Design of walnut online weighing system based on support vector regression

Authors

JIN Zuohui, Mechanical and Electrical Engineering College, Shihezi University, Shihezi, Xinjiang 832000, China; Key Laboratory of Northwest Agricultural Equipment, Ministry of Agriculture, Shihezi, Xinjiang 832000, China
ZHAI Zhiqiang, Mechanical and Electrical Engineering College, Shihezi University, Shihezi, Xinjiang 832000, China; Key Laboratory of Northwest Agricultural Equipment, Ministry of Agriculture, Shihezi, Xinjiang 832000, China
ZHANG Ruoyu, Mechanical and Electrical Engineering College, Shihezi University, Shihezi, Xinjiang 832000, China; Key Laboratory of Northwest Agricultural Equipment, Ministry of Agriculture, Shihezi, Xinjiang 832000, China
ZOU Kunlin, Mechanical and Electrical Engineering College, Shihezi University, Shihezi, Xinjiang 832000, China; Key Laboratory of Northwest Agricultural Equipment, Ministry of Agriculture, Shihezi, Xinjiang 832000, China
PANG Yujie, Mechanical and Electrical Engineering College, Shihezi University, Shihezi, Xinjiang 832000, China; Key Laboratory of Northwest Agricultural Equipment, Ministry of Agriculture, Shihezi, Xinjiang 832000, China

Abstract

In order to accurately detect walnut weight online, a walnut weight online testing system based on multi-sensor information fusion was designed, which was adopted the method of dynamic compensation and calibration to process signal collected from an acceleration sensor and symmetrical weight sensors and used the algorithm of support vector regression (SRV) to predict the walnut weight. Then, 400 walnuts were used to acquire weight data at speed of 0.02, 0.03 and 0.05 m/s respectively based on this system. Meanwhile the data were trained and verified. The better prediction model of walnut weight was determined as SVR model with linear kernel function, and the best test speed was determined as 0.03 m/s. Finally, 200 walnut samples were tested online at the speed of 0.03 m/s. The results showed that r² of linear fitting between the walnut weight prediction and their actual weight was 0.85, and the average absolute error of linear fitting was 1.67 g. The results indicated that the system can accurately online test walnut weight.

Publication Date

7-28-2018

First Page

90

Last Page

92,126

DOI

10.13652/j.issn.1003-5788.2018.07.019

Recommended Citation

Zuohui, JIN; Zhiqiang, ZHAI; Ruoyu, ZHANG; Kunlin, ZOU; and Yujie, PANG (2018) "Design of walnut online weighing system based on support vector regression," Food and Machinery: Vol. 34: Iss. 7, Article 19.
DOI: 10.13652/j.issn.1003-5788.2018.07.019
Available at: https://www.ifoodmm.cn/journal/vol34/iss7/19

References

[1] 张剑一. 动态称重数据处理算法及其在禽蛋和类球形水果分选中的应用研究[D]. 杭州: 浙江大学, 2017: 27-34.
[2] 李光梅, 魏新华, 李法德, 等. 水果机器视觉质量综合分选机的设计[J]. 农机化研究, 2008 (11): 124-126.
[3] 吴晓强, 黄云战, 赵永杰. 基于运动控制器的苹果质量分级系统[J]. 食品与机械, 2015, 31(5): 114-116.
[4] SUN Li, YUAN Lei-ming, CAI Jian-rong, et al. Egg freshness on-line estimation using machine vision and dynamic weighing[J]. Food Analytical Methods, 2015, 8(4): 922-928.
[5] ZHANG Jiang-yi, YING Yi-bin, JIANG Huan-yu, et al. Application of optimized digital filters and asymmetrically trimmed mean to improve the accuracy of dynamic egg weighing[J]. Transactions of the ASABE, 2017, 60(4): 1 099-1 111.
[6] LIU Tong-liang, ZHENG Xue-hai, LI Chen. Design of fresh sea cucumber weighing sorting machine[C]// International Conference on Advanced Information Technology and Sensor Application. New York: IEEE, 2015: 16-19.
[7] 韩乔生, 芦金石, 陶学恒, 等. 高效高精度动态静态组合块状食品称重分选系统[J]. 食品与机械, 2016, 32(10): 89-93.
[8] 毛建东. 动态称重系统的动态补偿和校正[J]. 食品与机械, 2006, 22(2): 84-86.
[9] 杜冬冬. 履带自走式甘蓝收获机研究及称重系统开发[D]. 杭州: 浙江大学, 2017: 11-17.
[10] PAWLOWSKI A, RODRIGUEZ F, SANCHEZ-HERMOSIL-LA J, et al. Fast nonstationary filtering for adaptive weighing system[C]// IEEE Conference on Emerging Technologies & Factory Automation. New York: IEEE, 2015: 1-6.
[11] 李殿起, 张艳珠. 永磁电动机转子非线性动力特性[J]. 机械强度, 2004, 26(2): 127-131.
[12] SMOLA A J, SCH LKOPF B. A tutorial on support vector regression[J]. Statistics & Computing, 2004, 14(3): 199-222.
[13] 田英杰. 支持向量回归机及其应用研究[D]. 北京: 中国农业大学, 2005: 22-24.