A Multi-Branch Convolution and Dynamic Weighting Method for Bearing Fault Diagnosis Based on Acoustic–Vibration Information Fusion

Rolling bearings, as critical components of rotating machinery, directly affect the reliability and efficiency of the system. Due to extended operation under high load, harsh environmental conditions, and continuous use, bearings become more susceptible to failure, leading to a higher likelihood of...

Full description

Saved in:
Bibliographic Details
Main Authors: Xianming Sun, Yuhang Yang, Changzheng Chen, Miao Tian, Shengnan Du, Zhengqi Wang
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Actuators
Subjects:
Online Access:https://www.mdpi.com/2076-0825/14/1/17
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832589447152009216
author Xianming Sun
Yuhang Yang
Changzheng Chen
Miao Tian
Shengnan Du
Zhengqi Wang
author_facet Xianming Sun
Yuhang Yang
Changzheng Chen
Miao Tian
Shengnan Du
Zhengqi Wang
author_sort Xianming Sun
collection DOAJ
description Rolling bearings, as critical components of rotating machinery, directly affect the reliability and efficiency of the system. Due to extended operation under high load, harsh environmental conditions, and continuous use, bearings become more susceptible to failure, leading to a higher likelihood of malfunction. To prevent sudden failures, reduce downtime, and optimize maintenance strategies, early and accurate diagnosis of rolling bearing faults is essential. Although existing methods have achieved certain success in processing acoustic and vibration signals, they still face challenges such as insufficient feature fusion, inflexible weight allocation, lack of effective feature selection mechanisms, and low computational efficiency. To address these challenges, we propose a dynamic weighted multimodal fault diagnosis model based on the fusion of acoustic and vibration information. This model aims to enhance feature fusion, dynamically adapt to signal characteristics, optimize feature selection, and reduce computational complexity. The model incorporates an adaptive fusion method based on a multi-branch convolutional structure, enabling unified processing of both acoustic and vibration signals. At the same time, a cross-modal dynamic weighted fusion mechanism is employed, allowing the real-time adjustment of weight distribution based on signal characteristics. By utilizing an attention mechanism for dynamic feature selection and weighting, the robustness of classification is further improved. Additionally, when processing acoustic signals, a depthwise separable convolutional network is used, effectively reducing computational complexity. Experimental results demonstrate that our method significantly outperforms other algorithms in terms of convergence speed and final performance. Additionally, the accuracy curve during training showed minimal fluctuation, reflecting higher robustness. The model achieved over 99% diagnostic accuracy under all signal-to-noise ratio (SNR) conditions, showcasing exceptional robustness and noise resistance in both noisy and high-SNR environments. Furthermore, its superiority across different data scales, especially in small-sample learning and stability, highlights its strong generalization capability.
format Article
id doaj-art-03bdfb3391f84b088dc38edb75819771
institution Kabale University
issn 2076-0825
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Actuators
spelling doaj-art-03bdfb3391f84b088dc38edb758197712025-01-24T13:15:11ZengMDPI AGActuators2076-08252025-01-011411710.3390/act14010017A Multi-Branch Convolution and Dynamic Weighting Method for Bearing Fault Diagnosis Based on Acoustic–Vibration Information FusionXianming Sun0Yuhang Yang1Changzheng Chen2Miao Tian3Shengnan Du4Zhengqi Wang5College of Mechanical and Automotive Engineering, Ningbo University of Technology, Ningbo 315336, ChinaSchool of Environmental and Chemical Engineering, Shenyang University of Technology, Shenyang 110870, ChinaSchool of Mechanical Engineering, Shenyang University of Technology, Shenyang 110870, ChinaCollege of Mechanical and Automotive Engineering, Ningbo University of Technology, Ningbo 315336, ChinaCollege of Mechanical and Automotive Engineering, Ningbo University of Technology, Ningbo 315336, ChinaSchool of Mechanical Engineering, Shenyang University of Technology, Shenyang 110870, ChinaRolling bearings, as critical components of rotating machinery, directly affect the reliability and efficiency of the system. Due to extended operation under high load, harsh environmental conditions, and continuous use, bearings become more susceptible to failure, leading to a higher likelihood of malfunction. To prevent sudden failures, reduce downtime, and optimize maintenance strategies, early and accurate diagnosis of rolling bearing faults is essential. Although existing methods have achieved certain success in processing acoustic and vibration signals, they still face challenges such as insufficient feature fusion, inflexible weight allocation, lack of effective feature selection mechanisms, and low computational efficiency. To address these challenges, we propose a dynamic weighted multimodal fault diagnosis model based on the fusion of acoustic and vibration information. This model aims to enhance feature fusion, dynamically adapt to signal characteristics, optimize feature selection, and reduce computational complexity. The model incorporates an adaptive fusion method based on a multi-branch convolutional structure, enabling unified processing of both acoustic and vibration signals. At the same time, a cross-modal dynamic weighted fusion mechanism is employed, allowing the real-time adjustment of weight distribution based on signal characteristics. By utilizing an attention mechanism for dynamic feature selection and weighting, the robustness of classification is further improved. Additionally, when processing acoustic signals, a depthwise separable convolutional network is used, effectively reducing computational complexity. Experimental results demonstrate that our method significantly outperforms other algorithms in terms of convergence speed and final performance. Additionally, the accuracy curve during training showed minimal fluctuation, reflecting higher robustness. The model achieved over 99% diagnostic accuracy under all signal-to-noise ratio (SNR) conditions, showcasing exceptional robustness and noise resistance in both noisy and high-SNR environments. Furthermore, its superiority across different data scales, especially in small-sample learning and stability, highlights its strong generalization capability.https://www.mdpi.com/2076-0825/14/1/17rolling bearingsdepthwise separableacoustic-vibration information fusionfault diagnosis
spellingShingle Xianming Sun
Yuhang Yang
Changzheng Chen
Miao Tian
Shengnan Du
Zhengqi Wang
A Multi-Branch Convolution and Dynamic Weighting Method for Bearing Fault Diagnosis Based on Acoustic–Vibration Information Fusion
Actuators
rolling bearings
depthwise separable
acoustic-vibration information fusion
fault diagnosis
title A Multi-Branch Convolution and Dynamic Weighting Method for Bearing Fault Diagnosis Based on Acoustic–Vibration Information Fusion
title_full A Multi-Branch Convolution and Dynamic Weighting Method for Bearing Fault Diagnosis Based on Acoustic–Vibration Information Fusion
title_fullStr A Multi-Branch Convolution and Dynamic Weighting Method for Bearing Fault Diagnosis Based on Acoustic–Vibration Information Fusion
title_full_unstemmed A Multi-Branch Convolution and Dynamic Weighting Method for Bearing Fault Diagnosis Based on Acoustic–Vibration Information Fusion
title_short A Multi-Branch Convolution and Dynamic Weighting Method for Bearing Fault Diagnosis Based on Acoustic–Vibration Information Fusion
title_sort multi branch convolution and dynamic weighting method for bearing fault diagnosis based on acoustic vibration information fusion
topic rolling bearings
depthwise separable
acoustic-vibration information fusion
fault diagnosis
url https://www.mdpi.com/2076-0825/14/1/17
work_keys_str_mv AT xianmingsun amultibranchconvolutionanddynamicweightingmethodforbearingfaultdiagnosisbasedonacousticvibrationinformationfusion
AT yuhangyang amultibranchconvolutionanddynamicweightingmethodforbearingfaultdiagnosisbasedonacousticvibrationinformationfusion
AT changzhengchen amultibranchconvolutionanddynamicweightingmethodforbearingfaultdiagnosisbasedonacousticvibrationinformationfusion
AT miaotian amultibranchconvolutionanddynamicweightingmethodforbearingfaultdiagnosisbasedonacousticvibrationinformationfusion
AT shengnandu amultibranchconvolutionanddynamicweightingmethodforbearingfaultdiagnosisbasedonacousticvibrationinformationfusion
AT zhengqiwang amultibranchconvolutionanddynamicweightingmethodforbearingfaultdiagnosisbasedonacousticvibrationinformationfusion
AT xianmingsun multibranchconvolutionanddynamicweightingmethodforbearingfaultdiagnosisbasedonacousticvibrationinformationfusion
AT yuhangyang multibranchconvolutionanddynamicweightingmethodforbearingfaultdiagnosisbasedonacousticvibrationinformationfusion
AT changzhengchen multibranchconvolutionanddynamicweightingmethodforbearingfaultdiagnosisbasedonacousticvibrationinformationfusion
AT miaotian multibranchconvolutionanddynamicweightingmethodforbearingfaultdiagnosisbasedonacousticvibrationinformationfusion
AT shengnandu multibranchconvolutionanddynamicweightingmethodforbearingfaultdiagnosisbasedonacousticvibrationinformationfusion
AT zhengqiwang multibranchconvolutionanddynamicweightingmethodforbearingfaultdiagnosisbasedonacousticvibrationinformationfusion