基于多传感器融合的鸡肉新鲜度检测方法-吉林大学学报.PDF

第43卷　 增刊 吉林 大 学 学报 ( 工 学版 ) 　 Vol.43　 Sup. 2013年3月 Journal of Jilin University (Engineering and Technology Edition) 　 Mar. 2013 基于多传感器融合的鸡肉新鲜度检测方法 1,2 1,2 1 1 3 1,2 常志勇 ,陈东辉 ,张　 凌 ,佟月英 ,翁小辉 ,佟　 金 (1.吉林大学 生物与农业工程学院,长春 130022;2. 吉林大学 工程仿生教育部重点实验室,长春 130022; 3.吉林大学机械科学与工程学院,长春 132022) 摘　 要:为了快捷、无损检测鸡肉新鲜度,建立了一套基于电子鼻和力学参数两种传感器以及 神经网络识别技术的智能检测系统。 根据鸡肉腐败机理,合理选择传感器。 采用RBF 神经网 络作为模式识别方法。 经理化试验证明系统检测鸡肉新鲜度准确率达93.65%,结果表明设 计的融合系统检测鸡肉新鲜度是可行的。 关键词:鸡肉新鲜度;多传感器融合;神经网络;模式识别 中图分类号:TG156　 　 文献标志码:A　 　 文章编号:1671-5497(2013)Sup.-0493-04 Method of chicken freshness detection based on multi-sensor fusion 1,2 1,2 1 1 CHANGZhi-yong ,CHEN Dong-hui ,ZHANG Ling ,TONG Yue-ying , 3 1,2 WENG Xiao-hui ,TONGJin (1.College of Biological and Agricultural Engineering,Jilin University, Changchun 130022,China;3. College of Mechanical Science and Engineering, Jilin University, Changchun 130022,China;2. Key Laboratory of Bionic Engineering,Ministry of Education,Changchun 130022,China) Abstract:In order to evaluate poultry freshness in a quick and non-destructive way,an intelligent inspection system was established based on neural network recognition technique and two types of sensors, including electronic nose and mechanical parameters. Sensorswere chosen accordingto chicken deteriorate mechanism. RBF neural network was used as method of pattern recognition. The accuracy of the system for chicken freshness detection is up to96.45% through physico-chemical examination. The experimental resultsindicate that it isfeasible to integrate multiple sensorsfor chicken freshness detection. Key words:chick