论文信息 - Autonomously Learning Fault Detection System for Gas Turbine Engines

Autonomously Learning Fault Detection System for Gas Turbine Engines

Abstract Highly sophisticated control strategies are generally employed to control aircraft gas turbine engines which have to operate in harsh environmental conditions. Faults are difficult to detect with this increased complexity and the present fault detection systems sometimes indicate the wrong components to be faulty. These faults cost the airline industry millions of pounds each year. To improve the performance of these existing systems an autonomously learning fault detection system is proposed. The system is capable of detecting new faults and also adapting to faults that are similar to faults previously encountered. This paper presents the performance of this system when applied to real engine data and gives details on the improvements made to the system.

Visakan Kadirkamanathan | Haydn A. Thompson | V. C. Patel

[1] Mark A. Kramer,et al. Diagnosing dynamic faults using modular neural nets , 1993, IEEE Expert.

[2] Guy Denney,et al. F16 jet engine trending and diagnostics with neural networks , 1993, Defense, Security, and Sensing.

[3] Visakan Kadirkamanathan,et al. Utilising a Simulink Gas Turbine Engine Model for Fault Diagnosis , 1995 .

[4] Visakan Kadirkamanathan,et al. A Function Estimation Approach to Sequential Learning with Neural Networks , 1993, Neural Computation.

[5] Timo Sorsa,et al. APPLICATION OF ARTIFICIAL NEURAL NETWORKS IN PROCESS FAULT DIAGNOSIS , 1992 .

[6] Liya Hou,et al. Diagnosis of multiple simultaneous fault via hierarchical artificial neural networks , 1994 .

[7] J. B. Gomm. Process Fault Diagnosis using a Self-Adaptive Neural Network with On-Line Learning Capabilities , 1995 .

[8] John C. Platt. Leaning by Combining Memorization and Gradient Descent , 1990, NIPS.

[9] Venkat Venkatasubramanian,et al. Neural network decomposition strategies for large-scale fault diagnosis , 1994 .

[10] Heikki N. Koivo,et al. Application of artificial neural networks in process fault diagnosis , 1991, Autom..

[11] A. Duyar,et al. A failure diagnosis system based on a neural network classifier for the Space Shuttle main engine , 1990, 29th IEEE Conference on Decision and Control.