猪胴体重在线分级预测线性回归模型研究  

Journal of Nanjing Agricultural University Study on linear regression model of pig carcass weight prediction for grading online

作　　者：陈鲁晟 陈祺祥 陈玉仑[2,3] 王胜 李毅念[2] 李春保[1,3] CHEN Lusheng;CHEN Qixiang;CHEN Yulun;WANG Sheng;LI Yinian;LI Chunbao(College of Food Science and Technology,Nanjing Agricultural University,Nanjing 210095,China;College of Engineering,Nanjing Agricultural University,Nanjing 210031,China;Key Laboratory of Animal Product Processing,Ministry of Agriculture and Rural Affairs/Key Laboratory of Meat Processing and Quality Control,Ministry of Education,Nanjing Agricultural University,Nanjing 210095,China)

机构地区：[1]南京农业大学食品科学技术学院,江苏南京210095 [2]南京农业大学工学院,江苏南京210031 [3]南京农业大学农业农村部畜产品加工重点实验室/教育部肉品加工与质量控制重点实验室,江苏南京210095

出　　处：《南京农业大学学报》2024年第4期803-808,共6页Journal of Nanjing Agricultural University

基　　金：国家生猪产业技术体系项目(CARS-35)。

摘　　要：[目的]针对国内大多数屠宰企业仍通过人工测量猪胴体背膘厚度,再结合胴体重对其进行分级,存在劳动强度大、作业效率低、人畜交叉污染风险高等问题,本文旨在建立猪胴体重预测模型,以便利用图像处理等技术获取模型中的相关参数,进而获得胴体重。[方法]在14:00—15:00、15:20—16:20、16:30—17:30三个时段内,随机选取按照标准化工艺屠宰后15 min左右、胴体重50~90 kg的猪胴体60头,在完成各试样前腿处横长(L_(f))、1/2处横长(L_( 1/2))、后腿处横长(L_(r))、1/2处背膘厚度(t_(1/2))、胴体直长(L_(t))及胴体重(w)等参数测定的基础上,建立不同的胴体重预测模型并进行优化及准确率验证。[结果]采用横长加权均值(L_(e))代替背膘厚度,与直长建立的胴体重预测模型为w=4.05L_(e)+0.45 L_(t)-116.32,其决定系数由0.48提高到0.96(P=0.01),预测准确率最高达94.16%。[结论]采用横长加权均值减小了误差,建立的猪胴体重预测模型准确性较其他模型高。[Objectives]In view of the fact that the backfat thickness of pig carcass is still measured manually in most slaughtering enterprises,and then pig carcasses are graded manually according to their weight and the backfat thickness,which results in such problems as labor intensive,time-consuming and high risk of disease transmission between humans and animals.This paper aimed to establish a prediction model for pig carcass weight.This model could be applied to predict the pig carcass weight and automatically grade pig carcass by using image processing and other technologies to obtain relevant parameters of the model from carcass.[Methods]Twenty pig carcasses removed hooves with weight 50-90 kg were selected respectively in the three periods of 14:00-15:00,15:20-16:20 and 16:30-17:30 after pig had been slaughtered within 15 min according to standardized technology.The models for pig carcass weight prediction were established,optimized,and accuracy verified,on the basis of the measured parameters of carcasses’three widths(L_(f),L_(1/2)and L_(r)),length(L_(t)),backfat thickness(t_(1/2))and weight(w).[Results]Test results showed that,by using weighted mean value of carcasses(L_(e))instead of t_(1/2),the carcass weight prediction model of w=4.05L_(e)+0.45 L_(t)-116.32 consisted of L_(t),L_(e) and constant,its correlation coefficient(R^(2))increased from 0.48 to 0.96,and significant coefficient was 0.01,and the prediction accuracy reached 94.16%.[Conclusions]The accuracy of the carcass weight prediction model established was further improved compared with other models due to reducing the error of the width by using weighted mean value.

关 键 词：猪胴体重 特征参数 预测 线性回归 模型 

分 类 号：TS251.1[轻工技术与工程—农产品加工及贮藏工程]