首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于声学响应和BP神经网络检测鸡蛋裂纹
引用本文:潘磊庆,屠康,刘明,詹歌,邹秀容.基于声学响应和BP神经网络检测鸡蛋裂纹[J].南京农业大学学报,2010,33(6).
作者姓名:潘磊庆  屠康  刘明  詹歌  邹秀容
作者单位:南京农业大学食品科学技术学院/农业部农畜产品加工与质量控制重点开放实验室,江苏,南京,210095
基金项目:国家863计划项目(2007AA10Z213); 南京农业大学青年科技创新基金项目(KG08022); 中农-南农青年教师开放基金项目(NC2008004)
摘    要:为了提高鸡蛋裂纹检测的准确性,建立了声学敲击检测鸡蛋裂纹的装置,采集和分析鸡蛋被敲击后的声音信号。提取了4个特征频率、偏斜度平均值和峰度平均值共6个特征参数,并作为神经网络的输入量,创建了基于MATLAB的结构为6-15-2的3层BP神经网络模型判别鸡蛋裂纹。检测结果显示:对蛋壳受各种程度破坏后的鸡蛋判别精度可达92%以上,对蛋壳完整的鸡蛋判别精度达到96%,对鸡蛋总体的判别精度可达94%。

关 键 词:鸡蛋裂纹  声学响应  BP神经网络  检测  

Eggshell crack detection based on acoustic response and BP neural network
PAN Lei-ging,TU Kang,LIU Ming,ZHAN Ge,ZOU Xiu-rong.Eggshell crack detection based on acoustic response and BP neural network[J].Journal of Nanjing Agricultural University,2010,33(6).
Authors:PAN Lei-ging  TU Kang  LIU Ming  ZHAN Ge  ZOU Xiu-rong
Institution:PAN Lei-qing,TU Kang,LIU Ming,ZHAN Ge,ZOU Xiu-rong ( College of Food Science and Technology/ Key Laboratory of Food Processing and Quality Control,Ministry of Agriculture,Nanjing Agricultural University,Nanjing 210095,China)
Abstract:In order to improve the accuracy of detection and classification of egg with cracks,an experimental system for the eggshell crack detection was built up based on acoustic response,in which the acoustic signal was captured and analyzed. Six parameters such as dominant frequency f1,f2,f3,f4,mean value of skewness ( S) ,and mean value of kurtosis ( K) were picked up. With the 6 parameters as input,the best back propagation ( BP) neural network ( 6 input nodes,15 hidden nodes,2 output nodes) using MATLAB was em...
Keywords:eggshell crack  acoustic response  BP neural network  detection  
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号