在航空发动机可视化协同维修中,利用声音提示技术,通过改进的梅尔频率倒谱系数(Mel Frequency Cepstral Coefficients,MFCC)与头相关传递函数(Head-Related Transfer Function,HRTF)构建“频域-空间”双重映射模型,实现故障声纹特征的...在航空发动机可视化协同维修中,利用声音提示技术,通过改进的梅尔频率倒谱系数(Mel Frequency Cepstral Coefficients,MFCC)与头相关传递函数(Head-Related Transfer Function,HRTF)构建“频域-空间”双重映射模型,实现故障声纹特征的精准提取与三维声场定位。结合增强现实界面,设计多故障优先级动态调控机制,优化声学信息传递链。实验结果表明,将声音提示技术应用于航空发动机可视化协同维修,故障维修响应时间缩短至1.3 s以内,故障定位误差控制在±1.0 mm和±1.0°,同时显著减少了协同误判频次,提升了航空发动机维修的实时性与准确性。展开更多
Anti-aliasing spectrum analysis is essential for rotor blade condition monitoring based on Blade Tip Timing(BTT).The Multiple Signal Classification(MUSIC)algorithm,which exploits the orthogonality between signal and n...Anti-aliasing spectrum analysis is essential for rotor blade condition monitoring based on Blade Tip Timing(BTT).The Multiple Signal Classification(MUSIC)algorithm,which exploits the orthogonality between signal and noise subspaces,has been successfully applied for this purpose.However,conventional subspace selection methods relying on fixed thresholds are sensitive to variations in large eigenvalues.Furthermore,the complex disturbances during rotor operation and measurement complicate the identification of blade vibration characteristics.To overcome these challenges,this paper proposes Adaptive Subspace Separation(ASS)and Local Spectral Centroid(LSC)methods to improve the adaptability of subspace selection and the stability of frequency identification,respectively.The impacts of overestimating and underestimating the subspace dimensions on MUSIC's performance are derived mathematically.Simulation and experiments demonstrate the effectiveness of proposed approaches:ASS offers more accurate and stable subspace dimension selection and tracking,while LSC reduces the standard deviation of estimated frequencies by 30 percent.展开更多
The machining precision of blades is critical to the service performance of aero engines.The Leading Edge(LE) of high-pressure compressor blades poses a challenge for precision machining due to its thin size, high deg...The machining precision of blades is critical to the service performance of aero engines.The Leading Edge(LE) of high-pressure compressor blades poses a challenge for precision machining due to its thin size, high degree of bending, and significant change of curvature. Aimed at optimizing the machining error, this paper presents a framework that integrates toolpath planning and process parameter regulation. Firstly, an Iterative Subdivision Algorithm(ISA) for clamped Bspline curve is proposed, based on which toolpath planning method towards the LE is developed.Secondly, the removal effect of Cutter Contact(CC) point on the sampling points is investigated in the calculation of grinding dwell time by traversing in u-v space. A global material removal model is constructed for the solution. Thirdly, the previous two steps are interconnected based on the Improved Whale Optimization Algorithm(IWOA), and the optimal parameter combination is searched using the Root Mean Square Error(RMSE) of the machining error as the objective function. Based on this, the off-line programming and robotic grinding experiments are carried out. The experimental results show that the proposed method with error optimization can achieve 0.0143 mm mean value and 0.0160 mm standard deviations of LE surface error, which is an improvement of32.5% and 33.9%, respectively, compared with previous method.展开更多
Blade Tip Timing(BTT)enables non-contact measurements of rotating blades by placing probes strategically.Due to the uneven probe layout,BTT signals exhibit periodic irregularities.While recovering parameters like freq...Blade Tip Timing(BTT)enables non-contact measurements of rotating blades by placing probes strategically.Due to the uneven probe layout,BTT signals exhibit periodic irregularities.While recovering parameters like frequency from such signals is possible,achieving high-precision vibration parameters remains challenging.This paper proposed a novel two-stage off-grid estimation method.It leverages a unique array layout(coprime array)to obtain a regular augmented covariance matrix.Subsequently,parameters in the matrix are recovered using the sparse iterative covariance-based estimation method based on covariance fitting criteria.Finally,high-precision estimates of imprecise parameters are obtained using unconditional maximum likelihood estimation,effectively eliminating the effects of basis mismatch.Through substantial numerical and experimental validation,the proposed method demonstrates significantly higher accuracy compared to classical BTT parameter estimation methods,approaching the lower bound of unbiased estimation variance.Furthermore,due to its immunity to frequency gridding,it can track minor frequency deviations,making it more suitable for indicating blade condition.展开更多
The original monitoring data from aero-engines possess characteristics such as high dimen-sionality,strong noise,and imbalance,which present substantial challenges to traditional anomalydetection methods.In response,t...The original monitoring data from aero-engines possess characteristics such as high dimen-sionality,strong noise,and imbalance,which present substantial challenges to traditional anomalydetection methods.In response,this paper proposes a method based on Fuzzy Fusion of variablesand Discriminant mapping of features for Clustering(FFD-Clustering)to detect anomalies in originalmonitoring data from Aircraft Communication Addressing and Reporting System(ACARS).Firstly,associated variables are fuzzily grouped to extract the underlying distribution characteristics and trendsfrom the data.Secondly,a multi-layer contrastive denoising-based feature Fusion Encoding Network(FEN)is designed for each variable group,which can construct representative features for each variablegroup through eliminating strong noise and complex interrelations between variables.Thirdly,a featureDiscriminative Mapping Network(DMN)based on reconstruction difference re-clustering is designed,which can distinguish dissimilar feature vectors when mapping representative features to a unified fea-ture space.Finally,the K-means clustering is used to detect the abnormal feature vectors in the unifiedfeature space.Additionally,the algorithm is capable of reconstructing identified abnormal vectors,thereby locating the abnormal variable groups.The performance of this algorithm was tested ontwo public datasets and real original monitoring data from four aero-engines'ACARS,demonstratingits superiority and application potential in aero-engine anomaly detection.展开更多
Predictive maintenance often involves imbalanced multivariate time series datasets with scarce failure events,posing challenges for model training due to the high dimensionality of the data and the need for domain-spe...Predictive maintenance often involves imbalanced multivariate time series datasets with scarce failure events,posing challenges for model training due to the high dimensionality of the data and the need for domain-specific preprocessing,which frequently leads to the development of large and complex models.Inspired by the success of Large Language Models(LLMs),transformer-based foundation models have been developed for time series(TSFM).These models have been proven to reconstruct time series in a zero-shot manner,being able to capture different patterns that effectively characterize time series.This paper proposes the use of TSFM to generate embeddings of the input data space,making them more interpretable for machine learning models.To evaluate the effectiveness of our approach,we trained three classical machine learning algorithms and one neural network using the embeddings generated by the TSFM called Moment for predicting the remaining useful life of aircraft engines.We test the models trained with both the full training dataset and only 10%of the training samples.Our results show that training simple models,such as support vector regressors or neural networks,with embeddings generated by Moment not only accelerates the training process but also enhances performance in few-shot learning scenarios,where data is scarce.This suggests a promising alternative to complex deep learning architectures,particularly in industrial contexts with limited labeled data.展开更多
Partial Differential Equations(PDEs)are model candidates of soft sensing for aero-engine health management units.The existing Physics-Informed Neural Networks(PINNs)have made achievements.However,unmeasurable aero-eng...Partial Differential Equations(PDEs)are model candidates of soft sensing for aero-engine health management units.The existing Physics-Informed Neural Networks(PINNs)have made achievements.However,unmeasurable aero-engine driving sources lead to unknown PDE driving terms,which weaken PINNs feasibility.To this end,Physically Informed Hierarchical Learning followed by Recurrent-Prediction Term(PIHL-RPT)is proposed.First,PIHL is proposed for learning nonhomogeneous PDE solutions,in which two networks NetU and NetG are constructed.NetU is for learning solutions satisfying PDEs;NetG is for learning driving terms to regularize NetU training.Then,we propose a hierarchical learning strategy to optimize and couple NetU and NetG,which are integrated into a data-physics-hybrid loss function.Besides,we prove PIHL-RPT can iteratively generate a series of networks converging to a function,which can approximate a solution to well-posed PDE.Furthermore,RPT is proposed for prediction improvement of PIHL,in which network NetU-RP is constructed to compensate for information loss caused by data sampling and driving sources’immeasurability.Finally,artificial datasets and practical vibration process datasets from our wear experiment platform are used to verify the feasibility and effectiveness of PIHL-RPT based soft sensing.Meanwhile,comparisons with relevant methods,discussions,and PIHL-RPT based health monitoring example are given.展开更多
The manufacturing processes of casing rings are prone to multi-type defects such as holes,cracks,and porosity,so ultrasonic testing is vital for the quality of aeroengine.Conventional ultrasonic testing requires manua...The manufacturing processes of casing rings are prone to multi-type defects such as holes,cracks,and porosity,so ultrasonic testing is vital for the quality of aeroengine.Conventional ultrasonic testing requires manual analysis,which is susceptible to human omission,inconsistent results,and time-consumption.In this paper,a method for automated detection of defects is proposed for the ultrasonic Total Focusing Method(TFM)inspection of casing rings based on deep learning.First,the original datasets of defect images are established,and the Mask R-CNN is used to increase the number of defects in a single image.Then,the YOLOX-S-improved lightweight model is proposed,and the feature extraction network is replaced by Faster Net to reduce redundant computations.The Super-Resolution Generative Adversarial Network(SRGAN)and Convolutional Block Attention Module(CBAM)are integrated to improve the identification precision.Finally,a new test dataset is created by ultrasonic TFM inspection of an aeroengine casing ring.The results show that the mean of Average Precision(m AP)of the YOLOX-S-improved model reaches 99.17%,and the corresponding speed reaches 77.6 FPS.This study indicates that the YOLOX-S-improved model performs better than conventional object detection models.And the generalization ability of the proposed model is verified by ultrasonic B-scan images.展开更多
文摘在航空发动机可视化协同维修中,利用声音提示技术,通过改进的梅尔频率倒谱系数(Mel Frequency Cepstral Coefficients,MFCC)与头相关传递函数(Head-Related Transfer Function,HRTF)构建“频域-空间”双重映射模型,实现故障声纹特征的精准提取与三维声场定位。结合增强现实界面,设计多故障优先级动态调控机制,优化声学信息传递链。实验结果表明,将声音提示技术应用于航空发动机可视化协同维修,故障维修响应时间缩短至1.3 s以内,故障定位误差控制在±1.0 mm和±1.0°,同时显著减少了协同误判频次,提升了航空发动机维修的实时性与准确性。
基金supported by the National Natural Science Foundation of China(Nos.52405088 and 92360306)the Postdoctoral Fellowship Program of CPSF,China(No.GZC20241446)+2 种基金the Natural Science Basic Research Program of Shaanxi,China(No.2024JC-YBMS-402)the Fundamental Research Funds for the Central Universities,CHD(No.300102254102)the Foundation of Beilin District,China(No.GX2455)。
文摘Anti-aliasing spectrum analysis is essential for rotor blade condition monitoring based on Blade Tip Timing(BTT).The Multiple Signal Classification(MUSIC)algorithm,which exploits the orthogonality between signal and noise subspaces,has been successfully applied for this purpose.However,conventional subspace selection methods relying on fixed thresholds are sensitive to variations in large eigenvalues.Furthermore,the complex disturbances during rotor operation and measurement complicate the identification of blade vibration characteristics.To overcome these challenges,this paper proposes Adaptive Subspace Separation(ASS)and Local Spectral Centroid(LSC)methods to improve the adaptability of subspace selection and the stability of frequency identification,respectively.The impacts of overestimating and underestimating the subspace dimensions on MUSIC's performance are derived mathematically.Simulation and experiments demonstrate the effectiveness of proposed approaches:ASS offers more accurate and stable subspace dimension selection and tracking,while LSC reduces the standard deviation of estimated frequencies by 30 percent.
基金supported by the National Natural Science Foundation of China (No. 52075059)Graduate Scientific Research and Innovation Foundation of Chongqing (No. CYB23021)the Innovation Fund of Aero Engine Corporation of China (No. ZZCX-2022-019)。
文摘The machining precision of blades is critical to the service performance of aero engines.The Leading Edge(LE) of high-pressure compressor blades poses a challenge for precision machining due to its thin size, high degree of bending, and significant change of curvature. Aimed at optimizing the machining error, this paper presents a framework that integrates toolpath planning and process parameter regulation. Firstly, an Iterative Subdivision Algorithm(ISA) for clamped Bspline curve is proposed, based on which toolpath planning method towards the LE is developed.Secondly, the removal effect of Cutter Contact(CC) point on the sampling points is investigated in the calculation of grinding dwell time by traversing in u-v space. A global material removal model is constructed for the solution. Thirdly, the previous two steps are interconnected based on the Improved Whale Optimization Algorithm(IWOA), and the optimal parameter combination is searched using the Root Mean Square Error(RMSE) of the machining error as the objective function. Based on this, the off-line programming and robotic grinding experiments are carried out. The experimental results show that the proposed method with error optimization can achieve 0.0143 mm mean value and 0.0160 mm standard deviations of LE surface error, which is an improvement of32.5% and 33.9%, respectively, compared with previous method.
基金the National Natural Science Foundation of China(Nos.52105117,52222504&51875433)the Funds for Distinguished Young talent of Shaanxi Province,China(No.2019JC-04)。
文摘Blade Tip Timing(BTT)enables non-contact measurements of rotating blades by placing probes strategically.Due to the uneven probe layout,BTT signals exhibit periodic irregularities.While recovering parameters like frequency from such signals is possible,achieving high-precision vibration parameters remains challenging.This paper proposed a novel two-stage off-grid estimation method.It leverages a unique array layout(coprime array)to obtain a regular augmented covariance matrix.Subsequently,parameters in the matrix are recovered using the sparse iterative covariance-based estimation method based on covariance fitting criteria.Finally,high-precision estimates of imprecise parameters are obtained using unconditional maximum likelihood estimation,effectively eliminating the effects of basis mismatch.Through substantial numerical and experimental validation,the proposed method demonstrates significantly higher accuracy compared to classical BTT parameter estimation methods,approaching the lower bound of unbiased estimation variance.Furthermore,due to its immunity to frequency gridding,it can track minor frequency deviations,making it more suitable for indicating blade condition.
基金co-supported by the National Science and Technology Major Project,China(No.J2019-I-0001-0001)the National Natural Science Foundation of China(No.52105545)。
文摘The original monitoring data from aero-engines possess characteristics such as high dimen-sionality,strong noise,and imbalance,which present substantial challenges to traditional anomalydetection methods.In response,this paper proposes a method based on Fuzzy Fusion of variablesand Discriminant mapping of features for Clustering(FFD-Clustering)to detect anomalies in originalmonitoring data from Aircraft Communication Addressing and Reporting System(ACARS).Firstly,associated variables are fuzzily grouped to extract the underlying distribution characteristics and trendsfrom the data.Secondly,a multi-layer contrastive denoising-based feature Fusion Encoding Network(FEN)is designed for each variable group,which can construct representative features for each variablegroup through eliminating strong noise and complex interrelations between variables.Thirdly,a featureDiscriminative Mapping Network(DMN)based on reconstruction difference re-clustering is designed,which can distinguish dissimilar feature vectors when mapping representative features to a unified fea-ture space.Finally,the K-means clustering is used to detect the abnormal feature vectors in the unifiedfeature space.Additionally,the algorithm is capable of reconstructing identified abnormal vectors,thereby locating the abnormal variable groups.The performance of this algorithm was tested ontwo public datasets and real original monitoring data from four aero-engines'ACARS,demonstratingits superiority and application potential in aero-engine anomaly detection.
基金Funded by the Spanish Government and FEDER funds(AEI/FEDER,UE)under grant PID2021-124502OB-C42(PRESECREL)the predoctoral program“Concepción Arenal del Programa de Personal Investigador en formación Predoctoral”funded by Universidad de Cantabria and Cantabria’s Government(BOC 18-10-2021).
文摘Predictive maintenance often involves imbalanced multivariate time series datasets with scarce failure events,posing challenges for model training due to the high dimensionality of the data and the need for domain-specific preprocessing,which frequently leads to the development of large and complex models.Inspired by the success of Large Language Models(LLMs),transformer-based foundation models have been developed for time series(TSFM).These models have been proven to reconstruct time series in a zero-shot manner,being able to capture different patterns that effectively characterize time series.This paper proposes the use of TSFM to generate embeddings of the input data space,making them more interpretable for machine learning models.To evaluate the effectiveness of our approach,we trained three classical machine learning algorithms and one neural network using the embeddings generated by the TSFM called Moment for predicting the remaining useful life of aircraft engines.We test the models trained with both the full training dataset and only 10%of the training samples.Our results show that training simple models,such as support vector regressors or neural networks,with embeddings generated by Moment not only accelerates the training process but also enhances performance in few-shot learning scenarios,where data is scarce.This suggests a promising alternative to complex deep learning architectures,particularly in industrial contexts with limited labeled data.
基金supported in part by the National Science and Technology Major Project of China(No.2019-I-0019-0018)the National Natural Science Foundation of China(Nos.61890920,61890921,12302065 and 12172073).
文摘Partial Differential Equations(PDEs)are model candidates of soft sensing for aero-engine health management units.The existing Physics-Informed Neural Networks(PINNs)have made achievements.However,unmeasurable aero-engine driving sources lead to unknown PDE driving terms,which weaken PINNs feasibility.To this end,Physically Informed Hierarchical Learning followed by Recurrent-Prediction Term(PIHL-RPT)is proposed.First,PIHL is proposed for learning nonhomogeneous PDE solutions,in which two networks NetU and NetG are constructed.NetU is for learning solutions satisfying PDEs;NetG is for learning driving terms to regularize NetU training.Then,we propose a hierarchical learning strategy to optimize and couple NetU and NetG,which are integrated into a data-physics-hybrid loss function.Besides,we prove PIHL-RPT can iteratively generate a series of networks converging to a function,which can approximate a solution to well-posed PDE.Furthermore,RPT is proposed for prediction improvement of PIHL,in which network NetU-RP is constructed to compensate for information loss caused by data sampling and driving sources’immeasurability.Finally,artificial datasets and practical vibration process datasets from our wear experiment platform are used to verify the feasibility and effectiveness of PIHL-RPT based soft sensing.Meanwhile,comparisons with relevant methods,discussions,and PIHL-RPT based health monitoring example are given.
基金supported by the Postdoctoral Fellowship Program of CPSF,China(No.GZC20232015)the China Postdoctoral Science Foundation(No.2024M752499)+3 种基金the Postdoctoral Project of Hubei Province,China(No.2024HBBHCXA076)the Wuhan East Lake New Technology Development Zone Open List Project,China(No.2022KJB128)the National Natural Science Foundation of China(No.51875428)the Fundamental Research Funds for the Central Universities,China(No.104972024RSCbs0013)。
文摘The manufacturing processes of casing rings are prone to multi-type defects such as holes,cracks,and porosity,so ultrasonic testing is vital for the quality of aeroengine.Conventional ultrasonic testing requires manual analysis,which is susceptible to human omission,inconsistent results,and time-consumption.In this paper,a method for automated detection of defects is proposed for the ultrasonic Total Focusing Method(TFM)inspection of casing rings based on deep learning.First,the original datasets of defect images are established,and the Mask R-CNN is used to increase the number of defects in a single image.Then,the YOLOX-S-improved lightweight model is proposed,and the feature extraction network is replaced by Faster Net to reduce redundant computations.The Super-Resolution Generative Adversarial Network(SRGAN)and Convolutional Block Attention Module(CBAM)are integrated to improve the identification precision.Finally,a new test dataset is created by ultrasonic TFM inspection of an aeroengine casing ring.The results show that the mean of Average Precision(m AP)of the YOLOX-S-improved model reaches 99.17%,and the corresponding speed reaches 77.6 FPS.This study indicates that the YOLOX-S-improved model performs better than conventional object detection models.And the generalization ability of the proposed model is verified by ultrasonic B-scan images.
