针对民机机械部件故障样本缺乏且类不平衡以及故障信号复杂多样导致的故障诊断精度低,识别不稳定的问题,提出基于增强元学习与通道注意力机制(learn to reweight with SE-1DleNet,LRS)的故障诊断方法。利用小样本平衡验证集指导了不平...针对民机机械部件故障样本缺乏且类不平衡以及故障信号复杂多样导致的故障诊断精度低,识别不稳定的问题,提出基于增强元学习与通道注意力机制(learn to reweight with SE-1DleNet,LRS)的故障诊断方法。利用小样本平衡验证集指导了不平衡训练集的损失权重更新以改善原始不均衡样本分布,提出元梯度增强的梯度裁剪策略;在1D-LeNet的基础上引入SE注意力机制对多维度故障特征通道自适应加权。结果表明:以民机大梁和机械轴承故障作为仿真试验数据集,与当前主流的故障诊断算法ProtoNet、DNCNN、GAN-CNN等相比,该方法诊断效果最优,在样本极端不平衡时准确率达95%以上,能够进行准确故障诊断。展开更多
To ensure the structural integrity of life-limiting component of aeroengines,Probabilistic Damage Tolerance(PDT)assessment is applied to evaluate the failure risk as required by airworthiness regulations and military ...To ensure the structural integrity of life-limiting component of aeroengines,Probabilistic Damage Tolerance(PDT)assessment is applied to evaluate the failure risk as required by airworthiness regulations and military standards.The PDT method holds the view that there exist defects such as machining scratches and service cracks in the tenon-groove structures of aeroengine disks.However,it is challenging to conduct PDT assessment due to the scarcity of effective Probability of Detection(POD)model and anomaly distribution model.Through a series of Nondestructive Testing(NDT)experiments,the POD model of real cracks in tenon-groove structures is constructed for the first time by employing the Transfer Function Method(TFM).A novel anomaly distribution model is derived through the utilization of the POD model,instead of using the infeasible field data accumulation method.Subsequently,a framework for calculating the Probability of Failure(POF)of the tenon-groove structures is established,and the aforementioned two models exert a significant influence on the results of POF.展开更多
Actuator faults can be critical in turbofan engines as they can lead to stall,surge,loss of thrust and failure of speed control.Thus,fault diagnosis of gas turbine actuators has attracted considerable attention,from b...Actuator faults can be critical in turbofan engines as they can lead to stall,surge,loss of thrust and failure of speed control.Thus,fault diagnosis of gas turbine actuators has attracted considerable attention,from both academia and industry.However,the extensive literature that exists on this topic does not address identifying the severity of actuator faults and focuses mainly on actuator fault detection and isolation.In addition,previous studies of actuator fault identification have not dealt with multiple concurrent faults in real time,especially when these are accompanied by sudden failures under dynamic conditions.This study develops component-level models for fault identification in four typical actuators used in high-bypass ratio turbofan engines under both dynamic and steady-state conditions and these are then integrated with the engine performance model developed by the authors.The research results reported here present a novel method of quantifying actuator faults using dynamic effect compensation.The maximum error for each actuator is less than0.06%and 0.07%,with average computational time of less than 0.0058 s and 0.0086 s for steady-state and transient cases,respectively.These results confirm that the proposed method can accurately and efficiently identify concurrent actuator fault for an engine operating under either transient or steady-state conditions,even in the case of a sudden malfunction.The research results emonstrate the potential benefit to emergency response capabilities by introducing this method of monitoring the health of aero engines.展开更多
文摘针对民机机械部件故障样本缺乏且类不平衡以及故障信号复杂多样导致的故障诊断精度低,识别不稳定的问题,提出基于增强元学习与通道注意力机制(learn to reweight with SE-1DleNet,LRS)的故障诊断方法。利用小样本平衡验证集指导了不平衡训练集的损失权重更新以改善原始不均衡样本分布,提出元梯度增强的梯度裁剪策略;在1D-LeNet的基础上引入SE注意力机制对多维度故障特征通道自适应加权。结果表明:以民机大梁和机械轴承故障作为仿真试验数据集,与当前主流的故障诊断算法ProtoNet、DNCNN、GAN-CNN等相比,该方法诊断效果最优,在样本极端不平衡时准确率达95%以上,能够进行准确故障诊断。
基金supported by the National Major Science and Technology Project,China(No.J2019-Ⅳ-0007-0075)the Fundamental Research Funds for the Central Universities,China(No.JKF-20240036)。
文摘To ensure the structural integrity of life-limiting component of aeroengines,Probabilistic Damage Tolerance(PDT)assessment is applied to evaluate the failure risk as required by airworthiness regulations and military standards.The PDT method holds the view that there exist defects such as machining scratches and service cracks in the tenon-groove structures of aeroengine disks.However,it is challenging to conduct PDT assessment due to the scarcity of effective Probability of Detection(POD)model and anomaly distribution model.Through a series of Nondestructive Testing(NDT)experiments,the POD model of real cracks in tenon-groove structures is constructed for the first time by employing the Transfer Function Method(TFM).A novel anomaly distribution model is derived through the utilization of the POD model,instead of using the infeasible field data accumulation method.Subsequently,a framework for calculating the Probability of Failure(POF)of the tenon-groove structures is established,and the aforementioned two models exert a significant influence on the results of POF.
基金support by the National Natural Science Foundation of China(Grant No.52402520)。
文摘Actuator faults can be critical in turbofan engines as they can lead to stall,surge,loss of thrust and failure of speed control.Thus,fault diagnosis of gas turbine actuators has attracted considerable attention,from both academia and industry.However,the extensive literature that exists on this topic does not address identifying the severity of actuator faults and focuses mainly on actuator fault detection and isolation.In addition,previous studies of actuator fault identification have not dealt with multiple concurrent faults in real time,especially when these are accompanied by sudden failures under dynamic conditions.This study develops component-level models for fault identification in four typical actuators used in high-bypass ratio turbofan engines under both dynamic and steady-state conditions and these are then integrated with the engine performance model developed by the authors.The research results reported here present a novel method of quantifying actuator faults using dynamic effect compensation.The maximum error for each actuator is less than0.06%and 0.07%,with average computational time of less than 0.0058 s and 0.0086 s for steady-state and transient cases,respectively.These results confirm that the proposed method can accurately and efficiently identify concurrent actuator fault for an engine operating under either transient or steady-state conditions,even in the case of a sudden malfunction.The research results emonstrate the potential benefit to emergency response capabilities by introducing this method of monitoring the health of aero engines.
