测试系统中波形的神经网络识别方法

为满足自动测试系统对信号波形的智能化识别要求,在对现有的波形识别方法进行研究的基础上,提出一种新的波形识别方法;该方法在利用离散余弦变换（DCT）对波形进行频域特征提取的基础上,将模式识别与BP神经网络理论相结合从而建立波形特征匹配模板,最终实现对信号波形的智能识别;对比试验表明,该方法与最大相关系数法（MCC）、最大相关差值法（MCD）相比很好地解决了待测波形与模板波形匹配过程中的相位对齐过程,而且更加快速、高效。

Waveform Recognition by Neural Network in Test System

To satisfy the intelligence requirements of recognizing signal waveform in test system,a new waveform recognition solution is presented on the basis of analyzing existing waveform recognition methods.This solution constructs waveform matching template which combines the pattern recognition and BP neural network after extracting waveform features through DCT and recognizes signal waceform intelligently in the end.The experiments show that this new solution can deal with the phase alignment problem and is more fast and effective than some current methods.