Matching Items (2)

157140-Thumbnail Image.png

Comparison of traditional two-spool and three-spool with vaneless counter-rotating: low-pressure turbine for aircraft propulsion power extraction

Description

In previous work, the effects of power extraction for onboard electrical equipment and flight control systems were studied to determine which turbine shaft (i.e. high power shaft vs low power

In previous work, the effects of power extraction for onboard electrical equipment and flight control systems were studied to determine which turbine shaft (i.e. high power shaft vs low power shaft) is best suited for power extraction. This thesis will look into an alternative option, a three-spool design with a high-pressure turbine, low-pressure turbine, and a turbine dedicated to driving the fan. One of the three-spool turbines is designed to be a vaneless counter-rotating turbine. The off-design performance of this new design will be compared to the traditional two-spool design to determine if the additional spool is a practical alternative to current designs for high shaft horsepower extraction requirements. Upon analysis, this thesis has shown that a three-spool engine with a vaneless counter-rotating stage has worse performance characteristics than traditional two-spool designs for UAV systems.

Contributors

Agent

Created

Date Created
  • 2019

153567-Thumbnail Image.png

A new machine learning based approach to NASA's propulsion engine diagnostic benchmark problem

Description

Gas turbine engine for aircraft propulsion represents one of the most physics-complex and safety-critical systems in the world. Its failure diagnostic is challenging due to the complexity of the model

Gas turbine engine for aircraft propulsion represents one of the most physics-complex and safety-critical systems in the world. Its failure diagnostic is challenging due to the complexity of the model system, difficulty involved in practical testing and the infeasibility of creating homogeneous diagnostic performance evaluation criteria for the diverse engine makes.

NASA has designed and publicized a standard benchmark problem for propulsion engine gas path diagnostic that enables comparisons among different engine diagnostic approaches. Some traditional model-based approaches and novel purely data-driven approaches such as machine learning, have been applied to this problem.

This study focuses on a different machine learning approach to the diagnostic problem. Some most common machine learning techniques, such as support vector machine, multi-layer perceptron, and self-organizing map are used to help gain insight into the different engine failure modes from the perspective of big data. They are organically integrated to achieve good performance based on a good understanding of the complex dataset.

The study presents a new hierarchical machine learning structure to enhance classification accuracy in NASA's engine diagnostic benchmark problem. The designed hierarchical structure produces an average diagnostic accuracy of 73.6%, which outperforms comparable studies that were most recently published.

Contributors

Agent

Created

Date Created
  • 2015