Study of the Silicon Carbide Wear Area after Micro-Scratching of Titanium, Zirconium, Niobium and Molybdenum at a Speed of 35 m/s

2021 ◽  
Vol 1037 ◽  
pp. 614-625
Author(s):  
Vladimir A. Nosenko ◽  
Aleksandr V. Fetisov ◽  
Sergey V. Nosenko ◽  
Viktor G. Karpov ◽  
Valeria E. Puzyrkova
Keyword(s):  
Silicon Carbide ◽  
Surface Defects ◽  
Chemical Elements ◽  
Average Concentration ◽  
Main Element ◽  
Wear Area ◽  
Molybdenum Alloys ◽  
Removal Of Metal ◽  
Titanium Zirconium

The authors conducted the study at micro-scratching of titanium, zirconium, niobium and molybdenum alloys. The content of the main element in alloys was from 99.5 to 99.7 %. Micro-cutting was carried out by specially prepared indenters with silicon carbide mono-crystals of a given shape. The state of the relief and the chemical composition of the wear area were studied using a scanning two-beam electron microscope. The micro-scratching speed was 35 m/s without cooling. The condition of the contact surfaces of silicon carbide and metals was studied at a magnification up to 100,000 times with the rotation and tilt of the microscope slide. The content of chemical elements was determined at individual spots of an object by scanning along the line and area. The authors also studied the condition of the wear area after micro-scratching of metals and after removal of metal adhesions by chemical etching. The intensity of metal transfer was determined by the average concentration of metal atoms at the wear area. The article also gives a classification of metals according to the intensity of transfer immediately after grinding and removal of metal adhesions. The influence of metal and the depth of micro-scratching on the morphology of the wear site is shown. It was found that molybdenum, having a low adhesive activity to silicon carbide, is able to penetrate microcracks and other surface defects during micro-scratching. The width of microcracks and the depth of metal penetration were determined

Steel Surface Defect Detection Using an Ensemble of Deep Residual Neural Networks

2021 ◽  
pp. 1-8
Author(s):  
Ihor Konovalenko ◽  
Pavlo Maruschak ◽  
Vitaly Brevus
Keyword(s):  
Neural Networks ◽  
Steel Surface ◽  
Production Efficiency ◽  
Surface Defects ◽  
Model Parameters ◽  
Feature Maps ◽  
Defect Diagnostics ◽  
Neuron Activation ◽  
Surface Defect Detection

Abstract Steel defect diagnostics is important for industry task as it is tied to the product quality and production efficiency. The aim of this paper is evaluating the application of residual neural networks for recognition of industrial steel defects of three classes. Developed and investigated models based on deep residual neural networks for the recognition and classification of surface defects of rolled steel. Investigated the influence of various loss functions, optimizers and hyperparameters on the obtained result and selected optimal model parameters. Based on an ensemble of two deep residual neural networks ResNet50 and ResNet152, a classifier was constructed to detect defects of three classes on flat metal surfaces. The proposed technique allows classifying images with high accuracy. The average binary accuracy of classifying the test data is 96.7% for all images (including defect-free ones). The fields of neuron activation in the convolutional layers of the model were investigated. Feature maps formed in the process were found to reflect the position, size and shape of the objects of interest very well. The proposed ensemble model has proven to be robust and able to accurately recognize steel surface defects. Erroneous recognition cases of the classifier application are investigated. It was shown that errors most often occur in ambiguous situations, where surface artifacts of different types are similar.

Attritious Wear of Silicon Carbide

1976 ◽  
Vol 98 (4) ◽  
pp. 1125-1134 ◽  
Author(s):  
R. Komanduri ◽  
M. C. Shaw
Keyword(s):  
Silicon Carbide ◽  
Electron Microscope ◽  
High Temperature ◽  
High Speed ◽  
Layer By Layer ◽  
Wear Area ◽  
Work Material ◽  
Transmission Electron ◽  
Metal Silicides ◽  
Boundary Fracture

Attritious wear of silicon carbide in simulated grinding tests against a cobalt base superalloy at high speed and extremely small feed rate was studied using a scanning electron microscope (SEM) and an auger electron spectroscope (AES). In many cases the wear area of silicon carbide was found to be concave rather than planar in shape. Several microcracks and grain boundary fracture were also observed. No evidence of metal build-up was observed on silicon carbide which was not the case with aluminum oxide. AES study of the rubbed surface on the work material and transmission electron microscope (TEM) investigation of the wear debris suggest that attritious wear of silicon carbide is due to one or more of the following mechanisms: 1 – Preferential removal of surface atoms on the abrasive, layer by layer, by oxidation under high temperature and a favorably directed shear stress; 2 – disassociation of silicon carbide at high temperature and (a) diffusion of silicon into the work material and formation of metal silicides and (b) diffusion of carbon into the work material and formation of unstable metal carbides (in the present case Ni3C and Co3C) which decompose during cooling to metal and carbon atoms; 3 – pinocoidal cleavage fracture of silicon carbide on basal planes c(0001) resulting in the removal of many micron-sized crystallites.

Detection and classification of surface defects of gun barrels using computer vision and machine learning

Measurement ◽  
2015 ◽  
Vol 60 ◽  
pp. 222-230 ◽  
Author(s):  
Rajalingappaa Shanmugamani ◽  
Mohammad Sadique ◽  
B. Ramamoorthy
Keyword(s):  
Machine Learning ◽  
Computer Vision ◽  
Surface Defects

Texture Descriptors for Automatic Classification of Surface Defects of the Hot-Rolled Steel Strip

2021 ◽  
pp. 251-260
Author(s):  
Virginia Riego del Castillo ◽  
Lidia Sánchez-González ◽  
Alexis Gutiérrez-Fernández
Keyword(s):  
Surface Defects ◽  
Steel Strip ◽  
Automatic Classification ◽  
Rolled Steel ◽  
Hot Rolled ◽  
Hot Rolled Steel

scholarly journals Deep Learning-Based Classification of Weld Surface Defects

2019 ◽  
Vol 9 (16) ◽  
pp. 3312 ◽  
Author(s):  
Zhu ◽  
Ge ◽  
Liu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Random Forest ◽  
Convolutional Neural Network ◽  
Surface Defects ◽  
Recognition Method ◽  
High Level ◽  
Intelligent Recognition ◽  
Non Destructive

In order to realize the non-destructive intelligent identification of weld surface defects, an intelligent recognition method based on deep learning is proposed, which is mainly formed by convolutional neural network (CNN) and forest random. First, the high-level features are automatically learned through the CNN. Random forest is trained with extracted high-level features to predict the classification results. Secondly, the weld surface defects images are collected and preprocessed by image enhancement and threshold segmentation. A database of weld surface defects is established using pre-processed images. Finally, comparative experiments are performed on the weld surface defects database. The results show that the accuracy of the method combined with CNN and random forest can reach 0.9875, and it also demonstrates the method is effective and practical.

Growth Kinetics and Mechanical Characterization of a Hard Boron Coating on a Tool Steel

2017 ◽  
Vol 380 ◽  
pp. 29-34 ◽  
Author(s):  
D. Sánchez Huerta ◽  
N. López Perrusquia ◽  
I. Hilerio Cruz ◽  
M.A. Doñu Ruiz ◽  
E.D. García Bustos ◽  
...  
Keyword(s):  
Activation Energy ◽  
Mechanical Characteristics ◽  
Mechanical Characterization ◽  
Chemical Elements ◽  
Thermochemical Treatment ◽  
X Ray Diffraction ◽  
X Ray ◽  
Optimal Classification

The mechanical characteristics are determined to a FeB/Fe2B coating applied in AISI L6 steel tool and blades make to cut paper. The thermochemical treatment was applied at temperatures of 1173, 1223 and 1273 K with permanence time of 0.5, 2 and 3 h for each temperature. The diffusion coefficient and activation energy for each phase is obtained for this boron coating on an AISI L6 steel. HRC test were made to establish the type of adherence (qualitative) and comparing with the VDI 3198 standard and the results were obtaining optimal classification of HF1-HF2 in condition for 3h of the three temperatures. The result by nanoidentation show hardness of 1000 - 2000 HV as well as the Young's modulus for each present phase of the coating. Through micrographs (SEM) are showing thicknesses up to 79.52 ± 18.82 μm for FeB and 97.80 ± 20.01μm for Fe2B, a morphology sawn ́s type is evidence. Through EDS and x-ray diffraction are used to show the chemical elements formed.

Sign in / Sign up

Export Citation Format

Share Document