Aero Engine Gas-Path Fault Diagnose Based on Multimodal Deep Neural Networks

Zhao, Liang; Mo, Chunyang; Sun, Tingting; Huang, Wei

doi:10.1155/2020/8891595

Cited by 19 publications

(7 citation statements)

References 33 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, on this public data set, we use the data of its fibrosis part to predict the classification of lung fibrosis. Wu Enda's team once proposed the CheXNet network framework on the basis of this data set [ 4 – 6 ] which claimed to have reached a level far surpassing professional radiologists. CheXNet is essentially a 121-layer DenseNet network.…”

Section: Prediction Of Lung Fibrosis Based On X-raysmentioning

confidence: 99%

Prediction of Pulmonary Fibrosis Based on X-Rays by Deep Neural Network

Liu

Luo

et al. 2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

As a fatal lung disease, pulmonary fibrosis can cause irreversible damage to the lung, affect normal lung function, and eventually lead to death. At present, the pathogenesis of this kind of disease is not completely clear, and there is no radical cure. The main purpose of the treatment of this disease is to slow down the deterioration of pulmonary fibrosis. For this kind of disease, if it can be found early, it can be treated as soon as possible and the life of patients will be prolonged. Clinically, the diagnosis of pulmonary fibrosis depends on the relevant imaging examination, lung biopsy, lung function examination, and so on. Imaging data such as X-rays is a common examination means in clinical medicine and also plays an important role in the prediction of pulmonary fibrosis. Through X-ray, radiologists can clearly see the relevant lung lesions so as to make the relevant diagnosis. Based on the common medical image data, this paper designs related models to complete the prediction of pulmonary fibrosis. The model designed in this paper is mainly divided into two parts: first, this paper uses a neural network to complete the segmentation of lung organs; second, the neural network of image classification is designed to complete the process from lung image to disease prediction. In the design of these two parts, this paper improves on the basis of previous research methods. Through the design of a neural network with higher performance, more optimized results are achieved on the key indicators which can be applied to the real scene of pulmonary fibrosis prediction.

show abstract

Section: Prediction Of Lung Fibrosis Based On X-raysmentioning

confidence: 99%

Prediction of Pulmonary Fibrosis Based on X-Rays by Deep Neural Network

Liu

Luo

et al. 2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…For example, a simple ANN is used to estimate the thickness, roughness and density of organic semiconductor thin films for obtaining various types of global data [39]. The backpropagation neural network is used to fit the true distribution of the original sample data, and the CNN is combined to improve the diagnosis accuracy [40]. Moreover, many SPs extracted from vibration and noise signals of in-wheel motor are selected to obey some kinds of Weibull distribution in the previous research [41].…”

Section: Hmm Based On Wmmmentioning

confidence: 99%

Diagnosis method based on hidden Markov model and Weibull mixture model for mechanical faults of in-wheel motors

Xue¹,

Liu²,

Ding³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

To effectively monitor the operation state of in-wheel motor used in electric vehicle and ensure the safety of the whole vehicle, a diagnosis method based on hidden Markov model (HMM) and Weibull mixture model (WMM) is proposed for mechanical fault of in-wheel motor, that is simply known as a WMM-HMM diagnosis method. Firstly, vibration signals of in-wheel motor are extracted for sensitive symptom parameters (SPs) which are used to characterize the operation state and establish the observation sequence. Secondly, Weibull mixture model is employed to expand the limited observation sequence under various operating states of in-wheel motor to obtain sufficient observation sequence as the training sample set of HMM, and HMM parameters are determined through combining supervised learning with unsupervised learning algorithm. Then the WMM-HMM diagnosis models are constructed under low and medium speed conditions respectively. Finally, the corresponding fault in-wheel motors are customized and the test bench is built to verify the proposed method. The test results show that the proposed method can accurately identify the mechanical fault state of in-wheel motor under different conditions and has good generalization and applicability in traditional methods comparison.

show abstract

“…17 Zhao et al proposed a multimodal method that integrates the classification ability of two neural network models so that complementary information can be identified to improve the accuracy of diagnosis results. 18 Pi et al designed a new Elman neural network (ENN) optimized by quantum-behaved adaptive particle swarm optimization (QAPSO) to achieve accurate results in aeroengine fault diagnosis. 19 These studies with classic and typical machine learning methods have demonstrated that the performance of data-based fault diagnosis can be high.…”

Section: Introductionmentioning

confidence: 99%

Method of aeroengine fault diagnosis based on a Fingerprint map

Gou

Pan³

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part G:

View full text Add to dashboard Cite

The electrification and intelligentization trends of aeroengine systems present new challenges for the diagnostics of traditionally centralized control architectures. Scientific and practical fault diagnosis is of great significance for reducing aeroengine failures, improving operation efficiency, and ensuring safety. To realize accurate fault diagnosis, an aeroengine fault diagnosis method based on an improved fingerprint map is proposed in this paper. Based on aeroengine data analysis, ISTOA-SVM diagnostic model that embeds improved fingerprint map data as a priori knowledge is adopted to identify the fault sets. Data based on the statistics of the fingerprint map are processed with a ratio coefficient, and the feature parameters are appended through Floyd-principal component analysis (Floyd-PCA) to increase the identification data dimension. On the other hand, to improve the diagnostic performance of the classifier, the sooty terns optimization algorithm algorithm combined with chaotic maps, a variable helix mechanism and a separating operator is designed, and the ISTOA-SVM is constructed. The fault diagnosis method was validated by using a real-world dataset of aeroengines. Comparison experiments show that the proposed method is superior in performance over the state-of-the-art approaches in diagnostic precision under the constraint of limited data. The ISTOA-SVM addresses the issue that similar features may be confused in traditional fingerprint maps. The results are presented through 5 practical cases. The study demonstrates that the proposed method achieves superior performance and can be applied to aeroengine fault diagnosis.

show abstract

Aero Engine Gas-Path Fault Diagnose Based on Multimodal Deep Neural Networks

Cited by 19 publications

References 33 publications

Prediction of Pulmonary Fibrosis Based on X-Rays by Deep Neural Network

Prediction of Pulmonary Fibrosis Based on X-Rays by Deep Neural Network

Diagnosis method based on hidden Markov model and Weibull mixture model for mechanical faults of in-wheel motors

Method of aeroengine fault diagnosis based on a Fingerprint map

Contact Info

Product

Resources

About