One-fault-shot learning for fault severity estimation of gears that addresses differences between simulation and experimental signals and transfer function effects

Matania, Omri; Bachar, Lior; Khemani, Varun; Das, Diganta Bhusan; Azarian, Michael H.; Bortman, Jacob

doi:10.1016/j.aei.2023.101945

Cited by 13 publications

(7 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The next section will explain how these methods can be used to detect faults in bearings and gears. All the data used in the tutorial are based on a bearing experiment with an outer race spall from the publicly available Paderborn University bearing dataset [ 29 ], a gear experiment with tooth breakage provided in references [ 30 ], a simulated gear signal generated from the dynamic model described in reference [ 16 ], and artificial white noise. The data are available via the link provided in reference [ 2 ].…”

Section: Basic Methods and Principlesmentioning

confidence: 99%

“…The two subsequent goals of condition-based maintenance are fault severity estimation and remaining useful life estimation. There are methods for achieving these goals, but they often require historical data on faults [ 16 ], making them less relevant to critical rotating systems such as helicopters. Furthermore, the algorithms for these goals are not based solely on signal processing but on statistics and machine learning.…”

Section: General Framework: Goal Fault Types and Sensorsmentioning

confidence: 99%

“…For fault classification, these approaches prove highly valuable when sufficient data, including faulty data, are available. However, they are less relevant in cases where faulty data are rare [ 16 , 28 ].…”

Section: General Framework: Goal Fault Types and Sensorsmentioning

confidence: 99%

See 2 more Smart Citations

Signal Processing for the Condition-Based Maintenance of Rotating Machines via Vibration Analysis: A Tutorial

Matania,

Bachar,

Bechhoefer

et al. 2024

Sensors

Self Cite

View full text Add to dashboard Cite

One of the common methods for implementing the condition-based maintenance of rotating machinery is vibration analysis. This tutorial describes some of the important signal processing methods existing in the field, which are based on a profound understanding of the component’s physical behavior. Furthermore, this tutorial provides Python and MATLAB code examples to demonstrate these methods alongside explanatory videos. The goal of this article is to serve as a practical tutorial, enabling interested individuals with a background in signal processing to quickly learn the important principles of condition-based maintenance of rotating machinery using vibration analysis.

show abstract

Section: Basic Methods and Principlesmentioning

confidence: 99%

Section: General Framework: Goal Fault Types and Sensorsmentioning

confidence: 99%

See 1 more Smart Citation

Signal Processing for the Condition-Based Maintenance of Rotating Machines via Vibration Analysis: A Tutorial

Matania,

Bachar,

Bechhoefer

et al. 2024

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, the current techniques do not enable the estimation of fault severity, and the remaining time until immediate maintenance action should be taken. While various machine learning approaches exist for these tasks, they are not applicable to critical rotating machines such as helicopters, where faulty data are not available during the training phase [ 23 ].…”

Section: Introductionmentioning

confidence: 99%

Digital Twin of a Gear Root Crack Prognosis

Matania,

Bechhoefer,

Bortman

2023

Sensors

Self Cite

View full text Add to dashboard Cite

Digital twins play a significant role in Industry 4.0, offering the potential to revolutionize machinery maintenance. In this paper, we introduce a new digital twin designed to address the open problem of predicting gear root crack propagation. This digital twin uses signal processing and model fitting to continuously monitor the condition of the root crack and successfully estimate the remaining time until immediate maintenance is required for the physical asset. The functionality of this new digital twin is demonstrated through the experimental data obtained from a planetary gear, where comparisons are made between the actual and estimated severity of the fault, as well as the remaining time until maintenance. It is shown that the digital twin addresses the open problem of predicting gear root crack propagation.

show abstract

“…One possible solution is to use machine-learning algorithms to enhance the accuracy of mathematical models using sensor data 28 . These algorithms can address the differences between simulation and reality 29 , 30 and, hence, provide DT improvements.…”

Section: Introductionmentioning

confidence: 99%

Development of an Operational Digital Twin of a Locomotive Parking Brake for Fault Diagnosis

Davidyan,

Bortman,

Kenett

2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

In recent years, a growing role in digital technologies has been filled by model-based digital twinning. A digital twin produces a one-to-one mapping of a physical structure, operating in the digital domain. Combined with sensor technology and analytics, a digital twin can provide enhanced monitoring, diagnostic, and optimization capabilities. This research harnesses the significant capabilities of digital twining for the unmitigated challenge of fault type classification of a locomotive parking brake. We develop a digital twin of the locomotive parking brake and suggest a method for fault type classification based on the digital twin. The diagnostic ability of the method is demonstrated on a large experimental dataset.

show abstract

One-fault-shot learning for fault severity estimation of gears that addresses differences between simulation and experimental signals and transfer function effects

Cited by 13 publications

References 57 publications

Signal Processing for the Condition-Based Maintenance of Rotating Machines via Vibration Analysis: A Tutorial

Signal Processing for the Condition-Based Maintenance of Rotating Machines via Vibration Analysis: A Tutorial

Digital Twin of a Gear Root Crack Prognosis

Development of an Operational Digital Twin of a Locomotive Parking Brake for Fault Diagnosis

Contact Info

Product

Resources

About