Aero engines are key power components that provide thrust for the aircraft.The cerme turbine disc allows the new-generation domestic fighter aircraft to increase the overall thrust of the aero engine.Quantifying coati...Aero engines are key power components that provide thrust for the aircraft.The cerme turbine disc allows the new-generation domestic fighter aircraft to increase the overall thrust of the aero engine.Quantifying coatings and analyzing the stress on the teeth play critical roles in improving the turbine disc’s performance,which are two issues must be solved urgently.First,this work pro poses a quantitative analysis algorithm to conduct the Three-Dimensional(3D)distribution informa tion mining of the extracted coatings.Then,it proposes an Industrial Computed Laminography(ICL)reconstruction algorithm for non-destructively reconstructing the turbine disc’s high-quality3D morphological actual feature.Finally,a Finite Element Analysis(FEA)under the ultimate thrus is conducted on ICL reconstruction to verify the working status of the new-generation aero-engine turbine disc.The results show that the proposed quantitative analysis algorithm digitizes the aggre gated conditions of the coating with a statistically normalized Z_(1)value of–2.15 and a confidence leve higher than 95%.Three image-quality quantitative indicators:Peak Signal-to-Noise Ratio(PSNR)Structural Similarity Index Measure(SSIM),and Normalized Mean Square Distance(NMSD)of the proposed ICL reconstruction algorithm on turbine disc laminographic image are 26.45,0.88,and 0.73respectively,which are better than other algorithms.The mechanical analysis of ICL more realisti cally reflects the stress and deformation than that of 3D modeling.This work provides new ideas for the iterative research of new-generation aero-engine turbine discs.展开更多
针对高转速、高温升、大载荷等持续复杂的工况波动引起的航空发动机高速轴承故障诊断问题,提出了一种新型的深度图迁移学习算法,以及波动工况下基于图迁移卷积网络(graph transfer convolutional networks,简称GTCNs)的航空发动机高速...针对高转速、高温升、大载荷等持续复杂的工况波动引起的航空发动机高速轴承故障诊断问题,提出了一种新型的深度图迁移学习算法,以及波动工况下基于图迁移卷积网络(graph transfer convolutional networks,简称GTCNs)的航空发动机高速轴承故障智能诊断方法。首先,利用阶比分析对波动工况下航空发动机高速轴承振动信号进行重采样,将其转化为阶次谱信号作为目标域与源域数据集;其次,采用训练好的一维图卷积网络(onedimensional graph convolutional networks,简称1dGCNs)作为特征提取器,对其高层敏感特征计算其动态多核-最大均值散度(dynamic multiple kernel-maximum mean discrepancy,简称DMKMMD)距离,同时匹配高层与低层特征的边缘分布差异;然后,将对齐后的特征输入到分类器softmax中进行智能故障诊断;最后,在航空发动机高速轴承故障数据上验证了所提方法的有效性与先进性。结果表明,该方法具有更高的诊断准确率与鲁棒性,可以消除大波动工况下健康状态样本分布的差异性,提高诊断可迁移性。展开更多
基金supported by the National Natural Science Foundation of China(No.51975026)。
文摘Aero engines are key power components that provide thrust for the aircraft.The cerme turbine disc allows the new-generation domestic fighter aircraft to increase the overall thrust of the aero engine.Quantifying coatings and analyzing the stress on the teeth play critical roles in improving the turbine disc’s performance,which are two issues must be solved urgently.First,this work pro poses a quantitative analysis algorithm to conduct the Three-Dimensional(3D)distribution informa tion mining of the extracted coatings.Then,it proposes an Industrial Computed Laminography(ICL)reconstruction algorithm for non-destructively reconstructing the turbine disc’s high-quality3D morphological actual feature.Finally,a Finite Element Analysis(FEA)under the ultimate thrus is conducted on ICL reconstruction to verify the working status of the new-generation aero-engine turbine disc.The results show that the proposed quantitative analysis algorithm digitizes the aggre gated conditions of the coating with a statistically normalized Z_(1)value of–2.15 and a confidence leve higher than 95%.Three image-quality quantitative indicators:Peak Signal-to-Noise Ratio(PSNR)Structural Similarity Index Measure(SSIM),and Normalized Mean Square Distance(NMSD)of the proposed ICL reconstruction algorithm on turbine disc laminographic image are 26.45,0.88,and 0.73respectively,which are better than other algorithms.The mechanical analysis of ICL more realisti cally reflects the stress and deformation than that of 3D modeling.This work provides new ideas for the iterative research of new-generation aero-engine turbine discs.
