Semester

Fall

Date of Graduation

1999

Document Type

Thesis

Degree Type

MS

College

Statler College of Engineering and Mineral Resources

Department

Lane Department of Computer Science and Electrical Engineering

Committee Chair

Bojan Cukic.

Abstract

One possible method of reliability assurance is the application of large testing sets upon a system via statistical reliability assessment. Under this method, a software system's operations are tested according to their actual usage. A problem with this approach is the large number of tests required to properly assess reliability. Complicating the process are situations where an input into the system is a trajectory of data, where a trajectory is defined as a series of data points with each point relying upon the previous points. Examples of trajectories of data include an airplane's flight path or data describing a nuclear reaction. Whereas test data generation has addressed the creation of individual test points, creating test trajectories have yet to be adequately studied.;This thesis focuses upon a trajectory generation algorithm using statistical regression models. The algorithm is developed to aid reliability assessment by increasing the size of the test data. An existing small set of trajectories is utilized to build the regressive models. Then, the independent variables of the model can be perturbed, thus allowing the generation of new trajectories.;A case study is conducted for a sensor failure detection, identification, and accommodation (SFDIA) flight control scheme. Our test trajectory generation algorithm uses test data collected from a flight simulator of a Boeing 777. The regressive models speed up the trajectory generation process by more than three orders of magnitude when compared with flight data collection.

Share

COinS