Enhanced data-driven fault diagnosis for machines with small and unbalanced data based on variational auto-encoder

Zhao, Dongfang; Liu, Shulin; Gu, Dan; Sun, Xin; Wang, Lu; Yuan, Wancheng; Zhang, Hongli

doi:10.1088/1361-6501/ab55f8

Cited by 80 publications

(30 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The former used the model to protect privacy, and the latter used the model to expand the classification model training data set and improve the classification model accuracy. Mahmud et al [ 20 ] and Zhao [ 21 ] proposed a fault diagnosis method based on variational AE and convolutional neural network to solve the problems of few fault samples and imbalanced data in the fault diagnosis method of the above-mentioned drive. Carden [ 22 ] proposed a strategy learning method, which uses part of the researchers' knowledge of probability transfer structure to transform it into an approximate generation model, from which to generate synthetic data.…”

Section: Related Workmentioning

confidence: 99%

Product Processing Quality Classification Model for Small-Sample and Imbalanced Data Environment

Liu

Dai

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

With the rapid development of machine learning technology, how to use machine learning technology to empower the manufacturing industry has become a research hotspot. In order to solve the problem of product quality classification in a small sample data and imbalanced data environment, this paper proposes a data generation model called MSMOTE-GAN, which is based on Mahalanobis Synthetic Minority Oversampling Technology (MSMOTE) and Generative Adversarial Network (GAN). Among them, MSMOTE is proposed to solve the problem of the sample biased to the majority class expanded by methods such as GAN in a sample imbalanced environment. Based on the traditional SMOTE method, the sample distance measurement method is modified from Euclidean distance to Mahalanobis distance, taking into account the correlation between attributes and the influence of dimensions on the sample distance. In the data generation model, MSMOTE is used to balance the positive and negative samples in the data. GAN generates fake data with the same distribution as the original data based on a balanced data set and expands the sample size to solve the problems of overfitting and insufficient model expression ability that occur when the sample size is too small. The quality classification framework of water heater liner based on the data generation model and Random Forest is constructed, and the process of the quality classification of water heater liner under the environment of small sample data and imbalanced data is fully described. This paper compares the MSMOTE-GAN model, Bootstrap, and tableGAN on the water heater liner production line data set and the public data set. The experimental result shows that the expanded data set of the MSMOTE-GAN model can effectively improve the performance of the classification model.

show abstract

Section: Related Workmentioning

confidence: 99%

Product Processing Quality Classification Model for Small-Sample and Imbalanced Data Environment

Liu

Dai

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…2.Furthermore, as previously stated, the PM conformance checking aims to provide methodologies to detect anomalies from the event log, by comparing the discovered models to the reference ones, or by reconstructing the event log from the generated model in the absence of reference ones. To fix the second case, a novel category of anomaly detection methods arises for rebuilding the event log itself through generative models such Generative Adversial Network (GAN) [72] and Variational Auto-Encoder (VAE) [73] architectures, where irregularities are determined by following the fundamental assumptions: no preceding process information, training in anomalies, no required model references, no required label and the algorithm has to eliminate the anomalous activity. In this scenario, authors in the 2nd study [74] propose a method for identifying and analyzing abnormalities in the execution of BP using an auto-encoder by reconstructing the event logs.…”

Section: Related Workmentioning

confidence: 99%

A Road-map for Mining Business Process Models via Artificial Intelligence Techniques

Chaima¹,

KHEBIZI²

2022

International Journal of Informatics and Applied Mathematics

View full text Add to dashboard Cite

Nowadays, the size of data recorded and stored in enterprises information systems (IS) is increasing every second. To face to this phenomenon, contemporary technologies play a major role for gathering, analyzing, storing, and distributing data that enables organizations to make smart decisions and to take full control of their activities. The traditional Business Process (BP) mining techniques were intensively used to discover, monitor, and optimize processes from event-logs without needing any priory model. However, the majority of the suggested algorithms have exhibited their limits (such as discovering nested loops, managing duplicate and hidden tasks as well as dealing with concurrent processes). In parallel, recent advances in the Artificial Intelligence (AI) discipline have generated a great deal of enthusiasm in a large spectrum of research area. In this perspective, AI methods emerge as one of the pillars to overcome the drawbacks of the conventional approaches allowing anomalies detection, prediction and recommendation tasks on ongoing process instances at run-time. The aim of this work is to explore towards the use of AI techniques in the field of business process mining by presenting a state-of-the-art review ranging from traditional PM approaches to AI ones, as well as outlining a prospective road-map for mining business process models basing on AI techniques.

show abstract

“…Martin et al [ 21 ] used a fully unsupervised deep VAE-based approach for dimensionality reduction and bearing fault diagnosis. Zhao et al [ 22 ] combined a VAE and CNN model to handle small fault sample data and identify faults in rolling bearings. Wang et al [ 23 ] applied a combination method, called conditional variational auto-encoder generative adversarial network (CVAE-GAN), to generate fault samples and diagnose imbalanced faults in a global gearbox.…”

Section: Theoretical Backgroundmentioning

confidence: 99%

Reliable Fault Diagnosis of Bearings Using an Optimized Stacked Variational Denoising Auto-Encoder

Yan

She

et al. 2021

Entropy

View full text Add to dashboard Cite

Variational auto-encoders (VAE) have recently been successfully applied in the intelligent fault diagnosis of rolling bearings due to its self-learning ability and robustness. However, the hyper-parameters of VAEs depend, to a significant extent, on artificial settings, which is regarded as a common and key problem in existing deep learning models. Additionally, its anti-noise capability may face a decline when VAE is used to analyze bearing vibration data under loud environmental noise. Therefore, in order to improve the anti-noise performance of the VAE model and adaptively select its parameters, this paper proposes an optimized stacked variational denoising autoencoder (OSVDAE) for the reliable fault diagnosis of bearings. Within the proposed method, a robust network, named variational denoising auto-encoder (VDAE), is, first, designed by integrating VAE and a denoising auto-encoder (DAE). Subsequently, a stacked variational denoising auto-encoder (SVDAE) architecture is constructed to extract the robust and discriminative latent fault features via stacking VDAE networks layer on layer, wherein the important parameters of the SVDAE model are automatically determined by employing a novel meta-heuristic intelligent optimizer known as the seagull optimization algorithm (SOA). Finally, the extracted latent features are imported into a softmax classifier to obtain the results of fault recognition in rolling bearings. Experiments are conducted to validate the effectiveness of the proposed method. The results of analysis indicate that the proposed method not only can achieve a high identification accuracy for different bearing health conditions, but also outperforms some representative deep learning methods.

show abstract

Enhanced data-driven fault diagnosis for machines with small and unbalanced data based on variational auto-encoder

Cited by 80 publications

References 35 publications

Product Processing Quality Classification Model for Small-Sample and Imbalanced Data Environment

Product Processing Quality Classification Model for Small-Sample and Imbalanced Data Environment

A Road-map for Mining Business Process Models via Artificial Intelligence Techniques

Reliable Fault Diagnosis of Bearings Using an Optimized Stacked Variational Denoising Auto-Encoder

Contact Info

Product

Resources

About