Evaluation of tile–wall bonding integrity based on impact acoustics and support vector machine

Tong, Fuchuan; Xu, Xiyan; Luk, B.L.; Liu, K.P.

doi:10.1016/j.sna.2008.01.020

Cited by 32 publications

(20 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ringing sounds which control the frequency response after the decay of the acceleration component have been traditionally recognized as useful for integrity inspection of material structures carried out in previous studies [27,28]. According to earlier research [27][28][29][30], for an impact between the flake structure scrap and a plate with larger mass and thickness than the tested scrap, as much as possible of the kinetic energy from a falling scrap should be converted to its own flexural-mode free-vibration, i.e., the ringing response or resonance which locates in the specific frequency domain. Hence all of the falling scrap pieces were designed to impact on a heavy stone plate which was sealed in an empty medium-density fiberboard (MDF) case whose inner surface is covered by sponge material in order to avoid the influence of ambient noises.…”

Section: Design Of Impact Testsmentioning

confidence: 99%

“…Therefore in principle, impact AE recognition could also be used for the sorting of crushed ELV plastic materials-the mechanical and geometrical structures of crushed plastic scraps are much simpler than nuts. Correlative researches [27,28] have shown that, characteristics of impact AE signals depend only on the mechanical and geometrical properties of the specific materials, theoretically crushed plastic scraps could be also recognized by using impact AE characterization. However, so far, related research has not been carried out.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Feasibility Study of Sensor Aided Impact Acoustic Sorting of Plastic Materials from End-of-Life Vehicles (ELVs)

2015

View full text Add to dashboard Cite

Abstract:The purpose of this feasibility research was to study a novel sensor based separation method for recycling of plastic materials from end-of-life vehicles (ELVs) by using eigen-frequency response of impact acoustic emission. In this research three kinds of commonly used plastics, polypropylene (PP), acrylonitrile-butadiene-styrene (ABS), and styrene-maleic-anhydride (SMA) sampled from end-of-life vehicles, were researched. Almost all the crushed plastic scraps had a flake structure, theoretically their impact response behaviors were determined by their diameters and thicknesses. The equivalent diameters of the scraps were characterized by fine sieving and their thicknesses were measured online by a 3D laser triangulation sensor above the conveying path. Following this the scraps were free dropped one-by-one to impact with an impact passive body on which impact acoustic emission (AE) signals were generated and acquired by an acoustic pickup sensor. Thirdly, the AE signals which carried eigen-frequency response features were processed and characterized. Results demonstrated that the scraps with diameters < 8 mm were too weak for the actual devices to process; the scraps with diameter from 8-13 mm still generated quite a lot of AE signals of inadequate intensity. Finally the general characterization and recognition yields were 64.6%, 61.7%, and 63.9% of PP, ABS, and SMA in mass, respectively of tested materials. OPEN ACCESSAppl. Sci. 2015, 5 1700

show abstract

Section: Design Of Impact Testsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Feasibility Study of Sensor Aided Impact Acoustic Sorting of Plastic Materials from End-of-Life Vehicles (ELVs)

2015

View full text Add to dashboard Cite

show abstract

“…Sansalone and Streett (1997) also points out that when the transducer is placed close to the impact point, the response is dominated by P-wave echoes, which can be analyzed by the Fourier transform technique. The PSD of the acoustic signal frequency is used as the source of the signal features, such as: the power accumulation ratio (Wu and Siegel 2000), the sound intensity ratio (Liu et al 2007), and the area of interval PSD (Tong et al 2008). The threshold limitation evaluation method, as a traditional approach, was applied by several researchers (Liu et al 2007;Ito and Uomoto 1997).…”

Section: Related Workmentioning

confidence: 99%

“…The extreme learning machine (ELM) approach, as a type of feed-forward neural networks, has been newly used to explored for the IE analysis (Zhang et al 2016). The drawbacks of ANN are that it needs a large amount of training samples, depends heavily on the empirical principles, and also the characteristics of the impact acoustic features suppress the generalization capability of ANN (Tong et al 2008).…”

Section: Related Workmentioning

confidence: 99%

“…Support vector machine (SVM), which is based on the statistical learning theory, is characterized for classification with the capability of learning from datasets at small size, and has been applied for the IE classification such as in Tong et al (2008) and in our previous research Li et al (2014). Farrar and Worden (2012) chapter 11 gives more details of SVM for structural health monitoring.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Wall-climbing robot for non-destructive evaluation using impact-echo and metric learning SVM

Ushiroda

Yang

et al. 2017

Int J Intell Robot Appl

View full text Add to dashboard Cite

The impact-echo (IE) acoustic inspection method is a non-destructive evaluation technique, which has been widely applied to detect the defects, structural deterioration level, and thickness of plate-like concrete structures. This paper presents a novel climbing robot, namely Rise-Rover, to perform automated IE signal collection from concrete structures with IE signal analyzing based on machine learning techniques. Rise-Rover is our new generation robot, and it has a novel and enhanced absorption system to support heavy load, and crawler-like suction cups to maintain high mobility performance while crossing small grooves. Moreover, the design enables a seamless transition between ground and wall. This paper applies the fast Fourier transform and wavelet transform for feature detection from collected IE signals. A distance metric learning based support vector machine approach is newly proposed to automatically classify the IE signals. With the visual-inertial odometry of the robot, the detected flaws of inspection area on the concrete plates are visualized in 2D/3D. Field tests on a concrete bridge deck demonstrate the efficiency of the proposed robot system in automatic health condition assessment for concrete structures.

show abstract

Trial inspection of exterior‐tile wall specimens with a prototyped tile‐debonding diagnostic device

Soeta¹,

Ito

Fujinuma³

et al. 2020

Japan Architectural Review

View full text Add to dashboard Cite

This paper details the ability of a tile‐debonding diagnostic device to detect artificially debonded areas on 12 exterior‐tile wall specimens, using a detection parameter proposed in a previous paper. The device has an impact force sensor and four microphones and outputs detection parameter RAF for each microphone. The maximum value of RAF at the four microphones was defined as RAF‐max. A threshold value of RAF‐max was set, and the results of detection of debonding were displayed on the figures of the specimens. Consequently, the effectiveness of the device and detection parameter was verified.

show abstract

Evaluation of tile–wall bonding integrity based on impact acoustics and support vector machine

Cited by 32 publications

References 12 publications

Feasibility Study of Sensor Aided Impact Acoustic Sorting of Plastic Materials from End-of-Life Vehicles (ELVs)

Feasibility Study of Sensor Aided Impact Acoustic Sorting of Plastic Materials from End-of-Life Vehicles (ELVs)

Wall-climbing robot for non-destructive evaluation using impact-echo and metric learning SVM

Trial inspection of exterior‐tile wall specimens with a prototyped tile‐debonding diagnostic device

Contact Info

Product

Resources

About