泛研网

公众版 查看说明
全球科研项目数据库2026版

大型旋转机械稳定运行机理及智能诊断研究

项目来源

国家自然科学基金(NSFC)

项目主持人

闻邦椿

项目受资助机构

东北大学

项目编号

U1708257

立项年度

2017

立项时间

未公开

研究期限

未知 / 未知

项目级别

国家级

受资助金额

250.00万元

学科

工程与材料科学-机械设计与制造-机械动力学

学科代码

E-E05-E0503

基金类别

联合基金项目-重点支持项目-NSFC-辽宁联合基金

关键词

运行稳定性 ; 转子系统 ; 故障诊断 ; 运行失稳 ; 非线性动力学 ; operation stability ; rotor system ; losting operation stability ; nonlinear dyanmics ; fault diagnosis

参与者

马辉；杨树华；冯坤；王平；孟继纲；姚红良；张学良；周世华；孙赵宁

参与机构

沈阳透平机械股份有限公司；北京化工大学

项目标书摘要：目前国产大型旋转机械存在运行稳定性差、智能诊断技术不足等问题，导致该类装备出现一些“该停车时不停，不该停车时停车”的现象，因此项目提出进行大型旋转机械运行稳定性和智能故障诊断的研究。.项目拟以大型离心压缩机机组为研究对象，结合非线性动力学理论和转子动力学理论，研究大型旋转机械多机组转子系统同步运行稳定性机理，以及典型故障和耦合故障下的失稳规律；结合模糊数学理论和系统评价理论，研究该类装备运行失稳的预测方法，以及提高同步运行稳定性的抑制方法问题；结合现代数字信号处理和模式识别方法，研究大型旋转机械失稳早期征兆辨识，以及失稳故障的准确智能诊断方法；结合专家系统理论，建立该类装备监控、预测、诊断、决策一体化软件框架，并编制出软件。.项目的成功，预计将减少大型旋转机械的停机次数，及时准确诊断出其早期故障，提高其运行稳定性，从而可以提升企业产品的竞争力和创新能力，为东北老工业基地的振兴做出贡献。

Application Abstract: The domestic large-scale rotating machinery has the problem of“can’t stop when must to stop,stop when not necessary to stop”sometime due to insufficient in intelligent fault diagnosis.To solve this problem,the project is proposed to study the operation stability mechanism and the intelligent fault diagnosis of the large-scale rotating machinery..The project will take the large-scale compressor sets as research objects.The multi-unit rotor system synchronization on operation stability and the principles of the stability losing under typical faults or multi-faults of the multi-unit rotor system will be studied based on nonlinear dynamics and rotor dynamics.The forecasting method of the multi-unit rotor operation stability of the large scale rotating machinery will also be studied based on fuzzy logic theory and system evaluation theory.The early signs identification and diagnosis method of the stability losing method and the precise intelligent diagnosis of early fault for the large-scale rotating machinery will be studied based on advanced digital signal processing methods and pattern recognition method.The software and framework of the platform which combining monitor,forecasting,diagnosis and decision-making together will be built by combining expert system theory..The success of the project can reduce the shutting down of the large-scale rotating machinery,precisely and intelligently diagnosis the rapidly processing faults,improve the operation stability and finally promote the technical innovations of enterprises and awaken the old northeast industrial base.

项目受资助省

辽宁省

项目结题报告(全文)

针对目前国产大型旋转机械存在运行稳定性差、智能诊断技术不足等问题，导致该类装备出现一些“该停车时不停，不该停车时停车”的现象，进行大型旋转机械运行稳定性和智能故障诊断的研究。项目的主要研究内容和结果如下：第一、结合非线性动力学理论和转子动力学理论，研究了以旋转件松动故障为代表的结构场失稳机理；以转静件摩擦故障为代表的结构场和热场耦合失稳机理；以气流激振故障为代表的流体场失稳机理，掌握了大型旋转机械多机组转子系统失稳机理。第二、建立了转子系统振动特征—运行稳定性的映射关系，实现单机组和多机组的稳定裕度描述。提出了基于改进AHP确定主观权重法和神经网络算法的多机组稳定性裕度评价体系，并研究了基于线性和非线性吸振器的转子系统稳定性在线提高方法。第三、针对大型旋转机械早期故障发展迅速，导致机组稳定裕度迅速下降的问题，研究微故障的智能诊断技术，提出了基于样本密度自适应的早期失稳故障信号采集方法、早期失稳故障微弱信号特征提取方法、基于案例数据学习早期失稳故障智能诊断方法、变工况条件早期失稳故障报警阈值自学习方法等。第四、编制了大型旋转机械运行稳定性分析软件、早期故障诊断软件等，提出了该类装备监控、诊断、评估决策一体化软件框架。将成果在实际工程的诊断和决策中加以应用，解决了工程实际问题。项目的成果对于掌握大型旋转机械的运行稳定性机理，减少大型旋转机械停机次数具有重要意义。项目成果已经应用于国产大型旋转机械的故障诊断和运行维护，及时准确诊断出了早期故障，提高其运行稳定性，减少了“该停车时不停，不该停车时停车”现象。项目的成果可以提升企业产品的竞争力和创新能力，为东北老工业基地的振兴做出贡献。

  • 排序方式：
  • 1
  • /

  • 1.热环境下纤维增强复合圆柱壳非线性振动模型

    • 关键词：
    • 非线性振动;纤维增强复合材料;圆柱壳;材料和几何非线性;热环境
    • 李晖;吕海宇;罗忠;孙伟;韩清凯;秦朝烨;闻邦椿
    • 《第十八届全国非线性振动暨第十五届全国非线性动力学和运动稳定性学术会议（NVND2021）》
    • 中国广东广州
    • 会议

    本文提出了热环境下纤维增强复合圆柱壳的非线性振动分析模型,该模型能够预测不同激励幅值和环境温度下结构的固有频率、阻尼比和振动响应。首先,基于Jones-Nelson材料非线性理论和复模量法,结合多项式拟合技术,给出了考虑振幅和温度依赖性的纤维增强复合材料的非线性杨氏模量、剪切模量和损耗因子的显示表达式。在此基础上,结合Love壳体理论、能量法和von-Karman非线性应变-位移关系,推导了热环境下结构系统的振动微分方程,还详细介绍了非线性杨氏模量、剪切模量和损耗因子拟合系数的确定方法。最后,基于自行搭建的热振实验平台,对CF120碳纤维/环氧复合材料圆柱壳试件开展了测试,验证了所提出的理论模型和分析结果的正确性,并对该类型结构的非线性振动现象进行了实验评估。测试结果表明,随着激励幅值的增大,复合材料壳试件的前3阶固有频率呈现先减后增的趋势,且当环境温度从20℃上升到200℃时,这种变化趋势变得更加显著,固有频率的最大变化程度为8.2%。另外,随着激励幅值和温度的增大,结构的阻尼性能和共振响应都呈现不断增大的趋势。但相对于激励幅值的增大,环境温度的升高对阻尼特性的影响更为显著,结构阻尼的最大变化程度可达到300.5%。

    ...

  • 2.Dynamic gas turbine condition monitoring scheme with multi-part neural network

    • 关键词：
    • Deterioration;Learning systems;Condition monitoring;Gases;Failure (mechanical);Health management systems;Industrial processs;Integrated networks;Machine learning methods;Performance parameters;Physical mechanism;Sensing performance;Traditional approaches
    • Li, Zhouzheng;Feng, Kun;Yan, Binbin
    • 《ASME Turbo Expo 2020: Turbomachinery Technical Conference and Exposition, GT 2020》
    • 2020年
    • September 21, 2020 - September 25, 2020
    • Virtual, Online
    • 会议

    Gas turbines are high value industrial assets with significant roles in various kinds of industrial processes, health management systems are therefore important for helping maintaining gas turbines' stability in long-term operations. With more and more performance data able to be collected by sensors and the new machine learning methods developed, researchers are able to build more powerful digital models to monitor the gas turbine. This paper introduces a performance parameters alarm scheme for gas turbine using an adaptive state following model. The proposed scheme consist of 3 parts: Part 1, a dynamically adaptive multi-part neural network trained using performance data that can simulate different parts of gas turbine and output "normal" sensor data to make comparison with the actual data collected; Part 2, a group of thresholds set according to system noise that flags sudden failures by sensing performance parameter outliers, this also decides which data should be used to update the neural network; Part3, a recorder for "reference point" outputs that can reflect change of the gas turbine's status and detect long-term degradation. Unlike traditional approaches, the proposed adaptive states following model separates long term degradation and short term sudden failure, therefore both faults can be detected more accurately. The core of the proposed method is that physical properties are embedded into the neural network as constraints to regulate training and make the model more interpretable. In our scheme, a gas turbine is divided into 4 parts referencing the equipment's physical mechanism, they are simulated digitally by 4 sub corresponding networks, which are then combined into the proposed integrated network. The proposed scheme achieves an overall pleasing result and shows potential in gas turbine fault analysis. Copyright © 2020 ASME

    ...
  • 排序方式：
  • 1
  • /