Key Technologies and Construction model for Unmanned Smart Farms: Taking the

doi:10.12133/j.smartag.SA202410033

Abstract

Abstract:

[Objective] As a key model of smart agriculture, the unmanned smart farm aims to develop a highly intelligent and automated system for high grain yields. This research uses the "1.5-Ton grain per Mu" farm in Dezhou city, Shandong province, as the experimental site, targeting core challenges in large-scale smart agriculture and exploring construction and service models for such farms. [Methods] The "1.5-Ton grain per Mu" unmanned smart farm comprehensively utilized information technologies such as the internet of things (IoT) and big data to achieve full-chain integration and services for information perception, transmission, mining, and application. The overall construction architecture consisted of the perception layer, transmission layer, processing layer, and application layer. This architecture enabled precise perception, secure transmission, analysis and processing, and application services for farm data. A perception system for the unmanned smart farm of wheat was developed, which included a digital perception network and crop phenotypic analysis. The former achieved precise perception, efficient transmission, and precise measurement and control of data information within the farm through perception nodes, self-organizing networks, and edge computing core processing nodes. Phenotypic analysis utilized methods such as deep learning to extract phenotypic characteristics at different growth stages, such as the phenological classification of wheat and wheat ear length. An intelligent controlled system had been developed. The system consisted of an intelligent agricultural machinery system, a field irrigation system, and an aerial pesticided application system. The intelligent agricultural machinery system was composed of three parts: the basic layer, decision-making layer, and application service layer. They were responsible for obtaining real-time status information of agricultural machinery, formulating management decisions for agricultural machinery, and executing operational commands, respectively. Additionally, appropriate agricultural machinery models and configuration references were provided. A refined irrigation scheme was designed based on the water requirements and soil conditions at different developmental stages of wheat. And, an irrigation control algorithm based on fuzzy PID was proposed. Finally, relying on technologies such as multi-source data fusion, distributed computing, and geographic information system (GIS), an intelligent management and control platform for the entire agricultural production process was established. [Results and Discussions] The digital perception network enabled precise sensing and networked transmission of environmental information within the farm. The data communication quality of the sensor network remained above 85%, effectively ensuring data transmission quality. The average relative error in extracting wheat spike length information based on deep learning algorithms was 1.24%. Through the coordinated operation of intelligent control system, the farm achieved lean and unmanned production management, enabling intelligent control throughout the entire production chain, which significantly reduced labor costs and improved the precision and efficiency of farm management. The irrigation model not only saved 20% of irrigation water but also increased the yield of "Jinan 17" and "Jimai 44" by 10.18% and 7%, respectively. Pesticide application through spraying drones reduced pesticide usage by 55%. The big data platform provided users with production guidance services such as meteorological disaster prediction, optimal sowing time, environmental prediction, and water and fertilizer management through intelligent scientific decision support, intelligent agricultural machinery operation, and producted quality and safety traceability modules, helping farmers manage their farms scientifically. [Conclusions] The study achieved comprehensive collection of environmental information within the farm, precise phenotypic analysis, and intelligent control of agricultural machinery, irrigation equipment, and other equipment. Additionally, it realized digital services for agricultural management through a big data platform. The development path of the "1.5-Ton grain per Mu" unmanned smart farm can provid references for the construction of smart agriculture.

Key words: unmanned smart farm, IoT, information collection, intelligent control, big data analysis

CLC Number:

LIU lining, ZHANG Hongqi, ZHANG Ziwen, ZHANG Zhenghui, WANG Jiayu, LI Xuanxuan, ZHU Ke, LIU Pingzeng. Key Technologies and Construction model for Unmanned Smart Farms: Taking the "1.5-Ton Grain per Mu" Unmanned Farm as An Example[J]. Smart Agriculture, 2025, 7(1): 70-84.

Figures/Tables 22

Fig. 1

Fig. 2

Fig. 3

Table 1

Table 2

Fig. 4

Fig. 5

Fig. 6

Table 3

Table 4

Table 5

Fig. 7

Fig. 8

Table 6

Fig. 9

Fig. 10

Table 7

Table 8

Table 9

Fig. 11

Fig. 12

Fig. 13

References 32

1	罗锡文, 胡炼, 何杰, 等. 中国大田无人农场关键技术研究与建设实践[J]. 农业工程学报, 2024, 40( 1): 1- 16.
	LUO X W, HU L, HE J, et al. Key technologies and practice of unmanned farm in China[J]. Transactions of the Chinese society of agricultural engineering, 2024, 40( 1): 1- 16.
2	钱震杰, 金诚谦, 刘政, 等. 无人农场中的智能控制技术应用现状与趋势[J]. 智能化农业装备学报(中英文), 2023, 4( 3): 1- 13.
	QIAN Z J, JIN C Q, LIU Z, et al. Development status and trends of intelligent control technology in unmanned farms[J]. Journal of Intelligent Agricultural Mechanization, 2023, 4( 3): 1- 13.
3	罗锡文, 廖娟, 胡炼, 等. 我国智能农机的研究进展与无人农场的实践[J]. 华南农业大学学报, 2021, 42( 6): 8- 17, 5.
	LUO X W, LIAO J, HU L, et al. Research progress of intelligent agricultural machinery and practice of unmanned farm in China[J]. Journal of South China agricultural university, 2021, 42( 6): 8- 17, 5.
4	赵春江, 范贝贝, 李瑾, 等. 农业机器人技术进展、调整与趋势[J]. 智慧农业(中英文), 2023, 5( 4): 1- 15.
	ZHAO C J, FAN B B, LI J, et al. Agricultural robots: Technology progress, challenges and trends[J]. Smart agriculture, 2023, 5( 4): 1- 15.
5	尹彦鑫, 孟志军, 赵春江, 等. 大田无人农场关键技术研究现状与展望[J]. 智慧农业(中英文), 2022, 4( 4): 1- 25.
	YIN Y X, MENG Z J, ZHAO C J, et al. State-of-the-art and prospect of research on key technical for unmanned farms of field corp[J]. Smart agriculture, 2022, 4( 4): 1- 25.
6	PARRA ALONSO I, IZQUIERDO GONZALO R, ALONSO J, et al. The experience of DRIVERTIVE-DRIVERless cooperaTIve VEhicle-team in the 2016 GCDC[J]. IEEE transactions on intelligent transportation systems, 2018, 19( 4): 1322- 1334.
7	韩树丰, 何勇, 方慧. 农机自动导航及无人驾驶车辆的发展综述[J]. 浙江大学学报(农业与生命科学版), 2018, 44( 4): 381- 391.
	HAN S F, HE Y, FANG H. Recent development in automatic guidance and autonomous vehicle for agriculture: A Review[J]. Journal of Zhejiang university (agriculture and life sciences), 2018, 44( 4): 381- 391.
8	LOWENBERG-DEBOER J, FRANKLIN K, BEHRENDT K, et al. Economics of autonomous equipment for arable farms[J]. Precision agriculture, 2021, 22( 6): 1992- 2006.
9	AL-AMIN A K M A, LOWENBERG-DEBOER J, FRANKLIN K, et al. Economics of field size and shape for autonomous crop machines[J]. Precision agriculture, 2023, 24( 5): 1738- 1765.
10	HAYASHI E. Selected PFALs in Japan[M]// Plant Factory. Cambridge: Academic Press, 2020: 437- 454.
11	孟祥, 赵莹, 徐卓威, 等. 基于LoRa技术的农田智能灌溉系统设计[J]. 中国农机化学报, 2023, 44( 9): 161- 168.
	MENG X, ZHAO Y, XU Z W, et al. Design of intelligent irrigation system for farmland based on LoRa technology [J]. Journal of Chinese agricultural mechanization, 2023, 44( 9): 161- 168
12	SONG Q L, LI L, HUANG X T. LELBC: A low energy lightweight block cipher for smart agriculture[J]. Internet of things, 2024, 25: ID 101022.
13	NAIR M, DANG S P, BEACH M A. IoT device authentication using self-organizing feature map data sets[J]. IEEE communications magazine, 2023, 61( 9): 162- 168.
14	齐小刚, 吴相远, 刘立芳. 无人机集群编队自组网可靠性评估[J]. 控制与决策, 2024, 39( 2): 689- 696.
	QI X G, WU X Y, LIU L F. Reliability evaluation of ad hoc network for UAV swarm formation[J]. Control and decision, 2024, 39( 2): 689- 696.
15	ZHOU M, ZHENG H B, HE C, et al. Wheat phenology detection with the methodology of classification based on the time-series UAV images[J]. Field crops research, 2023, 292: ID 108798.
16	承达瑜, 何伟德, 付春晓, 等. 融合无人机光谱信息与纹理特征的冬小麦综合长势监测[J]. 农业机械学报, 2024, 55( 9): 249- 261.
	CHENG D Y, HE W D, FU C X, et al. Comprehensive growth monitoring of winter wheat by integrating UAV spectral information and texture features[J]. Transactions of the Chinese society for agricultural machinery, 2024, 55( 9): 249- 261.
17	SAKAMOTO T, YOKOZAWA M, TORITANI H, et al. A crop phenology detection method using time-series MODIS data[J]. Remote sensing of environment, 2005, 96( 3/4): 366- 374.
18	LIU Z H, JIN S C, LIU X Q, et al. Extraction of wheat spike phenotypes from field-collected lidar data and exploration of their relationships with wheat yield[J]. IEEE transactions on geoscience and remote sensing, 2023, 61: 1- 13.
19	冯惠芬, 李映雪, 吴芳, 等. 机器学习结合高光谱植被指数与SPAD值估算冬小麦氮含量[J]. 农业工程学报, 2024, 40( 1): 227- 237.
	FENG H F, LI Y X, WU F, et al. Estimating winter wheat nitrogen content using SPAD and hyperspectral vegetation indices with machine learning[J]. Transactions of the Chinese society of agricultural engineering, 2024, 40( 1): 227- 237.
20	张天, 张智刚, 罗锡文, 等. 低功耗BDS-SPP/INS融合定位系统的设计与试验[J]. 华南农业大学学报, 2024, 45( 3): 437- 445.
	ZHANG T, ZHANG Z G, LUO X W, et al. Design and experiment of low-power BDS-SPP/INS fusion positioning system[J]. Journal of South China agricultural university, 2024, 45( 3): 437- 445.
21	曹冰雪, 李鸿飞, 赵春江, 等. 智慧农业科技创新引领农业新质生产力发展路径[J]. 智慧农业(中英文), 2024, 6( 4): 116- 127.
	Cao B X, Li H F, Zhao C J, et al Smart agricultural technology innovation leads the development path of new quality productivity in agriculture[J]. Smart agriculture, 2024, 6 ( 4): 116- 127
22	JAISWAL S, BALLAL M S. Fuzzy inference based irrigation controller for agricultural demand side management[J]. Computers and electronics in agriculture, 2020, 175: ID 105537.
23	BENYEZZA H, BOUHEDDA M, REBOUH S. Zoning irrigation smart system based on fuzzy control technology and IoT for water and energy saving[J]. Journal of cleaner production, 2021, 302: ID 127001.
24	贾红军. 基于计算机控制的智能灌溉系统优化研究[J]. 农机化研究, 2024, 46( 10): 37- 42.
	JIA H J. The optimization study for intelligent irrigation system based on computer control[J]. Journal of agricultural mechanization research, 2024, 46( 10): 37- 42.
25	RODRÍGUEZ J P, MONTOYA-MUNOZ A I, RODRIGUEZ-PABON C, et al. IoT-Agro: A smart farming system to Colombian coffee farms[J]. Computers and electronics in agriculture, 2021, 190: ID 106442.
26	CAMBRA BASECA C, SENDRA S, LLORET J, et al. A smart decision system for digital farming[J]. Agronomy, 2019, 9( 5): ID 216.
27	张洪奇, 张艳, 张晨, 等. 设施智慧农场大数据平台开发与应用[J]. 山东农业大学学报(自然科学版), 2024, 55( 3): 295- 303, 475.
	ZHANG H Q, ZHANG Y, ZHANG C, et al. Development and application of big data platform for facility intelligent farm[J]. Journal of Shandong agricultural university (natural science edition), 2024, 55( 3): 295- 303, 475.
28	张强, 贾海霞. 德州市“吨半粮”生产能力建设探析[J]. 农机科技推广, 2023( 10): 40- 42.
29	张强, 贾海霞, 张长明. “国之大者”农机当先——德州市“吨半粮”生产能力建设探析[J]. 山东农机化, 2023( 3): 11- 12.
30	RIGATOS G G. Distributed filtering over sensor networks for autonomous navigation of UAVs[J]. Intelligent service robotics, 2012, 5( 3): 179- 198.
31	邸斌, 周锐, 董卓宁. 考虑信息成功传递概率的多无人机协同目标最优观测与跟踪[J]. 控制与决策, 2016, 31( 4): 616- 622.
	DI B, ZHOU R, DONG Z N. Cooperative localization and tracking of multiple targets with the communication-aware unmanned aerial vehicle system[J]. Control and decision, 2016, 31( 4): 616- 622.
32	FU S W, ZHANG Y, CERIOTTI M, et al. Modeling packet loss rate of IEEE 802.15.4 links in diverse environmental conditions[C]// 2018 IEEE Wireless Communications and Networking Conference (WCNC). Piscataway, New Jersey, USA: IEEE, 2018.

物候期	精确率	召回率	F ₁值
Class 0	0.93	0.85	0.89
Class 1	0.91	0.82	0.86

序号	实际长度/cm	测试长度/cm	误差/%	序号	实际长度/cm	测试长度/cm	误差/%
1	7.50	7.88	5.07	6	6.20	6.18	0.32
2	6.80	6.74	0.88	7	7.10	7.05	0.70
3	7.50	7.28	2.93	8	7.00	6.85	0.72
4	7.50	7.64	1.87	9	8.20	8.12	0.98
5	7.20	7.18	0.28

名称	型号	产品参数
名称	型号	整机主要参数	智能驾驶主要参数
智能轮式拖拉机	M2004-5RP	潍柴200马力国四发动机，智能液晶仪表，四轮驱动，380 L油箱，24+24换挡，电控湿式动力输出，强压提升器	±2.5 cm精度自动驾驶，支持远程操控及多卫星信号，作业功能全面，IP67防护等级，系统可远程升级监控
自走式谷物联合收割机	4LZ-10M7（G4）	潍柴200 ps发动机，3 m割台，损失破碎含杂率低，雷沃变速箱，静液压前驱，400 L油箱，2.8 m³粮箱	智能驾驶±2.5 cm精度，支持远程作业遥控监视，手机/PC操控，多卫星信号，IP67防护，远程升级打点控制
自走式玉米收获机	4YZ-4EP	发动机162 kw，4行作业，速度1.83~9 km/h，轮胎15R24/300/80R15.3，整机7 600 kg，轴距3 m，油箱400 L	远程自主作业，APP/PC遥控，系统可升级，支持四大卫星信号，防护等级IP67。
复式精量条播机	2BGXF-20C	动力耙+条播复式作业，147~183 kw动力，20行，行距15 cm，排种无级调，链传动，橡胶轮覆土镇压，驱动靶整地	—
气吸式免耕精量播种机	2BMQE-6E	气力牵引式6行播种机，147~192.5 kw动力，种肥箱大，双圆盘开沟，离心风机，独立镇压，多级调节	—

工况	比例系数（ K_p ）	积分系数（ K_i ）	微分系数（ K_d ）	响应时间/s	超调量/%
平坦地形	0.8	0.2	0.1	1.2	5
复杂地形	1.2	0.1	0.3	1.5	8
播种作业	1.0	0.1	0.2	1.3	6

发育期	适宜范围/%	持续日期（月/日）	阶段天数/天
播种期	50—80	10/20—11/12	24
出苗期	60—80	11/13—11/29	17
越冬期	60—80	11/30—2/29	92
返青期	70—80	3/1—3/15	15
起身期	70—80	3/16—4/4	20
拔节期	70—80	4/5—4/19	15
孕穗期	70—80	4/20—4/22	3
抽穗期	70—80	4/23—4/27	5
开花期	70—80	4/28—4/30	3
灌浆期	70—80	5/1—5/21	21
成熟期	70—80	5/22—6/12	22