded data of 4 stations spread over Algeria were used to build different combination schemes for the different times series algorithms. The efficiency of the different models was calculated using a number of statistical indicators: the Mean Absolute Percentage Error (MAPE), the Mean Squared Error (RMSE), Mean Bias Error (MABE) and the Coefficient of Determination (R ²). The results obtained from these models were compared with the measured data.

In this paper, the problem of time series prediction is studied. A Bayesian procedure based on Gaussian Process (GP) model combined with Linear Discriminate Analysis (LDA) as dimensionality reduction method is proposed. To evaluate the proposed approach, its performance is assessed using three scenarios: long window (latest 50 variables), short window (latest 5 variables) and persistence. To evaluate the performance of the proposed forecast model, the results of the different scenarios are compared to that of Extreme Learning Machines (ELM). Based on measured irradiance data from Tamanrasset, Algeria, the present results describe the performance of the combination of LDA with GP for forecasting hourly global solar irradiance.

This paper proposes an improved approach based on MAS Architecture and Heuristic Algorithm for systematic maintenance to minimize makespan. We have implemented a problem-solving approach for optimizing the processing time, methods based on metaheuristics. The proposed approach is inspired by the behavior of the human body. This hybridization is between a multi-agent system and inspirations of the human body, especially genetics. The effectiveness of our approach has been demonstrated repeatedly in this paper. To solve such a complex problem, we proposed an approach which we have used advanced operators such as uniform crossover set and single point mutation. The proposed approach is applied to three preventive maintenance policies. These policies are intended to maximize the availability or to maintain a minimum level of reliability during the production chain. The results show that our algorithm outperforms existing algorithms. We assumed that the machines might be unavailable periodically during the production scheduling.

uring 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.

Presently, in industrial process plants, requirements for Continuous Emission Monitoring (CEM) have increased significantly. Most plants are investing in these systems in order to burn waste. In this work, we developed a Fuzzy Control of CEM (FCCEM). This system contains operator's stations to supervise the bag filter using Fuzzy Logic. This equipment 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 fuzzy logic involves the removal or filtration of smoke from the kiln and/or raw mill with control of temperature and pressure of fumes.

This paper proposes an improved approach based on MAS Architecture and Heuristic Algorithm for systematic maintenance to minimize makespan. We have implemented a problem-solving approach for optimizing the processing time, methods based on metaheuristics. The proposed approach is inspired by the behavior of the human body. This hybridization is between a multi-agent system and inspirations of the human body, especially genetics. The effectiveness of our approach has been demonstrated repeatedly in this paper. To solve such a complex problem, we proposed an approach which we have used advanced operators such as uniform crossover set and single point mutation. The proposed approach is applied to three preventive maintenance policies. These policies are intended to maximize the availability or to maintain a minimum level of reliability during the production chain. The results show that our algorithm outperforms existing algorithms. We assumed that the machines might be unavailable periodically during the production scheduling.

the work presented in this paper is dedicated to improving the methods of detection and diagnosis of faults affecting production systems, particularly photovoltaic systems. We proposed a new intelligent algorithm for the detection and diagnosis of PV installations, capable of detecting and resonate to define the type of defects that can affect this type of system. This new algorithm is based on the notion of pattern recognition, for that it is able to prepare the representation space and the decision space on the one hand, and on the other hand, the classification of all new observations collected during the functioning of the system. This algorithm mainly based on the method of knearest neighbor and two tools of artificial intelligence to improve this method and increasing the rate of its classification, which are fuzzy logic to optimize the location of the centers of gravity of classes and also the new observations, and the neural network that can classify the case of discharges ambiguity and releases distance which presents the limitations of the method of the k-nearest neighbor. We tested the performance of our algorithm on a database of a photovoltaic system at the research unit of GHARDAIA Algeria

Solar energy is expected to provide a major contribution to the future global energy supply, while helping the transition toward a carbon-free economy. Because of its variable character, its efficient use will necessitate trustworthy forecast information of its availability in a variety of spatial and time scales, depending on application. This study proposes a new forecasting approach for irradiance time series that combines mutual information measures and an Extreme Learning Machine (ELM). The method is referred to as Minimum Redundancy – Maximum Relevance (MRMR). To assess the proposed approach, its performance is evaluated against four scenarios: long window (latest 50 variables), short window (latest 5 variables), standard Principal Components Analysis (PCA) and clear-sky model. All these scenarios are applied to three typical forecasting horizons (15-min ahead, 1-h ahead and 24-h ahead). Based on measured irradiance data from 20 sites representing a variety of climates, the test results reveal that the selection of a good set of relevant variables positively impacts the forecasting performance of global solar radiation. The present findings show that the proposed approach is able to improve the accuracy of solar irradiance forecasting compared to other proposed scenarios.