Open-Set Classification for Signal Diagnosis of Machinery Sensor in Industrial Environment

Jian-ming, Chen; Wang, Guangjin; Lv, Jiancheng; He, Zhenan; Yang, Taibo; Tang, Chenwei

doi:10.1109/tii.2022.3169459

Cited by 9 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In industrial scenarios, during the running process of the device, the operating environment and condition may change over time, continuing generating data belong to unknown classes with new characteristics and distribution. To address this challenging problem, Chen et al [120] proposed a generic open set signal classification method, using Fourier transform and variational encoderclassifier network to determine whether samples belong to unknown or not.…”

Section: Data-driven Methodsmentioning

confidence: 99%

Artificial Intelligence Methods Applied to Catalytic Cracking Processes

Yang

Lei

et al. 2023

Big Data Min. Anal.

Self Cite

View full text Add to dashboard Cite

Fluidic Catalytic Cracking (FCC) is a complex petrochemical process affected by many highly non-linear and interrelated factors. Product yield analysis, flue gas desulfurization prediction, and abnormal condition warning are several key research directions in FCC. This paper will sort out the relevant research results of the existing Artificial Intelligence (AI) algorithms applied to the analysis and optimization of catalytic cracking processes, with a view to providing help for the follow-up research. Compared with the traditional mathematical mechanism method, the AI method can effectively solve the difficulties in FCC process modeling, such as high-dimensional, nonlinear, strong correlation, and large delay. AI methods applied in product yield analysis build models based on massive data. By fitting the functional relationship between operating variables and products, the excessive simplification of mechanism model can be avoided, resulting in high model accuracy. AI methods applied in flue gas desulfurization can be usually divided into two stages: modeling and optimization. In the modeling stage, data-driven methods are often used to build the system model or rule base; In the optimization stage, heuristic search or reinforcement learning methods can be applied to find the optimal operating parameters based on the constructed model or rule base. AI methods, including data-driven and knowledge-driven algorithms, are widely used in the abnormal condition warning. Knowledge-driven methods have advantages in interpretability and generalization, but disadvantages in construction difficulty and prediction recall. While the data-driven methods are just the opposite. Thus, some studies combine these two methods to obtain better results.

show abstract

Section: Data-driven Methodsmentioning

confidence: 99%

Artificial Intelligence Methods Applied to Catalytic Cracking Processes

Yang

Lei

et al. 2023

Big Data Min. Anal.

Self Cite

View full text Add to dashboard Cite

show abstract

“…CNNevt [17] utilized the Euclidean distance between the output logit vector and class center to determine whether an input sample is an unknown fault. OSSC [23] replaced the decoder of the VAE network with a classifier and trained an encoder-classifier network for discriminative feature extraction. The extreme value theory and entropy, which are termed as OSSCevt and OSSCentropy, respectively, were further used to detect the unknown fault.…”

Section: Comparison With Other Methodsmentioning

confidence: 99%

“…In addition, the F1 score is commonly used to evaluate the open-set classification performance of a model that is trained with K classes but outputs K + 1 classes [22], [23]. The F1 score is defined as…”

Section: Evaluation Metricsmentioning

confidence: 99%

“…He et al [22] simultaneously trained a VAE network and deep latent feature classifier, utilizing Bhattacharyya distances of latent features for unknown detection. Chen et al [23] directly replaced the decoder of the VAE network with a classifier and trained an encoder-classifier network for discriminative feature extraction. Zhang et al [24] employed a flow-based model to estimate the density of known-class features and treated its output density as a special distance for unknown detection.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Discriminative Angle Feature Learning for Open-Set Deep Fault Classification

et al. 2023

View full text Add to dashboard Cite

Unknown faults may occur in practical applications, necessitating an open-set classifier that can classify known classes as well as recognize unknown faults. The current deep open-set classification methods are implicit in optimizing the intra-or inter-class distances, which may result in performance degradation when the number of unknown classes far exceeds that of the known. In this study, the discriminative angle deep features for vibration signals are investigated. A novel normalized one-versus-all classification loss with center and contrastive regularization is proposed. The trained network can explicitly optimize deep features to ensure intra-class compactness and inter-class divergence. In this case, such discriminative features can be used for open-set fault classification. Furthermore, the effectiveness of the proposed method is verified using field-measured motor bearing and gear vibration signals. The results demonstrate the evident advantages of our proposed method over other approaches in practical fault diagnosis scenarios.

show abstract

“…As depicted in Figure 1,in OSR, known class data is recognized as specific categories, while data not belonging to known classes is identified as unknown categories. In the paper referenced as [7], the distinction between closed-set recognition and open-set recognition is clarified.…”

Section: Open Set Recognitionmentioning

confidence: 99%

Driver anomalous driving behavior detection based on supervised contrastive learning

Li,

Duan

2024

Fourth International Conference on Computer Vision and Data Mining (ICCVDM 2023)

View full text Add to dashboard Cite

In the context of vehicle operation, detecting and identifying abnormal driver behaviors is challenging due to the complex in-car environment, changing lighting, and varied driver postures. Our approach, utilizing supervised contrastive learning, categorizes driver behaviors as normal or abnormal. We employ depth images from the driver's front and above to address environmental complexities and improve accuracy. Our enhanced 3D-MobileNetV2architecture achieves impressive results on the DAD dataset test set, with a 94.18% accuracy rate and a 0.962AUC, validating the effectiveness of our method in driver anomaly detection.

show abstract

Open-Set Classification for Signal Diagnosis of Machinery Sensor in Industrial Environment

Cited by 9 publications

References 27 publications

Artificial Intelligence Methods Applied to Catalytic Cracking Processes

Artificial Intelligence Methods Applied to Catalytic Cracking Processes

Discriminative Angle Feature Learning for Open-Set Deep Fault Classification

Driver anomalous driving behavior detection based on supervised contrastive learning

Contact Info

Product

Resources

About