Diagnosis of CO Pollution in HTPEM Fuel Cell using Statistical Change Detection

The fuel cell technologies are advancing and maturing for commercial markets. However proper diagnostic tools needs to be developed in order to insure reliability and durability of fuel cell systems. This paper presents a design of a data driven method to detect CO content in the anode gas of a high temperature fuel cell. In this work the fuel cell characterization is based on an experimental equivalent electrical circuit, where model parameters are mapped as a function of the load current. The designed general likelihood ratio test detection scheme detects whether a equivalent electrical circuit parameter differ from the non-faulty operation. It is proven that the general likelihood ratio test detection scheme, with a very low probability of false alarm, can detect CO content in the anode gas of the fuel cell.