Fault Detection in Gears Using Fault Samples Enlarged by a Combination of Numerical Simulation and a Generative Adversarial Network

Gao, Yun; Liu, Xiaoyang; Xiang, Jiawei

doi:10.1109/tmech.2021.3132459

Cited by 72 publications

(30 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compare the anomaly detection performance of DUAL-ADGAN with the other nine unsupervised anomaly detection baseline models on three datasets, RealAdExchange-CPC, RealTraffic-SPEED, and Real-Traffic-TravelTime. (3) For epochs do (4) Feed the noise vector z into the generator G W to generate the data G W (5) Feed the generated data G W (z) and the real data x into the discriminator D W (6) Training G W and D W with WGAN-GP loss function (7) Return G W (8) If model is Fence-GAN: (9) For epochs do (10) Feed the noise vector z into the generator G F to generate the data G F (z) (11) Feed the generated data G F (z) and the real data x into the discriminator D F (12) Training G F and D F with Fence-GAN loss function (13) Step 2.…”

Section: Experimental Protocolmentioning

confidence: 99%

“…If a supervised anomaly detection method is used, the problem of insufficient anomaly samples in the training samples needs to be addressed. Gao et al [6][7][8] used numerical simulation or finite element simulation to simulate fault samples in a mechanical fault detection problem and combined with generative adversarial networks to synthesize fault samples to provide sufficient fault samples for training supervised models. However, when it is difficult to obtain anomaly samples, the unsupervised anomaly detection model is usually used for anomaly detection in timeseries data [9].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Research on DUAL-ADGAN Model for Anomaly Detection Method in Time-Series Data

Gong

Wang

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In recent years, anomaly detection techniques in time-series data have been widely used in manufacturing, cybersecurity, and other fields. Meanwhile, various anomaly detection models based on generative adversarial networks (GAN) are gradually used in time-series anomaly detection tasks. However, there are problems of unstable generator training, missed detection of anomalous data, and inconsistency between the discriminator’s discriminant and the anomaly detection target in GAN networks. Aiming at the above problems, the paper proposes a DUAL-ADGAN (Dual Anomaly Detection Generative Adversarial Networks) model for the detection of anomalous data in time series. First, the Wasserstein distance satisfying the Lipschitz constraint is used as the loss function of the data reconstruction module, which improves the stability of the traditional GAN network training. Second, by adding a data prediction module to the DUAL-ADGAN model, the distinction between abnormal and normal samples is increased, and the rate of missing abnormal data in the model is reduced. Third, by introducing the Fence-GAN loss function, the discriminator is aligned with the anomaly detection target, which effectively reduces the anomaly data false detection rate of the DUAL-ADGAN model. Finally, anomaly scores derived from the DUAL-ADGAN model are compared with dynamic thresholds to detect anomalies. The experimental results show that the average F1 of the DUAL-ADGAN model is 0.881, which is better than the other nine baseline models. The conclusions demonstrate that the DUAL-ADGAN model proposed in the paper is more stable in training while effectively solving the problems of anomaly miss detection and discriminator inconsistency with the anomaly detection target in the anomaly detection task.

show abstract

Section: Experimental Protocolmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Research on DUAL-ADGAN Model for Anomaly Detection Method in Time-Series Data

Gong

Wang

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Artificial intelligence (AI) models can automatically learn features without extensive prior knowledge and have been widely used for unknown abnormal condition detection and prediction [ 9 , 10 , 11 ], especially for SOC estimation for lithium-ion batteries [ 12 , 13 , 14 ]. For example, an adaptive back propagation neural network was introduced to improve the SOC estimation accuracy of an unscented Kalman filtering algorithm [ 15 ].…”

Section: Introductionmentioning

confidence: 99%

Stable and Accurate Estimation of SOC Using eXogenous Kalman Filter for Lithium-Ion Batteries

Lin

Tu³

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

The state of charge (SOC) for a lithium-ion battery is a key index closely related to battery performance and safety with respect to the power supply system of electric vehicles. The Kalman filter (KF) or extended KF (EKF) is normally employed to estimate SOC in association with the relatively simple and fast second-order resistor-capacitor (RC) equivalent circuit model for SOC estimations. To improve the stability of SOC estimation, a two-stage method is developed by combining the second-order RC equivalent circuit model and the eXogenous Kalman filter (XKF) to estimate the SOC of a lithium-ion battery. First, approximate SOC estimation values are observed with relatively poor accuracy by a stable observer without considering parameter uncertainty. Second, the poor accuracy SOC results are further fed into XKF to obtain relative stable and accurate SOC estimation values. Experiments demonstrate that the SOC estimation results of the present method are superior to those of the commonly used EKF method. It is expected that the present two-stage XKF method will be useful for the stable and accurate estimation of SOC in the power supply system of electric vehicles.

show abstract

“…Motived by this problem, some scholars combined simulation models with deep learning to detect faults. Tey established accurate models of rotating machinery, such as bearings, to simulate sufcient fault data, which can be used for the training of deep learning models [21,22]. Wang et al [23] developed the lumped parameter model of gears to generate samples.…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis Method for Bearing Based on Digital Twin

Xie

Yang

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The bearing is an essential component of rotating machinery, as its reliability and running state have a direct impact on the machinery’s performance. Considering that deep learning-based fault diagnosis methods for bearing require a large amount of labelled sample data, a novel fault diagnosis framework based on digital twin is proposed. In the case of fault data available, self-organizing maps with minimum quantization error and support vector machine are employed to analyze the data. Where fault data is unavailable, a bearing digital twin model is first constructed to simulate the data, and the convolutional neural network combined with transfer learning is utilized to diagnose the bearing faults. Then, the law of bearing performance degradation is investigated. The effectiveness of the proposed method is verified using bearing vibration data.

show abstract

Fault Detection in Gears Using Fault Samples Enlarged by a Combination of Numerical Simulation and a Generative Adversarial Network

Cited by 72 publications

References 40 publications

Research on DUAL-ADGAN Model for Anomaly Detection Method in Time-Series Data

Research on DUAL-ADGAN Model for Anomaly Detection Method in Time-Series Data

Stable and Accurate Estimation of SOC Using eXogenous Kalman Filter for Lithium-Ion Batteries

Fault Diagnosis Method for Bearing Based on Digital Twin

Contact Info

Product

Resources

About