基于卷积神经网络的拖拉机工况识别

doi:10.13733/j.jcam.issn.20955553.2021.11.22

中国农机化学报 ›› 2021, Vol. 42 ›› Issue (11): 144-150.DOI: 10.13733/j.jcam.issn.20955553.2021.11.22

基于卷积神经网络的拖拉机工况识别

孔庆好, 吐尔逊·买买提, 赵梦佳

新疆农业大学交通与物流工程学院,乌鲁木齐市,830052

收稿日期:2021-05-12 修回日期:2021-07-12 出版日期:2021-11-15 发布日期:2021-11-15
通讯作者: 吐尔逊·买买提,男,1975年生,新疆阿克苏人,博士,副教授;研究方向为智能交通与农机污染物排放。E-mail: tursun@xjau.edu.cn
作者简介:孔庆好,男,1991年生,浙江温州人,硕士研究生;研究方向为交通数据挖掘与农机污染物排放。E-mail: 447053371@qq.com
基金资助:
*国家自然科学基金项目(51768071);新疆农业大学研究生科研创新项目(XJAUGRI2021018)

Recognition of tractor working condition based on convolutional neural network

Kong Qinghao, Tursun Mamat, Zhao Mengjia

School of Traffic and Logistics Engineering, Xinjiang Agricultural University, Urumqi, 830052, China

Received:2021-05-12 Revised:2021-07-12 Online:2021-11-15 Published:2021-11-15

摘要/Abstract

摘要： 农机工况识别在细化农机作业状态和帮助掌握区域污染物排放趋势方面有着重要的研究价值。基于拖拉机不同运行状态下的行驶速度、发动机转速以及实时油耗等时间序列,首次提出将图像识别方法引入到拖拉机工况识别中的思路,并分别应用参数优化的支持向量机与卷积神经网络对实际作业拖拉机工况进行研究。结果表明:(1)基于参数优化的支持向量机可以较好地实现样本点的工况识别且识别准确度达到99.851 9%,但无法实现农机工况的连续性识别,同时无法对农机工况转换阶段进行有效识别。(2)以拖拉机运行速度与发动机转速等信息构建样本图像来描述农机工况变化的数据表达,并在此基础上应用卷积神经网络可以有效实现农机工况的连续性识别,且识别准确率可以达到93.3%。本研究在农机工况识别方面具有一定参考价值,并为后续农机不同工况下区域污染物排放研究提供技术支持。

关键词: 拖拉机, 工况识别, 支持向量机, 卷积神经网络

Abstract: In general, the identification of working conditions of agricultural machinery had significant research value in refining the working conditions of agricultural machinery and helping to master the trend of regional pollutant discharge. Based on the time series of the tractor running speed, engine speed, and real-time fuel consumption under different running conditions, the research introduced the image recognition method into tractor working condition identification for the first time. At the same time, the research also applied the parameter optimized support vector machine and the convolutional neural network (CNN) to conduct a systematical study related to the tractor working conditions. The related research results indicated that a support vector machine based on parameter optimization could realize the working condition identification of sample points in an ideal way, with the recognition accuracy reaching 99.851 9%. Nevertheless, it cannot realize the continuous identification of agricultural machinery working conditions, nor can it effectively identify the conversion stage of agricultural machinery working conditions. Moreover, in this study, a range of information, including tractor running speed and engine speed, are used to construct the sample image, thereby describing the data expression of agricultural machinery working condition change. The application of the convolutional neural network (CNN) is beneficial to realize the continuous recognition of agricultural machinery working conditions effectively, with the recognition accuracy reaching 93.3%. In short, the research not only provided reference value for the research related to the identification of agricultural machinery working conditions but also provided corresponding technical support for the subsequent research on the regional pollutant emissions produced by agricultural machinery under different working conditions.

Key words: tractor, working condition identification, support vector machines, convolutional neural network

中图分类号:

孔庆好, 吐尔逊·买买提, 赵梦佳. 基于卷积神经网络的拖拉机工况识别[J]. 中国农机化学报, 2021, 42(11): 144-150.

Kong Qinghao, Tursun Mamat, Zhao Mengjia. Recognition of tractor working condition based on convolutional neural network[J]. Journal of Chinese Agricultural Mechanization, 2021, 42(11): 144-150.

参考文献

[1] 张楚莹, 王书肖, 邢佳, 等. 中国能源相关的氮氧化物排放现状与发展趋势分析[J]. 环境科学学报, 2008, 28(12): 2470-2479.
Zhang Chuying, Wang Shuxiao, Xing Jia, et al. Current status and future projections of NO_X emissions from energy related industries in China [J]. Acta Scientiae Circumstantiae, 2008, 28(12): 2470-2479.
[2] 王培, 孟志军, 尹彦鑫, 等. 基于农机空间运行轨迹的作业状态自动识别试验[J]. 农业工程学报, 2015, 31(3): 56-61.
Wang Pei, Meng Zhijun, Yin Yanxin, et al. Automatic recognition algorithm of field operation status based on spatial track of agricultural machinery and corresponding experiment [J]. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(3): 56-61.
[3] 黄成, 安静宇, 鲁君. 长三角区域非道路移动机械排放清单及预测[J]. 环境科学, 2018, 39(9): 3965-3975.
Huang Cheng, An Jingyu, Lu Jun. Emission inventory and prediction of non-road machineries in the Yangtze River Delta Region, China [J]. Environmental science, 2018, 39(9): 3965-3975.
[4] 鲁君, 黄成, 胡磬遥, 等. 长三角地区典型城市非道路移动机械大气污染物排放清单[J]. 环境科学, 2017, 38(7): 2738-2746.
Lu Jun, Huang Cheng, Hu Qingyao, et al. Air pollutant emission inventory of non-road machineries in Typical Cities in Eastern China [J]. Environmental science, 2017, 38(7): 2738-2746.
[5] 张礼俊, 郑君瑜, 尹沙沙, 等. 珠江三角洲非道路移动源排放清单开发[J]. 环境科学, 2010, 31(4): 886-891.
Zhang Lijun, Zheng Junyu, Yin Shasha, et al. Development of non-road mobile source emission inventory for the Pearl River Delta Region [J]. Environmental science, 2010, 31(4): 886-891.
[6] 陈军民. 制度结构与家庭农场的运行效率及效益[J]. 华南农业大学学报(社会科学版), 2017, 16(5): 1-14.
Chen Junmin. Running efficiency and benefit of family farms from the perspective of institutional structure [J]. Journal of South China Agricultural University(Social Science Edition), 2017, 16(5): 1-14.
[7] 余印振, 韩哲哲, 许传龙. 基于深度卷积神经网络和支持向量机的NO_X浓度预测[J/OL]. 中国电机工程学报: 1-13[2021-04-12]. https://doi.org/10.13334/j.0258-8013.pcsee.210077.
[8] 王黎翔, 王安琪, 黄志祥. 基于多算法优化SVM的粗糙面参数反演[J]. 计算物理, 2019, 36(5): 577-585.
Wang Lixiang, Wang Anqi, Huang Zhixiang. Parameter inversion of rough surface optimization based on multiple algorithms for SVM [J]. Chinese Journal of Computational Physics, 2019, 36(5): 577-585.
[9] 段亮, 宋春元, 刘超, 等. 基于机器学习的高速列车轴承温度状态识别[J/OL]. 吉林大学学报(工学版): 1-8[2021-04-12]. https://doi.org/10.13229/j.cnki.jdxbgxb20200751.
[10] 付明亮, 丁焰, 尹航, 等. 实际作业工况下农用拖拉机的排放特性[J]. 农业工程学报, 2013, 29(6): 42-48.
Fu Mingliang, Ding Yan, Yin Hang, et al. Characteristics of agricultural tractors emissions under real-world operating cycle [J]. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29(6): 42－48.
[11] 龚丁禧, 曹长荣. 基于卷积神经网络的植物叶片分类[J]. 计算机与现代化, 2014(4): 12-15, 19.
Gong Dingxi, Cao Changrong. Plant leaf classification based on CNN [J]. Computer and Modernization, 2014(4): 12-15, 19.
[12] 童朝娣. 卷积神经网络在车牌字符识别中的应用[J]. 电子技术与软件工程, 2019(1): 68.
[13] 付明亮, 丁焰, 尹航, 等. 基于燃油消耗的工程机械排放因子研究[J]. 北京理工大学学报, 2014, 34(2): 138-142.
Fu Mingliang, Ding Yan, Yin Hang, et al. Study on fuel-based emission factors from construction equipment [J]. Transactions of Beijing Institute of Technology, 2014, 34(2): 138-142.

[1]	李贤哲, 张辉, 徐立友, 刘孟楠, , 闫祥海, , 张明柱. 液力机械复合传动拖拉机动力系统匹配特性研究[J]. 中国农机化学报, 2022, 43(4): 46-52.
[2]	董萍, 卫梦华, 时雷, 郭伟. 迁移学习在玉米叶片病害识别中的研究与应用[J]. 中国农机化学报, 2022, 43(3): 146-152.
[3]	高文强, , 肖志云, . 多尺度特征融合1D—CNN的马铃薯植株高光谱数据地物分类和缺素识别#br#[J]. 中国农机化学报, 2022, 43(3): 111-119.
[4]	赵延鹏, 王峰, 杨永发, 李玮, 王应彪, 费建国. 基于作业工况和退役锂离子电池的电动拖拉机电源系统优化[J]. 中国农机化学报, 2022, 43(2): 104-111.
[5]	吐尔逊·买买提, 赵梦佳, 孔庆好. 新疆县域拖拉机排放清单及其时空格局[J]. 中国农机化学报, 2022, 43(1): 195-202.
[6]	石洪康, 肖文福, 黄亮, 胡丛武, 胡光荣, 张剑飞. 基于卷积神经网络的家蚕病害识别研究[J]. 中国农机化学报, 2022, 43(1): 150-.
[7]	张三强, 邹星, 陈源, 章桃娟. 船式拖拉机气层减阻影响因素分析与参数优化研究[J]. 中国农机化学报, 2022, 43(1): 20-26.
[8]	扈凯;张文毅;李坤;刘宏俊;祁兵;纪要;. 基于模态规划法的履带拖拉机车架振动分析与优化[J]. 中国农机化学报, 2021, 42(8): 121-126.
[9]	王鹤树;曹丽英;. 基于全卷积神经网络的植物叶片自动分割及表型解析[J]. 中国农机化学报, 2021, 42(8): 161-168.
[10]	刘静;夏长高;孙闫;. 双能源电动拖拉机能量管理策略[J]. 中国农机化学报, 2021, 42(7): 115-121.
[11]	毛智琳;蒋建东;章沈强;杨振兴;张奋飞;杨锦章;. 全架式履带拖拉机机架设计与优化[J]. 中国农机化学报, 2021, 42(7): 122-129.
[12]	翁海勇;许金钗;陶铸;刘江洪;郑金贵;叶大鹏;. 高EGCG含量茶树品种光谱识别模型构建[J]. 中国农机化学报, 2021, 42(6): 111-117.
[13]	冯叶陶;廖敏;张小军;张涛;潘群林;. 丘陵山地拖拉机前驱动桥壳组件轻量化设计与试验研究[J]. 中国农机化学报, 2021, 42(5): 107-113.
[14]	陈强;戴军;. 农机驾驶人员疲劳驾驶行为检测研究[J]. 中国农机化学报, 2021, 42(5): 148-152.
[15]	刘学峰;仪垂良;张德学;张成保;任冬梅;高强;. 拖拉机转向驱动桥自动限滑差速器液压系统设计[J]. 中国农机化学报, 2021, 42(3): 7-12.

基于卷积神经网络的拖拉机工况识别

Recognition of tractor working condition based on convolutional neural network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价