Modeling Failures of Intermittently Used Machines.
Abstract
This research memorandum presents methodology for analyzing failures of machines that are repeatedly turned on and off. Because a machine can fail both when it is on and off, different parametric models for failure are used for each of these periods. An important issue addressed for such machines is how the intermittent use itself affects failure. Because the models can predict the chance of failure under different usage patterns, less harmful usage patterns can be recommended. As an example, the models are applied to a radar system, and both the immediate and cumulative effects of on-off cycling are demonstrated. Keywords: Regression analysis, Statistical analysis, Statistical models, Time intervals, Weibull model, Parametric analysis.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jul 01, 1987
- Accession Number
- ADA190298
Entities
People
- Dean A. Follmann
Organizations
- Center for Naval Analyses