Showing papers in "Ultrasonics in 2019"
••
TL;DR: This paper proposes to use convolutional neural networks (CNNs) for segmenting breast ultrasound images into four major tissues: skin, fibroglandular tissue, mass, and fatty tissue, on three‐dimensional (3D) Breast ultrasound images.
151 citations
••
TL;DR: The convolutional neural network is applied to noisy ultrasonic signatures to improve classification performance of weldment defects and applicability and the result shows that CNN is robust, does not require specific feature extraction methods and give considerable high defect classification accuracies even for noisy signals.
96 citations
••
TL;DR: The proposed DPU-Net leverages modern deep learning-based method for segmentation of lumen and the media vessel walls in both 20 MHz and 40 MHz IVUS B-mode images and achieves state-of-the-art results without any manual intervention.
91 citations
••
TL;DR: The results show that the PSO‐SVM classifier with all 9 features has a good accuracy, which verifies the feasibility and correctness of the spot welding quality classification method proposed in this paper.
61 citations
••
TL;DR: The proposed method reduces the magnitude of the artifacts compared to the time reversal of the non‐mode‐converted Lamb wave, and yields the focused spot whose size is associated with the size of the notch and the half wavelength of the time‐reversed wave mode.
57 citations
••
TL;DR: The piezoelectric semiconductor behaves like the viscoelastic solid to carry a decaying wave and the steady carrier density and biasing electric field have significant influences on the dispersion and attenuation features and can be used to regulate the propagation of the coupled elastic waves.
55 citations
••
TL;DR: Experimental investigations carried out to evaluate the effect of process parameters (power of ultrasonic vibration, rotational speed, axial depth of cut, feed rate and feed rate) on the cutting responses showed that the vibration reduced the mean cutting force and increased its deviation.
49 citations
••
TL;DR: A reverse‐time migration imaging algorithm was combined with a numerical simulator—the three‐dimensional (3D) elastodynamic finite integration technique (EFIT)—to provide multi‐mode damage imaging that enables characterization of damage type and size, general sensitivity to unknown damage types, higher resolution imaging, and detectability regardless of the data acquisition system used.
46 citations
••
TL;DR: The results presented in this work might pave the way for designing an effective detector that works over a wide range of neutron fluence.
45 citations
••
TL;DR: A novel signal post-processing algorithm for reconstruction of the joint area was developed and validated experimentally and it is shown that using the proposed technique the positions of different defects can be determined.
44 citations
••
TL;DR: Results of this study demonstrated that the ultrasound-intensified combined intermittent microwave - low temperature hot air drying may be a suitable alternative for industrial applications.
••
TL;DR: The bonding mechanism of hybrid AA5024/(GF‐)CF‐PEEK joints is explained and the kinematics of bonding formation is presented in detail, with the help of detailed process parameter recording and microscopic investigations.
••
TL;DR: The results show that the difference between the stress of dilatancy onset and the UCS, the deformation performance and the activity of AE signals during Dilatancy are positive correlated with the Talbot index of aggregate in cemented rockfill.
••
TL;DR: A combination of the laser ultrasonic pulse‐echo mode and the proposed quantitative strategy is practical for accurate detection of disbonds in multi‐layer bonded structures.
••
TL;DR: The LiTaO3/quartz structure can be optimized to allow longitudinal SAWs to propagate without attenuation and the existence of numerous orientations in quartz supporting the propagation of non-attenuated longitudinal Saws is explained.
••
TL;DR: Baseband DMAS (BB-DMAS) beamforming provides flexible manipulation of image quality by introducing baseband spatial coherence in the ultrasonic imaging by reducing the need for oversampling.
••
TL;DR: This work proposes an SH0 wave linear phased array SHM system based on the recently proposed omni-directional SH wave piezoelectric transducer (OSH-PT) and presents the working principle of the phased array system, which is capable of monitoring large structures and can detect multi-defects.
••
TL;DR: In this paper, a thickness-poled d15 PZT ring based omni-directional SH wave piezoelectric transducers (OSH-PT) consisting of different number of elements was investigated via finite element (FEM) simulations.
••
TL;DR: Development of a real‐time H‐scan US imaging technology that was implemented on a programmable US research scanner is detailed and is a promising approach for visualizing the relative size and distribution of acoustic scattering objects.
••
TL;DR: The bi‐directional evolutionary structure optimization (BESO) method is extended to the design of viscoelastic PCs with the maximum attenuation and stiffness and various novel topological patterns of the optimized viscoELastic PCs are found.
••
TL;DR: The proposed method has the advantages of high accuracy and high stability, being non‐interfering, non‐destructive, low‐cost, on‐line and with good adherence to health and safety, and it has significant application prospects in injection molding production.
••
TL;DR: This study proposes an automatic method for individual mode extraction using the inversible synchrosqueezed wavelet transform to obtain the high-resolution time-frequency representation (TFR) of the GW signal.
••
TL;DR: A new method using the rotational magnetic field to trap and vibrate magnetic microbubbles at target clot region and then using an intravascular forward-looking ultrasound transducer to activate them acoustically significantly enhances in vitro lysis of blood clot.
••
TL;DR: In this paper, an impedance matching is achieved by dispersing small, deeply subwavelength sized particles in a soft matrix, and the appropriate concentration is determined with the help of Coherent Potential Approximation and Waterman & Truell models.
••
TL;DR: The proposed nonlinear ultrasonic method provides high sensitivity to early fatigue damage, which makes it promising for the further early damage detection applications and guides further engineering applications.
••
TL;DR: For the first time, such unified porosity-phase velocity functional relationship is obtained for particulate reinforced metal-matrix composites completely different in fabrication techniques as well as in chemical composition and elastic properties of reinforcing particles.
••
TL;DR: A computer simulation is presented using a harmonic response analysis (HRA) in ANSYS to resolve and improve the efficacy of the tank and demonstrated that it can be applied to a 40 kHz tank as well.
••
TL;DR: A classification‐based MA border detection method with an embedded feature selection technique based on Fractional‐order Darwinian particle swarm optimization (FODPSO) algorithm that acquires better performances compared with two other automatic methods conducted on the same dataset available in literature.
••
TL;DR: An efficient numerical approach to the investigation of nonlinear scattering and mode conversion phenomena of Lamb waves as they interact with breathing cracks is presented and may provide guidelines for the effective design of sensor arrays utilizing nonlinear Lamb waves for fatigue crack detection.
••
TL;DR: To investigate the material removal mechanisms in rotary ultrasonic surface machining (RUSM) of CFRP, single abrasive scratching tests were conducted and the generation mechanisms of the delamination were analyzed and discussed.