Quantitative evaluation of pipe wall thinning defect sizes using microwave NDT

Guo, Yijun; Chen, Guanren; Katagiri, Takuya; Yusa, Noritaka; Hashizume, Hidetoshi

doi:10.1080/10589759.2022.2051505

Cited by 9 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another emerging technique is microwave NDT, which involves using microwave or radar signals to evaluate internal material properties, including the detection of defects and variations in composition. [ 48 ] However, interpreting microwave data can be complex and requires expertise in electromagnetic‐wave behavior and material interactions, making it less user‐friendly than the DIC method. Machine learning can be incorporated into microwave NDT to predict the geometry of defects.…”

Section: Discussionmentioning

confidence: 99%

“…Machine learning can be incorporated into microwave NDT to predict the geometry of defects. [ 48 ] Although microwave NDT is effective in detecting defects and shapes, DIC offers a more comprehensive range of information, including stress and strain distribution. Over the past few years, mechanoluminescence has risen as a promising avenue for transforming NDT.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Identification of Location and Geometry of Invisible Internal Defects in Structures using Deep Learning and Surface Deformation Field

Timilsina,

Jang,

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

On‐site inspection of invisible subsurface defects in multiscale structural materials by conventional nondestructive testing (NDT) methods, such as X‐ray and ultrasound, requires complex sample preparation and data acquisition processes. Moreover, the inspected area is very small. Herein, a simple, inexpensive, and ultrasensitive NDT method for identifying and classifying the geometries of subsurface defects using commercial cameras, digital image correlation software, and object detection (OD) algorithms is developed. Three OD algorithms—Faster region‐based convolutional neural network (Faster R‐CNN), Mask R‐CNN, and you‐only‐look‐once (YOLO)v3—are evaluated for their ability to locate defects and identify defect geometries. Specifically, bounding boxes of two sizes (large and small) are applied to the regions of defect‐induced perturbations in strain tensors, which serve as virtual representatives of invisible subsurface defects. The performance of the proposed approach is validated on test datasets of known and unknown defect types. The experimental results confirm that the proposed approach can effectively utilize the surface deformation field information to accurately and reliably locate and identify subsurface defects. The method is nondestructive and low cost, enables real‐time detection, is robust against noise‐dominated deformation fields, and can be applied to various structural deformations. The method is therefore suitable for multiscale structural health monitoring and characterization of internal defects in materials.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Identification of Location and Geometry of Invisible Internal Defects in Structures using Deep Learning and Surface Deformation Field

Timilsina,

Jang,

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

show abstract

“…A signal processing method was proposed in [13] to compensate for the phase difference due to the dispersion of microwave propagation along the pipe and acquire the explicit ToF signal for localization of defect. In addition to the time-domain feature, a signal processing method combining dispersion compensation and windowing was also proposed to extract the clear resonance frequency from frequency spectrum of pipe wall thinning reflected signals [14]. In particular, a back propagation neural network was trained in that study to quantitatively evaluate the depth and length of a wall thinning defect using the extracted resonant frequencies of TM 01 microwave signals and showed good performance.…”

Section: Introductionmentioning

confidence: 99%

Design of a simple side-incident TE₁₁ mode microwave probe for nondestructive pipe inspection

Guo

Yoshikawa

Yusa

et al. 2023

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

This study proposed a simple side-incident TE11 mode microwave probe for the rapid and long-range inspection of cracks in metallic pipes. The probe feeds the microwaves to a metallic pipe, which works as a waveguide; the reflection signal provoked by a defect is measured for detection and localization. The probe enables the detection of both circumferentially and axially oriented cracks, unlike those reported in earlier studies. To achieve better performance, numerical simulations were conducted to evaluate the conversion efficiency and optimize the insertion length of the coaxial cable and the exposed length of the cable core wire. The simulation results suggest that the optimized probe configuration is feasible for pipes with various diameters by proportionally changing the current probe configuration. Although injected microwaves propagated in two directions, the ratio of microwaves to one direction could be controlled by adjusting the inclination angle and the exposed length of the cable core wire. Subsequently, three TE11 probes fabricated according to the simulation results were used to detect circumferential and axial slits in a brass pipe. The results showed that circumferential slits in the vertical positions (parallel to the nontilted coaxial cable) and axial slits in the horizontal positions (perpendicular to the nontilted coaxial cable) caused large reflections, consistent with the electromagnetic field distribution of the TE11 mode microwaves in a circular waveguide. Further experiments verified the feasibility of the designed probe for pipes with different diameters and for directional pipe inspection.

show abstract

“…The ultrasonic test (UT) is mainly used to measure the pipe wall thickness in periodic inspection [ 7 , 8 ]. Since thickness measurement errors with UT can be caused by the operators and the inspection environment, how to reduce the measurement error of UT [ 9 , 10 ] and other types of non-destructive testing (NDT) inspection methods [ 11 , 12 ] have been studied. Since the traditional NDT inspection characteristics are point-by-point measurements, it is necessary to measure all points at regular intervals in a specific pipe area, which takes significant time.…”

Section: Introductionmentioning

confidence: 99%

Estimation of Elbow Wall Thinning Using Ensemble-Averaged Mel-Spectrogram with ResNet-like Architecture

Kim

Chung

Park

et al. 2022

Sensors

View full text Add to dashboard Cite

An elbow wall thinning diagnosis method by highlighting the stationary characteristics of the operating loop is proposed. The accelerations of curved pipe surfaces were measured in a closed test loop operating at a constant pump rpm, combined with curved pipe specimens with artificial wall thinning. The vibration characteristics of wall-thinned elbows were extracted by using a mel-spectrogram in which modal characteristic variation shifting can be expressed. To reduce the deviation of the model’s prediction values, the ensemble mean value of the mel-spectrogram was used to emphasize stationary signals and reduce noise signals. A convolutional neural network (CNN) regression model with residual blocks was proposed and showed improved performance compared to the models without the residual block. The proposed regression model predicted the thinning thickness of the elbow excluded in training dataset.

show abstract

Quantitative evaluation of pipe wall thinning defect sizes using microwave NDT

Cited by 9 publications

References 21 publications

Identification of Location and Geometry of Invisible Internal Defects in Structures using Deep Learning and Surface Deformation Field

Identification of Location and Geometry of Invisible Internal Defects in Structures using Deep Learning and Surface Deformation Field

Design of a simple side-incident TE₁₁ mode microwave probe for nondestructive pipe inspection

Estimation of Elbow Wall Thinning Using Ensemble-Averaged Mel-Spectrogram with ResNet-like Architecture

Contact Info

Product

Resources

About

Quantitative evaluation of pipe wall thinning defect sizes using microwave NDT

Cited by 9 publications

References 21 publications

Identification of Location and Geometry of Invisible Internal Defects in Structures using Deep Learning and Surface Deformation Field

Identification of Location and Geometry of Invisible Internal Defects in Structures using Deep Learning and Surface Deformation Field

Design of a simple side-incident TE11 mode microwave probe for nondestructive pipe inspection

Estimation of Elbow Wall Thinning Using Ensemble-Averaged Mel-Spectrogram with ResNet-like Architecture

Contact Info

Product

Resources

About

Design of a simple side-incident TE₁₁ mode microwave probe for nondestructive pipe inspection