Equipment Condition Monitoring and Prognostic Methods for Single Variable Systems 2009-01-3164
This paper introduces empirical modeling techniques for process and equipment monitoring, fault detection and diagnostics, and prognostics. The paper first provides a brief background and an overview of the theoretical foundations and presents a new method for applying these methods to systems which only have one useful measured variable. A case study is then presented for the application of the method to an aircraft generator that includes
Normal feature prediction over different operating conditions
Actual feature measurement and residual generation
Fault detection, identification, and quantification
Application of the proposed single variable monitoring system to the simulated aircraft generator data resulted in fault diagnosis accuracy of 96.3%, only one misdiagnosed case in 27, for the types and severities of faults considered. Future work in developing a prognostic model for a single-variable system will be outlined.