scholarly journals Automatic Identification and Quantitative Characterization of Primary Dendrite Microstructure Based on Machine Learning

Crystals ◽  
2021 ◽  
Vol 11 (9) ◽  
pp. 1060
Author(s):  
Weihao Wan ◽  
Dongling Li ◽  
Haizhou Wang ◽  
Lei Zhao ◽  
Xuejing Shen ◽  
...  
Keyword(s):  
Single Crystal ◽  
Gaussian Distribution ◽  
Nearest Neighbor ◽  
Primary Dendrite ◽  
Voronoi Tessellation ◽  
Dendrite Core ◽  
Test Time ◽  
Automatic Identification ◽  
Full Field ◽  
Statistical Analysis Method

Dendrites are important microstructures in single-crystal superalloys. The distribution of dendrites is closely related to the heat treatment process and mechanical properties of single-crystal superalloys. The primary dendrite arm spacing (PDAS) is an important length scale to describe the distribution of dendrites. In this work, the second-generation single crystal superalloy HT901 with a diameter of 15 mm was imaged under a metallurgical microscope. An automatic dendrite core identification and full-field quantitative statistical analysis method is proposed to automatically detect the dendrite core and calculate the local PDAS. The Faster R-CNN algorithm combined with test time augmentation (TTA) technology is used to automatically identify the dendrite cores. The local multi-directional algorithm combined with Voronoi tessellation is used to determine the local nearest neighbor dendrite and calculate the local PDAS and coordination number. The accuracy of using Faster R-CNN combined with TTA to detect the dendrite core of HT901 reaches 98.4%, which is 15.9% higher than using Faster R-CNN alone. The algorithm calculates the local PDAS of all dendrites in H901 and captures the Gaussian distribution of the local PDAS. The average PDAS determined by the Gaussian distribution is 415 μm, which is only a small difference from the average spacing λ¯ (420 μm) calculated by the traditional method. The technology analyzes the relationship between the local PDAS and the distance from the center of the sample. The local PDAS near the center of HT901 are larger than those near the edge. The results suggests that the method enables the rapid, accurate and quantitative dendritic distribution characterization.

scholarly journals Uniformity Assessment of TRISO Fuel Particle Distribution in Spherical HTGR Fuel Element Using Voronoi Tessellation and Delaunay Triangulation

2018 ◽  
Vol 2018 ◽  
pp. 1-6 ◽  
Author(s):  
Libing Zhu ◽  
Xincheng Xiang ◽  
Yi Du ◽  
Gongyi Yu ◽  
Ziqiang Li ◽  
...  
Keyword(s):  
Fuel Element ◽  
Delaunay Triangulation ◽  
Nearest Neighbor ◽  
Voronoi Tessellation ◽  
Fission Products ◽  
Fuel Particle ◽  
Volume Distribution ◽  
Triso Fuel ◽  
Triso Particles ◽  
Log Normal

Nonuniform distribution of tri-structural-isotropic (TRISO) fuel particles in a spherical fuel element (SFE) may increase the failure probability of the SFE in the high-temperature gas-cooled reactor, leading to the release of fission products. To evaluate the uniformity of the TRISO particles nondestructively, 3-dimensional cone-beam computed tomography is used to image the SFE, and TRISO particles are segmented. After TRISO particle positions are identified, the Voronoi tessellation and Delaunay triangulation are used to extract several geometric metrics. Results indicate that both the Voronoi volume distribution and the nearest neighbor-distance distribution follow the log-normal distributions, which provide strong evidence that the TRISO particles are approximately randomly uniformly distributed. Further study will be focused on validating the conclusion with more SFE data.

Test Reliability of Impurity Parameters of Uster AFIS

2011 ◽  
Vol 331 ◽  
pp. 516-527
Author(s):  
Peng Zi Sun ◽  
Ji Peng Cao
Keyword(s):  
Statistical Analysis ◽  
Test Reliability ◽  
Test Time ◽  
Test Results ◽  
Analysis Method ◽  
Sample Weight ◽  
Reliable Test ◽  
Sampling Process ◽  
Statistical Analysis Method ◽  
Card Sliver

This paper presents test reliablity of Uster AFIS for impurity test by calculating the Reliable Test Time (hereinafter referred to as RTT) and CV% of test results. The CV% value of test results of impurity-related parameters in card sliver obtained in 8 experiments totally with 313 different plans were calculated. By statistical analysis method, the reliable test time of AFIS for some impurity-related parameters was estimated. It is concluded that the impurity result obtained by 10-time tests with AFIS was inaccurate. The reasons for this are that the sample weight is too small, the impurity is unevenly distributed and the impurity in card sliver may have some loss in the manually-sampling process.

The Automated Risk Estimation for the Navigation of Autonomous Ships by Learning with Navigation Feature

2020 ◽  
pp. 2041003
Author(s):  
Wei Chian Tan ◽  
Kie Hian Chua ◽  
Yanling Wu
Keyword(s):  
Nearest Neighbor ◽  
Dimensional Space ◽  
Risk Estimation ◽  
Nearest Neighbor Search ◽  
Mathematical Representation ◽  
Automatic Identification ◽  
Identification System ◽  
North West ◽  
The North ◽  
Neighbor Search

This work presents a data-driven approach for the automated risk estimation of the voyage of a vessel or ship. While the industry is moving from a compliance-based framework with existing rules to a risk-based one, there is also a need to monitor the risk of a vessel from the perspective of the navigation. This is of even higher importance for the case of autonomous ships. Built based on the state-of-the-art mathematical representation, the navigation feature, each existing voyage is transformed into a corresponding series of points in [Formula: see text]-dimensional space. During the stage of pre-processing, given a set of historical Automatic Identification System (AIS) data, those records that belong to the same vessel within a certain period of time are taken as a voyage and mapped to the corresponding space of the navigation feature. After the pre-processing and during the online monitoring, the current trajectory of the vessel is transformed into the corresponding representation in the same way. Based on a nearest-neighbor search scheme, the distance from the nearest neighbor is taken as the risk of the current voyage. In other words, the deviation from the closest route in the historical data is taken as the risk. The developed method has demonstrated encouraging performance on a set of challenging historical AIS data from the Australian Maritime Safety Authority, covering three regions in the Australian territory, namely, the Bass Strait, the Great Australian Bight and the North West.

Effect of Hot Isostatic Pressing on the Microstructure of Single Crystal Ni-Based Superalloy DD10

2013 ◽  
Vol 747-748 ◽  
pp. 772-776
Author(s):  
Li Jun Liu ◽  
Ming Xue ◽  
Jing Yang Chen ◽  
La Mei Cao
Keyword(s):  
Electron Microscope ◽  
Single Crystal ◽  
Interdendritic Region ◽  
Hot Isostatic Pressing ◽  
Optical Microscope ◽  
Dendrite Core ◽  
Dendritic Segregation ◽  
Third Generation ◽  
Isostatic Pressing ◽  
Scanning Electron

The effects of hot isostatic pressing on the microstructures of a third generation single crystal Ni-based superalloy DD10 were investigated by using optical microscope (OM), scanning electron microscope (SEM), electron microprobe analyzer (EPMA). The results showed that the micropores in the interdendritic region were eliminated completely after hot isostatic pressing at 1320 and 150MPa. Meanwhile, the morphology of γ precipitates changed to be more cuboidal and the distribution of γ precipitates in both dendrite core and interdendritic region became more uniform after hot isostatic pressing. Hot isostatic pressing also promoted the homogenization of the composition between dendrite core and interdendritic region and the dendritic segregation of Re, W, Al and Ta was decreased.

Directional Solidification Behavior of CMSX-6 Superalloy

2014 ◽  
Vol 788 ◽  
pp. 554-559
Author(s):  
Shuai Zheng ◽  
Yu Liang Jia ◽  
Jiao Tang
Keyword(s):  
Single Crystal ◽  
Directional Solidification ◽  
Thermal Gradient ◽  
First Generation ◽  
Primary Dendrite ◽  
Solidification Rate ◽  
Experimental Results ◽  
Single Crystal Superalloy ◽  
Solidification Behavior ◽  
Rate Range

The directional solidification behavior of a first generation single crystal superalloy CMSX-6 was investigated. The solidification rate range in 25μm/s to 100μm/s and a thermal gradient G of 30K/cm were used for the present study. The experimental results show that the primary dendrite arm space (PDAS) decreased from (432±8) μm to (369±4) μm as the solidification rate increased, and the sizes of the eutectic pools also decreased as the solidification rate increased. And the volume fractions of eutectic γ/γ' were about 7% to 9% with different solidification rate. The γ/γ'- eutectic was comprised with coarse γ' phase and fine γ/γ' network. The morphology of the γ/γ’ eutectic supported the possibility that the solidification of γ/γ’ eutectic initiates with the formation of fine γ/γ’.

Optimization of Ta Content of a Third Generation Ni3Al Base Single Crystal Superalloy

2015 ◽  
Vol 816 ◽  
pp. 304-309
Author(s):  
Song Ming Han ◽  
Wei Li ◽  
Yue Ma ◽  
Xin Bao Zhao ◽  
Shu Suo Li ◽  
...  
Keyword(s):  
Single Crystal ◽  
Thermodynamic Calculation ◽  
Volume Fraction ◽  
Primary Dendrite ◽  
Solution Treatment ◽  
Experimental Results ◽  
Single Crystal Superalloy ◽  
Third Generation ◽  
Primary Dendrite Arm Spacing ◽  
Calculation Results

In order to optimize the Ta content of a newly developed 3rd generation Ni3Al-based single crystal superalloy, a series of alloys with the varying of Ta content of 3.0, 4.2, 4.5, 6.0wt. % were prepared. The experimental results showed that with the addition of Ta, the size and volume fraction of bulky γ' phase significantly increased while the primary dendrite arm spacing decreased. Meanwhile, the difficulty of solution treatment significantly increased with increasing Ta content. And the thermodynamic calculation results showed that the volume fractions of γ' phase in this series of alloys were significantly higher than those of typical Ni based single crystal superalloys, indicating that the 3rd generation Ni3Al based single crystal superalloys can serve in the temperature of 1150oC to 1200oC.

Sign in / Sign up

Export Citation Format

Share Document