Please wait a minute...
浙江大学学报(工学版)  2019, Vol. 53 Issue (9): 1663-1673    DOI: 10.3785/j.issn.1008-973X.2019.09.004
机械工程     
液压挖掘机作业循环状态智能识别方法
黄杰1,2(),王东1,3,*(),王新晴1,殷勤1,邵发明1
1. 陆军工程大学 野战工程学院,江苏 南京 210007
2. 武警工程大学(乌鲁木齐校区),新疆 乌鲁木齐 830049
3. 南部战区 陆军第二工程科研设计所,云南 昆明 650222
Intelligent recognition method for working-cycle state of hydraulic excavator
Jie HUANG1,2(),Dong WANG1,3,*(),Xin-qing WANG1,Qin YIN1,Fa-ming SHAO1
1. College of Field Engineering, Army Engineering University of PLA, Nanjing 210007, China
2. Engineering University of PAP, Urumqi Campus, Urumqi 830049, China
3. Second Institute of Engineering Research and Design,Southern Theatre Command, Kunming 650222, China
 全文: PDF(1536 KB)   HTML
摘要:

为实现液压挖掘机作业循环阶段状态的自动识别,提出采用时窗滑移特征提取与PCA-SVM相结合的方法. 以液压挖掘机2个主泵压力信号为研究对象,采用时窗滑移截取各阶段状态的小段波形,提取所有截取波段相应的时频参数并进行特征值归一化,经PCA降维处理后作为输入特征集,采用SVM进行状态分类,并分别讨论时窗宽度与重叠率对识别准确率的影响. 引入即时校正策略,对直接识别结果进行自动检验校正,纠正不符合挖掘机循环作业逻辑规则的误判结果,从而使识别准确率由80.85%提高到89.36%. 实验结果表明,所提方法能准确有效地实现液压挖掘机作业循环各阶段状态的自动识别.

关键词: 液压挖掘机作业循环状态识别支持向量机(SVM)即时校正策略    
Abstract:

A novel intelligent recognition method based on the combination of PCA-SVM and feature extraction with sliding time-window was proposed to recognize each state in working cycle stages of hydraulic excavator. The pressure signals of two pumps were taken as recognizing object, and small waveform segments of each state in a working cycle of hydraulic excavator were intercepted by adopting sliding time-window method. The corresponding time domain and frequency domain parameters of all waveform segments were extracted and the eigenvalue normalization was carried out. The normalized set was used as input feature set after reduction of dimensionality with principal component analysis (PCA), then state classification was conducted by adopting the SVM algorithm, and the effects of sliding time-window width and overlap rate to the recognition accuracy were discussed, respectively. Besides, a real-time correction strategy was introduced to automatically check and correct the direct recognition results; the misjudgment results against the logic rule of excavator operation was verified, and the recognition accuracy was improved from 80.85% to 89.36%. Results prove that the proposed method can realize the state recognition of each stage in a working cycle of hydraulic excavator effectively and accurately.

Key words: hydraulic excavator    working cycle    state recognition    SVM    real-time correction strategy
收稿日期: 2018-07-22 出版日期: 2019-09-12
CLC:  TU 621  
通讯作者: 王东     E-mail: huangjie051501@126.com;dyhkxydfbb@163.com
作者简介: 黄杰(1989—),男,讲师,博士,从事机械信号处理研究. orcid.org/0000-0003-2657-2931. E-mail: huangjie051501@126.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章  
黄杰
王东
王新晴
殷勤
邵发明

引用本文:

黄杰,王东,王新晴,殷勤,邵发明. 液压挖掘机作业循环状态智能识别方法[J]. 浙江大学学报(工学版), 2019, 53(9): 1663-1673.

Jie HUANG,Dong WANG,Xin-qing WANG,Qin YIN,Fa-ming SHAO. Intelligent recognition method for working-cycle state of hydraulic excavator. Journal of ZheJiang University (Engineering Science), 2019, 53(9): 1663-1673.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2019.09.004        http://www.zjujournals.com/eng/CN/Y2019/V53/I9/1663

图 1  液压挖掘机的主要动作
图 2  2个主泵压力传感器的安装图
图 3  液压挖掘机作业循环示意图
图 4  液压系统控制原理图
图 5  挖掘阶段压力波形
图 6  提升阶段压力波形
图 7  液压挖掘机作业循环状态的识别流程
图 8  时窗滑移过程示意图
图 9  主成分分析(PCA)处理特征集
$\Delta t$/s Q1/ % Q2/ % $\Delta t$/s Q1/ % Q2/ %
0.1 45.05 45.33 0.6 76.56 82.79
0.2 70.31 77.82 0.7 75.64 79.11
0.3 73.41 77.75 0.8 76.88 84.78
0.4 73.36 74.55 0.9 76.67 81.86
0.5 80.22 86.40 1.0 74.76 81.97
表 1  时窗宽度变化时的直接识别结果与校正具体结果
$\varphi $ Q1/ % Q2/ % $\varphi $ Q1/ % Q2/ %
0 80.22 86.40 0.500 76.64 82.57
0.125 80.72 88.01 0.625 75.28 82.69
0.250 81.21 88.50 0.750 76.14 82.69
0.375 78.74 85.66 ? ? ?
表 2  重叠率变化时的直接识别结果与校正具体结果
实际状态 Q $/$% N Nr
S1 86.86 175 152
S2 77.42 62 48
S3 78.43 102 80
S4 62.32 69 43
S5 53.20 94 50
S6 88.62 167 148
S7 97.14 140 136
总计 81.21 809 657
表 3  最优取值时的直接识别结果
w/Ne 误判状态
S1 S2 S3 S4 S5 S6 S7



S1 ? 0.057 1/10 ? ? ? 0.068 6/12 0.005 7/1
S2 0.012 9/8 ? ? 0.080 6/5 ? 0.016 1/1 ?
S3 ? ? ? ? 0.215 7/22 ? ?
S4 0.029 0/2 0.275 4/19 ? ? ? 0.058 0/4 0.014 5/1
S5 0.053 2/5 ? 0.414 9/39 ? ? ? ?
S6 0.060 0/10 ? 0.018 0/3 0.006 0/1 ? ? 0.030 0/5
S7 ? ? ? ? ? 0.028 6/4 ?
总计 0.030 9/25 0.035 8/29 0.051 9/42 0.007 4/6 0.027 2/22 0.025 9/21 0.008 6/7
表 4  最优取值时的误判详情
图 10  典型循环作业过程的识别结果与真实状态
图 11  即时校正结果与对应的真实状态
1 谢科. 基于环境识别平台的挖掘机智能作业试验系统研制[D]. 杭州: 浙江大学, 2016.
XIE Ke. Research and development of excavator intellig- ent operation test system based on environment identification platform[D]. Hangzhou: Zhejiang University, 2016.
2 朱建新, 沈东羽, 吴钪 基于激光点云的智能挖掘机目标识别[J]. 计算机工程, 2017, 43 (1): 297- 302
ZHU Jian-xin, SHEN Dong-yu, WU Kang Target recognition for intelligent excavator based on laser point cloud[J]. Computer Engineering, 2017, 43 (1): 297- 302
doi: 10.3969/j.issn.1000-3428.2017.01.051
3 TANAKA M, DOISHITA K. Method and system for supporting fuel cost saving operation of construction machine: JP, 082506 [P]. 2008-10-09.
4 柳齐. 基于动作序列识别的挖掘机智能节能方法研究[D]. 厦门: 华侨大学, 2014.
LIU Qi. Intelligent energy-saving method research of excavator based on identifying the sequence of actions [D]. Xiamen: Huaqiao University, 2014.
5 郝鹏, 何清华, 张新海, 等 挖掘机负载和工况识别技术研究[J]. 液压气动与密封, 2008, 28 (5): 8- 13
HAO Peng, HE Qing-hua, ZHANG Xin-hai, et al Study on load and operation mode identification of excavator[J]. Hydraulic Pneumatics and Seal, 2008, 28 (5): 8- 13
doi: 10.3969/j.issn.1008-0813.2008.05.003
6 ZAROTTI, S, PAOLUZZI R, GANASSI G, et al. Analysis of hydraulic excavator working cycle [C] // Proceedings of the 11th European Regional Conference of the ISTVS. Bremen: ISTVS, 2009: 153-160.
7 于洪光, 高峰, 柳桂国, 等 液压挖掘机标准负载工况的研究[J]. 机电工程, 2013, 30 (1): 43- 46
YU Hong-guang, GAO Feng, LIU Gui-guo, et al Research of standard load condition of hydraulic excavator[J]. Journal of Mechanical and Electrical Engineering, 2013, 30 (1): 43- 46
8 TIMUSK M A, LIPSETTM G, MCBAIN J, et al Automated operating mode classification for online monitoring systems[J]. Journal of Vibration and Acoustics, 2009, 131 (4): 1124- 1124
9 MINTAH B, PRICE R J, KING K D, et al. Adaptive work cycle control system: US, 8024095 [P]. 2011-09-20.
10 冯培恩, 彭贝, 高宇, 等 液压挖掘机作业循环阶段的智能识别[J]. 浙江大学学报: 工学版, 2016, 50 (2): 209- 217
FENG Pei-en, PENG Bei, GAO Yu, et al Intelligent identification for working-cycle stages of hydraulic excavator[J]. Journal of Zhejiang University: Engineering Science, 2016, 50 (2): 209- 217
11 杨永文 詹阳GJW111高原型挖掘机[J]. 工程机械与维修, 2010, (5): 145- 145
YANG Yong-wen GJW111 plateau excavator of Zhanyang[J]. Construction Machinery and Maintenance, 2010, (5): 145- 145
doi: 10.3969/j.issn.1006-2114.2010.05.032
12 刘志东, 李莺莺, 杨清淞, 等 挖掘机液压系统载荷数据测试方法研究[J]. 工程机械, 2013, 44 (3): 18- 25
LIU Zhi-dong, LI Ying-ying, YANG Qing-song, et al Research on test method of payload data of the excavator ’s hydraulic system[J]. Construction Machinery and Equipment, 2013, 44 (3): 18- 25
doi: 10.3969/j.issn.1000-1212.2013.03.006
13 陈仁祥, 陈思杨, 杨黎霞, 等 基于振动敏感时频特征的航天轴承寿命状态识别方法[J]. 振动与冲击, 2016, 35 (17): 134- 139
CHEN Ren-xiang, CHEN Si-yang, YANG Li-xia, et al Life state recognition method for space bearings based on sensitive time-frequency features of vibration[J]. Journal of Vibration and Shock, 2016, 35 (17): 134- 139
14 时培明, 梁凯, 赵娜, 等 基于深度学习特征提取和粒子群支持向量机状态识别的齿轮智能故障诊断[J]. 中国机械工程, 2017, 28 (9): 1056- 1061
SHI Pei-ming, LIANG Kai, ZHAO Na, et al Intelligent fault diagnosis for gears based on deep learning feature extraction and particle swarm optimization SVM state identification[J]. China Mechanical Engineering, 2017, 28 (9): 1056- 1061
doi: 10.3969/j.issn.1004-132X.2017.09.009
15 YANG C Y, WU T Y Diagnostics of gear deterioration using EEMD approach and PCA process[J]. Measurement, 2015, 61: 75- 87
doi: 10.1016/j.measurement.2014.10.026
16 刘金刚, 周晓群, 王凯 基于PCA和SVM的盾构液压系统故障诊断[J]. 计算机仿真, 2017, (12): 426- 430
LIU Jin-gang., ZHOU Xiao-qun, WANG Kai. Fault diagnosis of hydraulic system for shield machine based on PCA and SVM[J]. Computer Simulation, 2017, (12): 426- 430
doi: 10.3969/j.issn.1006-9348.2017.12.094
[1] 高新智,刘作军,张燕,陈玲玲. 基于GWO-SVM的下肢假肢穿戴者骑行相位识别[J]. 浙江大学学报(工学版), 2021, 55(4): 648-657.
[2] 蔡畅,黄亦翔,邢宏文. 基于梯度提升树的飞机机身对接状态识别[J]. 浙江大学学报(工学版), 2019, 53(7): 1274-1281.
[3] 都明宇, 鲍官军, 杨庆华, 王志恒, 张立彬. 基于改进支持向量机的人手动作模式识别方法[J]. 浙江大学学报(工学版), 2018, 52(7): 1239-1246.
[4] 赵晓东, 刘作军, 陈玲玲, 杨鹏. 下肢假肢穿戴者跑动步态识别方法[J]. 浙江大学学报(工学版), 2018, 52(10): 1980-1988.
[5] 李麟玮, 吴益平, 苗发盛. 基于灰狼支持向量机的非等时距滑坡位移预测[J]. 浙江大学学报(工学版), 2018, 52(10): 1998-2006.
[6] 袁红, 王波, 王丽, 许睦旬. 以轮廓为对象的体态特征情绪分类与预测[J]. 浙江大学学报(工学版), 2018, 52(1): 160-165.
[7] 尤海辉, 马增益, 唐义军, 王月兰, 郑林, 俞钟, 吉澄军. 循环流化床入炉垃圾热值软测量[J]. 浙江大学学报(工学版), 2017, 51(6): 1163-1172.
[8] 廖苗, 赵于前, 曾业战, 黄忠朝, 张丙奎, 邹北骥. 基于支持向量机和椭圆拟合的细胞图像自动分割[J]. 浙江大学学报(工学版), 2017, 51(4): 722-728.
[9] 钟崴, 彭梁, 周永刚, 徐剑, 从飞云. 基于小波包分析和支持向量机的锅炉结渣诊断[J]. 浙江大学学报(工学版), 2016, 50(8): 1499-1506.
[10] 赵凌, 黄平捷, 刘宝玲, 赵树浩, 侯迪波, 张光新. 多层导电结构内部状态脉冲涡流检测分析方法[J]. 浙江大学学报(工学版), 2016, 50(4): 603-608.
[11] 冯培恩, 彭贝, 高宇, 邱清盈. 液压挖掘机作业循环阶段的智能识别[J]. 浙江大学学报(工学版), 2016, 50(2): 209-217.
[12] 王飞, 管成, 肖扬, 李威. 挖掘机动臂势能回收系统的压力滑模控制[J]. 浙江大学学报(工学版), 2016, 50(2): 201-208.
[13] 潘翔,童伟淮,张三元,郑河荣. 结合语义本体与泊松方程的动画角色模型分割[J]. 浙江大学学报(工学版), 2015, 49(9): 1634-1641.
[14] 管成,王飞,解泽哲,肖扬. 功率差值补偿式挖掘机液压混合动力系统[J]. 浙江大学学报(工学版), 2015, 49(5): 813-820.
[15] 陈进,庆飞,庞晓平. 基于组合挖掘的反铲液压挖掘机工作装置优化设计[J]. 浙江大学学报(工学版), 2014, 48(9): 1654-1660.