Wear detection of WC-Cu based impregnated diamond bit matrix based on SEM image and deep learning

To reduce the friction coefficient between impregnated diamond bit and rock, experiments on addition of graphite to the matrix material of bit cutters were conducted. The cutters were made up of diamond contained working layers and binding layers. The friction and wear properties of cutters and binding layers were investigated using a pin-on-disc friction & wear tester with granite as tribopair. The results showed that with addition of graphite, the hardness and friction coefficient of binding layer decreased, but its wear resistance increased; compared to cutters without graphite, those cutters containing graphite had lower wear loss and friction coefficient and their sliding wear process was much steadier, but diamond protrusion was still normal.

Download Full-text

Deep-learning-based SEM image denoiser (Conference Presentation)

Metrology, Inspection, and Process Control for Microlithography XXXIII ◽

10.1117/12.2515182 ◽

2019 ◽

Author(s):

Dorin Cerbu ◽

Sandip Halder ◽

Philippe Leray

Keyword(s):

Deep Learning ◽

Sem Image

Download Full-text

Prediction of Mechanical Strength Based on Deep Learning Using the Scanning Electron Image of Microscopic Cemented Paste Backfill

Advances in Civil Engineering ◽

10.1155/2018/6245728 ◽

2018 ◽

Vol 2018 ◽

pp. 1-7 ◽

Cited By ~ 2

Author(s):

Xuebin Qin ◽

Shifu Cui ◽

Lang Liu ◽

Pai Wang ◽

Mei Wang ◽

...

Keyword(s):

Deep Learning ◽

Mechanical Strength ◽

Mechanical Response ◽

Cemented Paste Backfill ◽

Sem Images ◽

Important Indicator ◽

Sem Image ◽

Paste Backfill ◽

The Difference ◽

Scanning Electron

The mechanical strength of cemented backfill is an important indicator in mining filling. To study the nonlinear relationship between cemented paste backfill (CPB) and mechanical response, a deep learning technique is employed to establish the end-to-end mapping relationship between the scanning electron microscope (SEM) images and mechanical strength. A seven-layer convolution neural network is set up in the experiment, and the relationship between the SEM image and mechanical strength is established. In addition, the difference between the measured and predicted values is calculated and the mean and variance of the error are analyzed. The average accuracy of the mechanical strength prediction is found to be 8.28%. Thus, the proposed method provides a new technique for the quantitative analysis of mechanical strength of microscale CPB.

Download Full-text

Predicting Compressive Strength of Cement-Stabilized Rammed Earth Based on SEM Images Using Computer Vision and Deep Learning

Applied Sciences ◽

10.3390/app9235131 ◽

2019 ◽

Vol 9 (23) ◽

pp. 5131 ◽

Cited By ~ 6

Author(s):

Piotr Narloch ◽

Ahmad Hassanat ◽

Ahmad S. Tarawneh ◽

Hubert Anysz ◽

Jakub Kotowski ◽

...

Keyword(s):

Computer Vision ◽

Compressive Strength ◽

Deep Learning ◽

Prediction Accuracy ◽

Image Database ◽

Rammed Earth ◽

Sem Images ◽

Current Testing ◽

Sem Image ◽

Reasonable Prediction

Predicting the compressive strength of cement-stabilized rammed earth (CSRE) using current testing machines is time-consuming and costly and may harm the environment due to the samples’ waste. This paper presents an automatic method using computer vision and deep learning to solve the problem. For this purpose, a deep convolutional neural network (DCNN) model is proposed, which was evaluated on a new in-house scanning electron microscope (SEM) image database containing 4284 images of materials with different compressive strengths. The experimental results show reasonable prediction results compared to other traditional methods, achieving 84% prediction accuracy and a small (1.5) oot Mean Square Error (RMSE). This indicates that the proposed method (with some enhancements) can be used in practice for predicting the compressive strength of CSRE samples.

Download Full-text