一种基于小波的发动机数据融合算法

Multi-Sensor Data Fusion Method Based on Wavelets

航空发动机测试中,内部气流工况十分复杂,使用多传感器对同一截面进行测试表征一个面的气流状态,其结果往往有个别点不符合规律。为此,提出一种基于小波分析的解决方案。首先对发动机多传感器测试数据进行小波分频。然后从相似性、能量衰减等多个角度进行分析,指出高频和低频的不同特征,并提出对高频与低频部分使用不同方法进行融合的思路。最后总结出一种适用于航空发动机高空模拟试验数据使用的基于小波的数据融合算法。

Multi-sensors are often used in engine tests. However the results sometimes are difficult to inter- pret especially when data are irregular distributed and even inconsistent because of the complex environ- ment. A new fusion way based on wavelet analysis was presented. The sensor data were divided into two parts： high frequency and low frequency areas, which were examined from various aspects such as similarity and energy attenuation. It is found that there are many different characteristics between the two parts, and it is necessary to use different fusion methods to hand them. Finally a fusion algorithm based on wavelets has been presented.