Estimation of Screw’s Physical Properties Using Neural Network

Lu, Nan; Huang, Huang-Chu; Wu, Shanjun; Hwang, Rey-Chue

doi:10.18494/sam.2021.3243

Cited by 1 publication

(1 citation statement)

References 25 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An artificial neural network (ANN) was used to predict the physical properties of screws after heat treatments. A physical property estimation model was employed to determine the appropriate control parameters in the screw manufacturing process [11]. ANN has assisted in accurately predicting the mechanical properties of rolling materials [12].…”

Section: Introductionmentioning

confidence: 99%

Prediction of micro-hardness in thread rolling of St37 by convolutional neural networks and transfer learning

Soleymani

Khoshnevisan

Davoodi

2022

Int J Adv Manuf Technol

View full text Add to dashboard Cite

This study introduces a non-destructive method by applying convolutional neural networks (CNN) to predict the microhardness of the thread-rolled steel. Material microstructure images were collected for our research, and micro-hardness tests were conducted to label the extracted microstructure images. In recent years, researchers have used machine learning (ML) and deep learning (DL) models to predict material properties for forming, machining, additive manufacturing, and other processes. However, they encountered industrial limitations primarily because of the absence of historical information on new and unknown materials, which are necessary to predict material properties by DL models. These problems can be solved by employing CNN models. In our work, we used a CNN model with two convolutional layers and visual geometry group (VGG19) as transfer learning (TL). We predicted four classes of micro-hardness of the St37 rolled threads. The prediction results of the micro-hardness test images by our proposed CNN model and pre-trained VGG19 model are comparable. Our proposed model has produced the same precision and recall scores as VGG19 for class B and class C hardness. VGG19 performed slightly better than our model for precision in class A and recall in class D. We observed that the training time of our proposed model using the CPU (central processing unit) was approximately nine times faster than the VGG19 model. Our proposed CNN and VGG19 have direct applications in advanced manufacturing (AM). They can automatically predict the micro-hardness in the thread rolling of St37. Our proposed model requires less memory and computational power and can be deployed more efficiently than the VGG19 model.

show abstract

Section: Introductionmentioning

confidence: 99%