基于互信息和BO-LSTM的挖掘机液压系统压力软测量

doi:10.3901/JME.2025.16.384

机械工程学报 ›› 2025, Vol. 61 ›› Issue (16): 384-393.doi: 10.3901/JME.2025.16.384

• 交叉与前沿 • 上一篇

扫码分享

基于互信息和BO-LSTM的挖掘机液压系统压力软测量

谭林¹, 马伟¹, 殷晨波¹, 杨中良², 王大宇³

1. 南京工业大学车辆与工程机械研究所南京 211816；
2. 三一重机有限公司大挖研究院苏州 215300；
3. 中国工程机械工业协会科技质量部北京 100032

接受日期:2024-08-20 出版日期:2025-03-13 发布日期:2025-03-13
作者简介:谭林，男，1998年出生。主要研究方向为工程机械智能化，机器学习。E-mail：tanlin_iacm@163.com;马伟，男，1994年出生，博士研究生。主要研究方向为挖掘机流体传动，工程机械智能化。E-mail：mawei_iacm@163.com;殷晨波，男，1963年出生，博士，教授，博士研究生导师。主要研究方向为工程机械数字化创新与制造，再制造技术在起重机械上的应用。E-mail：yinchenbo@njtech.edu.cn
基金资助:
国家重点研发计划(2021YFB2011904)和江苏省自然科学基金(BK20221342)资助项目

Pressure Soft Measurement of Excavator Hydraulic System Based on Mutual Information and BO-LSTM

TAN Lin¹, MA Wei¹, YIN Chenbo¹, YANG Zhongliang², WANG Dayu³

1. Institute of Automobile and Construction Machinery, Nanjing Tech University, Nanjing 211816;
2. Institute of Large Excavator Research, Sany Heavy Machinery, Suzhou 215300;
3. Department of Science and Technology Quality, Chain Construction Machinery Association, Beijing 100032

Accepted:2024-08-20 Online:2025-03-13 Published:2025-03-13

摘要/Abstract

摘要： 压力信号是参与挖掘机电液比例控制的重要参数。目前，压力信号的获取依赖于压力传感器，但在恶劣的工作条件下，传感器容易出现故障，导致挖掘机控制失效。因此，提出一种基于长短时记忆(Long-short term memory, LSTM)网络的压力软测量模型。先分析SY375IDS挖掘机的液压系统原理，然后利用互信息法(Mutual information, MI)，确定了模型的输入。为了解决LSTM网络超参数选择困难的问题，利用贝叶斯优化(Bayesian optimization, BO)算法进行调优。最后，使用挖掘机90°甩方作业的实测压力数据验证了该模型的有效性。试验结果表明，与其他模型相比较，基于BO-LSTM的压力软测量模型具有更高的准确性和稳定性。考虑到多个传感器同时失效的情况，进行了进一步研究，构建基于BO-LSTM的多输出传统预测(Multi-output traditional prediction, MOTP)模型和多输出循环预测(Multi-output cyclic prediction, MOCP)模型。通过试验比较，MOCP模型表现出更优异的性能。

关键词: 压力传感器, 失效, 长短时记忆网络, 互信息, 贝叶斯优化

Abstract: The pressure signal is a crucial parameter in the electro-hydraulic ratio control of excavators. Currently, pressure sensors are used to acquire pressure signals. However, these sensors are susceptible to failure when operating under harsh conditions, which can lead to control failure in excavators. Therefore, a pressure soft measurement model based on long-short term memory (LSTM) network is proposed. Firstly, the hydraulic system principle of the SY375IDS excavator is analyzed. Then, the input of the model is determined using mutual information(MI). To address the challenge of selecting appropriate hyperparameters for the LSTM network, the Bayesian optimization(BO) algorithm is employed for tuning. Finally, the effectiveness of the model is verified by using the measured pressure data of the excavator during the 90° digging and dumping operation. The experimental results demonstrate that the BO-LSTM-based pressure soft measurement model exhibits higher accuracy and stability when compared to other models. In order to address the issue of simultaneous failure of multiple sensors, we conducted further research and developed a multi-output traditional prediction(MOTP) model and a multi-output cyclic prediction(MOCP) model based on BO-LSTM. Experimental comparison revealed that the MOCP model exhibited better performance.

Key words: pressure sensors, failure, long-short term memory(LSTM), mutual information, Bayesian optimization

中图分类号:

TP212

谭林, 马伟, 殷晨波, 杨中良, 王大宇. 基于互信息和BO-LSTM的挖掘机液压系统压力软测量[J]. 机械工程学报, 2025, 61(16): 384-393.

TAN Lin, MA Wei, YIN Chenbo, YANG Zhongliang, WANG Dayu. Pressure Soft Measurement of Excavator Hydraulic System Based on Mutual Information and BO-LSTM[J]. Journal of Mechanical Engineering, 2025, 61(16): 384-393.

参考文献

[1] ZHANG Weiting , YANG Dong , WANG Hongchao. Data-driven methods for predictive maintenance of industrial equipment: A Survey[J]. IEEE Systems Journal, 2019, 13(3): 2213-2227.
[2] 彭宇,刘大同. 数据驱动故障预测和健康管理综述[J]. 仪器仪表学报, 2014, 35(3): 481-495. PENG Yu, LIU Datong. Data-driven prognostics and health management : A review of recent advances[J]. Chinese Journal of Scientific Instrument, 2014, 35(3): 481-495.
[3] 王丹,康琦,杨居衡,等. 基于 UKF 的海上天然气井数据驱动软测量方法[J]. 天然气工业, 2022, 42(9): 84-92. WANG Dan, KANG Qi, YANG Juheng, et al. UKF-based data-driven soft sensing for offshore gas wells[J]. Natural Gas Industry, 2022, 42(9): 84-92.
[4] WANG Lei. BP network implementation based on computer Matlab neural network toolbox[J]. Journal of Physics: Conference Series, 2020, 1648(2): 022134.
[5] HUANG Limin, JING Yu, CHEN Hangyu, et al. A regional wind wave prediction surrogate model based on CNN deep learning network[J]. Applied Ocean Research, 2022, 126: 103287.
[6] AMALOU I, MOUHNI N, ABDALI A. Multivariate time series prediction by RNN architectures for energy consumption forecasting[J]. Energy Reports, 2022, 8(9): 1084-1091.
[7] NGUYEN N D, NGUYEN V T. Development of ANN structural optimization framework for data-driven prediction of local two-phase flow parameters[J]. Progress in Nuclear Energy, 2022, 146: 104176.
[8] YUAN Xiaofeng, LI Lin, SHARDT Y A W, et al. Deep learning with spatiotemporal attention-based LSTM for industrial soft sensor model development[J]. IEEE Transactions on Industrial Electronics, 2020, 68(5): 4404-4414.
[9] ZHANG Junhui, WANG Di, XU Bing, et al. Flow control of a proportional directional valve without the flow meter[J]. Flow Measurement and Instrumentation, 2019, 67: 131-141.
[10] HUO Dongyang, CHEN Jinshi, ZHANG Han, et al. Intelligent prediction for digging load of hydraulic excavators based on RBF neural network[J]. Measurement, 2023, 206: 112210.
[11] KILIC E, DOLEN M, CALISKAN H, et al. Pressure prediction on a variable-speed pump controlled hydraulic system using structured recurrent neural networks[J]. Control Engineering Practice, 2014, 26: 51-71.
[12] WU Yuting, YUAN Mei, DONG Shaopeng, et al. Remaining useful life estimation of engineered systems using vanilla LSTM neural networks[J]. Neurocomputing, 2018, 275: 167-179.
[13] EISAID A, HIGGINS J, HIGGINS J, et al. Optimizing long short-term memory recurrent neural networks using ant colony optimization to predict turbine engine vibration[J]. Applied Soft Computing Journal, 2018, 73: 969-991.
[14] ZHANG Bin, ZHANG Shaohui, LI Weihua. Bearing performance degradation assessment using long short-term memory recurrent network[J]. Computers in Industry, 2019, 106: 14-29.
[15] CABRERA D, GUAMÁN A, ZHANG Shaohui, et al. Bayesian approach and time series dimensionality reduction to LSTM-based model-building for fault diagnosis of a reciprocating compressor[J]. Neurocomputing, 2019, 380: 51-66.
[16] 崔佳旭,杨博. 贝叶斯优化方法和应用综述[J]. 软件学报, 2018, 29(10): 3068-3090. CUI Jiaxu, YANG Bo. Survey on bayesian optimization methodology and applications[J]. Journal of Software, 2018, 29(10): 3068-3090.
[17] GUO Xiaohui , WANG Yuanfeng , MEI Shengqi. Monitoring and modelling of PM2.5 concentration at subway station construction based on IoT and LSTM algorithm optimization[J]. Journal of Cleaner Production, 2022, 360: 132179.
[18] 季天瑶,王挺韶. 基于词嵌入与卷积神经网络的建筑能耗预测[J]. 华南理工大学学报(自然科学版), 2021, 49(6): 40-48. JI Tianyao , WANG Tingshao. Building energy consumption prediction based on word embedding and convolutional neural network[J]. Journal of South China University of Technology(Natural Science Edition), 2021, 49(6): 40-48.
[19] 石怀涛,尚亚俊,白晓天,等. 基于贝叶斯优化的 SWDAE-LSTM 滚动轴承早期故障预测方法研究[J]. 振动与冲击, 2021, 40(18): 286-297. SHI Huaitao, SHANG Yajun, BAI Xiaotian, et al. Early fault prediction method combining SWDAE and LSTM for rolling bearings based on Bayesian optimization[J]. Journal of Vibration and Shock, 2021, 40(18): 286-297.
[20] 曹东辉,师建鹏,石向星,等. 电液比例挖掘机闭环控制技术思考[J]. 液压与气动, 2021, 45(6): 142-149. CAO Donghui, SHI Jianpeng, SHI Xiangxing, et al. Thinking of closed loop control technology of electrohydraulic proportional excavator[J]. Chinese Hydraulics ＆ Pneumatics, 2021, 45(6): 142-149.
[21] 刘鸿泉,陈少林,孙晓颖,等. 基于神经网络的核电厂设备易损性分析[J]. 力学学报, 2022, 54(7): 2059-2070. LIU Hongquan, CHEN Shaolin, SUN Xiaoying, et al. Vulnerability analysis of NPP equipment based on neural network[J]. Chinese Journal of Theoretical and Applied Mechanics, 2022, 54(7): 2059-2070.
[22] 王岩,陈耀然,韩兆龙,等. 基于互信息理论与递归神经网络的短期风速预测模型[J]. 上海交通大学学报, 2021, 55(9): 1080-1086. WANG Yan, CHEN Yaoran, HAN Zhaolong, et al. Short-term wind speed forecasting model based on mutual information and recursive neural network[J]. Journal of Shanghai Jiao Tong University, 2021, 55(9): 1080-1086.
[23] LI Daoqing, YU Xiaodong, LIU Shulin, et al. Wind power prediction based on PSO-Kalman[J]. Energy Reports, 2022, 4(8): 958-968.
[24] LIMA F T , SOUZA V. A large comparison of normalization methods on time series[J]. Big Data Research, 2023, 34: 100407.
[25] 李鹏,冯存前,许旭光,等. 一种利用贝叶斯优化的弹道目标微动分类网络[J]. 西安电子科技大学学报, 2021, 48(5): 139-148. LI Peng, FENG Cunqian, XU Xuguang, et al. Ballistic target fretting classification network based on Bayesian optimization[J]. Journal of Xidian University, 2021, 48(5): 139-148.

基于互信息和BO-LSTM的挖掘机液压系统压力软测量

Pressure Soft Measurement of Excavator Hydraulic System Based on Mutual Information and BO-LSTM

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

[1]	弓展, 康仁科, 杨峰, 董志刚, 李坤, 鲍岩. 微织构形貌对TC4黏接表面结合强度的影响[J]. 机械工程学报, 2025, 61(9): 78-88.
[2]	付昊宁, 关庆华, 王鹏, 温泽峰. 地铁弹性车轮对钢轨波磨段扣件弹条的减振作用[J]. 机械工程学报, 2025, 61(8): 240-249.
[3]	李存晰, 宋立明, 郭振东, 李军. 基于知识迁移的高效涡轮叶栅智能气动优化方法[J]. 机械工程学报, 2025, 61(4): 333-343.
[4]	汪汉明, 董庆兵, 陈壮, 赵波, 史修江. 行星轮系竞争失效的寿命预测及试验研究[J]. 机械工程学报, 2025, 61(3): 284-298.
[5]	周汶蓉, 熊世权, 杨秦秦, 叶驰川, 徐梦宇, 易茜, 冯毅雄, 易树平. 一种主观人因失效防范的核电建造协同质量智能见证方法[J]. 机械工程学报, 2025, 61(15): 324-338.
[6]	赵强强, 刘世伟, 姜冬磊, 余德文, 李明, 陈飞飞, 郭俊康, 王柏村, 张进华, 洪军. 基于人在回路的大型星载平面天线形面精度调控[J]. 机械工程学报, 2025, 61(15): 399-416.
[7]	郭晓强, 吕俊霖, 梁豪, 李潇, 胡宁, 柳军, 郭守金. 深海采矿水力提升管多场耦合多重非线性振动模型及疲劳失效机理研究[J]. 机械工程学报, 2025, 61(14): 321-335.
[8]	戴明华, 胡平, 盈亮, 陈帅, 王永青, 韩小强. 考虑损伤的热成形淬硬硼钢失效行为建模研究[J]. 机械工程学报, 2024, 60(6): 218-226.
[9]	王淞立, 方续东, 高博楠, 赵立波, 田边, 林启敬, 张仲恺, 饶浩, 李瑜, 蒋庄德. 硅微谐振压力传感器自动增益控制与相位补偿研究[J]. 机械工程学报, 2024, 60(4): 82-91.
[10]	赵家浩, 黄汉雄. 微乳突提高低力学刺激下微结构柔性压力传感器的性能[J]. 机械工程学报, 2024, 60(4): 222-229.
[11]	任亚平, 任莹, 郭洪飞, 张超勇. 工序随机失效及其修复条件下的退役机电产品拆解工艺路线决策研究[J]. 机械工程学报, 2024, 60(24): 365-376.
[12]	钱萍, 刘鑫雨, 陈文华, 王哲, 郭明达. 电连接器用聚氨酯胶密封件贮存可靠性建模[J]. 机械工程学报, 2024, 60(20): 361-371.
[13]	余海燕, 贺宏伟, 邢萍. 考虑不同刚度退化模式的碳纤维增强复合材料失效模型开发[J]. 机械工程学报, 2024, 60(2): 197-208.
[14]	付涛, 张天赐, 崔允浩, 宋学官. 深度学习增强的智能矿用电铲挖掘轨迹跟踪控制[J]. 机械工程学报, 2024, 60(16): 357-366.
[15]	王振亚, 刘韬, 伍星. 互信息规范的卷积神经网络及其在轴承故障特征提取中的应用[J]. 机械工程学报, 2024, 60(12): 137-146.