摘要
研究了基于可见及近红外反射光谱的生鲜牛肉多品质参数检测模型,优化确定了建模所需的系统主要参数。利用可见及近红外光谱检测系统和手持式检测探头,进行信号采集和光谱预处理,在保证一定检测精度和稳定性的条件下,设定400~700 nm范围内扫描10次,700~2 000 nm范围扫描30次,采集时间大约900 ms。通过对原始数据进行不同预处理,并用样品光谱杠杆值剔除掉异常样品,建立PLSR校正模型,对比得到了预测效果最佳的校正模型,结果表明:经过SNV变量标准化校正的模型效果最好,模型预测相关系数和均方根误差分别为最大剪切力0.906 8和7.196 3 N,肉色3参数L*为0.885 4和2.362 8,a*为0.836 2和2.296 9,以及蒸煮损失率为0.845 3和2.105 4%。对检测系统进行模型植入后加以验证,牛肉主要参数的验证结果相关系数均达到0.8以上,对牛肉老嫩等级的判别准确率达到93.5%,基本实现牛肉多品质参数的可见近红外光谱快速检测。
A beef quality on-line detection and classification models by Vis /NIR reflectance spectroscopy was established.The system parameters were optimized.Signal collection and spectroscopy preprocess were carried out by Vis/NIR reflectance spectroscopy and a handheld probe device.The scanning times were set on condition that system kept proper detection accuracy and stability,which was 10 times in wavelength range of 400 ~ 700 nm and 30 times in wavelength range of 700 ~ 2 000 nm,and acquisition time of 900 ms.Spectra leverage value of beef was calculated to eliminate abnormal samples,and then different data processing methods were used to establish beef quality PLSR models which finally showed the optimal result of beef quality prediction.The results indicated that the PLSR model with SNV processing had better performance,with the correlation coefficient of 0.906 8 and root mean square error of 7.196 3 N for validation set of beef tenderness,0.885 4 and 2.362 8 for L*,0.836 2 and 2.296 9 for a*,0.845 3 and 2.105 4% for validation set of beef cooking loss,respectively.The correlation coefficient was above 0.8 and the tenderness classification accuracy reached to 93.5%.
出处
《农业机械学报》
EI
CAS
CSCD
北大核心
2013年第S1期171-176,共6页
Transactions of the Chinese Society for Agricultural Machinery
基金
公益性行业(农业)科研专项经费资助项目(201003008)
