Generative Adversarial Networks for Unsupervised Fault Detection

Plakias, Spyridon; Boutalis, Yiannis S.

doi:10.23919/ecc.2018.8550560

Cited by 17 publications

(13 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…and GAN [38], OCSVM (results reported in Spyridon and Boutalis,2018) reported previously. It can be seen that the proposed method also outperforms these DNN based methodologies.…”

Section: Case Study: Tennessee Eastman Processsupporting

confidence: 73%

See 1 more Smart Citation

Explainability: Relevance based Dynamic Deep Learning Algorithm for Fault Detection and Diagnosis in Chemical Processes

Agarwal¹,

Tamer²,

Budman³

2021

Preprint

View full text Add to dashboard Cite

The focus of this work is on Statistical Process Control (SPC) of a manufacturing process based on available measurements. Two important applications of SPC in industrial settings are fault detection and diagnosis (FDD). In this work a deep learning (DL) based methodology is proposed for FDD. We investigate the application of an explainability concept to enhance the FDD accuracy of a deep neural network model trained with a data set of relatively small number of samples. The explainability is quantified by a novel relevance measure of input variables that is calculated from a Layerwise Relevance Propagation (LRP) algorithm. It is shown that the relevances can be used to discard redundant input feature vectors/ variables iteratively thus resulting in reduced over-fitting of noisy data, increasing distinguishability between output classes and superior FDD test accuracy. The efficacy of the proposed method is demonstrated on the benchmark Tennessee Eastman Process.

show abstract

“…and GAN [38], OCSVM (results reported in Spyridon and Boutalis,2018) reported previously. It can be seen that the proposed method also outperforms these DNN based methodologies.…”

Section: Case Study: Tennessee Eastman Processsupporting

confidence: 73%

“…[6], Stacked Autoencoder (SAE) [6], Generative Adversarial Network (GAN) [38] and One-Class SVM (OCSVM) [38]. It can been seen from Table 5 that the proposed method outperformed the linear multivariate methods and other DL based methods for most fault modes.…”

Section: Case Study: Tennessee Eastman Processmentioning

confidence: 99%

Explainability: Relevance based Dynamic Deep Learning Algorithm for Fault Detection and Diagnosis in Chemical Processes

Agarwal¹,

Tamer²,

Budman³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…GANs were introduced by Ian Goodfellow and his fellow researchers at the University of Montreal in 2014 [48]. A GAN consists of two neural networks, as Figure 5 shows [49]:…”

Section: Generative Adversarial Network (Gans)mentioning

confidence: 99%

Variational Autoencoders and Wasserstein Generative Adversarial Networks for Improving the Anti-Money Laundering Process

2021

View full text Add to dashboard Cite

There has been much recent work on fraud and Anti Money Laundering (AML) detection using machine learning techniques. However, most algorithms are based on supervised techniques. Studies show that supervised techniques often have the limitation of not adapting well to new irregular fraud patterns when the dataset is highly imbalanced. Instead, unsupervised learning can have a better capability to find anomalous and irregular patterns in new transaction. Despite this, unsupervised techniques also have the disadvantage of not being able to give state-of-the-art detection results. We propose a suite of unsupervised and deep learning techniques to implement an anti-money laundering and fraud detection system to resolve this limitation. The system leverages three deep learning models: autoencoder (AE), variational autoencoder (VAE), and a generative adversarial network. We preprocess the given dataset to separate the Transaction Date attribute into its base components to capture time-related fraud patterns. Also, Wasserstein Generative Adversarial Network (WGAN) is used to generate fraud transactions, which are then mixed with the base dataset to form a more balanced mixed dataset. These two datasets are used to train the AE and VAE models. We built two versions of the AE model (single-loss and multi-loss) besides a novel method of calculating the anomaly score threshold, called Recall-First Threshold (RFT), which helps enhance the model's performance. Experimental results demonstrated that the False Positive Rate (FPR) drops down to as low as 7% in the proposed multi-loss AE model. In comparison, we achieved an accuracy of 93%, with 100% of the fraud transactions recalled successfully.

show abstract

“…A support vector clustering-based probabilistic approach was developed for unsupervised chemical process monitoring and fault classification by Yu [16]. Spyridon et al proposed a fault detection scheme based on the unsupervised training of a generative adversarial network [17]. Bezerra et al proposed applying typicality and eccentricity data analytics, a fully autonomous algorithm, to address the problem of fault detection in industrial processes [18].…”

Section: Introductionmentioning

confidence: 99%

Graph-Based Method for Fault Detection in the Iron-Making Process

Yang

Pan

2020

IEEE Access

View full text Add to dashboard Cite

Since the iron-making process is performed in complicated environments and controlled by operators, observation labeling is difficult and time-consuming. Therefore, unsupervised fault detection methods are a promising research topic. Recently, an unsupervised graph-based change point detection method has been introduced, and the graph of observations is constructed by the minimum spanning tree. In this paper, a novel fault detection method based on the graph for an iron-making process is proposed, and a weight calculation method for constructing the minimum spanning tree is introduced. The Euclidean distance and Mahalanobis distance are combined to calculate the weights in the minimum spanning tree, which contain important relations of variables. The distance calculation method is determined by the correlation coefficients of variables. Each testing observation is set as a change point candidate, and a change point candidate divides the observations into two groups. The number of a special type of edge in the minimum spanning tree is used as a fault detection statistic. That special edge connects two observations from two different groups. The minimum number of that type of edge corresponding to the change point candidate is a true change point. Finally, numerical simulation is used to test the power of the proposed method, and a real iron-making process including low stock, cooling, and slip faults is implemented to illustrate the effectiveness of fault detection in industrial processes.

show abstract

Generative Adversarial Networks for Unsupervised Fault Detection

Cited by 17 publications

References 14 publications

Explainability: Relevance based Dynamic Deep Learning Algorithm for Fault Detection and Diagnosis in Chemical Processes

Explainability: Relevance based Dynamic Deep Learning Algorithm for Fault Detection and Diagnosis in Chemical Processes

Variational Autoencoders and Wasserstein Generative Adversarial Networks for Improving the Anti-Money Laundering Process

Graph-Based Method for Fault Detection in the Iron-Making Process

Contact Info

Product

Resources

About