A convolutional multisensor fusion fault diagnosis framework based on multidimensional distance matrix for rotating machinery DOI
Tianzhuang Yu, Zeyu Jiang, Zhaohui Ren

et al.

Structural Health Monitoring, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 25, 2024

Intelligent fault diagnosis based on multisensor data fusion techniques and two-dimensional convolutional neural network (CNN) has been widely developed achieved numerous excellent results. Existing studies usually develop multi-input models to facilitate fusion, lacking schemes for realizing the in process of data-to-image. Traditional methods that convert signals grayscale maps concatenate them into RGB images lose temporal correlation are susceptible interference. Besides, few integrated favorable features at different stages CNN diagnosis, which limits diagnostic performance. To this end, article proposes a multisource signal-to-image method called multidimensional distance matrix (MDM) multi-scale adaptive feature (MAFFCNN). First, MDM emphasize interrelationships between points moments time series preserve correlation. Then, conv block MAFFCNN can extract scales image, its attention branch better aggregate location information. Also, introduces efficient cross-spatial learning generate learnable weights importance achieve fusion. Finally, above is validated using established gear dataset public bearing dataset. The experimental results demonstrate effectiveness proposed their robustness complex environments.

Language: Английский

An improved D-S evidence fusion algorithm for sub-area collaborative guided wave damage monitoring of large-scale structures DOI

Yuelin Du,

Hongmei Ning,

Yehai Li

et al.

Ultrasonics, Journal Year: 2025, Volume and Issue: unknown, P. 107644 - 107644

Published: March 1, 2025

Language: Английский

Citations

0
Semi-supervised Feature Contrast Incremental Learning Framework for Bearing Fault Diagnosis with Limited Labeled Samples DOI
X. Tao, Changqing Shen, Lin Li

et al.

Applied Soft Computing, Journal Year: 2025, Volume and Issue: unknown, P. 113172 - 113172

Published: April 1, 2025

Language: Английский

Citations

0
A feature extension and reconstruction method with incremental learning capabilities under limited samples for intelligent diagnosis DOI
Kui Hu, Zhihao Bi, Qingbo He

et al.

Advanced Engineering Informatics, Journal Year: 2024, Volume and Issue: 62, P. 102796 - 102796

Published: Sept. 2, 2024

Language: Английский

Citations

2
A partial domain adaptation broad learning system for machinery fault diagnosis DOI
Aisong Qin, Qin Hu, Qinghua Zhang

et al.

Measurement, Journal Year: 2024, Volume and Issue: 243, P. 116437 - 116437

Published: Dec. 9, 2024

Language: Английский

Citations

2
Weak Fault Feature Extraction of the Rotating Machinery Using Flexible Analytic Wavelet Transform and Nonlinear Quantum Permutation Entropy DOI Open Access
Lili Bai, Wenhui Li, He Ren

et al.

Computers, materials & continua/Computers, materials & continua (Print), Journal Year: 2024, Volume and Issue: 79(3), P. 4513 - 4531

Published: Jan. 1, 2024

Addressing the challenges posed by nonlinear and non-stationary vibrations in rotating machinery, where weak fault characteristic signals hinder accurate state representation, we propose a novel feature extraction method that combines Flexible Analytic Wavelet Transform (FAWT) with Nonlinear Quantum Permutation Entropy.FAWT, leveraging fractional orders arbitrary scaling translation factors, exhibits superior translational invariance adjustable fundamental oscillatory characteristics.This flexibility enables FAWT to provide well-suited wavelet shapes, effectively matching subtle components avoiding performance degradation associated fixed frequency partitioning low-oscillation bases detecting faults.In our approach, gearbox vibration undergo obtain sub-bands.Quantum theory is then introduced into permutation entropy Entropy, more accurately characterizes operational of simulation signals.The quantum extracted from sub-bands utilized characterize operating machinery.A comprehensive analysis rolling bearings gearboxes validates feasibility proposed method.Comparative assessments parameters derived traditional entropy, sample transform (WT), empirical mode decomposition (EMD) underscore effectiveness this approach detection classification for machinery.

Language: Английский

Citations

1
The application and challenges of spectral and image two-modal fusion techniques in coal gangue recognition DOI
Xiaoyu Li, Rui Xia, Juanli Li

et al.

International Journal of Coal Preparation and Utilization, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 31

Published: Sept. 13, 2024

Language: Английский

Citations

0
Fault diagnosis of rolling bearings driven by multi-channel data fusion and feature fusion under time-varying speed conditions DOI
Zonghao Jiao, Zhongwei Zhang, Y F Li

et al.

Measurement Science and Technology, Journal Year: 2024, Volume and Issue: 36(1), P. 015125 - 015125

Published: Nov. 13, 2024

Abstract Bearings, as the core component for power transmission, are crucial in ensuring safe and reliable operation of equipment. However, fault information contained a single-channel vibration signal is inherently limited. Additionally, under time-varying speed conditions, features prone to drift, cross-domain diagnostic performance most traditional domain adaptation (DA) models may drop dramatically. To solve above problems enhance ability DA extracting invariant features, this paper introduces Multi-channel data fusion Attention-guided Multi-feature Fusion-driven Center-aligned Network (MAMC). Initially, multi-channel time-frequency strategy based on wavelet transform constructed achieve comprehensive data, thereby obtaining richer feature representations. Subsequently, multi-branch network, integrated with an attention mechanism, devised capture significant across various dimensions scales, resulting more representative features. Finally, novel Center-Aligned Domain Adaptation method (CADA) proposed adversarial methods center loss. By minimizing distance between deep trainable common class centers, issue shift effectively alleviated, conditions improved. The experimental results indicate that MAMC exhibits superior both bearing datasets promising approach intelligent diagnosis.

Language: Английский

Citations

0
A multi-sensor fused incremental detection model for blade crack with cross-attention mechanism and Dempster-Shafer evidence theory DOI
Tianchi Ma, Yuguang Fu

Advanced Engineering Informatics, Journal Year: 2024, Volume and Issue: 62, P. 102952 - 102952

Published: Oct. 1, 2024

Language: Английский

Citations

0
A convolutional multisensor fusion fault diagnosis framework based on multidimensional distance matrix for rotating machinery DOI
Tianzhuang Yu, Zeyu Jiang, Zhaohui Ren

et al.

Structural Health Monitoring, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 25, 2024

Intelligent fault diagnosis based on multisensor data fusion techniques and two-dimensional convolutional neural network (CNN) has been widely developed achieved numerous excellent results. Existing studies usually develop multi-input models to facilitate fusion, lacking schemes for realizing the in process of data-to-image. Traditional methods that convert signals grayscale maps concatenate them into RGB images lose temporal correlation are susceptible interference. Besides, few integrated favorable features at different stages CNN diagnosis, which limits diagnostic performance. To this end, article proposes a multisource signal-to-image method called multidimensional distance matrix (MDM) multi-scale adaptive feature (MAFFCNN). First, MDM emphasize interrelationships between points moments time series preserve correlation. Then, conv block MAFFCNN can extract scales image, its attention branch better aggregate location information. Also, introduces efficient cross-spatial learning generate learnable weights importance achieve fusion. Finally, above is validated using established gear dataset public bearing dataset. The experimental results demonstrate effectiveness proposed their robustness complex environments.

Language: Английский

Citations

0