International audienceThis paper deals with an image processing methodology based on a sky-imaging system developed at the PROMES-CNRS laboratory. It is a part of a project which aims at improving solar plant control procedures using Direct Normal Irradiance (DNI) forecasts under various sky conditions at short term horizon (5-30 minutes) and high spatial resolution (~1 km²). The work presented in this paper is about the improvement of the cloud cover estimation, which is the main step in DNI forecasting. First, an overview of the existing sky-imaging systems and the current cloud detection algorithms is presented. Next, the experimental setup is introduced. Then, the methodology used to estimate the cloud cover is detailed. Finally, the paper ends with some results and discussion

International audienceThe present work is part of a global development of reliable real time control and supervision tools applied to wastewater pollution removal processes. In this processes, oxygen is a key substrate in animal cell metabolism and its consumption is thus a parameter of great interest for the monitoring. In this paper, are presented and discussed the results of the Dissolved Oxygen (DO) control in a SBR pilot plant based on a predefined 8 hours step-feed cycle. As first approach, the application of classical methods (on/off and PID) was considered. Due to the non linear character of the process, the PID parameter adjusting was very difficult and the obtained results showed a beating phenomenon around the setpoint. This phenomenon was more and less amplified according to the step of the cycle and the water pollution level. The second approach to achieve more stable DO control was based on a fuzzy logic strategy, taking into account the step and the difference between the measured DO and the setpoint. In this case, control action performances were highly improved. It's also shown that, using the fuzzy controller, the pH profile made it possible to clearly detect the ammonia valley during the aerobic phases. Thus, fuzzy logic proved to be a robust and effective DO control tool, easy to integrate in a global monitoring system for cost managing

To cite this version:Julien Eynard, Stéphane Grieu, Monique Polit. Wavelet-based multi-resolution analysis and artificial neural networks for forecasting temperature and thermal power consumption. Engineering Applications of Artificial Intelligence, Elsevier, 2011, 24 (3) Domitia, 52 Av. Paul Alduy, 66860, Perpignan, Abstract: as part of the OptiEnR research project, the present paper deals with outdoor temperature and thermal power consumption forecasting. This project focuses on optimizing the functioning of a multi-energy district boiler (La Rochelle, west coast of France), adding to the plant a thermal storage unit and implementing a model-based predictive controller. The proposed short-term forecast method is based on the concept of time series and uses both a wavelet-based multi-resolution analysis and multi-layer artificial neural networks. One could speak of "MRA-ANN" methodology. The discrete wavelet transform allows decomposing sequences of past data in subsequences (named coefficients) according to different frequency domains, while preserving their temporal characteristics. From these coefficients, multi-layer Perceptrons are used to estimate future subsequences of 4 hours and 30 minutes. Future values of outdoor temperature and thermal power consumption are then obtained by simply summing up the estimated coefficients. Substituting the prediction task of an original time series of high variability by the estimation of its wavelet coefficients on different levels of lower variability is the main idea of the present work. In addition, the sequences of past data are completed, for each of their components, by both the minute of the day and the day of the year to place the developed model in time. The present paper mainly focuses on the impact on forecast accuracy of various parameters, related with the discrete wavelet transform, such as both the wavelet order and the decomposition level, and the topology of the neural networks used. The number of past sequences to take into account and the chosen time step were also major concerns. The optimal configuration for the tools used leads to very good forecasting results and validates the proposed MRA-ANN methodology.