| 15 | 0 | 30 |
| 下载次数 | 被引频次 | 阅读次数 |
爬模式组塔平台是一种稳定且操作简便的组塔技术，其通过液压系统驱动实现平台的往复顶升，为高空作业和物料起吊提供安全支撑。针对液压系统机理复杂、难以建立精确模型及传统方法诊断效率低的问题，本文在AMESim软件中建立了液压系统仿真模型，通过故障注入获得多种典型故障数据。随后，构建基于双向长短期记忆网络（Bi-directional Long Short-Term Memory,BiLSTM）的端到端故障诊断模型，直接以压力、流量和位移等多通道信号为输入，自动提取时序特征并进行分类，实现了无需人工特征设计的智能诊断。实验结果表明，该方法在仿真数据集上的故障识别准确率达到98.5%，验证了其在液压系统故障识别中的有效性与鲁棒性，为组塔设备的安全运行与智能维护提供了新思路和技术支撑。
Abstract：The technique of climbing-mode tower erection platform is stable and user-friendly. It is driven by a hydraulic system to perform reciprocating lifting of the platform, ensuring safety during elevated work and material hoisting. To address the challenges of complex hydraulic system mechanisms, difficulty in establishing precise models, and low diagnostic efficiency of traditional methods, a hydraulic system simulation model is established in AMESim, and Multiple typical fault datasets are obtained through fault injection. Subsequently, an end-to-end fault diagnosis model based on a bidirectional long short-term memory network(BiLSTM) is constructed. This model directly takes multi-channel signals, such as pressure, flow rate, and displacement, as inputs, automatically extracts temporal features, and performs classification, enabling intelligent diagnosis without manual feature design. Experimental results demonstrate that the proposed method achieves a fault recognition accuracy of 98.5% on the simulation dataset, which validates its effectiveness and robustness in hydraulic system fault identification. This approach provides new insights and technical support for the safe operation and intelligent maintenance of tower erection equipment.
[1]杜名喆，王宝中．基于经验小波分解和卷积神经网络的液压泵故障诊断[J]．液压与气动，2020(1):163-170.
[2]WANG ZHENYA,CHENLU,JIAN MA,et al. Novel method for performance degradation assessment and prediction of hydraulic servo system[J]. Scientia Iranica,2015,22(4):1604-1615.
[3]WANG HAICHENG,ZHOU JUAN,CHEN HU,et al. Hydraulic system fault diagnosis decoupling method based on 2D time-series modeling and self-attention fusion[J]. Scientific Reports,2024,14(1),15620.
[4]姜万录，杨旭康，赵永会，等.轻量化卷积神经网络在调门油动机故障诊断中的应用[J].液压与气动，2025,49(2):58-68.
[5]MA ZHONGHAI,WANGSHAOPING,SHI JIAN,et al. Fault diagnosis of an intelligent hydraulic pump based on a nonlinear unknown input observer[J]. Chinese Journal of Aeronautics,2018,31(2):385-394.
[6]ZHU YONG , WU QINGYI , TANG SHENGNAN , et al.Intelligent fault diagnosis methods for hydraulic piston pumps:a review[J]. Journal of Marine Science and Engineering,2023,11(8):1609.
[7]DAI JUYING , TANG JIAN , HUANG SHUZHAN , et al.Signal-based intelligent hydraulic fault diagnosis methods:Review and prospects[J]. Chinese Journal of Mechanical Engineering,2019,32(1):75-92.
[8]杨民强.盾构机液压系统研究进展综述[J].液压与气动，2022,46(10):170-181.
[9]WANG LIHUA,WU XIAOQIANG,ZHANG CHUNYOU,et al.Hydraulic system fault diagnosis method based on a multi-feature fusion support vector machine[J]. The Journal of Engineering,2019,2019(13):215-218.
[10]JIN YAO,SHAN CHANGZHENG,WU YAN,et al. Fault Diagnosis of Hydraulic Seal Wear and Internal Leakage Using Wavelets and Wavelet Neural Network[J]. IEEE Transactions on Instrumentation and Measurement,2019,68(4):1026-1034.
[11]GUO PENGFEI, WU JUN, XU XUEBING ,et al. Health condition monitoring of hydraulic system based on ensemble support vector machine[C]. Qingdao:2019 Prognostics and System Health Management Conference(PHM-Qingdao),2019.
[12]JEGADEESHWARAN R,SUGUMARAN V. Fault diagnosis of automobile hydraulic brake system using statistical features and support vector machines[J]. Mechanical Systems and Signal Processing,2015(52-53):436-446.
[13]SHERSTINSKY A. Fundamentals of recurrent neural network(RNN)and long short-term memory(LSTM)network[J]. Physica D:Nonlinear Phenomena,2020(404):132306.
[14]ZHANG SHU, ZHENG DEQUAN, HU XINCHEN,et al.Bidirectional long short-term memory networks for relation classification[C]. Shanghai:Proceedings of the 29th Pacific Asia conference on language,information and computation,2015.
[15]梁全，苏齐莹.液压系统AMESim计算机仿真指南[M].北京：机械工业出版社，2014.
基本信息:
中图分类号:TP18;TM75;TH137
引用信息:
[1]李刚,景文川,蓝健均,等.基于深度学习的爬模式组塔液压机构故障诊断研究[J].机械,2026,53(04):75-80.
基金信息:
国网四川省电力公司科技项目（SGSC0000KXJS2310211）
2026-04-15
2026-04-15