An end-of-life prediction system developed for electric machines and their loads could be used in integrated vehicle health monitoring at NASA and in other government agencies. This system will provide on-line, real-time condition assessment and end-of-life prediction of electric machines (e.g., motors, generators) and/or their loads of mechanically coupled machinery (e.g., pumps, fans, compressors, turbines, conveyor belts, magnetic levitation trains, and others). In long-duration space flight, the ability to predict the lifetime of machinery could spell the difference between mission success or failure. Therefore, the system described here may be of inestimable value to the U.S. space program.

No known system (hardware, software, or hybrids) currently exists that performs this function. While there are several software programs used commercially that address various aspects of the off-line diagnostics analysis of rotating equipment — including motors, generators, turbines, and the like — the ineffectiveness of these programs in diagnosing incipient failures is well documented. Indeed, industry feedback suggests that the majority of these software tools will provide accurate diagnoses in only about 60 to 65 percent of analyzed cases.

The system differs greatly from commercial software because the system will provide continuous monitoring for on-line condition assessment and end-of-life prediction as opposed to the current offline diagnoses. Similarly, the system will also provide real-time condition assessment and end-of-life prediction as contrasted with the delayed diagnosis of commercially available software. Indeed, this system also will provide automated condition assessment and end-of-life prediction (not manual fault diagnosis analysis), integrated condition assessment and end-of-life prediction capability (not the current sensor-dependent fault diagnosis analysis), and machine and/or load-independent condition assessment and end-of-life prediction, which differs significantly from the machine-dependent diagnosis of commercial software systems. In sum, therefore, this invention provides the following new and critical features:

  • an all-in-one on-line, real-time condition assessment and end-of-life prediction system for electric machines and their loads;
  • a machine- and load-independent condition assessment and end-of-life prediction system; and
  • enhanced effectiveness resulting from the information-processing technologies used.

The system clearly advances the state-of-the-art. Its software is independent of any specific hardware platform, no third-party programs are required for operations, and the system can be implemented with any high- or low-level programming language. Potential users of this software will run the gamut from the space program (for which it was developed) to anyone who maintains electric machines and their loads.

This work was done by Alexander G. Parlos and Hamid A. Toliyat of Texas A&M University, Departments of Mechanical and Electrical Engineering for Johnson Space Center. For further information, contact:

Alexander G. Parlos
E-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Refer to MSC-22894, volume and number of this NASA Tech Briefs issue, and the page number.

ORIGINAL URL - /Briefs/Oct05/MSC_22894.html