A dual-imaging framework for multi-scale measurements of fatigue crack evolution in metallic materials

Dharmadhikari, Susheel; Keller, Eric; Ray, Asok; Basak, Amrita

doi:10.1016/j.ijfatigue.2020.105922

Cited by 8 publications

(11 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 1A shows the design of the specimen with the V‐notch. The one‐sided notch design, which conforms to the ASTM standard E466, 30 imposes a stress concentration near its base thus allowing controlled initiation of fatigue cracks 29,31 . The notch geometries are designed in Solidworks to achieve a stress concentration of 7.1.…”

Section: Experimental Methodsmentioning

confidence: 99%

“…The onesided notch design, which conforms to the ASTM standard E466, 30 imposes a stress concentration near its base thus allowing controlled initiation of fatigue cracks. 29,31 The notch geometries are designed in Solidworks to achieve a stress concentration of 7.1. Waterjet machining is used to manufacture specimens from sheets.…”

Section: Specimen Designmentioning

confidence: 99%

“…This figure is reprinted with permission from Dharmadhikari et al 27 The confocal microscope is oriented at the notch's base and focuses on capturing the initiation of fine crack. 29 The digital microscope is oriented at the specimen's side and focuses on capturing larger cracks. An automated routine is set up in the MTS controller to stop every 500 cycles at the maximum load and allows the microscopes to take images.…”

Section: Fatigue Test Apparatusmentioning

confidence: 99%

“…Moreover, the experimental setup used in the study is aided by a high-resolution confocal microscope and a digital microscope that can detect damage in the short and long crack regimes, respectively. 29 Consequently, four features, namely, average displacement, material stiffness, energy dissipation rate, and cumulative energy dissipation, are derived from the corresponding global force and displacement data. They are further analyzed pairwise for their capability of fatigue damage detection by using a random forest classifier.…”

Section: Introductionmentioning

confidence: 99%

“…These two sensors are readily available as a part of the testing setup and, therefore, need no additional preparations unlike strain gauges or ultrasonics. Moreover, the experimental setup used in the study is aided by a high‐resolution confocal microscope and a digital microscope that can detect damage in the short and long crack regimes, respectively 29 . Consequently, four features, namely, average displacement, material stiffness, energy dissipation rate, and cumulative energy dissipation, are derived from the corresponding global force and displacement data.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A random forest‐based fatigue damage classification framework using global loading and displacement information

Lee

Dharmadhikari

Basak

2023

Fatigue Fract Eng Mat Struct

Self Cite

View full text Add to dashboard Cite

The article presents a random forest‐based damage classification methodology built upon the force and displacement data obtained via fatigue testing of Al7075‐T6 specimens. Four features, namely, average displacement (D), material stiffness (ST), energy dissipation rate (EDR), and cumulative energy dissipation (CED), are defined from the collected data. These features are classified into healthy and cracked states based on the information obtained from a high‐resolution confocal microscope and a digital microscope. Random forest‐based classifiers are, thereafter, trained and tested using the individual as well as different combinations of the four features. The results reveal that, when used individually, CED shows the best accuracy of 80% in detecting a fatigue crack. When two or more pairs of features are used, the accuracy increases significantly to beyond 95%. CED is observed to be the most important feature for developing efficient classifiers for fatigue crack detection. The results demonstrate that the random forest classifier is a viable option to accurately detect fatigue damage based on the four features using only global information.

show abstract

Section: Experimental Methodsmentioning

confidence: 99%

Section: Specimen Designmentioning

confidence: 99%