Abstract:For a single-structure deep learning fault diagnosis model, its disadvantages are an insufficient feature extraction and weak fault classification capability. This paper proposes a multi-scale deep feature fusion intelligent fault diagnosis method based on information entropy. First, a normal autoencoder, denoising autoencoder, sparse autoencoder, and contractive autoencoder are used in parallel to construct a multi-scale deep neural network feature extraction structure. A deep feature fusion strategy based on… Show more
“…The convolutional neural network proposed by G. E. Hinton et al [16], as a new approach in the field of deep learning, has a unique network structure, powerful learning ability and high generalization capability. Therefore, this approach is widely used in the fields of image recognition, speech recognition and fault diagnosis [17][18][19][20][21][22][23][24].…”
Intelligent diagnosis of faults in an aero-hydraulic pipeline is important for condition monitoring of its systems. However, there are no more qualitative formulas or feature indicators to describe the faults of aero-hydraulic pipelines because of the complexity and diversity of aero-hydraulic pipeline systems, which leads to a very complex pipeline fault mechanism. In addition, although it is well known that the expression of interpretable and representable pipeline intelligent diagnosis models with pipeline fault characteristics are buried in high background noise and strong noise disturbance conditions in practical industrial scenarios, this has yet to be discussed. Inspired by the demand, this paper proposes a novel diagnosis strategy: the 1D-convolutional space-time fusion strategy for aero-engine hydraulic pipelines. Firstly, by optimizing the convolutional neural network and using it to design a one-dimensional convolutional neural network (1DCNN) with a wide input scale to expand the input field of perception, thereby obtaining more comprehensive spatial information of the pipeline data, which can effectively extract richer short sequence features. Secondly, a network of bidirectional gated recurrent Unit (Bi-GRU) is proposed, which integrates a short sequence of high-dimensional features for temporal information fusion, resulting in a certain degree of avoiding memory loss and gradient dispersion caused by the too-large step size. It is demonstrated that, for the noise signal and variable pressure signal, the fault identification accuracy approximated 95.9%, proving the proposed strategy’s robustness. By comparing with the other five methods, the proposed strategy has the ability to identify 10 different fault states in the aero-hydraulic pipeline with higher accuracy.
“…The convolutional neural network proposed by G. E. Hinton et al [16], as a new approach in the field of deep learning, has a unique network structure, powerful learning ability and high generalization capability. Therefore, this approach is widely used in the fields of image recognition, speech recognition and fault diagnosis [17][18][19][20][21][22][23][24].…”
Intelligent diagnosis of faults in an aero-hydraulic pipeline is important for condition monitoring of its systems. However, there are no more qualitative formulas or feature indicators to describe the faults of aero-hydraulic pipelines because of the complexity and diversity of aero-hydraulic pipeline systems, which leads to a very complex pipeline fault mechanism. In addition, although it is well known that the expression of interpretable and representable pipeline intelligent diagnosis models with pipeline fault characteristics are buried in high background noise and strong noise disturbance conditions in practical industrial scenarios, this has yet to be discussed. Inspired by the demand, this paper proposes a novel diagnosis strategy: the 1D-convolutional space-time fusion strategy for aero-engine hydraulic pipelines. Firstly, by optimizing the convolutional neural network and using it to design a one-dimensional convolutional neural network (1DCNN) with a wide input scale to expand the input field of perception, thereby obtaining more comprehensive spatial information of the pipeline data, which can effectively extract richer short sequence features. Secondly, a network of bidirectional gated recurrent Unit (Bi-GRU) is proposed, which integrates a short sequence of high-dimensional features for temporal information fusion, resulting in a certain degree of avoiding memory loss and gradient dispersion caused by the too-large step size. It is demonstrated that, for the noise signal and variable pressure signal, the fault identification accuracy approximated 95.9%, proving the proposed strategy’s robustness. By comparing with the other five methods, the proposed strategy has the ability to identify 10 different fault states in the aero-hydraulic pipeline with higher accuracy.
“…The research on the vibration monitoring signal processing method mainly focuses on the non-stationary and nonlinear vibration signal processing technology, mining the signal features that can effectively identify the fault, to improve the fault diagnosis accuracy of the system. For example, Fourier transform [7,8], wavelet decomposition [9,10], and modal decomposition [11,12] are the main research orientation. With the rapid development of machine learning and intelligent optimization algorithms, many intelligent classification algorithms have been applied to HGU fault diagnosis and achieved certain results.…”
Early fault detection of hydropower generation unit (HGU) is of great significance for the safe operation of the hydropower plant. Most of the related research focuses on the decomposition and feature extraction of single vibration monitoring signals. However, HGU is a typical coupling system with multi-channel vibration signals, and the subtle information transfer among signals is the precursor factor leading to the changes in the whole system. There has not been any research considering this potential factor in HGU or other system. Here, we proposed a novel monitoring method based on dynamic information transfer and principal component analysis (DIT-PCA). The process state of the unit is monitored by principal component analysis of the subtle dynamic transmitted information between the unit monitoring variables, which information is revealed for the first time. Normal monitoring samples are used for the offline training at first. Then, the confidence limits and fault contribution rates of two monitoring indicators Hotelling statistic and square prediction error of the model after training are applied to monitor the same test samples to achieve online fault detection and location. Moreover, the proposed model is applied to the state process of a real HGU, which has a superior sensitivity than two available detection methods. The results provide a direct reference for the early fault detection of the engineering system.
“…Meanwhile, with the development and gradual improvement of deep learning frameworks, intelligent fault diagnosis based on deep learning methods has become a research hotspot in recent years. At the same time, the application of deep learning in rotating machinery is also increasing [4][5][6][7].…”
Intelligent fault diagnosis is an important method in rotating machinery fault diagnosis and equipment health management. To deal with co-frequency vibration faults, a type of typical fault in rotating machinery, this paper proposes a fault diagnosis method based on the stacked autoencoder (SAE) and ensembled ResNet-SVM. Furthermore, the time- and frequency-domain features of several co-frequency vibration faults are summarized based on the mechanism analysis and calculated using actual vibration data. To realize and validate the high-precision diagnosis method of rotating equipment with co-frequency faults proposed in this study, the following three criteria are required: First, to improve the effectiveness and robustness of the ensembled model and the sliding window using data augmentation, adding noise, autoencoder (AE) and SAE methods are analyzed in terms of principle and practical effects. Second, ResNet is used as the feature extractor for the ensembled ResNet-SVM model. Feature extraction is carried out twice, and the extracted co-frequency fault features are more comprehensive. Finally, the data augmentation method and ensemble ResNet-SVM are combined for fault diagnosis and compared with other methods. The experimental results show that the accuracy of the proposed method can exceed 99.9%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.