基于Bayes判别的禽蛋破损检测模型研究

Research of Model for Detecting of Eggshell Crack Based on Bayes Discriminance

通过对敲击蛋壳的声音信号进行功率谱分析,得到功率谱面积的平均值、最大功率谱面积与最小功率谱面积的差值、X轴方向上质心的平均值等8个反映蛋壳破损特征的参数;再运用Bayes判别原理建立与这些特征参数相关的蛋壳破损检测模型。试验研究表明,该模型准确率达到92%。

Eight Characteristic variables such as the average area of power spectrum, the difference between the maximum and minimum values of area of the power spectrums and the average of the x-coordinate of centriod etc, were achieved by analyzing power spectrums of cracked eggs and normal eggs in this research; Then according to these characteristic variables and using Bayes discriminance theorem, discrimination models of cracked eggs and normal eggs were developed. The test showed the average accuracy of detection models was about 92%.