Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)  2023, Vol. 57 Issue (10): 2028-2041    DOI: 10.3785/j.issn.1008-973X.2023.10.012
机械工程、能源工程     
基于IndRNN-1DLCNN的负载口独立控制阀控缸系统故障诊断
孙炜(),刘恒,陶建峰*(),孙浩,刘成良
上海交通大学 机械系统与振动国家重点实验室，上海 200240
IndRNN-1DLCNN based fault diagnosis of independent metering valve-controlled hydraulic cylinder system
Wei SUN(),Heng LIU,Jian-feng TAO*(),Hao SUN,Cheng-liang LIU
State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai 200240, China
 全文: PDF(3321 KB)   HTML
摘要：

为了解决负载口独立控制阀控液压缸系统故障信息相似表征下的故障元件识别难题，提出基于独立循环神经网络(IndRNN)和一维大核卷积神经网络(1DLCNN)结合的故障诊断方法. 构建负载口独立控制阀控液压缸系统，针对系统提出压力与位移信号的状态感知方案，分析了系统故障的信号特征. 设计一种基于IndRNN-1DLCNN的深度神经网络模型，模型引入残差结构进行多层IndRNN设计并引入1DLCNN增强全局信息捕捉能力，实现多源信号的融合，识别发生故障的具体元件. 结果表明在不同的负载工况下，利用提出的方法均能够准确地将系统故障定位至4个先导阀、2个主阀、1组位移传感器以及1个液压缸共8类具体元件，系统的整体诊断准确率最高达到96%，单一元件的故障识别准确率均大于93%.
关键词： 负载口独立控制;  阀控液压缸系统;  独立循环神经网络;  一维大核卷积神经网络;  故障诊断    
Abstract:

A fault diagnosis method was proposed to address the problem of fault components identification under similar fault information representations in an independent metering valve-controlled hydraulic cylinder system. An independently recurrent neural network (IndRNN) and a one-dimensional large-kernel convolution neural network (1DLCNN) was combined in the method. An independent metering valve-controlled hydraulic cylinder system was constructed. A state-sensing scheme was presented for capturing pressure and displacement signals. The signal characteristics under different fault conditions were analyzed. A deep neural network model utilizing IndRNN-1DLCNN was established. The deep network architecture of multi-layer IndRNN with a residual structure was adopted. The 1DLCNN was developed to enhance the global information capture capability. The model structure facilitated multi-sensor information fusion and specific fault component identification. Results showed that the proposed method could accurately distinguish eight specific fault components, including four pilot valves, two main valves, displacement sensors and a hydraulic cylinder in the case of different working conditions. The overall diagnostic accuracy of the system could reach up to 96% for the discussed working conditions. The fault identification accuracy of one component was above 93% under the working condition.
Key words: independent metering control    valve-controlled hydraulic cylinder system    independently recurrent neural network    one-dimensional large-kernel convolution neural network    fault diagnosis
收稿日期: 2022-10-21 出版日期: 2023-10-18
CLC:  TH 137  
基金资助: 国家重点研发计划资助项目（2020YFB2009703）；教育部-中国移动联合基金资助建设项目（MCM20180703）
通讯作者: 陶建峰     E-mail: fireire233@sjtu.edu.cn;jftao@sjtu.edu.cn
作者简介: 孙炜（1999—），男，硕士生，从事液压阀故障诊断研究. orcid.org/0000-0001-9960-2762. E-mail： fireire233@sjtu.edu.cn
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　　
孙炜
刘恒
陶建峰
孙浩
刘成良

引用本文:

孙炜,刘恒,陶建峰,孙浩,刘成良. 基于IndRNN-1DLCNN的负载口独立控制阀控缸系统故障诊断[J]. 浙江大学学报(工学版), 2023, 57(10): 2028-2041.

Wei SUN,Heng LIU,Jian-feng TAO,Hao SUN,Cheng-liang LIU. IndRNN-1DLCNN based fault diagnosis of independent metering valve-controlled hydraulic cylinder system. Journal of ZheJiang University (Engineering Science), 2023, 57(10): 2028-2041.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2023.10.012    或    https://www.zjujournals.com/eng/CN/Y2023/V57/I10/2028

图 1  负载口独立控制阀控液压缸系统的原理图
图 2  负载口独立控制阀控液压缸系统的实物图
参数 参数值 参数 参数值
$ {p}_{\mathrm{s}} $ 10.00 MPa $ {M}_{\mathrm{p}} $ 0.05 kg
$ {p}_{\mathrm{s}\mathrm{p}} $ 3.20 MPa $ {D}_{\mathrm{c}} $ 140.00 mm
$ {D}_{\mathrm{v}} $ 16.00 mm $ {D}_{\mathrm{r}} $ 100.00 mm
$ {M}_{\mathrm{v}} $ 1.00 kg M 100.00 kg
$ {D}_{\mathrm{p}} $ 8.00 mm K 2.50×106 N/m
表 1  阀控液压缸系统参数
图 3  高速开关阀驱动电压的示意图
图 4  负载口独立控制阀控液压缸系统的控制策略
参数符号 参数值
PID1比例环节 $ {K}_{\mathrm{p}\mathrm{v}1}、{K}_{\mathrm{p}\mathrm{v}2} $ 60.00
PID1积分环节 $ {K}_{\mathrm{i}\mathrm{v}1}、{K}_{\mathrm{i}\mathrm{v}2} $ 0
PID1微分环节 $ {K}_{\mathrm{d}\mathrm{v}1}、{K}_{\mathrm{d}\mathrm{v}2} $ 0.10
PID1转换系数 $ {K}_{\mathrm{v}1} $ ?0.01
PID1转换系数 $ {K}_{\mathrm{v}2} $ 0.01
PID2比例环节 $ {K}_{\mathrm{p}\mathrm{l}1}、{K}_{\mathrm{p}\mathrm{l}2}、{K}_{\mathrm{p}\mathrm{r}1}、{K}_{\mathrm{p}\mathrm{r}2} $ 100.00
PID2积分环节 $ {K}_{\mathrm{i}\mathrm{l}1}、{K}_{\mathrm{i}\mathrm{l}2}、{K}_{\mathrm{i}\mathrm{r}1}、{K}_{\mathrm{i}\mathrm{r}2} $ 0
PID2微分环节 $ {K}_{\mathrm{d}\mathrm{l}1}、{K}_{\mathrm{d}\mathrm{l}2}、{K}_{\mathrm{d}\mathrm{r}1}、{K}_{\mathrm{d}\mathrm{r}2} $ 0.10
PID2转换系数 $ {K}_{\mathrm{l}1}、{K}_{\mathrm{r}1} $ 250.00
PID2转换系数 $ {K}_{\mathrm{l}2}、{K}_{\mathrm{r}2} $ ?250.00
表 2  阀控液压缸系统的控制器参数
图 5  系统模型的结构简图
图 6  阀口流量与压损特性验证
图 7  阶跃响应特性验证
图 8  系统阶跃响应特性的验证
图 9  高速开关阀的套筒锈蚀
类型 正常值区间 故障值区间
${d}_{\mathrm{C} }$/s [0， 0.0003] (0.0003， 0.0010]
$ {f}_{\mathrm{C}} $/Hz [48， 52] [40， 48)， (52， 60]
${N}_{\mathrm{P} }$/N [1.3， 1.5] [0.6， 1.3)
kP/(N·mm?1) [4.6， 4.8] [3.5， 4.6)
表 3  先导阀的故障参数
图 10  左先导阀1的故障示意图
参数 正常值区间 故障值区间
rV/mm [0.001， 0.015] (0.015， 0.080]
lV/mm [0.001， 0.015] (0.015， 0.080]
NV/N [133， 149] [70， 133)
kV/(N·mm?1) [13.4， 14.8] [7.0， 13.4)
表 4  主阀故障参数
图 11  左主阀故障的示意图
参数 正常值区间 故障值区间
$ {\delta }_{\mathrm{V}} $/mm [0， 0.03] (0.03， 0.15]
$ {\delta }_{\mathrm{C}} $/mm [0， 0.01] (0.01， 0.50]
表 5  位移传感器反馈故障参数
图 12  多层IndRNN网络示意图
图 13  1DLCNN网络示意图
图 14  基于IndRNN-1DLCNN故障诊断模型
故障类型 标签 故障类型 标签 故障类型 标签
系统无故障 0 左先导阀1故障 3 右主阀故障 6
左先导阀1故障 1 左先导阀2故障 4 液压缸故障 7
左先导阀2故障 2 左主阀故障 5 传感器故障 8
表 6  系统故障类型标签
网络层 输入维度 输出维度 关键参数
IndRNN 9×2000 64×2000 IndRNN单元个数：7
隐层特征个数：64
残差连接个数：3
1DLCNN 64×2000 120×39 卷积核大小：100
步长：50
MaxPooling1 120×29 120×5 池化核大小：20
步长：4
1DCNN 120×5 200×3 卷积核大小：3
步长：1
MaxPooling2 200×3 200×1 池化核大小：3
步长：1
表 7  IndRNN-1DLCNN的模型参数
模型 精度/% 模型 精度/%
LSTM 25.6 IndRNN 84.7
2DCNN 87.9 1DLCNN 90.9
1DCNN 85.1 IndRNN-1DLCNN 96.0
表 8  系统的故障诊断精度
图 15  故障诊断测试集的混淆矩阵
图 16  故障诊断模型的特征可视化
图 17  不同工况下的故障诊断算法精度
模型 ACC/%
工况A 工况B 工况C
2DCNN 87.9 89.1 90.2
1DCNN 85.1 84.5 86.7
IndRNN 84.7 84.8 83.7
1DLCNN 90.9 93.0 91.3
IndRNN-1DLCNN 96.0 96.0 95.4
表 9  不同工况下的故障诊断算法精度对比
1 徐兵, 丁孺琦, 张军辉 基于泵阀联合控制的负载口独立系统试验研究[J]. 浙江大学学报: 工学版, 2015, 49 (1): 93- 101
XU Bing, DING Ru-qi, ZHANG Jun-hui Experiment research on individual metering systems of mobile machinery based on coordinate control of pump and valves[J]. Journal of Zhejiang University: Engineering Science, 2015, 49 (1): 93- 101
2 CAMPANINI F, BIANCHI R, VACCA A, et al. Optimized control for an independent metering valve with integrated diagnostic features [C]// ASME/BATH Symposium on Fluid Power and Motion Control. Sarasota: ASME, 2017: 1-10.
3 钟麒. 面向负载口独立控制的可编程阀关键技术研究[D]. 杭州: 浙江大学, 2019: 85-141.
ZHONG Qi. Research on key technologies of programmable valve for independent metering control [D]. Hangzhou: Zhejiang University, 2019: 85-141.
4 牛善帅, 王军政, 张鹏, 等 基于负载口独立控制的双伺服阀控缸系统[J]. 北京理工大学学报, 2019, 39 (12): 1292- 1297
NIU Shan-shuai, WANG Jun-zheng, ZHANG Peng, et al A dual servo-valved cylinder system based on load port independent control[J]. Transactions of Beijing Institute of Technology, 2019, 39 (12): 1292- 1297
5 OPDENBOSCH P, SADEGH N, BOOK W, et al. Auto-calibration based control for independent metering of hydraulic actuators [C]// IEEE International Conference on Robotics and Automation. Shanghai: IEEE, 2011: 153-158.
6 LÜBBERT J, SITTE A, BECK B, et al. Load-force-adaptive outlet throttling: an easily commissionable independent metering control strategy [C]// BATH/ASME Symposium on Fluid Power and Motion Control. Bath: ASME, 2016: 1-13.
7 ABUOWDA K, NOROOZI S, DUPAC M, et al. Algorithm design for the novel mechatronics electro-hydraulic driving system: micro-independent metering [C]// IEEE International Conference on Mechatronics. Ilmenau: IEEE, 2019: 7-12.
8 ZHONG Q, BAO H M, LI Y B, et al Investigation into the independent metering control performance of a twin spools valve with switching technology-controlled pilot stage[J]. Chinese Journal of Mechanical Engineering, 2021, 34 (5): 242- 258
9 LI C, LYU L T, HELIAN B B, et al Precision motion control of an independent metering hydraulic system with nonlinear flow modeling and compensation[J]. IEEE Transactions on Industrial Electronics, 2022, 69 (7): 7088- 7098
doi: 10.1109/TIE.2021.3102434
10 ABUOWDA K, OKHOTNIKOV I, NOROOZI S, et al A review of electrohydraulic independent metering technology[J]. ISA Transactions, 2020, 98: 364- 381
doi: 10.1016/j.isatra.2019.08.057
11 RANNOW M. Fail operational controls for an independent metering valve [C]// 10th International Fluid Power Conference. Dresden: Technische Universität Dresden, 2016: 465-476.
12 DING R, CHENG M, JIANG L, et al Active fault-tolerant control for electro-hydraulic systems with an independent metering valve against valve faults[J]. IEEE Transactions on Industrial Electronics, 2020, 68 (8): 7221- 7232
13 OPDENBOSCH P, SADEGH N, BOOK W Intelligent controls for electro-hydraulic poppet valves[J]. Control Engineering Practice, 2013, 21 (6): 789- 796
doi: 10.1016/j.conengprac.2013.02.008
14 BECK B, WEBER J. Enhancing safety of independent metering systems for mobile machines by means of fault detection [C]// 15th Scandinavian International Conference on Fluid Power. Linköping: LUEP, 2017: 92-102.
15 BIANCHI R, VACCA A, CAMPANINI F. Combining control and monitoring in mobile machines: the case of an hydraulic crane [C]// 11th International Fluid Power Conference. Aachen: RWTH, 2018: 307-319.
16 WANG S, ZHANG B, ZHONG Q, et al Study on control performance of pilot high-speed switching valve[J]. Advances in Mechanical Engineering, 2017, 9 (7): 1- 18
17 ZHONG Q, ZHANG B, YANG H Y, et al Performance analysis of a high-speed on/off valve based on an intelligent pulse-width modulation control[J]. Advances in Mechanical Engineering, 2017, 9 (11): 1- 11
18 RITELLI G F, VACCA A Energetic and dynamic impact of counterbalance valves in fluid power machines[J]. Energy Conversion and Management, 2013, 76: 701- 711
doi: 10.1016/j.enconman.2013.08.021
19 LI Y, WANG N, DENG S, et al. Performance analysis of high-speed on-off valve coupled with thermal effect [C]// CSAA/IET International Conference on Aircraft Utility Systems. Nanchang: IET, 2022: 559-606.
20 孙博文. 基于对偶空间变换与深度神经网络的闭环控制系统故障诊断方法研究 [D]. 长沙: 国防科技大学, 2019: 13-35.
SUN Bo-wen. Fault diagnosis for closed-loop control systems based on parity space transformation and deep neural network [D]. Changsha: National University of Defense Technology, 2019: 13-35.
21 SHI J C, YI J Y, REN Y, et al Fault diagnosis in a hydraulic directional valve using a two-stage multi-sensor information fusion[J]. Measurement, 2021, 179: 109460
doi: 10.1016/j.measurement.2021.109460
22 刘渊, 张天宏, 周俊 航空发动机燃油调节执行机构及其传感器的故障诊断与半物理仿真[J]. 推进技术, 2016, 37 (11): 2165- 2172
LIU Yuan, ZHANG Tian-hong, ZHOU Jun Fault diagnosis and semi-physical simulation for actuator and sensor of aero-engine fuel regulator[J]. Journal of Propulsion Technology, 2016, 37 (11): 2165- 2172
23 周诗金. 光栅线位移传感器可靠性试验过程状态监测及故障诊断[D]. 长春: 吉林大学, 2019: 9-20.
ZHOU Shi-jin. Condition monitoring and fault diagnosis of reliability test process of raster line displacement sensor [D]. Changchun: Jilin University, 2019: 9-20.
24 GUO J X, TAO J F, LI L, et al. Diagnosis method for valve-controlled hydraulic cylinder leakage based on subspace identification [C]// BATH/ASME Symposium on Fluid Power and Motion Control. Bath: ASME, 2018: 1-6.
25 LI S, LI W Q, COOK C, et al. Independently recurrent neural network (IndRNN): building a longer and deeper RNN [C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake: IEEE, 2018: 5457-5466.
[1] 王誉翔,钟智伟,夏鹏程,黄亦翔,刘成良. 基于改进Transformer的复合故障解耦诊断方法[J]. 浙江大学学报(工学版), 2023, 57(5): 855-864.
[2] 牛英杰,苏燕辰,程敦诚,廖家,赵海波,高永强. 高铁接触网U型抱箍螺母故障检测算法[J]. 浙江大学学报(工学版), 2021, 55(10): 1912-1921.
[3] 金列俊,詹建明,陈俊华,王涛. 基于一维卷积神经网络的钻杆故障诊断[J]. 浙江大学学报(工学版), 2020, 54(3): 467-474.
[4] 谢乐,衡熙丹,刘洋,蒋启龙,刘东. 基于线性判别分析和分步机器学习的变压器故障诊断[J]. 浙江大学学报(工学版), 2020, 54(11): 2266-2272.
[5] 林京京,沈艳霞. 永磁同步电机驱动系统电流传感器容错控制[J]. 浙江大学学报(工学版), 2019, 53(9): 1815-1825.
[6] 张政,周学军,王希晨,周媛媛. 缆系水下信息网恒流远供系统短路故障诊断及区间定位方法[J]. 浙江大学学报(工学版), 2019, 53(6): 1190-1197.
[7] 童水光, 张依东, 徐剑, 从飞云. 频带多尺度复合模糊熵及其在轴承故障诊断中的应用[J]. 浙江大学学报(工学版), 2018, 52(8): 1509-1516.
[8] 葛云龙, 陈自强, 郑昌文. UTSTF锂离子电池时变参数估计与故障诊断[J]. 浙江大学学报(工学版), 2018, 52(6): 1223-1230.
[9] 余建波, 李传锋, 吕靖香. 轴承故障信号的平均组合差值形态滤波分析[J]. 浙江大学学报(工学版), 2018, 52(10): 1845-1853.
[10] 祝文颖, 冯志鹏. 基于迭代Hilbert变换的行星齿轮箱振动信号分析[J]. 浙江大学学报(工学版), 2017, 51(8): 1587-1595.
[11] 丁孺琦, 徐兵, 张军辉. 负载口独立控制系统压力速度复合控制的耦合特性[J]. 浙江大学学报(工学版), 2017, 51(6): 1126-1134.
[12] 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.
[13] 陈辰,厉小润. 基于线圈电流分析的操动机构故障诊断方法[J]. 浙江大学学报(工学版), 2016, 50(3): 527-535.
[14] 韩玲, 卢延辉, 安颖, 田丽媛. 基于容错理论无级变速器故障诊断分类[J]. 浙江大学学报(工学版), 2016, 50(10): 1927-1936.
[15] 罗林, 苏宏业, 班岚. Dirichlet过程混合模型在非线性过程监控中的应用[J]. 浙江大学学报(工学版), 2015, 49(11): 2230-2236.