Ball bearing fault detection via multi-sensor data fusion with accelerometer and microphone

Safizadeh, M S; Golmohammadi, A.

doi:10.1784/insi.2021.63.3.168

Cited by 7 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e algorithm for panoramic video multitarget tracking uses the RGB color space model, this algorithm applies a learning technique, the RGB component of the image generates alternative targets, combines weak classifiers into strong classifiers, and uses classifiers to locate grayscale blocks in the image to achieve tracking, and the classifiers are automatically updated online with strong robustness to changes such as illumination [24]. e panoramic video multitarget tracking algorithm with multifeature fusion creates histograms of multiple features of the tracked target, and experiments show that the algorithm can avoid the interference of complex backgrounds and has obvious advantages over single-feature tracking, which can adapt to more complex background scenes [25].…”

Section: Panoramic Video Multitarget Real-time Trackingmentioning

confidence: 99%

Real-Time Multitarget Tracking for Panoramic Video Based on Dual Neural Networks for Multisensor Information Fusion

Lin

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

A multitarget real-time tracking system for panoramic video with multisensor information fusion dual neural networks is studied and implemented by combining dual neural networks, fused geometric features, and deep learning-based target real-time tracking algorithms. The motion model of multisensor information fusion is analyzed, the dual neural network perturbation model is introduced, and the state variables of the system are determined. Combined with the data structure model of multisensor information fusion, a least-squares-based optimization function is constructed. In this optimization function, the image sensor is constructed as an observationally constrained residual term based on the pixel plane, the inertial measurement unit is constructed as an observationally constrained residual term based on the motion model, and the motion relationship between sensors is constructed as a motion-constrained residual term to derive a mathematical model for real-time multitarget tracking of panoramic video. The simulation experimental results show that the integrated position estimation accuracy of the multisensor information fusion dual neural network-based panoramic video multitarget real-time tracking fusion algorithm is 10.5% higher than that of the optimal distributed panoramic video multitarget fusion algorithm without feedback. The results of the simulation experiments show that the integrated position estimation accuracy of the multitarget real-time tracking fusion algorithm for panoramic video improves by 10.96%, and the integrated speed estimation accuracy improves by 6.32% compared with the optimal distributed multitarget fusion algorithm without feedback. The proposed panoramic video multitarget real-time tracking algorithm based on the dual neural network can effectively improve the target tracking accuracy of the model on degraded frames (motion blur, target occlusion, out-of-focus, etc.), and the stability of the algorithm for target location and category detection is effectively improved by multiframe feature fusion. The research in this paper provides better technical support and research theory for panoramic video multitarget real-time tracking.

show abstract

Section: Panoramic Video Multitarget Real-time Trackingmentioning

confidence: 99%

Real-Time Multitarget Tracking for Panoramic Video Based on Dual Neural Networks for Multisensor Information Fusion

Lin

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…The convective heat transfer coefficient between the outer bearing's seat surface and air can be calculated using (26):…”

Section: Dynamic Simulation Modelmentioning

confidence: 99%

“…In 2021, Safizadeh et al implemented information fusion for rolling bearings using an accelerometer and a microphone. In addition, they performed feature extraction by principal component analysis (PCA) and decision fusion using the K-nearest neighbor method in the classification module [26]. Li et al investigated rolling bearing information fusion using oil analysis data, microscopic debris analysis data, and vibration data.…”

Section: Introductionmentioning

confidence: 99%

Rolling Bearing Fault Diagnosis Based on Deep Learning and Autoencoder Information Fusion

Zhang

2021

Symmetry

View full text Add to dashboard Cite

The multisource information fusion technique is currently one of the common methods for rolling bearing fault diagnosis. However, the current research rarely fuses information from the data of different sensors. At the same time, the dispersion itself in the VAE method has asymmetric characteristics, which can enhance the robustness of the system. Therefore, in this paper, the information fusion method of the variational autoencoder (VAE) and random forest (RF) methods are targeted for subsequent lifetime evolution analysis. This fusion method achieves, for the first time, the simultaneous monitoring of acceleration signals, weak magnetic signals and temperature signals of rolling bearings, thus improving the fault diagnosis capability and laying the foundation for subsequent life evolution analysis and the study of the fault–slip correlation. Drawing on the experimental procedure of the CWRU’s rolling bearing dataset, the proposed VAERF technique was evaluated by conducting inner ring fault diagnosis experiments on the experimental platform of the self-research project. The proposed method exhibits the best performance compared to other point-to-point algorithms, achieving a classification rate of 98.19%. The comparison results further demonstrate that the deep learning fusion of weak magnetic and vibration signals can improve the fault diagnosis of rolling bearings.

show abstract

“…For example, References [21,22] worked on fault detection specifically for Markov jump system. In addition, much focus has been laid on data fusion from a variety of instruments for fault detection [23][24][25][26].…”

Section: Introductionmentioning

confidence: 99%

Robust Detection of Minute Faults in Uncertain Systems Using Energy Activity

2021

View full text Add to dashboard Cite

Fault detection is one of the key steps in Fault Detection and Isolation (FDI) and, therefore, critical for subsequent prognosis or implementation of Fault Tolerant Control (FTC). It is, therefore, advisable to utilize detection algorithms which are quick and can detect the smallest faults. Model-based detection methods satisfy both these criteria and should be preferred. However, a big limitation for model-based methods is that they require the accurate value of the component parameters, which is difficult to obtain in real situations. This limits the accuracy of model-based methods. This paper proposes a new method for fault detection using Energy Activity (EA) which can detect minute levels of fault in systems with high component uncertainty. Different forms of EA are developed for use as an FDI metric. The proposed forms are simulated using a two-tank system under various types of faults. The results are compared with each other and with the traditional model-based FDI method using Analytical Redundancy Relations (ARRs). The simulations are performed considering model uncertainties to check the inherent performance of the methods. From initial simulations, it is established that the integral form of EA is most suited for fault detection. The integral for if EA is then tested using a real two-tank system considering both the model and measurement uncertainties.

show abstract

Ball bearing fault detection via multi-sensor data fusion with accelerometer and microphone

Cited by 7 publications

References 0 publications

Real-Time Multitarget Tracking for Panoramic Video Based on Dual Neural Networks for Multisensor Information Fusion

Real-Time Multitarget Tracking for Panoramic Video Based on Dual Neural Networks for Multisensor Information Fusion

Rolling Bearing Fault Diagnosis Based on Deep Learning and Autoencoder Information Fusion

Robust Detection of Minute Faults in Uncertain Systems Using Energy Activity

Contact Info

Product

Resources

About