@article{MRL_Model_Validation_Testing,

title = {A general model validation and testing tool},

author = {Kevin Vanslette and Tony Tohme and Kamal Youcef-Toumi},

url = {https://www.sciencedirect.com/science/article/pii/S0951832019302571},

doi = {https://doi.org/10.1016/j.ress.2019.106684},

issn = {0951-8320},

year  = {2019},

date = {2019-10-28},

journal = {Reliability Engineering & System Safety},

volume = {195},

pages = {106684},

publisher = {Elsevier BV},

abstract = {We construct and propose the “Bayesian Validation Metric” (BVM) as a general model validation and testing tool. We find the BVM to be capable of representing all of the standard validation metrics (square error, reliability, probability of agreement, frequentist, area, probability density comparison, statistical hypothesis testing, and Bayesian model testing) as special cases and find that it can be used to improve, generalize, or further quantify their uncertainties. Thus, the BVM allows us to assess the similarities and differences between existing validation metrics in a new light. The BVM has the capacity to allow users to invent and select models according to novel validation requirements. We formulate and test a few novel compound validation metrics that improve upon other validation metrics in the literature. Further, we construct the BVM Ratio for the purpose of quantifying model selection under user defined definitions of agreement in the presence or absence of uncertainty. This construction generalizes the Bayesian model testing framework.},

keywords = {Algorithms, Computational Intelligence, Control Theory, Experimentation, intelligent systems, Probabilistic neural networks for robust machine learning, Simulation},

pubstate = {published},

tppubtype = {article}

}

@article{MRL_AFM_MPPT_Controller_Ants,

title = {A new MPPT controller based on the Ant colony optimization algorithm for Photovoltaic systems under partial shading conditions},

author = {Sabrina Titri and Cherif Larbes and Kamal Youcef Toumi and Karima Benatchba},

url = {https://www.sciencedirect.com/science/article/pii/S1568494617302703},

doi = {https://doi.org/10.1016/j.asoc.2017.05.017},

issn = {1568-4946},

year  = {2017},

date = {2017-09-01},

journal = {Applied Soft Computing},

volume = {58},

pages = {465-479},

abstract = {The Maximum Power Point Tracking controller (MPPT) is a key element in Photovoltaic systems (PV). It is used to maintain the PV operating point at its maximum under different temperatures and sunlight irradiations. The goal of a MPPT controller is to satisfy the following performances criteria: accuracy, precision, speed, robustness and handling the partial shading problem when climatic changes variations occur. To achieve this goal, several techniques have been proposed ranging from conventional methods to artificial intelligence and bio-inspired methods. Each technique has its own advantage and disadvantage. In this context, we propose in this paper, a new Bio- inspired MPPT controller based on the Ant colony Optimization algorithm with a New Pheromone Updating strategy (ACO_NPU MPPT) that saves the computation time and performs an excellent tracking capability with high accuracy, zero oscillations and high robustness. First, the different steps of the design of the proposed ACO_NPU MPPT controller are developed. Then, several tests are performed under standard conditions for the selection of the appropriate ACO_NPU parameters (number of ants, coefficients of evaporation, archive size, etc.). To evaluate the performances of the obtained ACO_NPU MPPT, in terms of its tracking speed, accuracy, stability and robustness, tests are carried out under slow and rapid variations of weather conditions (Irradiance and Temperature) and under different partial shading patterns. Moreover, to demonstrate the superiority and robustness of the proposed ACO_NPU_MPPT controller, the obtained results are analyzed and compared with others obtained from the Conventional Methods (P&O_MPPT) and the Soft Computing Methods with Artificial intelligence (ANN_MPPT, FLC_MPPT, ANFIS_MPPT, FL_GA_MPPT) and with the Bio Inspired methods (PSO) and (ACO) from the literature. The obtained results show that the proposed ACO_NPU MPPT controller gives the best performances under variables atmospheric conditions. In addition, it can easily track the global maximum power point (GMPP) under partial shading conditions.},

keywords = {Algorithms, Computational Intelligence, intelligent systems, Mechatronic Design, Probabilistic neural networks for robust machine learning, Simulation},

pubstate = {published},

tppubtype = {article}

}