Hypersphere-Guided Reciprocal Point Learning for Open-Set Industrial Process Fault Diagnosis
Open Access
- 16 November 2025
- Vol. 13 (11) , 3698
Abstract
Deep neural networks (DNNs) have achieved superior performance in diagnosing process faults, but they lack robustness when encountering novel fault types absent from training sets. Such unknown faults commonly appear in industrial settings, and conventional DNNs often misclassify them as one of the known fault types. To address this limitation, we formulate the concept of open-set fault diagnosis (OSFD), which seeks to distinguish unknown faults from known ones while correctly classifying the known faults. The primary challenge in OSFD lies in minimizing both the empirical classification risk associated with known faults and the open space risk without access to training data for unknown faults. In order to mitigate these risks, we introduce a novel approach called hypersphere-guided reciprocal point learning (SRPL). Specifically, SRPL preserves a DNN for feature extraction while constraining features to lie on a unit hypersphere. To reduce empirical classification risk, it applies an angular-margin penalty that explicitly increases intra-class compactness and inter-class separation for known faults on the hypersphere, thereby improving discriminability among known faults. Additionally, SRPL introduces reciprocal points on the hypersphere, with each point acting as a classifier by occupying the extra-class region associated with a particular known fault. The interactions among multiple reciprocal points, together with the deliberate synthesis of unknown fault features on the hypersphere, serve to lower open-space risk: the reciprocal-point interactions provide an indirect estimate of unknowns, and the synthesized unknowns provide a direct estimate, both of which enhance distinguishability between known and unknown faults. Extensive experimental results on the Tennessee Eastman process confirm the superiority of the proposed method compared to state-of-the-art OSR algorithms, e.g., an 82.32% AUROC score and a 71.50% OSFDR score.Keywords
Funding Information
- Guangdong Polytechnic Normal University (2024SDKYA015, 2023SDKYA010)
- Basic and Applied Basic Research Foundation of Guangdong Province (2023A1515240001)
- Heyuan Social Development Science and Technology Program (200)
- Key-Area Research and Development Program of Guangdong Province (2024B1111080003)
This publication has 34 references indexed in Scilit:
- Generalized Out-of-Distribution Detection: A SurveyInternational Journal of Computer Vision, 2024
- A novel deep metric learning model for imbalanced fault diagnosis and toward open-set classificationKnowledge-Based Systems, 2021
- Learning Open Set Network with Discriminative Reciprocal Points2020
- Semi-supervised process fault classification based on convolutional ladder network with local and global feature fusionComputers & Chemical Engineering, 2020
- Gaussian Discriminative Analysis aided GAN for imbalanced big data augmentation and fault classificationJournal of Process Control, 2020
- Classification-Reconstruction Learning for Open-Set Recognition2019
- Between-Class Learning for Image Classification2018
- Towards Open Set Deep Networks2016
- Fault detection in industrial processes using canonical variate analysis and dynamic principal component analysisChemometrics and Intelligent Laboratory Systems, 2000
- A plant-wide industrial process control problemComputers & Chemical Engineering, 1993