当前位置：首页>农业>中国热带农业科学院牛钊君副研究员等:单芽段糖料蔗切种机目标检测方案与种植机排种器取种方案优化

中国热带农业科学院牛钊君副研究员等:单芽段糖料蔗切种机目标检测方案与种植机排种器取种方案优化

2026-03-30 20:26:48

点击上方蓝字关注我们！

单芽段糖料蔗切种机目标检测方案与种植机排种器取种方案优化

牛钊君^1,2†，葛畅^1,2†，韦丽娇^1,2，宋刚^2*，侯明鑫³，李明^1,2，黄涛^1*

欧忠庆^1,2，孟庆河^1,2，张坚敏⁴

(1. 中国热带农业科学院农业机械研究所，湛江524013，广东，中国；

2. 农业农村部热带作物农业装备重点实验室，湛江524091，广东，中国；

3. 广东海洋大学，机械与动力工程学院，湛江524088，广东，中国；

4. 广西双高农业机械有限公司，南宁530104，广西，中国)

摘要：甘蔗机械化种植技术包含蔗种制备与田间种植两部分。针对单芽段甘蔗自动切种机作业易伤种，缺乏智能选种标定技术且识别准确率低，以及配套种植机排种器需要人工喂入且漏种的问题。该研究基于机械视觉深度学习，优化蔗种特征标定方法，提出改进型的YoLoV5-STD目标检测算法，提高蔗种特征识别准确率，优化整机工程架构；配套的种植机方面，以天然橡胶为基材混合聚苯乙烯设计新型排种器盛料斗，解析柔性自动排种机制，实现自动喂入自动排种。

依据中国热带农业科学院农业机械研究所企业标准制定试验考核指标，试验结果表明2DZ-2型单芽锻智能切种机识别准确率≥95%，伤芽率<1.8%，切种合格率达95.8%，单通道切种效率为64颗(芽)/min；2CZD-2C型单芽段种植机，种植合格率96.6%，种植效率为每分钟208颗（芽），漏栽率<2.1%。

关键词：目标检测；方案优化；自动切种；柔性排种

DOI: 10.25165/j.ijabe.20251805.9144

引用信息: Niu Z J, Ge C, Wei L J, Song G, Hou M X, Li M, et al. Optimization of target detection scheme for single-bud segment sugarcane cutting machine and seed-picking scheme for planter seed meter. Int J Agric & Biol Eng, 2025; 18(5): 165–170.

Optimization of target detection scheme for single-bud segment sugarcane cutting machine and seed-picking scheme for planter seed meter

Zhaojun Niu^1,2†, Chang Ge^1,2†, Lijiao Wei^1,2, Gang Song^2*, Mingxin Hou³, Ming Li^1,2, Tao Huang^1*, Zhongqing Ou^1,2, Qinghe Meng^1,2, Jianmin Zhang⁴

(1. Institute of Agricultural Machinery Research, Chinese Academy of Tropical Agricultural Sciences, Zhanjiang, 524013, Guangdong, China;

2. Key Laboratory of Tropical Crop Agricultural Equipment, Ministry of Agriculture and Rural Affairs, Mazhang District, Zhanjiang, 524091, Guangdong, China;

3. Guangdong Ocean University, School of Mechanical and Power Engineering, Zhanjiang, 524088, Guangdong, China;

4. Guangxi Shuanggao Agricultural Machinery Co., Ltd., Nanning, 530104, Guangxi, China)

Abstract: Sugarcane mechanized planting technology consists of seed preparation and field planting. This study aims at the issues of easy damage to the seeds during the operation of the automatic cutting machine for single-bud segment sugarcane, lack of intelligent seed selection and calibration technology, low recognition accuracy, and the need for manual feeding of the planting machine’s seed meter which leads to seed leakage. This study, based on machine vision and deep learning, optimizes the seed calibration method and proposes an improved YoloV5-STD target detection algorithm to improve the recognition accuracy of seed characteristics and optimize the overall engineering structure. For the planting machine, a new type of hopper for the seed meter is designed using natural rubber as the base material mixed with polystyrene, and the flexible automatic seed metering mechanism is analyzed to achieve automatic feeding and seed metering. Test assessment indicators were formulated based on the enterprise standards of the Institute of Agricultural Machinery Research, Chinese Academy of Tropical Agricultural Sciences. Experimental results show that the recognition accuracy of the 2DZ-2 type single-bud segment intelligent cutting machine is ≥95%, the bud injury rate is <1.8%, the qualified rate of cutting is 95.8%, and the single-channel cutting efficiency is 64 buds/min. The 2CZD-2C type single-bud segment planter has a planting qualification rate of 96.6%, a planting efficiency of 208 buds/min, and a seed leakage rate of <2.1%.

Keywords: target detection, scheme optimization, automatic seed cutting, flexible seed metering

DOI: 10.25165/j.ijabe.20251805.9144

Citation:Niu Z J, Ge C, Wei L J, Song G, Hou M X, Li M, et al. Optimization of target detection scheme for single-bud segment sugarcane cutting machine and seed-picking scheme for planter seed meter. Int J Agric & Biol Eng, 2025; 18(5): 165–170.

END