A Fault Diagnosis Method for Piston Pump Under Variable Speed Conditions Using Parameterized Demodulation

doi:10.7652/xjtuxb202110003

您当前的位置：

首页 >

文章列表页 >

A Fault Diagnosis Method for Piston Pump Under Variable Speed Conditions Using Parameterized Demodulation

更新时间：2025-07-09

- A Fault Diagnosis Method for Piston Pump Under Variable Speed Conditions Using Parameterized Demodulation
- Vol. 55, Issue 10, Pages: 19-29(2021)
- 作者机构：
  
  上海交通大学机械与动力工程学院,上海,200240
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb202110003
  CLC： TH165.3;TH322
- Online First：10 October 2021，
  
  Published：2021
- 稿件说明：
移动端阅览
A Fault Diagnosis Method for Piston Pump Under Variable Speed Conditions Using Parameterized Demodulation[J]. 2021, 55(10): 19-29.
DOI：

A Fault Diagnosis Method for Piston Pump Under Variable Speed Conditions Using Parameterized Demodulation[J]. 2021, 55(10): 19-29. DOI： 10.7652/xjtuxb202110003.

摘要

针对柱塞泵在变转速工况下运行时

存在因时变信号特征提取不易和噪声抑制困难导致的故障诊断准确度低的问题

提出一种以参数化解调为基础的柱塞泵空化故障诊断方法。首先

采用粒子群算法对泵出口时变压力信号重点分量的相位参数进行估计

再根据估计得的参数将信号解调至平稳化并滤波

接着对滤波后的信号进行反解调来获取单一信号分量; 然后迭代执行参数化解调的上述步骤以提取所有重点分量并实现信号重构; 最后对重构信号进行切片来构建数据集

再将数据集输入一维卷积-长短期记忆神经网络(1DCNN-LSTM)中提取局域特征并学习长期时序信息

从而实现准确地识别柱塞泵空化等级。流体仿真实验验证了参数化解调在信号分量提取上的有效性。使用实测信号进行空化故障诊断实验

结果表明:相比未经参数化解调的诊断方法

该方法的空化等级识别准确率提高了6.5%

达到95.4%

且具有更好的泛化性能; 在信噪比为0 dB的强噪声环境下

准确率维持在90%以上。

Abstract

In order to solve the problem of low fault diagnosis accuracy of piston pump under variable speed conditions

caused by the difficulty of time-varying signal features extraction and noise suppression

a piston pump cavitation detection method based on parameterized demodulation is proposed. Firstly

a particle swarm optimization algorithm is used to estimate the phase parameters of the key component of the pump outlet time-varying pressure signal

and the signal is demodulated to be stabilized and filtered according to the estimated parameters. Then the filtered signal is recovered to obtain a single signal component. The above steps of parameterized demodulation are iteratively performed to extract all key components and realize signal reconstruction. Finally

the reconstructed signal is sliced to construct the dataset

which is then fed into one dimensional convolutional long short term memory neural network(1DCNN-LSTM)to extract local features and learn long-term time series information

so as to realize the accurate identification of the piston pump cavitation degrees. The fluid simulation signals validate the effectiveness of the parameterized demodulation in extracting signal components. Real signals are used to conduct cavitation fault diagnosis experiments. The results show that

compared with the diagnostic method without the parameterized demodulation

the identification accuracy increases by 6.5%

and achieves to 95.4%

and the proposed model has better generalization performance. In the strong noise environment with SNR of 0 dB

the accuracy rate of diagnosis is maintained above 90%.

关键词

Keywords

references

李琳, 陶建峰, 黄亦翔, 等. 基于BP神经网络的液压缸内泄漏诊断 [J]. 液压与气动, 2017(7): 11-15.

LI Lin, TAO Jianfeng, HUANG Yixiang, et al. Internal leakage detection of hydraulic cylinder based on BP neural network [J]. Chinese Hydraulics & Pneumatics, 2017(7): 11-15.

习仁国, 刘卫国, 陈焕明. 电静液作动器的建模仿真与试验研究 [J]. 机床与液压, 2013, 41(19): 40-44.

XI Renguo, LIU Weiguo, CHEN Huanming. Modeling simulation and experimental research on electro-hydrostatic actuator(EHA)[J]. Machine Tool Hydraulics, 2013, 41(19): 40-44.

潮群. EHA轴向柱塞泵高速化若干关键技术研究 [D]. 杭州: 浙江大学, 2019: 24-25.

王海燕. 轴向柱塞泵气蚀机理及仿真研究 [D]. 太原: 中北大学, 2014: 2-15.

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): 1-22.

SIANO D, PANZA M A. Diagnostic method by using vibration analysis for pump fault detection [J]. Energy Procedia, 2018, 148: 10-17.

PANDA A K, RAPUR J S, TIWARI R. Prediction of flow blockages and impending cavitation in centrifugal pumps using support vector machine(SVM)algorithms based on vibration measurements [J]. Measurement, 2018, 130: 44-56.

XIAO D Y, HUANG Y X, WANG H R, et al. Health assessment for piston pump using LSTM neural network [C]∥2018 International Conference on Sensing, Diagnostics, Prognostics, and Control. Piscataway, NJ, USA: IEEE, 2018: 131-137.

CHAO Qun, TAO Jianfeng, WEI Xiaoliang, et al. Identification of cavitation intensity for high-speed aviation hydraulic pumps using 2D convolutional neural networks with an input of {RGB}-based vibration data [J]. Measurement Science and Technology, 2020, 31(10): 105102.

GUO Yu, LIU Tingwei, NA Jing, et al. Envelope order tracking for fault detection in rolling element bearings [J]. Journal of Sound and Vibration, 2012, 331(25): 5644-5654.

ZHAO Dezun, LI Jianyong, CHENG Weidong, et al. Compound faults detection of rolling element bearing based on the generalized demodulation algorithm under time-varying rotational speed [J]. Journal of Sound and Vibration, 2016, 378: 109-123.

LU Siliang, YAN Ruqiang, LIU Yongbin, et al. Tacholess speed estimation in order tracking: A review with application to rotating machine fault diagnosis [J]. IEEE Transactions on Instrumentation and Measurement, 2019, 68(7): 2315-2332.

WANG Tianyang, LIANG Ming, LI Jianyong, et al. Rolling element bearing fault diagnosis via fault characteristic order(FCO)analysis [J]. Mechanical Systems and Signal Processing, 2014, 45(1): 139-153.

OLHEDE S, WALDEN A T. A generalized demodulation approach to time-frequency projections for multicomponent signals [EB/OL].(2005-06-10)[2021-03-20]. https:∥core.ac.uk/download/pdf/295591.pdf.

MA Zengqiang, LU Feiyu, LIU Suyan, et al. An adaptive generalized demodulation method for multimedia spectrum analysis is applied in rolling bearing fault diagnosis [J]. IEEE Access, 2020, 8: 20687-20699.

FENG Zhipeng, CHEN Xiaowang, LIANG Ming, et al. Time-frequency demodulation analysis based on iterative generalized demodulation for fault diagnosis of planetary gearbox under nonstationary conditions [J]. Mechanical Systems and Signal Processing, 2015, 62/63: 54-74.

王晓华, 彭程, 梁静. STFT时频分析算法研究及其在列车振动分析中的应用 [J]. 噪声与振动控制, 2011, 31(1): 65-68.

WANG Xiaohua, PENG Cheng, LIANG Jing. Research of STFT time-frequency analysis algorithm and its application in train vibration analysis [J]. Noise and Vibration Control, 2011, 31(1): 65-68.

YANG Yang, DONG Xingjian, PENG Zhike, et al. Component extraction for non-stationary multi-component signal using parameterized de-chirping and band-pass filter [J]. IEEE Signal Processing Letters, 2015, 22(9): 1373-1377.

杨扬. 参数化时频分析理论、方法及其在工程信号分析中的应用 [D]. 上海: 上海交通大学, 2013: 43.

KIRANYAZ S, AVCI O, ABDELJABER O, et al. 1D convolutional neural networks and applications: A survey [J]. Mechanical Systems and Signal Processing, 2021, 151: 107398.

CHEN Xiaohan, ZHANG Beike, GAO Dong. Bearing fault diagnosis base on multi-scale CNN and LSTM model [J]. Journal of Intelligent Manufacturing, 2021, 32(4): 971-987.

KINGMA D, BA J. Adam: a method for stochastic optimization[EB/OL].(2014-12-22)[2021-03-20]. https: ∥arxiv.org/abs/1412.6980.

SINGHAL A K, ATHAVALE M M, LI Huiying, et al. Mathematical basis and validation of the full cavitation model [J]. Journal of Fluids Engineering, 2002, 124(3): 617-624.

Parametric Technology Corporation. Creo parametric 7 online help[EB/OL].(2020-05-11)[2021-03-20]. https:∥support.ptc.com/help/creo/creo_pma/r7.0/usascii/#page/simulate/cfd/Cavitation/CavitationModel s.html.

KUNKIS M, WEBER J. Experimental and numerical assessment of an axial piston pump's speed limit [C]∥BATH/ASME 2016 Symposium on Fluid Power and Motion Control. Norcross, GA, USA: American Society of Mechanical Engineers, 2016: 201650031123 43.

CHAO Qun, TAO Jianfeng, WEI Xiaoliang, et al. Cavitation intensity recognition for high-speed axial piston pumps using 1-D convolutional neural networks with multi-channel inputs of vibration signals [J]. Alexandria Engineering Journal, 2020, 59(6): 4463-4473.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Application of Mayfly Algorithm Optimized Dual-Channel Network in Gearbox Fault Diagnosis

A Deep Learning Fault Diagnosis Model with Strong Anti-Noise Ability

Improved CNN-Based Fault Diagnosis Method for Rolling Bearings under Variable Working Conditions

Application of One-Dimensional Convolutional Neural Network in Fault Diagnosis of Reciprocating Compressor Air Valve

Construction and Application of Multi-Agent Large Language Model for Power Transformer Fault Diagnosis

Related Author

YU Ning

WEI Chenqian

TIAN Liyong

ZHAO Jianjun

YU Xiaohan

吴春志

吴守军

冯辅周

Related Institution

College of Mechanical Engineering, Liaoning Technical University

Department of Vehicle Engineering, Academy of Army Armored Forces

College of Electrical Engineering and Information Engineering, Lanzhou University of Technology

Key Laboratory of Gansu Advanced Control for Industrial Processes, Lanzhou University of Technology

National Experimental Teaching Center of Electrical and Control Engineering, Lanzhou University of Technology

⁰