This paper discusses the limitations of time-based equipment maintenance methods and the advantages of predictive or online maintenance techniques in identifying the onset of equipment failure. The three major predictive maintenance techniques, defined in terms of their source of data, are described as follows: 1) the existing sensor-based technique; 2) the test-sensor-based technique (including wireless sensors); and 3) the test-signal-based technique (including the loop current step response method, the time-domain reflectrometry test, and the inductancecapacitance-resistance test). Examples of detecting blockages in pressure sensing lines using existing sensor-based techniques and of verifying calibration using existing-sensor direct current output are given. Three Department of Energy (DOE)-sponsored projects, whose aim is to develop online and wireless hardware and software systems for performing predictive maintenance on critical equipment in nuclear power plants, DOE research reactors, and general industrial applications, are described.
