Sensor fault diagnosis of gas turbine engines using an integrated scheme based on improved least squares support vector regression

As the flight envelope is widening continuously and operational capability is improving sequentially, gas turbine engines are faced with new challenges of increased operation and maintenance requirements for efficiency, reliability, and safety. The measures for security and safety and the need for reducing the life cycle cost make it necessary to develop more accurate and efficient monitoring and diagnostic schemes for the health management of gas turbine components. Sensors along the gas path are one of the components in gas turbines that play a crucial role in turbofan engines owing to their safety criticality. Failures in sensor measurements often result in serious problems affecting flight safety and performance. Therefore, this study aims to develop an online diagnosis system for gas path sensor faults in a turbofan engine. The fault diagnosis system is designed and implemented using a genetic algorithm optimized recursive reduced least squares support vector regression algorithm. This method uses a reduction technique and recursion strategy to obtain a better generalization performance and sparseness, and exploits an improved genetic algorithm to choose the optimal model parameters for improving the training precision. The effectiveness of the sensor fault diagnosis system is then validated through typical fault modes of single and dual sensors.