The flywheel fault detection based on Kernel principal component analysis

Li, Gan-hua; Li, Jiancheng; Cao, Ya-ni; Xu, Min; Xia, Keqiang; Wei, Jun; Lan, Baojun; Li, Dong

doi:10.1109/itnec.2019.8729163

Cited by 7 publications

(5 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More specifically, the proposed model is built from the Back-Propagation Neural Networks (BPNNs) to detect CCF and a combination of SMOTE with Tomek links to tackle the imbalanced data problem in order to enhance the model prediction performance of legitimate and fraudulent transactions. In the area of the CCFD, the concept of classifiers combination is proving to be an important new path for improving individual classifiers' performance in terms of accurate and precise results [46]- [48].…”

Section: The Proposed Approachmentioning

confidence: 99%

“…A combination of Tomek Links and SMOTE is recommended in [54] [48] to exploit the advantages of each approach for tackling the imbalanced data and improving the classification performances of a fraud identification model.…”

Section: F Tomek Links Techniquementioning

confidence: 99%

“…It adjusts the weights of the connections in the neural network by Also, SMOTE as a method usable at the algorithmic level, has the capacity to increment the learning of the algorithm with regard to reducing both the FNR (False Negative Rate) and FPR (False Positive Rate). In the view of Kumari and Mishra [48], SMOTE is written in the following way:…”

Section: G Deep Neural Network Algorithm For Ccfdmentioning

confidence: 99%

See 2 more Smart Citations

An Efficient Deep Learning Classification Model for Predicting Credit Card Fraud on Skewed Data

Rtayli

2022

JISCR

View full text Add to dashboard Cite

Due to fast-evolving technology, the world is moving to the use of credit cards rather than money in their daily lives, giving rise to many new opportunities for fraudsters to use credit cards maliciously. Based on the Nilson report, losses related to global cards were estimated to be over $35 billion by 2020. In order to maintain the security of users of these cards, the credit card company must develop a service to ensure that users are protected from any risks they may be exposed to. For this reason, we introduce a fraud detection model, denoted ST-BPNN, which is based on machine and deep learning approaches to identify fraudulent transactions. ST-BPNN was applied on real fraud detection data provided by the European bank. Comparing the obtained results from ST-BPNN with a recent state-of-the-art approach shows that our proposed model demonstrates high predictive performance for detecting fraudulent transactions.

show abstract

Section: The Proposed Approachmentioning

confidence: 99%

Section: F Tomek Links Techniquementioning

confidence: 99%

Section: G Deep Neural Network Algorithm For Ccfdmentioning

confidence: 99%

See 1 more Smart Citation

An Efficient Deep Learning Classification Model for Predicting Credit Card Fraud on Skewed Data

Rtayli

2022

JISCR

View full text Add to dashboard Cite

show abstract

“…Many papers in the literature address the AOCS fault diagnosis based on model reasoning approaches, such as neural networks (Lee, Lim, Cho & Kim, 2020;Liu, Pan, Wang & He, 2019;Sun, Hicham HENNA et al This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Li, Li, Cao, Xu, Xia, Wei & Dong, 2019). However, these approaches suffer from several limits (Henna et al 2020) because they require prior knowledge about failure dynamics.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Data-Driven Approach for Fault Diagnostic of Spacecraft Gyroscope

Henna

Toubakh²,

KAFI³

et al. 2022

PHM_CONF

View full text Add to dashboard Cite

In spacecraft attitude control, maintaining an accurate estimate of attitude readings is crucial. Due to aging factors of sensors like gyroscopes, emerged drift or bias from the correct rate values lead to decreased pointing accuracy. This paper proposes unsupervised data-driven approach in order to diagnose in early stage abnormal drifts in spacecraft attitude sensors. Three types of faults are injected in the satellite attitude control simulator. The obtained results are compared with other similar data-driven methods. The comparison shows the superiority of our method in terms of missed alarm rate and incorrect detection rate. In addition, our approach does not require prior knowledge and labels about the attitude sensors faults.

show abstract

“…Various other machine learning approaches such as minimum error minimax probability machine [16], gradient boosting machines (GBM) [17], and kernel principal component analysis [18] are used for fault detection and isolation in aerospace applications.…”

Section: Introductionmentioning

confidence: 99%

Data-Driven Fault Diagnosis for Satellite Control Moment Gyro Assembly with Multiple In-Phase Faults

Farahani

Rahimi

2021

Electronics

View full text Add to dashboard Cite

A satellite can only complete its mission successfully when all its subsystems, including the attitude control subsystem, are in healthy condition and work properly. Control moment gyroscope is a type of actuator used in the attitude control subsystems of satellites. Any fault in the control moment gyroscope can cause the satellite mission failure if it is not detected, isolated, and resolved in time. Fault diagnosis provides an opportunity to detect and isolate the occurring faults and, if accompanied by proactive remedial actions, it can avoid failure and improve the satellite reliability. In this paper, an enhanced data-driven fault diagnosis is introduced for fault isolation of multiple in-phase faults of satellite control moment gyroscopes that has not been addressed in the literature before with high accuracy. The proposed method is based on an optimized support vector machine, and the results yield fault predictions with up to 95.6% accuracy. In addition, a sensitivity analysis with regard to noise, missing values, and missing sensors is done. The results show that the proposed model is robust enough to be used in real applications.

show abstract

The flywheel fault detection based on Kernel principal component analysis

Cited by 7 publications

References 3 publications

An Efficient Deep Learning Classification Model for Predicting Credit Card Fraud on Skewed Data

An Efficient Deep Learning Classification Model for Predicting Credit Card Fraud on Skewed Data

Unsupervised Data-Driven Approach for Fault Diagnostic of Spacecraft Gyroscope

Data-Driven Fault Diagnosis for Satellite Control Moment Gyro Assembly with Multiple In-Phase Faults

Contact Info

Product

Resources

About