Fast detection of wheat flour ash content based on GA-PLS algorithm

SUN Xiao-rong; ZHOU Zi-jian; LIU Cui-ling; FU Xin-xin; DOU Ying

doi:10.13873/j.1000-9787(2018)05-0135-03

Chinese

您当前的位置：

首页 >

文章列表页 >

Fast detection of wheat flour ash content based on GA-PLS algorithm

更新时间：2025-09-11

- Fast detection of wheat flour ash content based on GA-PLS algorithm
- Issue 5, Pages: 135-137+143(2018)
- 作者机构：
  
  北京工商大学计算机与信息工程学院食品安全大数据技术北京市重点实验室
- 作者简介：
- 基金信息：
- DOI：10.13873/j.1000-9787(2018)05-0135-03
  CLC： TP18;TS211.7
- Published：2018
- 稿件说明：
移动端阅览
SUN Xiao-rong, ZHOU Zi-jian, LIU Cui-ling, et al. Fast detection of wheat flour ash content based on GA-PLS algorithm[J]. 2018, (5): 135-137+143.
DOI：

SUN Xiao-rong, ZHOU Zi-jian, LIU Cui-ling, et al. Fast detection of wheat flour ash content based on GA-PLS algorithm[J]. 2018, (5): 135-137+143. DOI： 10.13873/j.1000-9787(2018)05-0135-03.

摘要

为得到噪声小、准确性强、自适应性良好的模型

对实验所得的近红外光谱进行预处理及优化波长是十分必要的。实验确定小麦粉中灰分含量为研究对象

提出将光谱预处理及遗传算法（GA）优化波长用于提高偏最小二乘法（PLS）定量建模的稳健性。对比在不同预处理方法下相关系数R

、矫正标准差（RMSEC）、预测标准偏差（RMSEP）3个指标

随机选择130份样本

建立预处理+GA+PLS定量分析模型。实验结果为:R

从70.31%提到了97.46%

RMSEC从0.0775降低到了0.0226

RMSEP从0.0996降低到了0.021 3

表明基于光谱预处理结合GA优化谱区定量分析小麦粉中灰分含量可行

模型预测能力和精度更高。

Abstract

To obtain a low-noise

high-accuracy and good self-adaptvity model

it is essential to preprocess near infrared（ NIR） spectrum and optimize wave length.Experiment ensures ash content in wheat flour as research object and improve robustness of partial least squares method（ PLS） model by combining genetic algorithm（ GA）-wavelength-optimization with spectral pretreatment. Contrast the three indexes

R~2

RMSEC and RMSEP

by different data preprocessing methods

130 samples are selected randomly to establish spectral data pretreatment +GA+PLS model.According to the result

R~2 is increased from 70.31 % to 97.46 %

RMSEC is reduced from 0.077 5 to 0.022 6

RMSEP is reduced from 0. 0996 to 0. 021 3. It is feasible to quantitatively analyze on wheat flour ash content by GA and spectral preprocessing

prediction ability and precision of the obtained model is much more higher.

关键词

Keywords

references

Views

189

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on sleeping posture recognition method based on flexible pressure sensor

Prediction of corrosion rate in oil pipeline based on improved BP neural network

Classification and recognition of 2D mechanical parts based on GA

Image segmentation of KSW entropic based on chain competitive genetic algorithm

Optimal duty cycle solution based on critical path and improved genetic algorithm

Related Author

GUO Shijie

JIA Xiaohui

ZHOU Zhiwen

LIU Jinyue

LIANG Rui

YU Jianping

XU Lushuai

LING Xiao

Related Institution

Hebei Key Laboratory of Smart Sensing and Human-Robot Interaction

School of Mechanical Engineering,Hebei University of Technology

College of Petroleum and Chemical Engineering,Lanzhou University of Technology

School of Mechanical Engineering,Shandong University

School of Computer and Information Engineering,Henan University

⁰