Unsupervised Gear Fault Diagnosis Using Raw Vibration Signal Based on Deep Learning

Li, Xueyi; Liu, Zhendong; Qu, Yongzhi; He, David

doi:10.1109/phm-chongqing.2018.00182

Cited by 8 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1. nivic: Gear Pitting Fault Diagnosis using Domain Generalizations and Specialization Techniques (Chu et al, 2023) 2. Thumper: Interpolate and Extrapolate Machine Learning Models using An Unsupervised Method (Liu, 2023) 3.…”

Section: Discussionmentioning

confidence: 99%

An Introduction to 2023 PHM Data Challenge: The Elephant in the Room and an Analysis of Competition Results

Qu,

William,

Saxena

et al. 2023

PHM_CONF

View full text Add to dashboard Cite

The trend in diagnostics and prognostics for PHM is shifting toward explainable data-driven models. However, complex engineered systems are typically challenging to develop entirely explainable models for, whether they are grounded in physics or data-driven techniques. Consequently, the development of machine learning models, including hybrid variants capable of both interpolation and extrapolation, holds significant promise for enhancing the practicality of system simulation, analysis, modeling, and control in industry. The primary objective of this data challenge is to encourage contributions that expand the scope of model generalization beyond the training domain. The second aim of this data challenge is to quantify model uncertainty and methods to incorporate it into predictions. For most PHM tasks, clear guidance of the required action is ideal. To issue a definitive guidance to end users, it is useful to quantify uncertainty for the whole model. This data challenge addresses both estimation and uncertainty.

show abstract

Section: Discussionmentioning

confidence: 99%

An Introduction to 2023 PHM Data Challenge: The Elephant in the Room and an Analysis of Competition Results

Qu,

William,

Saxena

et al. 2023

PHM_CONF

View full text Add to dashboard Cite

show abstract

“…In [183] AE based models can be naturally integrated with kinds of classifiers to tackle the fault diagnosis problems. A most commonly used classifier is "softmax" [185][186][187][188][189]. For example, Shao et al [185] design a new AE with a maximum correntropy based loss function, which can eliminate the impact of background noise in the raw rotating machinery signals.…”

Section: A Auto-encoder (Ae)mentioning

confidence: 99%

A Survey of Predictive Maintenance: Systems, Purposes and Approaches

Ran,

Zhou,

Lin

et al. 2019

Preprint

View full text Add to dashboard Cite

This paper provides a comprehensive literature review on Predictive Maintenance (PdM) with emphasis on system architectures, purposes and approaches. In industry, any outages and unplanned downtime of machines or systems would degrade or interrupt a company's core business, potentially resulting in significant penalties and unmeasurable reputation loss. Existing traditional maintenance approaches suffer from some assumptions and limits, such as high prevent/repair costs, inadequate or inaccurate mathematical degradation processes and manual feature extraction. With the trend of smart manufacturing and development of Internet of Things (IoT), data mining and Artificial Intelligence (AI), etc., PdM is proposed as a novel type of maintenance paradigm to perform maintenances only after the analytical models predict certain failures or degradations. In this survey, we first provide a high-level view of the PdM system architectures including the Open System Architecture for Condition Based Monitoring (OSA-CBM), cloud-enhanced PdM system and PdM 4.0, etc. Then, we make clear the specific maintenance purposes/objectives, which mainly comprise cost minimization, availability/reliability maximization and multiobjective optimization. Furthermore, we provide a review of the existing approaches for fault diagnosis and prognosis in PdM systems that include three major subcategories: knowledge based, traditional Machine Learning (ML) based and DL based approaches. We make a brief review on the knowledge based and traditional ML based approaches applied in diverse industrial systems or components with a complete list of references, while providing a comprehensive review of DL based approaches. Finally, important future research directions are introduced.

show abstract

“…This method was experimented on the real vibration signals by addressing various fault classes, under various running circumstances of velocity and load. [13].The paper suggested ADSAE method for the diagnosis of gear wearing fault by comparatively original vibration data. The technique in framed on the wearing fault diagnosis by means of innovatively combining with the data augmentation and deep sparse algorithm.…”

Section: Related Workmentioning

confidence: 99%

Fault Monitoring System for the Multistage Gear Box Based on MSTFT and GFLA Algorithm

Ghulanavar*,

Dama

2020

IJITEE

View full text Add to dashboard Cite

Gearbox functions as a significant transmission module in the mechanical devices in spite of its failure prone nature and hence there exists a need for the diagnosing the gearbox faults with an optimized solution and new methods should be engaged for improving the effectiveness, accuracy, reliability and few other such parameters. These attempts could meet the growing requirements for the condition monitoring in the detection of gear faults. The feature selection process is a notable process in the machine learning to achieve good performance in the diagnostic process. This framework builds up an innovative structure for fault diagnosis in the gearbox system. Six vibrating signals which are healthy gear signal, fault gear signal, healthy gear signal affected by noise, faulty gear signal affected by noise, distributed fault signal, and local fault signal have been generated with the prescribed dataset and the feature extraction was done by employing the Modified Short-Time Fourier Transform on the basis of Blackman window. This step was followed by selection of the features by using the combination of Genetic algorithm and Frog Leaping algorithm that is termed as GFLA.This novelty approach enhances the initialization process thereby enabling for the calculation of accurate best score calculation. The classification method is performed Support points on the basis of neural network. Finally the performance analysis with respect to the existing methodologies proved the efficiency in detecting the fault of the proposed framework.

show abstract

Unsupervised Gear Fault Diagnosis Using Raw Vibration Signal Based on Deep Learning

Cited by 8 publications

References 12 publications

An Introduction to 2023 PHM Data Challenge: The Elephant in the Room and an Analysis of Competition Results

An Introduction to 2023 PHM Data Challenge: The Elephant in the Room and an Analysis of Competition Results

A Survey of Predictive Maintenance: Systems, Purposes and Approaches

Fault Monitoring System for the Multistage Gear Box Based on MSTFT and GFLA Algorithm

Contact Info

Product

Resources

About