摘要
通过选择合适的嵌入维数以及计算关联维数可用来表征柴油机振动信号的分形性质,但实际测取的振动信号中存在着许多干扰信息。利用改进的小波包分解和重构算法对原始信号进行降噪处理,可使信号关联维数较为接近于系统的真值。实验分析表明,利用降噪后的信号关联维数判断柴油机运行状态具有准确性高的特点。
With proper embedded dimensions, the calculated correlation dimension can reflect the fractal quality of the diesel vibration signals. Though some noise may exist in the measured signals, the ameliorated wavelet packet analysis and reconstruction algorithm can de-noise the original signals and make their correlation dimension near the true value of the system. The case study shows that it is of high accuracy to use the de-noised signal correlation dimension to judge the running state of the diesel.
出处
《船海工程》
2009年第1期36-38,共3页
Ship & Ocean Engineering
关键词
关联维数
故障诊断
振动信号
小波包算法
correlation dimension
fault diagnosis
vibration signal
wavelet packet de-noise
