Deep-Learning-Based Open Set Fault Diagnosis by Extreme Value Theory

Yu, Xiaolei; Zhao, Zhibin; Zhang, Xingwu; Zhang, Xingwu; Liu, Yilong; Sun, Chuang; Chen, Xuefeng

doi:10.1109/tii.2021.3070324

Cited by 103 publications

(25 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we verifiy the effectiveness and superiority of the proposed method by comparing the performances of 1DCNN+EVT [18], DVAEC [19], and DOC [16] as reported in their corresponding literature. Table 10 shows the comparative results on four experimental tasks of the CWRU dataset in the literature [18].…”

Section: Comparison Methodsmentioning

confidence: 99%

“…The OSA-based classification method has been studied in many fields, mainly in the field of face recognition [13], security field [14], text classification [15,16], and network traffic [17], etc. However, there are few studies on OSA-based methods in the field of industrial bearings [18,19], and their experimental data are insufficient, so there is still much room to improve the rejection ability of UC. Therefore, it is urgent to explore a bearing fault diagnosis method based on OSA.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent Bearing Fault Diagnosis Based on Open Set Convolutional Neural Network

Zhang

Zhou

et al. 2022

Mathematics

View full text Add to dashboard Cite

Traditional data-driven intelligent fault diagnosis methods have been successfully developed under the closed set assumption (CSA). CSA-based fault diagnosis assumes that the fault types in the test set are consistent with that in the training set, which can achieve high accuracy, but this is generally not valid in real-world industrial applications where the collection of data in industrial applications is often limited. As it is unrealistic to assume that the training set will cover all fault types, the application of the fault classifier may fail when the test set contains unknown fault types because the probability of input samples belonging to unknown types cannot be obtained. To solve the problem of how unknown fault types may be accurately identified, this paper further studies the open set assumption (OSA) fault diagnosis. We propose an open set convolutional neural network (OS-CNN) method and apply our OS-CNN model to an improved OpenMax method as a deep network to accurately detect unknown fault types. The overall performance was significantly improved as our OS-CNN model was able to effectively tighten the boundary of known classes and limit the open-space risk for the OpenMax method based on distance modeling. The overall effectiveness of the proposed method was verified by experimental studies based on four different bearing datasets. Compared with state-of-the-art OSA fault diagnosis method, our method cannot only realize the correct classification of the known fault classes, but it can also accurately detect the unknown fault classes.

show abstract

Section: Comparison Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Intelligent Bearing Fault Diagnosis Based on Open Set Convolutional Neural Network

Zhang

Zhou

et al. 2022

Mathematics

View full text Add to dashboard Cite

show abstract

“…For example, (Wu et al 2021) fit a GPD to the residuals of a neural network to help detect cyber risks. Similarly, Yu et al (Yu et al 2021) identify samples with unknown classes at test time using the Weibull distribution. Weng et al (Weng et al 2018) utilize EVT to derive a neural network robustness metric called CLEVER.…”

Section: Related Workmentioning

confidence: 99%

DeepGPD: A Deep Learning Approach for Modeling Geospatio-Temporal Extreme Events

Wilson

Tan

Luo

2022

AAAI

View full text Add to dashboard Cite

Geospatio-temporal data are pervasive across numerous application domains.These rich datasets can be harnessed to predict extreme events such as disease outbreaks, flooding, crime spikes, etc. However, since the extreme events are rare, predicting them is a hard problem. Statistical methods based on extreme value theory provide a systematic way for modeling the distribution of extreme values. In particular, the generalized Pareto distribution (GPD) is useful for modeling the distribution of excess values above a certain threshold. However, applying such methods to large-scale geospatio-temporal data is a challenge due to the difficulty in capturing the complex spatial relationships between extreme events at multiple locations. This paper presents a deep learning framework for long-term prediction of the distribution of extreme values at different locations. We highlight its computational challenges and present a novel framework that combines convolutional neural networks with deep set and GPD. We demonstrate the effectiveness of our approach on a real-world dataset for modeling extreme climate events.

show abstract

“…The next remark uses techniques from [19], [20], [25] to provide analytical expressions for v α,Y θ (24) and c α,Y θ (25).…”

Section: B Evt-based Estimator For ρ α (Y)mentioning

confidence: 99%

“…Deo and Murthy have estimated the CVaR and an associated gradient by combining tools from EVT and importance sampling [23]. In a classification problem, EVT has been used to estimate the probability of a sample belonging to an undetected class [24].…”

mentioning

confidence: 99%

Toward Scalable Risk Analysis for Stochastic Systems Using Extreme Value Theory

Arsenault¹,

Wang²,

Chapman³

2022

Preprint

View full text Add to dashboard Cite

We aim to analyze the behaviour of a finitetime stochastic system, whose model is not available, in the context of more rare and harmful outcomes. Standard estimators are not effective in predicting the magnitude of such outcomes due to their rarity. Instead, we leverage Extreme Value Theory (EVT), the study of the long-term behaviour of normalized maxima of random variables. In this letter, we quantify risk using the upper-semideviation E(max{Y − E(Y), 0}), which is the expected exceedance of a random variable Y above its mean E(Y). To assess more rare and harmful outcomes, we propose an EVT-based estimator for this functional in a given fraction of the worst cases. We show that our estimator enjoys a closed-form representation in terms of a popular functional called the conditional value-at-risk. In experiments, we illustrate the extrapolation power of our estimator when a small number of i.i.d. samples is available (<50). Our approach is useful for estimating the risk of finite-time systems when models are inaccessible and data collection is expensive. The numerical complexity does not grow with the size of the state space. This letter initiates a broader pathway for estimating the risk of large-scale systems.

show abstract

Deep-Learning-Based Open Set Fault Diagnosis by Extreme Value Theory

Cited by 103 publications

References 36 publications

Intelligent Bearing Fault Diagnosis Based on Open Set Convolutional Neural Network

Intelligent Bearing Fault Diagnosis Based on Open Set Convolutional Neural Network

DeepGPD: A Deep Learning Approach for Modeling Geospatio-Temporal Extreme Events

Toward Scalable Risk Analysis for Stochastic Systems Using Extreme Value Theory

Contact Info

Product

Resources

About