A computer program partly automates the analysis, classification, and display of waveforms represented by digital samples. In the original application for which the program was developed, the raw waveform data to be analyzed by the program are acquired from space shuttle auxiliary power units (APUs) at a sampling rate of 100 Hz. The program could also be modified for application to other waveforms — for example, electrocardiograms. Before this program became available, the raw APU waveforms were recorded on paper strip charts — a practice that imposed a substantial workload on human operators and was not conducive to consistently accurate, real-time analysis and classification. The program reduces the operator workload, increases the accuracy of classifications, and presents results in real time.

The program begins by performing principal-component analysis (PCA) of 50 normal-mode APU waveforms. Each waveform is segmented. A covariance matrix is formed by use of the segmented waveforms. Three eigenvectors corresponding to three principal components are calculated. To generate features, each waveform is then projected onto the eigenvectors. These features are displayed on a three-dimensional diagram, facilitating the visualization of the trend of APU operations.

It is necessary to classify each of the normal-mode waveforms as being characteristic of one of three mode types known among APU specialists as "nominal," "engine," or "aero." For this purpose, each waveform is segmented and its average energy is computed. For engine and aero modes, time information is also used, and information about peaks in the waveforms is used to determine which mode is present.

It is also necessary, when there is a malfunction, to classify waveforms as being characteristic of one or more error mode(s). To enable such classification of a waveform in real time, it is necessary to prepare the software and associated data base in a prior process that includes a careful analysis of the wave-form known to be associated with each of at least five known error modes to which the APUs are subject. For each error mode, some distinct features of the waveform are extracted. Thereafter, in operation, a waveform is automatically classified as belonging to an error mode according to a few rules based on these features.

This program was written by Chiman Kwan, Roger Xu, David Mayhew, and Frank Zhang of Intelligent Automation, Inc., and Alan Zide and Jeff Bonggren of the Boeing Co. for Kennedy Space Center. In accordance with Public Law 96-517, the contractor has elected to retain title to this invention. Inquiries concerning rights for its commercial use should be addressed to:

Intelligent Automation, Inc.
Attn. Chiman Kwan
7519 Standish Place, Suite 200
Rockville, MD 20855
Phone: (301) 294-5238
E-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Refer to KSC-12568, volume and number of this NASA Tech Briefs issue, and the page number.