Internal Defects Detection Method of the Railway Track Based on Generalization Features Cluster Under Ultrasonic Images

There may be several internal defects in railway track work that have different shapes and distribution rules,and these defects affect the safety of high-speed trains.Establishing reliable detection models and methods for these internal defects remains a challenging task.To address this challenge,in this study,an intelligent detection method based on a generalization feature cluster is proposed for internal defects of railway tracks.First,the defects are classified and counted according to their shape and location features.Then,generalized features of the internal defects are extracted and formulated based on the maximum difference between different types of defects and the maximum tolerance among same defects’types.Finally,the extracted generalized features are expressed by function constraints,and formulated as generalization feature clusters to classify and identify internal defects in the railway track.Furthermore,to improve the detection reliability and speed,a reduced-dimension method of the generalization feature clusters is presented in this paper.Based on this reduced-dimension feature and strongly constrained generalized features,the K-means clustering algorithm is developed for defect clustering,and good clustering results are achieved.Regarding the defects in the rail head region,the clustering accuracy is over 95%,and the Davies-Bouldin index(DBI)index is negligible,which indicates the validation of the proposed generalization features with strong constraints.Experimental results prove that the accuracy of the proposed method based on generalization feature clusters is up to 97.55%,and the average detection time is 0.12 s/frame,which indicates that it performs well in adaptability,high accuracy,and detection speed under complex working environments.The proposed algorithm can effectively detect internal defects in railway tracks using an established generalization feature cluster model.

Regardless of the Puncture Angle, a Tuohy Needle with Sand-Blasted Steel at the Tip of the Bevel Is a Valid Needle on the Ultrasonic Images

Background: A high ability to visualize the needle on the ultrasonic images is necessary to perform the ultrasound-guided nerve block safely. The Rafa Tuohy needleR (Vygon, Paris, France, Rafa) is a non-stimulating Tuohy needle with sand-blasted steel at the tip of the bevel. We examined the degree to which the Rafa enhanced the visibility of ultrasonic images compared with the non-coated Tuohy needle. Methods: We punctured the Blue Phantom. The dimensions of both the Rafa and the non-coated Tuohy needles were 18 G × 80 mm. The puncture angle is 30 degrees and 45 degrees from the Blue Phantom. We measured the intensity of the tip of the bevel at a depth of 0.5, 1.0, 1.5 and 2.0 cm for the puncture angle of 30 degrees, and 0.5, 1.0, 1.5, 2.0, 2.5 and 3.0 cm for the puncture angle of 45 degrees. Six anesthesiologists with more than seven years of experience performed three punctures using each needle. Results: As an outcome, we concluded that at a puncture angle of both 30 degrees and 45 degrees, the intensity of the non-coated Tuohy needle decreased with the depth. On the other hand, at an angle of 30 degrees, the intensity of the Rafa needle did not decrease, and at an angle of 45 degrees the intensity only decreased very slightly as the depth increased. Conclusions: The Tuohy needle with sand-blasted steel at the tip of the bevel provided greater visualization than the non-coated Tuohy needle on the ultrasound images.

Extraction of Submerged Topographic Line in B-Scan Ultrasonic Image

The analysis of underwater topography ultrasonic image, which can be obtained by using B-scan ultrasound imaging technique, is the basis and important work in topography study. In this paper, we present a novel self-adapted method for the extraction of submerged topographic line. Since the distribution of gray values in the image has a mutation process, this feature is used to appropriately track the topographic line of imaging band, and wavelet denoising method is applied to denoise the obtained lines. The described method also takes the continuity of topography into consideration during tracking procedure. The results show that the extraction error is within 2-pixel width（approximate 1 mm）. This method is suitable for the extraction of current model topographic lines with the advantages of good self-adaption, high speed and high resolution.

Hybrid Segmentation Approach for Different Medical Image Modalities

The segmentation process requires separating the image region into sub-regions of similar properties.Each sub-region has a group of pixels having the same characteristics,such as texture or intensity.This paper suggests an efficient hybrid segmentation approach for different medical image modalities based on particle swarm optimization(PSO)and improved fast fuzzy C-means clustering(IFFCM)algorithms.An extensive comparative study on different medical images is presented between the proposed approach and other different previous segmentation techniques.The existing medical image segmentation techniques incorporate clustering,thresholding,graph-based,edge-based,active contour,region-based,and watershed algorithms.This paper extensively analyzes and summarizes the comparative investigation of these techniques.Finally,a prediction of the improvement involves the combination of these techniques is suggested.The obtained results demonstrate that the proposed hybrid medical image segmentation approach provides superior outcomes in terms of the examined evaluation metrics compared to the preceding segmentation techniques.

Finite element modeling of heating phenomena of cracks excited by high-intensity ultrasonic pulses

A three-dimensional thermo-mechanical coupled finite element model is built up to simulate the phenomena of dynamical contact and frictional heating of crack faces when the plate containing the crack is excited by high-intensity ultrasonic pulses. In the finite element model, the high-power ultrasonic transducer is modeled by using a piezoelectric thermal-analogy method, and the dynamical interaction between both crack faces is modeled using a contact-impact theory. In the simulations, the frictional heating taking place at the crack faces is quantitatively calculated by using finite element thermal-structural coupling analysis, especially, the influences of acoustic chaos to plate vibration and crack heating are calculated and analysed in detail. Meanwhile, the related ultrasonic infrared images are also obtained experimentally, and the theoretical simulation results are in agreement with that of the experiments. The results show that, by using the theoretical method, a good simulation of dynamic interaction and friction heating process of the crack faces under non-chaotic or chaotic sound excitation can be obtained.

Ultrasonic C-scanning imaging inspection of superplastic solid-state welded joint quality

Based on a large amount of dissection at welded interface and quantitative microscopic examination of welded rate, the suitable limit grey scale value was determined, and the welded rate of superplastic solid state welding interface of heterogeneous steel was systematically studied by means of self made ultrasonic C scanning imaging inspection system. The experimental results show: the welded state of superplastic solid state welding interface of heterogeneous steel can be conducted to be more accurately, reliably and quickly inspected by means of this system, and the ultrasonic testing results are good consistent with actual examination results of the interface defective distribution. Within the extent of the suitble welded rate,the welded rate in 40Cr/T10A superplastic welding process tested by this system is linear with its tensile strength of joint.

FEATURE EXTRACTION OF BONES AND SKIN BASED ON ULTRASONIC SCANNING

In the prosthetic socket design, aimed at the high cost and radiation deficiency caused by CT scanning which is a routine technique to obtain the cross-sectional image of the residual limb, a new ultrasonic scanning method is developed to acquire the bones and skin contours of the residual limb. Using a pig fore-leg as the scanning object, an overlapping algorithm is designed to reconstruct the 2D cross-sectional image, the contours of the bone and skin are extracted using edge detection algorithm and the 3D model of the pig fore-leg is reconstructed by using reverse engineering technology. The results of checking the accuracy of the image by scanning a cylinder work pieces show that the extracted contours of the cylinder are quite close to the standard circumference. So it is feasible to get the contours of bones and skin by ultrasonic scanning. The ultrasonic scanning system featuring no radiation and low cost is a kind of new means of cross section scanning for medical images.

An ultrasonic multi-wave focusing and imaging method for linear phased arrays

To overcome the inherent limits of traditional single wave imaging for nondestructive testing,the multi-wave focusing and imaging method is thoroughly studied.This method makes the compressional waves and shear waves focused in both emission and reception processes,which strengthens the focusing energy and improves the signal-to-noise ratio of received signals.A numerical model is developed to study the characteristics of a multi-wave focusing field.It is shown that the element width approaching 0.8 wavelengths of shear waves can keep a balance between the radiation energy of two waves,which can achieve a desirable multi-wave focusing performance.And an experiment using different imaging methods for a linear phased array is performed.It can be concluded that due to the combination of the propagation and reflection characteristics of two waves,the multi-wave focusing and imaging method can significantly improve the imaging distinguishability of defects and expand the available sweeping range to a sector of-650 to 65°.

Wavelet-Based Hybrid Thresholding Method for Ultrasonic Liver Image Denoising

This paper presents a wavelet-based hybrid threshold method according to the soft- and hard-threshold functions proposed by Donoho. The wavelet-based hybrid threshold method may help doctors to know more details on the liver disease through denoising the ultrasound image of the liver. First of all, an analytical expression for the hybrid threshold function is discussed. The wavelet-based hybrid threshold method is then investigated for ultrasound image of the liver. Finally, we test the influence of this parameter on the proposed method with the real ultrasound image corrupted by speckle noise with different variances. Moreover, we compare the proposed method under the varying parameters with the soft-threshold function and the hard-threshold function. Three metrics, which are correlation coefficient, edge preservation index and structural similarity index, are measured to quantify the denoised results of ultrasound liver image. Experimental results demonstrate the potential of the proposed method for ultrasound liver image denosing.

Advances in the Diagnosis of Breast Tumor by Using Imaging Technology

Breast tumor is the most common tumor in the world. The most important method to reduce the mortality due to breast tumor is diagnosed and found as early as possible. Imaging technology is one of the most important means to help doctors diagnose tumor early. This paper first simply introduces the common imaging technology. Then the mechanism and application of the ultrasonic elastic imaging technology in the diagnosis of breast tumor are summarized and discussed detailly. The methods for image treatment are introduced also. At last the development trend is analyzed. It is shown that the ultrasonic imaging technology is the most convenient and the cheapest relative to other imaging technologies such as nuclear magnetic imaging (NMI) and computer tomography (CT). Especially the ultrasonic elastic imaging technology can provide not only imaging information but also mechanism parameters, which helps to improve the accuracy of diagnosis obviously. Therefore, the ultrasonic elastic imaging technology is worthy of being studied further. More effective image analysis method is required.

MODIFIED SZABO'S WAVE EQUATION FOR ARBITRARILY FREQUENCY-DEPENDENT VISCOUS DISSIPATION IN SOFT MATTER WITH APPLICATIONS TO 3D ULTRASONIC IMAGING

Soft matters are observed anomalous viscosity behaviors often characterized by a power law frequency dependent attenuation in acoustic wave propagation. Recent decades have witnessed a fast growing research on developing various models for such anomalous viscosity behaviors among which one of the present authors proposed the modified Szabo＇s wave equation via the positive fractional derivative. The purpose of this study is to apply the modified Szabo＇s wave equation to simulate a recent ultrasonic imaging technique called the clinical amplitude- velocity reconstruction imaging （CARI） of breast tumors which are of typical soft tissue matters. Investigations have been made on the effects of the size and position of tumors on the quality of ultrasonic medical imaging. It is observed from numerical results that the sound pressure along the reflecting line, which indicates the detection results, varies obviously with sizes and lateral positions of tumors, but remains almost the same for different axial positions.

Adaptive speckle reduction of ultrasound images based on maximum likelihood estimation

A method has been developed in this paper to gain effective speckle reduction in medical ultrasound images. To exploit full knowledge of the speckle distribution, here maximum likelihood was used to estimate speckle parameters corresponding to its statistical mode. Then the results were incorporated into the nonlinear anisotropic diffusion to achieve adaptive speckle reduction. Verified with simulated and ultrasound images, we show that this algorithm is capable of enhancing features of clinical interest and reduces speckle noise more efficiently than just applying classical filters. To avoid edge contribution, changes of contrast-to-noise ratio of different regions are also compared to investigate the performance of this approach.

Feasibility of photoacoustic tomography for ophthalmology

For the eyeball composed of membrane and liquid, the contrast of ultrasound imaging is not high due to its small variance in acoustic impedance. As a new imaging modality, photoacoustic tomography combines the advantages of pure optical and ultrasonic imaging together and can provide high resolution, high contrast images. In this paper, the feasibility of photoacoustic tomography for ophthalmology is studied experimentally. A Q-switched Nd：YAG pulsed laser with 7-ns pulse width is used to generate photoacoustic signal of a porcine eyeball in vitro. The two-dimensional （2D） optical absorption image of the entire eyeball is reconstructed by time-domain spherical back projection algorithm. The imaging results agree well with the histological structure of the eyeball and show a high imaging contrast.

A new scheme of coded ultrasound using Golay codes

Golay codes are the most practical code in coded ultrasound imaging systems.But the trade-off for perfect range sidelobe cancellation is the requirement for two firings, thus resulting in motion-dependent decoding errors.In view of this, we propose a new scheme using the simultaneous emission of code pairs.The code pair is allocated to different elements of an aperture and transmitted simultaneously.The process of separating the code pair from the echo received is based on the orthogonality of the code pair.At last the autocorrelation functions of the individual Golay codes are added together.The simultaneous emission of code pairs instead of two firings recovers the frame rate loss, and eliminates the motion-dependent decoding error.Our theoretical analysis and simulations show that the scheme can be used to eliminate the tissue motion effects.