Damage Detection in Composite Materials Using Tap Test Technique and Neural Networks

Queiroz, João C. S.; Santos, Ygor T. B.; Silva, Ivan C. da; Farias, Cláudia T. T.

doi:10.1007/s10921-021-00759-9

Cited by 8 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, they use BPNN to realize automatic examining of glass bottles. Queiroz [16] detected polymeric resin by analysis acceleration signal and signal collected by microphone, and compared different time and frequency domain of different kinds of samples, they extract the peak of time domain and width of signal, peak frequency point of spectrum as the input of BPNN, and compare this result with the result of thermography, experiment proved the effectiveness of this method. Yu et al [17] applied improved grey clustering, they considered the whole difference of time series to make grey clustering more accurate, and they proved their method is effective.…”

Section: Introductionmentioning

confidence: 96%

Nondestructive Detection of Ceramic Products Based on Tapping Sound Signal Feature Recogition

Liu

Jiang

Qiao

2021

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Recent studies on the test of ceramic non-destructive testing are mainly based on high cost technologies, image processing and so on, these method possesses some drawback of low efficiency, high cost and so on. What’s more, detecting whether the ceramic products by human through listening to sound of tapping is also effectless. This paper proposed a non-destructive method for ceramic products to solve this problem. This non-destructive method consists of a tapping device and a signal processing module. The tapping device will be applied to generate the tapping sound signal and the signal processing system will be applied to analysis signal. After the process of signal analysis, sample length and peak of spectrum 2 parameters is extracted, then use these parameters to train SVM, the results will be compared with BP neural network (BPNN). The result of experiment shows that SVM with different kernels of linear, poly, rbf, sigmoid respectively reach the accuracy of 96.29%, 96.29%, 46.29%, 93.82%, while BPNN reaches the accuracy of 93.21%. This result proves that SVM can effectively complete the task of identifying defective ceramics, and its performance is better than BPNN.

show abstract

Section: Introductionmentioning

confidence: 96%

Nondestructive Detection of Ceramic Products Based on Tapping Sound Signal Feature Recogition

Liu

Jiang

Qiao

2021

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…The microphone maps revealed a greater defective area than the accelerometer. The capabilities and limitations of the tap test method was investigated by using numerical simulations to simulate and analyse the dynamic response of composite structures [24]. The study also explored the effects of different factors, such as the size and location of the impact, on the results of the tap test.…”

Section: Introductionmentioning

confidence: 99%

Bio-Inspired Robotic Tap Testing: An Innovative Approach for Nondestructive Testing of Wooden Structures

Nemati,

Dehghan-Niri

2024

Preprint

View full text Add to dashboard Cite

Tap testing is an effective way of characterizing material conditions and flaws in various materials, including wood. Given its versatility and widespread usage, wood requires thorough inspection to assess its quality, identify potential defects, and ensure the safety and durability of wooden structures across diverse applications. This technique has the advantage of being simple, efficient and inexpensive. The tap testing method, when performed manually, requires an operator to tap each point of the structure using a hand-held object (e.g., a coin or tap hammer). Consequently, the precision of this test is highly reliant on the inspector's subjective interpretation of the vibrational acoustic response. In order to overcome this drawback, a bio-inspired tap testing approach with augmented objectivity of signal analysis has been proposed. The pioneer tap testing is inspired by an animal named aye-aye recognized for its unique acoustic-based foraging behavior called 'tap-scanning' or 'percussive foraging'. The aye-aye's near-field versatile acoustic sensing capabilities enable it to locate small cavities beneath a tree bark with complex materials. Current work describes a quantitative and instrumented robotic tap test system that creates repeatable mechanical impacts using a biomimetic approach. Two specimens were utilized to validate the effectiveness of this biomimetic approach. One of the specimens possessed identical diameter flat bottom holes but of varying depths, and the other had different diameters at positions of the same thickness from the test surface. Biomimetic tap scanning was applied over the defect-free and damaged areas of the specimens utilizing the 3D printed animal pinna and head in the experimental setup. The findings indicated that the biological characteristics of the animal's external auditory organs including the pinna and ear cannel substantially enhanced the system's sensitivity in detecting artificial defects within wooden blocks. This enhancement was primarily attributed to a notable improvement in the signal-to-noise ratio. Moreover, the outcomes demonstrated that the head and external ear structure exerted a superior discriminating factor for damage detection compared to both the pinna with ear canal configuration and the microphone-only setup within the experimental framework. The underlying cause behind this heightened discriminating factor remains undetermined and warrants further investigation by the research team.

show abstract

“…Despite this, non-uniform response and propagation of surface vibration frequencies produces irregular results over the surface, highlighting machine learning methods as a necessary method to enhance signal interpretation. The Neural Network approach investigated by [13] found that the fusion of force/sound could provide a 100% true negative rate for non-defective regions, and a high true-positive rate for defects in fibreglass and Balsa wood samples. While this this is a demonstrably successful approach, there are two draw-backs of this approach for this use case.…”

Section: Introductionmentioning

confidence: 99%

Force and Sound Data Fusion for Enhanced Tap Testing Scanning of Composites

Poole

Hartley

2023

IEEE Access

View full text Add to dashboard Cite

Coin or hammer tap testing is one of the oldest methods of NDT inspection. Inspection techniques originated with human operators observing the tonal change of the audible sound produced by striking were later automated with use of mechanical instruments that measured surface stiffness from the contact time of the striker. Numerous applications have evolved from this technique, from predicting rock falls to defect detection and identification in composite structures. Since operator applied tap testing requires extensive training and knowledge of the part's structure to accurately locate defects, it is widely regarded as a subjective method and does not allow for digitised recording of results or validation against reference standards. In addition, this type of tap testing is generally confined to simple structural materials such as thin skin composites with foam or honeycomb cores, where defects can easily be identified. More complex structures with varying thicknesses present a much greater challenge for this method, as defects may have a similar response signal to thinner, non-defective regions, so neither force nor sonic data can differentiate between the two. This article seeks to introduce a novel analysis technique, applying the principle of resonant membranes to global and local frequency perspectives to generate two functions. The first sharpens tap testing images from the sonic and force responses returning greater clarity when observing the underlying structure, the second creating a local ranking of defect positions allowing an automatic highlighting of regions of high depth flux. The outcome is a process that enables operators to identify disbonds within an unknown composite structure with greater precision than either force or sound approaches on their own in lieu of prior information of defect, surface, or global resonance modes. The developed technique is suitable for application with a robotic platform to unknown curved composites surfaces since future developments will aim to achieve robotised TT deployment. The algorithm is validated within a laboratory environment on a physical reference sample, representative of an RNLI Severn class lifeboat hull, imitating a dry-dock inspection scenario.INDEX TERMS Tap testing, force/sound data fusion, thick composite inspection.

show abstract

Damage Detection in Composite Materials Using Tap Test Technique and Neural Networks

Cited by 8 publications

References 24 publications

Nondestructive Detection of Ceramic Products Based on Tapping Sound Signal Feature Recogition

Nondestructive Detection of Ceramic Products Based on Tapping Sound Signal Feature Recogition

Bio-Inspired Robotic Tap Testing: An Innovative Approach for Nondestructive Testing of Wooden Structures

Force and Sound Data Fusion for Enhanced Tap Testing Scanning of Composites

Contact Info

Product

Resources

About