Characterization of microstructural changes due to prolonged thermal exposure of directionally solidified Ni-base super alloy CM 247LC using ultrasonic

Mukhopadhyay, A. K.; Chatterjee, Dibyendu; Mondal, Chandan; Punnose, Sony; Gopinath, K.

doi:10.1016/j.ultras.2018.05.007

Cited by 9 publications

(10 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The weights initialized by a DBN must then be fine-tuned before we get a DBN-DNN [13], [14], [16]. DBN-DNNs have proven their advantages in digital speech-processing applications [14], [15], [25], [17]- [24].…”

Section: A Deep Belief Networkmentioning

confidence: 99%

Sequence-to-Sequence Acoustic-to-Phonetic Conversion Using Spectrograms and Deep Learning

et al. 2021

View full text Add to dashboard Cite

Distinctive phonetic features (DPFs) abstractedly describe the place, manner of articulation, and voicing of the language phonemes. While DPFs are powerful features of speech signals that capture the unique articulatory characteristics of each phoneme, the task of DPF extraction is challenged by the need for efficient computational model. Unlike the ordinary acoustic features that can be directly determined form speech waveform using closed-form expressions, DPF elements are extracted from acoustic features using machine learning (ML) techniques. Therefore, for the objective of developing an acoustic-to-phonetic converter of high accuracy and low complexity, it is important to select the input acoustic features that are simple, yet carry adequate information. This paper examines the effectiveness of using spectrogram as the acoustic feature with DPFs modeled using two deep learning techniques: the deep belief network (DBN) and the convolutional recurrent neural network (CRNN). The proposed method is applied on Modern Standard Arabic (MSA). Multi-label modeling is considered in the proposed acoustic-to-phonetic converter. The learning techniques were evaluated by proper evaluation measures that accommodate the imbalanced nature of DPF elements. The results showed that the CRNN is more accurate in extracting the DPFs than the DBN.INDEX TERMS Distinctive phonetic features, Spectrograms, speech processing, convolutional recurrent neural network, deep belief networks, KAPD corpus, Arabic, MSA.

show abstract

Section: A Deep Belief Networkmentioning

confidence: 99%

Sequence-to-Sequence Acoustic-to-Phonetic Conversion Using Spectrograms and Deep Learning

et al. 2021

View full text Add to dashboard Cite

show abstract

“…As on-line and real-time applications require a stable parameter, insensitive to physical changes in the emulsion, the slope of the phase spectrum seems to meet this requirement. The use of algorithms based on the slope of the phase spectrum has been reported in the literature to accurately calculate the propagation velocity for material characterization [ 21 , 23 , 24 , 25 , 26 ]. The phase slope provides an accurate way to determine the time delay and thus the propagation velocity, which is useful in dispersive media where the ultrasonic pulse is distorted as it propagates [ 27 ].…”

Section: Introductionmentioning

confidence: 99%

Ultrasonic Monitoring of the Water Content in Concentrated Water–Petroleum Emulsions Using the Slope of the Phase Spectrum

Franco

Reyna

Duran

et al. 2022

Sensors

View full text Add to dashboard Cite

This work proposes the slope of the phase spectrum as a signal processing parameter for the ultrasonic monitoring of the water content of water-in-crude oil emulsions. Experimental measurements, with water volume fractions from 0 to 0.48 and test temperatures of 20 °C, 25 °C, and 30 °C, were carried out using ultrasonic measurement devices operating in transmission–reception and backscattering modes. The results show the phase slope depends on the water volume fraction and, to a lesser extent, on the size of the emulsion droplets, leading to a stable behavior over time. Conversely, the behavior of the phase slope as a function of the volume fraction is monotonic with low dispersion. Fitting a power function to the experimental data provides calibration curves that can be used to determine the water content with percentage relative error up to 70% for a water volume fraction of 0.06, but less than 10% for water volume fractions greater than 0.06. Furthermore, the methodology works over a wide range of volume fractions.

show abstract

“…Ultrasonic properties, which result from the interactions between the ultrasonic wave and the microstructures of materials, have been extensively used for optimizing heat treatment processes [ 12 , 13 ] and characterizing the microstructures [ 14 , 15 ] and mechanical properties [ 16 , 17 ] of materials. Ultrasonic velocity and attenuation reflect variations in the grain size [ 18 , 19 ], volume fraction, the size of the precipitated phase [ 20 , 21 , 22 , 23 ], the type of precipitated phase [ 15 , 24 ], and the defects during the heat treatment of superalloys. Ultrasonic velocity has been reported to increase with the formation of the precipitate phases, whereas the dissolving or coarsening of precipitates leads to decreases in velocity [ 12 , 14 , 15 , 16 , 20 , 21 , 22 , 25 ].…”

Section: Introductionmentioning

confidence: 99%

“…Ultrasonic velocity and attenuation reflect variations in the grain size [ 18 , 19 ], volume fraction, the size of the precipitated phase [ 20 , 21 , 22 , 23 ], the type of precipitated phase [ 15 , 24 ], and the defects during the heat treatment of superalloys. Ultrasonic velocity has been reported to increase with the formation of the precipitate phases, whereas the dissolving or coarsening of precipitates leads to decreases in velocity [ 12 , 14 , 15 , 16 , 20 , 21 , 22 , 25 ]. This is mainly because the formation and dissolution of the intermetallic precipitates change the composition of an alloy, improving the elastic modulus and increasing the ultrasonic velocity [ 14 , 16 , 20 , 22 ].…”

Section: Introductionmentioning

confidence: 99%

“…Further, it has been found that the change in ultrasonic velocity caused by the change in the microstructure of a superalloy is consistent with the change in mechanical properties. Additionally, various precipitates scatter sound waves, which influence attenuation values [ 21 , 26 ]. The phase change and microstructure characteristic parameters show strong correlations with variation trends in the ultrasonic attenuation coefficient.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Effect of Nano-Sized γ′ Phase on the Ultrasonic and Mechanical Properties of Ni-Based Superalloy

Jie

Yang

et al. 2022

Nanomaterials

View full text Add to dashboard Cite

The effect of the nano-sized γ′ phase on the ultrasonic and mechanical properties of the IN939 superalloy was investigated. The results indicate that the microstructure characteristics of the nano-sized γ′ phase directly affected the ultrasonic longitudinal velocity, the attenuation coefficient, and the mechanical properties. The ultrasonic longitudinal velocity increased with the volume fraction of the γ′ phase, whereas the attenuation coefficient was similar to the fractional change in the γ channel width. The lower fractional change in the γ channel width, in combination with a high volume fraction of the γ′ phase, was conducive to improving the mechanical properties of the superalloy. Additionally, the variation in the ultrasonic properties could reflect the variation in the mechanical properties of the IN939 superalloy, which was beneficial for optimizing the heat treatment process and characterizing the γ′ phase precipitation behavior in a nondestructive manner.

show abstract

Characterization of microstructural changes due to prolonged thermal exposure of directionally solidified Ni-base super alloy CM 247LC using ultrasonic

Cited by 9 publications

References 29 publications

Sequence-to-Sequence Acoustic-to-Phonetic Conversion Using Spectrograms and Deep Learning

Sequence-to-Sequence Acoustic-to-Phonetic Conversion Using Spectrograms and Deep Learning

Ultrasonic Monitoring of the Water Content in Concentrated Water–Petroleum Emulsions Using the Slope of the Phase Spectrum

Effect of Nano-Sized γ′ Phase on the Ultrasonic and Mechanical Properties of Ni-Based Superalloy

Contact Info

Product

Resources

About