Orchard M., Lacalle M., Olivares B., Cerda M., Silva J F., 2013, Information-Theoretic Measures and Sequential Monte Carlo Methods for Detection of Regeneration Phenomena in the Degradation of Energy Storage Devices, Chemical Engineering Transactions, 33, 73-78.
This paper compares the performance of several approaches for anomaly detection that are based on a combination of information-theoretic measures and sequential Monte Carlo methods for state estimation in nonlinear, non-Gaussian dynamic systems. All approaches conveniently use properties of the differential entropy to quantify the impact of process measurements on the posterior probability density function (PDF) of the state, assuming that sub-optimal Bayesian estimation algorithms such as classic particle filters (PF) or risk-sensitive particle filters (RSPF) are to be used to obtain an empirical representation of the system uncertainty. The proposed anomaly detection strategies are tested and evaluated both in terms of (i) detection time (early detection) and (ii) false alarm rate, when utilized to identify the existence of capacity regeneration phenomena ([A-h]) in energy storage devices (particularly, Lithium-Ion batteries).
