Dynamic Adaptive Multimodal Early Fault Diagnosis Model of Offshore Wind Turbine Bearings via Energy-Decoupled Learning and Bilateral Acoustic–Vibration Coordination
Authors:
- Zijian KangZKZijian Kang
- Shuang HanSHShuang Han
- Xianghong ChenXCXianghong Chen
- Xinjian BaiXBXinjian Bai
- Jiabao LiJLJiabao Li
- Jialin HanJHJialin Han
- Yang YiYYYang Yi
- Yuanchi MaYMYuanchi Ma
- Yongqian LiuYLYongqian Liu
Preprint
- 18 September 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
Offshore wind turbine bearings are susceptible to degradation, while restricted offshore accessibility can delay maintenance and increase failure-related costs, highlighting the need for early fault detection and diagnosis. However, early bearing faults produce weak and stage-dependent acoustic and vibration responses, limiting the generalization of models trained on developed faults. To address these issues, a dynamic adaptive multimodal framework based on energy-decoupled learning and acoustic-vibration coordination, DAMEC-Net, is proposed. First, a Dynamic Adaptive Rectangular Convolution Network dynamically predicts convolution kernel sizes according to local structures at different spatial locations in vibration time-frequency images, enhancing the extraction of multiscale weak fault features. Second, an Energy-Decoupled Learning Constraint introduces energy attenuation perturbations and enforces feature consistency across energy levels, promoting evolution-robust intrinsic representations. Finally, a Bilateral Complementary Feature Coordination module performs bidirectional interaction between global acoustic and vibration semantics with adaptive fusion, exploiting cross-modal complementarity while mitigating semantic shift. Trained on faulty samples and tested on developing samples, DAMEC-Net achieves accuracies of 96.13% and 100% on two public bearing datasets. Ablation and visualization results further verify the effectiveness of the proposed modules in improving early fault diagnosis and cross-stage generalization, supporting DAMEC-Net as a candidate algorithmic module for multimodal offshore drivetrain condition monitoring.Keywords
This publication has 12 references indexed in Scilit:
- A unified Cross-Modal adaptive contrastive learning framework for acoustic fault diagnosis of rolling bearing under limited & imbalanced dataMechanical Systems and Signal Processing, 2025
- Adaptive Rectangular Convolution for Remote Sensing Pansharpening2025
- Fault diagnosis of wind turbine pitch bearings via transfer learning and an improved residual networkMeasurement, 2025
- A Novel Wind Turbine Pitch Bearing Fault Diagnosis Using Signal Encoding and Attention Mechanism Dual-Channel Parallel Fusion NetworkIEEE Transactions on Instrumentation and Measurement, 2025
- Residual attention guided vision transformer with acoustic-vibration signal feature fusion for cross-domain fault diagnosisAdvanced Engineering Informatics, 2024
- Vibration, acoustic, temperature, and motor current dataset of rotating machine under varying operating conditions for fault diagnosisData in Brief, 2023
- PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern RecognitionIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2020
- Extraction of weak fault transients using variational mode decomposition for fault diagnosis of gearbox under varying speedEngineering Failure Analysis, 2020
- A study of the development of a condition-based maintenance system for an LNG FPSOOcean Engineering, 2018
- Deformable Convolutional Networks2017