摘要
针对传统转子系统不平衡故障诊断存在的故障数据不足、仿真模型精确度不高等问题,提出基于最大不确定度改善加点(maximize uncertainty improvement infill,简称MUII)法和协同克里金(co-kriging,简称CK)法的不平衡故障定量诊断方法,记为MUII-CK。首先,利用仿真数据和实验数据分别构建低、高可信度克里金代理模型;其次,针对高可信度数据空间填充不足的区域进行估算加点,通过CK法实现实验数据与仿真模型融合的振动响应预测;最后,借助预测模型生成的大量故障样本构建参数辨识反问题模型,实现准确的不平衡故障定量诊断。结果表明:即使在实验数据不足和仿真模型存在较大偏差的情况下,所提方法仍能实现振动响应预测和故障参数辨识,并且在模型建成后能直接利用振动响应信号进行实时故障诊断,展现出良好的工程应用前景。
Regarding the problems of insufficient fault data and the difficult construction of accurate simulation modal for traditional rotor system imbalance fault diagnosis,a quantitative diagnosis method based on maximize uncertainty improvement infill and co-kriging(MUII-CK)is proposed.First,low-and high-fidelity kriging surrogate models are built using simulation data and experimental data.Second,points in the regions with low high-fidelity data density are estimated and added,the vibration response is predicted by fusing data and model with co-kriging.Finally,a parameter identification inverse problem model is built by many fault samples from the prediction model,thereby achieving accurate quantitative diagnosis of imbalance fault.The results show that the proposed method can effectively predict the vibration response and identify the fault parameters under the conditions of insufficient experimental data and large simulation model deviation,and can directly use the vibration response signal for real-time fault diagnosis after the model is built,showing broad engineering application prospects.
作者
徐忠霆
柳祯
陈志昊
薛志钢
胡越
包文杰
李富才
XU Zhongting;LIU Zhen;CHEN Zhihao;XUE Zhigang;HU Yue;BAO Wenjie;LI Fucai(State Key Laboratory of Mechanical System and Vibration,Shanghai Jiao Tong University Shanghai,200240,China;Special Equipment Safety Supervision Inspection Institute of Jiangsu Province Nanjing,210036,China;School of Mechanical and Power Engineering,East China University of Science and Technology Shanghai,200237,China)
出处
《振动.测试与诊断》
北大核心
2025年第6期1188-1194,1277,共8页
Journal of Vibration,Measurement & Diagnosis
基金
国家自然科学基金资助项目(52175104)
军科委基础加强计划重点基础研究资助项目(2019-JCJQ-ZD-133-00)
江苏省特种设备安全监督检验研究院科研资助项目(2021MK044)。
