大田智能农机关键作业参数感知与检测方法综述

Review of Perception and Detection Methods for Key Operational Parameters of Intelligent Field Agricultural Machinery

摘要:

关键作业参数的合理选取和可靠获取是实现大田智能农机自主作业、智能决策与精准调控的重要基础,对提升田间复杂作业环境的感知能力和调控效率具有关键支撑作用。受作业环境多变、作业机理差异显著等因素影响,当前大田智能农机在参数采集过程仍面临数据冗余、感知结果与控制单元耦合度不足以及系统集成与通用性较弱等问题,制约作业决策精度与整机作业效能进一步提升。本文围绕大田作业耕作、播种、作物管理与收获4个阶段,系统梳理了大田作业不同环节关键作业参数类型、感知和主要检测方法,并对国内外相关学术研究成果与国际智能农机装备技术方案进行综合述评,在此基础上,归纳总结现有参数检测方法存在的问题,并从参数体系构建、感知与控制协同和系统集成等方面进行分析与讨论。最后,结合智能农机技术发展趋势,对多源数据筛选与融合、高鲁棒性感知系统设计、跨平台数据共享与标准化以及参数驱动的调控策略优化等研究方向进行展望,为大田智能农机关键作业参数高效感知系统构建提供参考。

Abstract:

The rational selection and reliable acquisition of key operational parameters constitute a fundamental basis for enabling autonomous operation,intelligent decision-making,and precise control in large-scale smart agricultural machinery. They play a critical role in supporting the enhancement of perception capabilities and control efficiency under complex field operation conditions. Due to the variability of operational environments and significant differences in working mechanisms,challenges persist in the parameter acquisition process of large-scale smart agricultural machinery. These included data redundancy,insufficient coupling between perception results and control units,and limited system integration and generalizability,which constrained the further improvement of operational decision accuracy and overall machine performance. The types of key operational parameters,sensing,and primary detection methods were systematically reviewed across four major stages of field operations: tillage,seeding,crop management,and harvesting. Relevant domestic and international research findings,as well as technological solutions of global smart agricultural machinery,were critically assessed. Based on this review,existing issues in parameter acquisition methods were summarized,and analyses were conducted from the perspectives of parameter system construction,coordination between sensing and control,and system integration. Finally,in light of the development trends in smart agricultural machinery,future research directions were identified,including multi-source data selection and fusion,design of high-robustness sensing systems,cross-platform data sharing and standardization,and optimization of parameter-driven control strategies. These directions were expected to guide the development of efficient perception systems for key operational parameters in large-scale smart agricultural machinery.