A Weight Multinet Architecture for Bearing Fault Classification Under Complex Speed Conditions

Ding, Xiaoxi; Lin, Lun; He, Dong; Wang, Liming; Huang, Wenbin; Shao, Yimin

doi:10.1109/tim.2020.3026461

Cited by 9 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the existing literature, signal decomposition is utilized through two approaches for feature extraction; each approach serves a distinct objective: 1) Extraction of highly discriminative features: In these methods, features are extracted from elementary modes resulting from the decomposition process. Accordingly, feature extraction methods can be generally grouped under four main categories: entropy-based [262], [263], [267], [273], [274], [283], energy-based [251], [257], [264], [265], spectral-based [44], [252], [266], [272], [275], [280], [282], [283], and statistical-based [247],…”

Section: Signal Decomposition-based Methodsmentioning

confidence: 99%

On the Intersection of Signal Processing and Machine Learning: A Use Case-Driven Analysis Approach

Aburakhia,

Shami,

Karagiannidis

2024

Preprint

View full text Add to dashboard Cite

Recent advancements in sensing, measurement, and computing technologies have significantly expanded the potential for signal-based applications, leveraging the synergy between signal processing and Machine Learning (ML) to improve both performance and reliability. This fusion represents a critical point in the evolution of signal-based systems, highlighting the need to bridge the existing knowledge gap between these two interdisciplinary fields. Despite many attempts in the existing literature to bridge this gap, most are limited to specific applications and focus mainly on feature extraction, often assuming extensive prior knowledge in signal processing. This assumption creates a significant obstacle for a wide range of readers. To address these challenges, this paper takes an integrated article approach. It begins with a detailed tutorial on the fundamentals of signal processing, providing the reader with the necessary background knowledge. Following this, it explores the key stages of a standard signal processing-based ML pipeline, offering an in-depth review of feature extraction techniques, their inherent challenges, and solutions. Differing from existing literature, this work offers an application-independent review and introduces a novel classification taxonomy for feature extraction techniques. Furthermore, it aims at linking theoretical concepts with practical applications, and demonstrates this through two specific use cases: a spectral-based method for condition monitoring of rolling bearings and a wavelet energy analysis for epilepsy detection using EEG signals. In addition to theoretical contributions, this work promotes a collaborative research culture by providing a public repository of relevant Python and MATLAB signal processing codes. This effort is intended to support collaborative research efforts and ensure the reproducibility of the results presented.

show abstract

Section: Signal Decomposition-based Methodsmentioning

confidence: 99%

On the Intersection of Signal Processing and Machine Learning: A Use Case-Driven Analysis Approach

Aburakhia,

Shami,

Karagiannidis

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The performance of ACNN is verified on gear dataset and bearing dataset. The gear dataset [24] came from Chongqing University, and the bearing dataset came from Case Western Reserve University (CWRU) [25].…”

Section: Experimental Verification and Analysismentioning

confidence: 99%

Rotating Machinery Fault Identification via Adaptive Convolutional Neural Network

et al. 2022

Self Cite

View full text Add to dashboard Cite

Rotating machinery plays an important role in transportation, petrochemical industry, industrial production, national defence equipment, and other fields. With the development of artificial intelligence, the equipment condition monitoring especially needs an intelligent fault identification method to solve the problem of high false alarm rate under complex working conditions. At present, intelligent recognition models mostly increase the complexity of the network to achieve the purpose of high recognition rate. This method often needs better hardware support and increases the operation time. Therefore, this paper proposes an adaptive convolutional neural network (ACNN) by combining ensemble learning and simple convolutional neural network (CNN). ACNN model consists of input layer, subnetwork unit, fusion unit, and output layer. The input of the model is one-dimensional (1D) vibration signal sample, and the subnetwork unit consists of several simple CNNs, and the fusion unit weights the output of the subnetwork units through the weight matrix. ACNN recognizes the self-adaptive of weight factors through the fusion unit. The adaptive performance and robustness of ACNN for sample recognition under variable working conditions are verified by gear and bearing experiments.

show abstract

“…Rolling-element bearings play vital roles in dynamic vibration performance, running stability, and service life of the whole machinery. It is of great significance to study the underlying dynamic characteristics of rolling-element bearing for mechanical maintenance, machine health monitoring, quality inspection, and design of rolling-element bearing [1]. Therefore, the accurate dynamic modeling of rolling-element bearings has attracted more and more attention in the field of the mechanical industry.…”

Section: Introductionmentioning

confidence: 99%

A Study on the Modeling Method of Cage Slip and Its Effects on the Vibration Response of Rolling-Element Bearing

Luo

Chen

et al. 2022

Energies

View full text Add to dashboard Cite

Rolling-element bearings play vital roles in the dynamic vibration performance of the whole machinery. Hence, accurate modeling and assessment of the rolling-element bearing are beneficial for the well understanding of the vibration response of rolling-element bearing. However, cage slip is usually ignored in the traditional rolling-element bearing modeling methods, which has a direct influence on the rotating speed and friction force of the rolling elements. To settle the modeling problem of rolling-element bearing with cage slip, in this study, a nonlinear dynamic model with multiple degrees of freedom of the roller bearing is established. The cage slip, the motion of each roller, nonlinear contact, damping, and friction are taken into consideration. With the proposed method, a nonlinear traction model is presented to describe the friction forces induced by cage slip. Furthermore, both the friction force acting on rolling elements and the effects of cage slip on the vibration response are investigated based on the established model. Some comparisons between the proposed modeling method with cage slip and the classical method without cage slip are made. The results show that the friction force applied to the balls increases with the cage slip, friction coefficient, rotational speed, and radial load. A slight cage slip could be beneficial for reducing the vibration energy of rolling-element bearing; however, it will result in more friction loss and impact components.

show abstract

A Weight Multinet Architecture for Bearing Fault Classification Under Complex Speed Conditions

Cited by 9 publications

References 30 publications

On the Intersection of Signal Processing and Machine Learning: A Use Case-Driven Analysis Approach

On the Intersection of Signal Processing and Machine Learning: A Use Case-Driven Analysis Approach

Rotating Machinery Fault Identification via Adaptive Convolutional Neural Network

A Study on the Modeling Method of Cage Slip and Its Effects on the Vibration Response of Rolling-Element Bearing

Contact Info

Product

Resources

About