航空发动机传感器故障诊断

研究航空发动机传感器故障诊断问题,由于发动机传感器故障样本有限、小样本、非线性变化特点,传统大样本传统故障方法故障诊断准确率低。为提高传感器故障诊断准确率,提出一种混沌粒子群算法(CPSO)和最小二乘支持向量机(LSS-VM)相结合的传感器故障诊断算法(CPSO-LSSVM)。首先将发动机传感器信号输入到LSSVM进行学习,并采用CPSO进行优化,找到最优LSSVM参数,从而建立传感器故障诊断模型,最后采用已建立模型对传感器故障进行仿真测试。仿真结果表明,CPSO-LSSVM提高了航空发动机传感器故障诊断的准确率,能准确地对空发动机传感器故障进行诊断,提供民飞行安全性能保障。

Fault Diagnosis for Sensors in Aeroengine

Because aeroengine sensors are working in complex environment,the fault samples of engine sensor are limited,and the fault diagnosis based on large samples is prone to failure.This paper presents a sensor fault diagnosis algorithm(CPSO-LSSVM) based on least squares support vector machine(LSSVM) and chaos particle swarm optimization algorithm(CPSO).The engine sensor signal was input to the LSSVM for learning,and then the LSSVM parameters were optimized by CPSO,thereby established the sensor fault diagnosis model.Finally,the established model was test by sensor fault simulation experiment.The simulation results show that the proposed algorithm can improve the aircraft engine sensor fault diagnosis accuracy and diagnose faults timely and accurately.