Progressive Improved Convolutional Neural Network for Avionics Fault Diagnosis

Chen, Shuwen; Ge, Hongjuan; Jing, Li; Pecht, Michael

doi:10.1109/access.2019.2954170

Cited by 18 publications

(7 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e pattern can be described as the relationship between data sets, the relationship between data in a single data record, or a specific frequency. It mainly includes classification analysis, cluster analysis, association analysis, anomaly analysis, evolution analysis, and specific group analysis [13,14]. Classification analysis is to establish a certain objective function based on variables of known categories and then classify the target variables according to the original category.…”

Section: Related Workmentioning

confidence: 99%

Evaluation Model of Employment and Entrepreneurship of University Students Based on Classification Algorithm

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

As a new data analysis tool, data mining has developed rapidly. Various types of data sets can be used as data mining objects. Faced with more and more data sources and larger amounts of data today, data mining can effectively obtain valuable information from them and can enable people to better predict possible data information in the future, thereby improving work efficiency. Pheromone update uses a combination of global update and local update. The improved algorithm can balance the relationship between ants’ exploration and development in the process of searching rules. The government’s macroentrepreneurial policy has an important impact on college students’ entrepreneurship. Whether the entrepreneurship can obtain government financial support, whether the entrepreneurial process is simple and easy to do, etc., all affect the enthusiasm of college students to start a business and the success of the business. As an important place for college students to live and study, colleges and universities play a vital role in the growth and future development of college students. Major colleges and universities should improve entrepreneurship education, provide materials and manpower such as teaching materials and teachers, and improve the entrepreneurial quality of college students. In addition, colleges and universities should actively establish and improve the entrepreneurial practice platform for college students to help students gain entrepreneurial experience from practice. As the backbone of the social economy, enterprises should play an appropriate role in college students’ entrepreneurship. On the one hand, they should actively provide entrepreneurial funds, and they should be willing to give college students experience guidance. Only with the joint efforts of the government, universities, and enterprises, can it be possible to establish a practical and effective support system for undergraduate entrepreneurship, promote undergraduate entrepreneurship, and increase the success rate of undergraduate entrepreneurship.

show abstract

Section: Related Workmentioning

confidence: 99%

Evaluation Model of Employment and Entrepreneurship of University Students Based on Classification Algorithm

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…The loss function is used to estimate the difference between the actual value Gj and the model predicted value f(CQj) that corresponds to the sample, which is expressed by L(Gj, f(CQj)). This article uses the following two loss functions: the SVM type loss function is shown in formula (8), and the logistic regression type loss function is shown in formula ( 9):…”

Section: ) Fault Classification and Prediction Model Based On Stochastic Gradient Descentmentioning

confidence: 99%

“…Compared with early fault diagnosis methods, artificial intelligence diagnosis methods have been applied in the fields of fault diagnosis and prediction, such as fuzzy diagnosis methods [3], diagnosis methods based on genetic algorithms [4][5], fault diagnosis methods using expert systems [6][7], methods based on neural networks [8][9][10], and diagnosis methods using the support vector machine (SVM) [11][12]. The effective use of these artificial intelligence technology methods has been superior to early diagnosis methods to a certain extent.…”

Section: Introductionmentioning

confidence: 99%

Power System Fault Classification and Prediction Based on a Three-Layer Data Mining Structure

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

In traditional fault diagnosis methods in power systems, it is difficult to accurately classify and predict the types of faults. With the emergence of big data technology, the fault classification and prediction methods based on big data analysis and processing have been applied in power systems. To make the classification and prediction of the fault types more accurate, this paper proposes a hybrid data mining method for power system fault classification and prediction based on clustering, association rules and stochastic gradient descent. This method uses a three-layer data mining model: The first layer uses the K-means clustering algorithm to preprocess the original fault data source, and it proposes to use self-encoding to simplify the data form. The second layer effectively eliminates the data that have little impact on the prediction results by using association rules, and the highly correlated data are mined to become the regression training data. The third layer first uses the cross-validation method to obtain the optimal parameters of each fault model, and then, it uses stochastic gradient descent for data regression training to obtain a classification and prediction model for each fault type. Finally, a verification example shows that compared with a single data mining algorithm model, the proposed method is more comparative in terms of the data mining, and the established power system fault classification and prediction model has global optimality and higher prediction accuracy, which has a certain feasibility for real-time online power system fault classification and prediction. This method reduces the disturbances from low-impact or irrelevant data by mining the fault data three times, and it uses cross-validation to optimize the multiple regression parameters of the regression model to solve the problems of low accuracy, large errors and easily falling into a local optimum, given the conduct of fault classification and prediction.

show abstract

“…In [ 36 ], Wang et al proposed a 1-D CNN (1D-CNN)-based Hiller system fault diagnosis method that combines 1D-CNN and a gated recurrent unit to perform the fault identification task. In [ 37 ], a random oversampling-based CNN FD method was presented by Chen et al to handle fault confusing problems and is applied in avionics FD. In [ 38 ], Wen et al presented a CNN-based FD algorithm in which a CNN is used to learn fault features from reconstructed raw data directly without complex feature extracting operation.…”

Section: Related Workmentioning

confidence: 99%

“…Deep learning (DL) learns features from big data [ 32 , 33 ] and avoids the complex processes stemming from handcrafted features. CNN is a powerful DL model for handling two-dimensional (2-D) images and has been used in FD research, such as mechanical systems FD [ 34 , 35 ], circuit systems FD [ 36 ], and avionics FD [ 37 ]. In FD applications, because raw data is often sampled in one-dimensional (1-D) format, researchers have turned to feature extraction operations that construct 2-D features for addressing FD problems using CNNs, such as sliding window [ 38 , 39 ], short time Fourier transform (STFT) [ 40 ], discrete wavelet transform (DWT) [ 41 , 42 ], and Hilbert–Huang transform (HHT) [ 43 , 44 ].…”

Section: Introductionmentioning

confidence: 99%

Method for Fault Diagnosis of Temperature-Related MEMS Inertial Sensors by Combining Hilbert–Huang Transform and Deep Learning

Gao

Wei

Zhou

et al. 2020

Sensors

View full text Add to dashboard Cite

In this paper, we propose a novel method for fault diagnosis in micro-electromechanical system (MEMS) inertial sensors using a bidirectional long short-term memory (BLSTM)-based Hilbert–Huang transform (HHT) and a convolutional neural network (CNN). First, the method for fault diagnosis of inertial sensors is formulated into an HHT-based deep learning problem. Second, we present a new BLSTM-based empirical mode decomposition (EMD) method for converting one-dimensional inertial data into two-dimensional Hilbert spectra. Finally, a CNN is used to perform fault classification tasks that use time–frequency HHT spectrums as input. According to our experimental results, significantly improved performance can be achieved, on average, for the proposed BLSTM-based EMD algorithm in terms of EMD computational efficiency compared with state-of-the-art algorithms. In addition, the proposed fault diagnosis method achieves high accuracy in fault classification.

show abstract

Progressive Improved Convolutional Neural Network for Avionics Fault Diagnosis

Cited by 18 publications

References 42 publications

Evaluation Model of Employment and Entrepreneurship of University Students Based on Classification Algorithm

Evaluation Model of Employment and Entrepreneurship of University Students Based on Classification Algorithm

Power System Fault Classification and Prediction Based on a Three-Layer Data Mining Structure

Method for Fault Diagnosis of Temperature-Related MEMS Inertial Sensors by Combining Hilbert–Huang Transform and Deep Learning

Contact Info

Product

Resources

About