Degradation Prognostics in Gas Turbine Engines Using Neural Networks

Modeling and Control of Gas Turbine Combustor with Dynamic and Adaptive Neural Networks (TECHNICAL NOTE)

A distributed Intelligent Agent Architecture for Gas-Turbine Engine Health Management

Control and Health Monitoring of complex systems such as Gas-Turbine Engines can potentially receive great benefits from the use of advanced software technologies. However, techniques such as Intelligent Agents, Neural Networks and Genetic Algorithms are predominately designed to optimally perform specific functions, while the rest of the functionality is better achieved using conventional tech...

Embedded Prognostics Health Monitoring

The Pacific Northwest National Laboratory (PNNL) has conducted R&D for the US Army on prognostics health monitoring (PHM). The main focus of the work was to demonstrate the feasibility of developing an onboard PHM system for the gas turbine engine used on the M1 Abrams tank. Research was performed on methods for real time, onboard prognostics/engine life expectancy forecasting, and a prototype ...

Optimum Gain-scheduling Pid Controllers for Gas Turbine Engines Based on Narmax and Neural Network Models

This paper presents PID controller designs based on NARMAX and feedforward neural network models of a Spey gas turbine engine. Both models represent the dynamic relationship between the fuel flow and shaft speed. Due to the engine non-linearity, a single set of PID controller parameters is not sufficient to control the gas turbine throughout the operating range. Gain-scheduling PID controllers ...

Using Safety Critical Artificial Neural Networks in Gas Turbine Aero-Engine Control

‘Safety Critical Artificial Neural Networks’ (SCANNs) have been previously defined to perform nonlinear function approximation and learning. SCANN exploits safety constraints to ensure identified failure modes are mitigated for highly-dependable roles. It represents both qualitative and quantitative knowledge using fuzzy rules and is described as a ‘hybrid’ neural network. The ‘Safety Lifecycle...