In the context of the electricity production, the solar energy is appropriate and endless. At present the technologies of solar concentration are the one which present most possibilities for commercial use. Thus, it is necessary not only to design processes of conversion of energy, but it is also important to assure an availability of these equipment by the conception of fault detection and isolation (FDI) systems. To improve the behavior of the solar power plant, we use a model based on differential algebraic equations to describe variations of the solar radiation, ambient temperature, flow rate and temperature of fluid. These phenomena are highly nonlinear. Moreover, a large class of nonlinear systems can be well approximated by T-S fuzzy models. The diagnosis scheme is based on a fuzzy observer to estimate faults and faulty system states; a proportional (P) observer to estimate constant faults in then adopted. Using descriptor redundancy property, a solution is proposed in terms of linear matrix inequalities (LMI). The performance of the proposed approach is pointed out by focusing on a model of solar power plant through numerical results.
Nowadays, rotating machines (RM) plays an important role in industry. Therefore detection a precise faults in main part of RM will avoid non programmed stops of production by real time management of machine status. Different detection methods using vibration signature analysis, noise signature analysis and lubricant signature analysis were presented in literature reviews however there is no much techniques using bio-inspired features. In this work acoustic signal analysis and processing based on speech recognition techniques were used to detect early faults in REB namely: faults in rolling ball, in inner race, outer race and protecting cage. Commonly used Speech recognition features were selected, also two classifiers, used in ASR, were tested Euclidian distance and K-NN method, the overage results obtained using combination of features and ED is 92% while the results are improved using the K-NN methods to the average of 94%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.