Dynamic System Fault Diagnosis Under Sparseness Assumption

Dynamic system fault diagnosis is often faced with a large number of possible faults. The purpose this paper to propose an efficient method for such situations. To avoid intractable combinatorial problems, sparse estimation techniques appear be powerful tool isolating faults, under the assumption that only small faults can simultaneously active. However, studied in framework linear algebraic equations , whereas model-based usually investigated xmlns:xlink="http://www.w3.org/1999/xlink">dynamic systems modeled xmlns:xlink="http://www.w3.org/1999/xlink">state involving xmlns:xlink="http://www.w3.org/1999/xlink">internal states . main contribution link between these two formalisms through and reliable algorithms, mainly relying on advanced analyses residuals generated Kalman Kitanidis filters. Based results, it becomes straightforward solve problems by applying well known techniques, general time varying state-space unknown inputs.