TCN-MBMAResNet: a novel fault diagnosis method for small marine rolling bearings based on time convolutional neural network in tandem with multi-branch residual network
- 21 January 2025
- journal article
- research article
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (2) , 026212
Abstract
Centrifugal pumps are key components of marine systems, and the health of their internal rolling bearings is critical for the normal operation of ships. In small ship replenishment systems, the rolling bearings of centrifugal pumps often have short failure times, making it difficult to gather balanced failure data. This paper addresses the challenges in extracting fault features from centrifugal pump bearings in ship water replenishment systems and the low accuracy of fault identification caused by unbalanced data samples. A fault diagnosis method is proposed that combines a time convolutional neural network (TCN) with multi-branch mixed attention residual networks (MBMAResNet). This paper introduces TCN to capture dependencies in long time series and optimize the feature distribution of raw data. The captured multi-channel 1-D feature sequences are converted into 2D feature maps to provide spatially correlated features for the designed MBMAResNet. Multiple single path fusion residual blocks with different scales are designed in the MBMAResNet to further extract effective fault features from the unbalanced samples, and a feature fusion structure is utilized for further feature enhancement. Additionally, improved convolutional block attention modules are integrated into the network to increase the significance of valid channels and spatial locations. Experiments on an unbalanced public dataset and a private centrifugal pump faulty bearing dataset achieved diagnostic accuracies of 99.71% and 98.50%, respectively, demonstrating that the proposed method offers higher accuracy and generalizability compared to other methods.Keywords
Funding Information
- National Natural Science Foundation of China (62276117)
This publication has 36 references indexed in Scilit:
- Triplet attention-enhanced residual tree-inspired decision network: A hierarchical fault diagnosis model for unbalanced bearing datasetsAdvanced Engineering Informatics, 2023
- ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and BeyondInternational Journal of Computer Vision, 2023
- A power information guided-variational mode decomposition (PIVMD) and its application to fault diagnosis of rolling bearingDigital Signal Processing, 2022
- A wind turbine bearing fault diagnosis method based on fused depth features in time–frequency domainEnergy Reports, 2022
- Enhanced dictionary learning based sparse classification approach with applications to planetary bearing fault diagnosisApplied Acoustics, 2022
- An efficient diagnosis approach for bearing faults using sound quality metricsApplied Acoustics, 2022
- Experimental IoT study on fault detection and preventive apparatus using Node-RED ship's main engine cooling water pump motorEngineering Failure Analysis, 2022
- An improved image enhancement framework based on multiple attention mechanismDisplays, 2021
- Modified multiscale weighted permutation entropy and optimized support vector machine method for rolling bearing fault diagnosis with complex signalsISA Transactions, 2021
- Automated bearing fault diagnosis scheme using 2D representation of wavelet packet transform and deep convolutional neural networkComputers in Industry, 2019