Research on Probabilistic Contrastive Learning and Quadratic Convolutional Neural Network for Intelligent Diagnosis of Long-Tailed Bearing Data
Open Access
- 9 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-15
Abstract
Deep learning methods have demonstrated impressive effectiveness in diagnosing bearing faults. Nevertheless, their performance tends to decline significantly in the presence of long-tailed distributions, where certain fault types are underrepresented, which is common in industrial environments where fault occurrences are rare. To address the challenges posed by long-tailed data in fault diagnosis, this paper proposes the Probabilistic Contrastive Quadratic Network (PCQNet), a novel framework designed to enhance the diagnostic capabilities of neural networks under class imbalance conditions. PCQNet consists of three core components: a quadratic convolutional residual network that strengthens feature representations through higher-order interactions; a Probabilistic Contrastive Loss (PCL) that models class features using the von Mises-Fisher (vMF) distribution, combining class expectations and prior probabilities to adaptively balance the contributions of each class, effectively mitigating long-tail bias; and a logit-adjusted cross-entropy loss that improves the discrimination ability for minority classes while enhancing classification fairness. The parabolic decay formula dynamically adjusts the dominance of these two loss functions during training, ensuring the model achieves both effective feature learning and accurate classification.The effectiveness of PCQNet is validated on one public dataset and two self-constructed datasets, demonstrating its superior performance in handling long-tailed data. Analysis of the attention mechanism derived from quadratic neurons further explains the excellent feature extraction capability of the quadratic network. Building on this analysis, ablation studies further verify the independent contributions and synergistic effects of each module, confirming their critical roles in improving diagnostic performance.Keywords
Funding Information
- S&T Program of Hebei (22321902D)
- Xingdian Talent Support Program (YNWR-QNBJ-2018-349)
This publication has 32 references indexed in Scilit:
- Recognition of rolling bearing life status based on GI performance degradation indicator and AGNCNMeasurement, 2025
- A novel adaptive gating neurons model with physical features weighted for bearing fault diagnosis under strong noiseEngineering Applications of Artificial Intelligence, 2025
- Information guided attention network for bearing remaining useful life prediction adaptive to working conditions and fault modesEngineering Applications of Artificial Intelligence, 2025
- Imbalance fault diagnosis under long-tailed distribution: Challenges, solutions and prospectsKnowledge-Based Systems, 2022
- A class-aware supervised contrastive learning framework for imbalanced fault diagnosisKnowledge-Based Systems, 2022
- Self-supervised pretraining via contrast learning for intelligent incipient fault detection of bearingsReliability Engineering & System Safety, 2022
- An improved ensemble fusion autoencoder model for fault diagnosis from imbalanced and incomplete dataControl Engineering Practice, 2020
- Universal approximation with quadratic deep networksNeural Networks, 2020
- Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark studyMechanical Systems and Signal Processing, 2015
- Rolling element bearing diagnostics—A tutorialMechanical Systems and Signal Processing, 2011