应用图像处理进行内燃机故障诊断时应注意的几个问题

Several Problems in Fault Diagnosis of Internal Combustion Engines with Image Processing

图像处理技术在内燃机的故障诊断与状态监测中应用还很少 ,本文探讨了应用于这方面时应注意的几个问题。指出利用缸盖振动信号小波包分解后的时 -频分布图的灰度直方图进行故障诊断的效果并不好 ,并分析了原因 ;进行了信号加噪声与不加噪声的诊断效果对比 ,发现噪声对基于图像处理的气门机构故障诊断的影响不大 ,验证了这一方法的工程实用性和可用性。

There are few applications of image processing technology to the diagnosing and state monitoring for internal combustion engines.Some notes are presented in this paper when one takes this method.It has been proved that it has no good effect to diagnose with gray histogram of the time frequency image brought by the cylinder head vibration signal after it is been processed with wavelet packet algorithm.The reason is given in this paper.Comparisons of diagnosing effect are carried out between noise-added signal and source signal.It has a little effect to the diagnosing after signal has been added with noise.It is of good engineering practicability and feasibility.