Selection of Heating Lines in the Line Heating Process for Steel Plates Using Faster R−CNN

Young-Soo Yang,Hyeon-Woo Nam,Kang-Yul Bae 한국정밀공학회 2024 International Journal of Precision Engineering and Vol.25 No.8

In the process of surface forming through line heating of a steel plate, accurately determining the position of the heating lines is crucial to achieving the desired curvature. In this study, we propose a Faster R−CNN based model to predict the positions of heating lines from images of the desired curved surface. Initially, a finite element model for line heating on a steel plate is employed to obtain deformation analysis results based on the positions of the heating lines. The shape resulting from the combination of heating lines is acquired by superimposing the deformation analysis results of each heating line. Color map images of curved surfaces and corresponding information about heating lines are utilized as training data for the proposed model. The model is subjected to training through backpropagation to minimize the total output error. Testing the trained model revealed that the model accurately predicted the positions of the heating lines to achieve the desired surface. Furthermore, validation of the model on a surface with arbitrary curvature confirmed that heating the plate based on the predicted positions of the heating lines resulted in obtaining a curved surface that was very similar to the arbitrary target surface. Consequently, it was determined that the model could be effectively utilized to predict the positions of the heating lines in the line heating process.

신경회로망을 이용한 선상가열공정의 가열선 위치선정에 관한 연구

손광재,양영수,배강열 대한용접접합학회 2003 대한용접·접합학회지 Vol.21 No.4

Line heating is an effective and economical process for forming flat metal plates into three-dimensional shapes for plating of ships. Because the nature of the line heating process is a transient thermal process, followed by a thermo elastic plastic stress field, predicting deformed shapes of plate is very difficult and complex problem. In this paper, neural network model o3r solving the inverse problem of metal forming is proposed. The backpropagation neural network systems for determining line-heating positions from object shape of plate are reported in this paper. Two cases of the network are constructed-the first case has 18 lines which have different positions and directions and the second case has 10 parallel heating lines. The input data are vertical displacements of plate and the output data are selected heating lines. The train sets of neural network are obtained by using an analytical solution that predicts plate deformations in line heating process. This method shows the feasibility that the neural network can be used to determine the heating-line positions in line heating process.

Using Artifical Neural Network to predict locations of Induction Heating Lines in forming process

Truong-Thinh Nguyen,Young-Soo Yang 제어로봇시스템학회 2011 제어로봇시스템학회 국제학술대회 논문집 Vol.2011 No.10

An artificial neural network model based on backpropagation algorithm for determining heating area’s positions from object shape of plate is presented in this paper. This model can help manufacturers determine the positions of induction heating areas and their heating parameters to form a desired shape of plate. The input data are vertical displacements of deformed plate and the output data are selected heating lines composed by the areas. The training patterns of neural network are obtained using an analytical solution that is derived from the plate theory to predict plate deformations in induction heating process. This method shows the feasibility that the neural network can be used to determine the heating-line positions in line heating process. A back-propagation neural network with one hidden layer was used to predict the line heating in shipyard. The system was trained and evaluated with analytical solutions, as well as several different forms of experimental results provided by several shipyard factories.

Determination of line heating conditions for plate forming using the strain directed boundary method based on deformation superposition

윤희찬,노홍준,Young-Hwan Han,Hun Bong Lim,양현익 대한기계학회 2023 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.37 No.11

This study proposes a method to determine the location, magnitude, and sequence of line heating to form a target shape using the strain directed as boundary (SDB) method. The analysis model was constructed by considering the phase transformation caused by line heating. The results of the analytical model were compared with the experimental results. The deformation at an arbitrary heating location and heating magnitude was calculated using a verified model. The locations and magnitudes were determined by optimization. The deformation reflecting the optimization result confirmed an error of 5.91 % compared to the experimental results. The scale factor for the optimal heating sequence was determined via optimization by line heating sequence. The deformations caused by the heating sequence of the concave and saddle shapes confirmed errors of 7.04 % and 8.59 %, respectively. The proposed method provides guidelines for heat forming.

이동열원의 조건 변화가 선상가열에 미치는 영향에 관한 연구

최윤환(Yoon Hwan Choi),이연원(Yeon Won Lee),최광(Kwang Choi) 한국마린엔지니어링학회 2010 한국마린엔지니어링학회 학술대회 논문집 Vol.2010 No.4

Line heating is a manufacture method, which was widely used to machining a curved surface in the ship construction. The qualities using by line heating are very difference compare to the proficiency level of the engineer. So it's mainly depend on the automation equipment instead of the proficiency level engineer. In this study, it would be investigate the temperature distribution of the heating plate, which was used by the automation equipment according to line heating. The main factors are the moving velocity of the heating source, strength and the heating method separately, in temperature distribution while line heating. In this paper, it was investigated the temperature change with the vary of each three variables. The numerical result showed that peak temperature decrease if the moving velocity of the heating source increased. It can also calculate the change quantitatively that the peak temperature and temperature distribution changed linearly with the vary of the heating source. following instructions give you basic guidelines for preparing camera-ready papers for the Journal of the KOSME. We recommend you to use the HWP word processor.

고주파 유도가열을 이용한 선상가열 시 각 변형 예측에 관한 연구

박동환,진형국,박성식,신상범,Park, Dong-Hwan,Jin, Hyung-Kook,Park, Soung-Sig,Shin, Sang-Beom 대한용접접합학회 2015 대한용접·접합학회지 Vol.33 No.1

The purpose of this study is to establish the predictive method of the angular distortion caused by the line heating process with high frequency induction heating. In order to do it, the heat input model for the high frequency induction heating system was established through comparing the temperature evaluation results obtained by both FEA and experiment. The critical heating conditions to prevent the degradation of the work piece with various thicknesses were identified by FEA and microstructure test results. Under the critical heating conditions, the extensive line heating tests were performed. According to the test results, it was found that the angular distortion behavior of the heated plates could be defined as the function of heat intensity and the rigidity of heated plate. In addition, it was clarified that the angular distortion strongly depended on the size of test specimen such as the length and the width of the heated plate. Based on these results, the predictive equation for the angular distortion was established with the function of heat intensity, bending rigidity and size of heated plate.

A study on the simulation of water cooling process for the prediction of plate deformation due to line heating

Nomoto, Toshiharu,Jang, Chang-Doo,Ha, Yun-Sok,Lee, Hae-Woo,Ko, Dae-Eun Korean Society of Ocean Engineers 2011 International journal of ocean system engineering Vol.1 No.1

In a line heating process for hull forming, the phase of the steel transforms from austenite to martensite, bainite, ferrite, or pearlite depending on the actual speed of cooling following line heating. In order to simulate the water cooling process widely used in shipyards, a heat transfer analysis on the effects of impinging water jet, film boiling, and radiation was performed. From the above simulation it was possible to obtain the actual speed of cooling and volume percentage of each phase in the inherent strain region of a line heated steel plate. Based on the material properties calculated from the volume percentage of each phase, it should be possible to predict the plate deformations due to line heating with better precision. Compared to the line heating experimental results, the simulated water cooling process method was verified to improve the predictability of the plate deformation due to line heating.

Using a Novel CNN Model for Predicting the Induction Heating Lines to Obtain a Desired Deformed Shape of Steel Plate

Nguyen Truong Thinh,Kang-Yul Bae,Young-Soo Yang 한국정밀공학회 2023 International Journal of Precision Engineering and Vol.24 No.10

Induction heating is a fast and energy-efficient method of heating steel plates in the shipyard industry due to the increasing demand for steel plate deformation. In this study, deep learning models are proposed with abstract representations of heatmap images allowing efficient recognition of complex and nonlinear patterns. The model for determining the heating type for the plastic zone is a fairly simple and effective approach to perform the heating type determination with the choice of weight optimization of network. A novel Convolutional Neural Network (CNN) is trained to predict heating regions from heatmap images with different vertical displacements of the required steel plate. We have proposed a Region based CNN (R-CNN) model using a sparse group to classify heating lines based on heatmap images of desired complex shape as input. The rotated region of interest pool layers and the rotated bounding box regression are also suggested to recognize inclined slender shapes of heating lines. The R-CNN is trained to detect heating regions bounded by labelled boxes within the confines of the steel plate. A frame-based event predictor for deformation areas is trained independently to analyse each individual box in the regions proposed. Then a post-processing step is based on the output of the R-CNN to determine the actual heating zones. By evaluating through the data sets, we have experimentally found that the proposed algorithm has performed well and achieved better results than other conventional methods.

Prediction of Heating-Line Paths in Induction Heating Process using the Artificial Neural Network

Truong-Thinh Nguyen,양영수,김기성,현충민 한국정밀공학회 2011 International Journal of Precision Engineering and Vol. No.

This paper presents the development of a back propagation neural network model for the prediction of heating-line positions in induction heating process. The vertical displacements of plate have been considered as the input parameters and the selected induction heating lines as output parameters to develop the model. The training patterns of neural network are obtained using an analytical solution that predicts plate deformations in induction heating process. The feasibility test reveals that the developed method can be used to determine the heating-line positions in line heating process.

선상가열시 이동열원 조건에 따른 가열 판재의 온도분포에 관한 연구

최윤환(Yoon-Hwan Choi),이연원(Yeon-Won Lee),최광(Kwang Choi) 한국마린엔지니어링학회 2010 한국마린엔지니어링학회지 Vol.34 No.4

선박 건조공정에서 외피의 곡면 가공에 많이 사용하는 가공법을 선상가열법이라고 한다. 선상가 열법은 엔지니어의 숙련도에 따라 품질의 차이가 커지기 때문에 현재에는 엔지니어의 숙련도에 의존하지 않는 자동화기기를 사용하여 선상가열을 수행하는 경우가 많다. 본 연구에서는 자동화기기를 사용한 선상가열에 의한 가열판재의 온도분포를 조사하고자 한다. 선상가열시 적용되는 주요한 변수는 가열원의 이동속도, 강도 및 가열 방식 등이 있으며, 본 연구에서는 세 가지 변수를 중심으로 가열판재의 표면 및 내부온도가 어떻게 변화하는지를 조사하였다. 해석결과 가열원의 이동속도가 빨라질수록 판재의 피크온도는 낮게 형성되는 것을 확인하였고, 또한 열원의 크기에 따른 피크온도 및 온도분포가 선형적으로 변화하는 것을 정량적으로 계산할 수 있었다. Line heating is a manufacture method, which was widely used to machining a curved surface in the ship construction. The qualities using by line heating are very difference compare to the proficiency level of the engineer. So it's mainly depend on the automation equipment instead of the proficiency level engineer. In this study, it would be investigate the temperature distribution of the heating plate, which was used by the automation equipment according to line heating. The main factors are the moving velocity of the heating source, strength and the heating method separately, in temperature distribution while line heating. In this paper, it was investigated the temperature change with the vary of each three variables. The numerical result showed that peak temperature decrease if the moving velocity of the heating source increased. It can also calculate the change quantitatively that the peak temperature and temperature distribution changed linearly with the vary of the heating source.