利用敲击声音信号进行禽蛋破损检测和模糊识别

Detection of cracked-shell eggs using acoustic signal and fuzzy recognition

为了在蛋品加工中能够快速检测并剔除异常蛋(钢壳蛋、尖嘴蛋)和破损蛋,利用一个微型话筒和声卡采集蛋在敲击时的声脉冲信号,将采集到的声脉冲信号送计算机处理和分析。研究结果表明:正常蛋、破损蛋、钢壳蛋、尖嘴蛋的敲击声音信号在衰竭时间、最小共振峰频率和四点最大频率差等参数上存在差异,且差异的边界是模糊的。利用最大隶属度原则进行模糊识别,破损蛋的识别准确率达95%。

In order to quickly find out and pick out cracked-shell eggs in the processing of eggs, the acoustics signals created by striking the eggshells are acquired by an electrict microphone and a sound card and transformed into digital signals. Through analyzing those signals, it is found that the normal-shell eggs, cracked-shell eggs, hard-shell eggs and unequal-shell eggs are different with their signal decayed time, their minimum peak resonant frequencies and their maximum difference of the peak resonant frequencies from four points on the egg shell. The boundaries of these differences are fuzzy. By use of the principle of the max membership function to make fuzzy recognition, the accurate recognition ratio for cracked-shell eggs is up to 95 percent.