Triangle Heating Research Articles

Curved Hull Plate Classification for Determining Forming Method using Deep Learning

Curved hull plate forming, the process of forming a flat plate into a curved surface that can fit into the outer shell of a ship's hull, can be achieved through either cold or thermal forming processes, with the latter processes further subcategorizable into line or triangle heating. The appropriate forming process is determined from the plate shape and surface classification, which must be determined in advance to establish a precise production plan. In this study, an algorithm to extract two-dimensional features of constant size from three-dimensional design information was developed to enable the application of machine and deep learning technologies to hull plates with arbitrary polygonal shapes. Several candidate classifiers were implemented by applying learning algorithms to datasets comprising calculated features and labels corresponding to various hull plate types, with the performance of each classifier evaluated using cross-validation. A classifier applying a convolution neural network as a deep learning technology was found to have the highest prediction accuracy, which exceeded the accuracies obtained in previous hull plate classification studies. The results of this study demonstrate that it is possible to automatically classify hull plates with high accuracy using deep learning technologies and that a perfect level of classification accuracy can be approached by obtaining further plate data. 1. Introduction The outer shell of a ship is composed of hull plates that are generally formed as curved surfaces. To produce a curved surface from a flat steel plate, a curved hull plate-forming process involving the application of heat or pressure to the plate must be undertaken. Such forming processes can be categorized as either cold forming, in which the plate is bent using physical pressure, or thermal forming, in which bending stress is generated by applying heat to the plate. The former process is generally used to bend plates into cylindrical shapes using a rolling machine, whereas the latter is used to form more complex curved surfaces. In most shipyards, thermal forming is performed by skilled workers who apply direct heat to plates using a torch; accordingly, thermal forming is more difficult and time-consuming than machine-based cold forming and often constitutes a crucial bottleneck process in shipyard operation.

An Improved Method of Computing Heating Information for Triangle Heating for an Automated Thermal Forming System

In this paper, a novel method of computing heating information for triangle heating is proposed for improving the accuracy of forming in an automated thermal forming system. The current method of computing heating information through triangle heating cannot be readily used for an automated thermal forming system because of a limited range of plates that the method can handle, and undesirable deformation on the boundary such as "over-bending" and buckling when the plate is heated using the computed heating information. Therefore, a lot of man-hours are required for correcting such defects, leading to delayed fabrication in the downstream fabrication processes. In order to overcome these problems, a method is developed using formulae for handling an extended range of plates, and considering the effect of the initial curvature of a plate in the computation of heating information. Various examples used in the ship construction show that the proposed method can improve the forming accuracy of the automated thermal forming system. 1. Introduction The bow and stern of a ship directly influences the ship's operational efficiency. Therefore, it is necessary to design and fabricate such parts with good accuracy. This means that because a ship hull is obtained by assembling a collection of small parts, maintaining accuracy in forming each curved part and accurate assemblage of them are important. In order to create a curved plate, a thermal forming method is usually used. In this method, the plate is heated using a gas torch that generates local expansion and shrinkage on the plate, inducing deformation on the heated area. It is a standard process in fabricating curved plates in most shipyards around the world. The thermal forming method, however, generates intense heat and noise, making the working environment unfavorable. Moreover, it is considered as a bottleneck in the whole fabrication process because it is performed manually. Hence, the demand for automating this process has been raised constantly. Recently, Park et al. (2016) presented a full-fledged automated thermal forming system. The system consists of modules for measurement, heating information computation, and heating, and yields designed curved plates with good accuracy in most cases.

Numerical analysis and experimental research of triangle induction heating of the rolled plate

In shipyard, triangle heating technology with irregular multi-heating paths and highly concentrated heat input is used to form a curved plate, especially a concave type plate. Compared with line heating process with simple line segment path, its main purpose is to get a bigger contraction deformation at the plate edge. Hence, triangle heating technology is important for most shipyards to increase hull-forming productivity and study the automation. This paper focuses on the moveable triangle induction heating technology. An electromagnetic coupling finite element model is built to simulate the moveable triangle induction heating process and reveal the temperature characteristics and deformation behavior. The results of the simulation are compared with those obtained from experiments and show good agreement. It demonstrates that the numerical model used in this study is effective for simulating triangle heating for the steel plate forming process in shipbuilding. With the numerical model, the paper further investigates the effect of heating parameters on temperature and shrinkage deformation. These are traced here with a modified mechanical model whose results are in accord with the numerical results. This modified model can be applied to predict the edge shrinkage and explain the effect of heating parameters on transverse shrinkage.

곡판 가공방법 적용을 위한 곡률면적 분석

The ship hull is accomplished by assembling various curved surfaces. There are numerous existing methods for ship hull processing, which need certain appropriate processing methods to enable it to be more efficient. The curved hull plates can be divided into convex region and saddle region. It is common to use line heating method to form a saddle region, when it comes to a convex region, it will be triangle heating method to be utilized. A precise analysis for curvature domain is required for the application of proper processing method. There exist various problems on existing calculation methods of curvature domain. Therefore, a more powerful method is demanded to it more accurately. In this study, a method called Dual Contouring is applied to extract curved surfaces, which is able to improve accuracy of extracted area. Based on all above, a best-suited heat processing method should be selected.

An artificial neural network system for predicting the deformation of steel plate in triangle induction heating process

This paper presents the development of an artificial neural network (ANN) model to predict the positions and sizes of induction triangle heating based on laminated plate theory combined with Finite Element Method (FEM) solutions. The vertical displacements and transverse shrinkage of nodes on the plate are used as inputs to the network and the position of the heating triangles on the plate, heated surface, and size of the heating triangles are the outputs of the models. The developed feed-forward ANN with 242-100-72 arrangement is capable of estimating all necessary conditions for the induction triangle heating process. The training patterns of the neural network are obtained using an analytical solution derived from the plate laminate theory to predict the plate deformations in the induction heating process. The developed neural network model is tested to demonstrate its feasibility for determining the heating positions on the surface of a flat steel plate in the triangle induction heating process for forming a desired shape.

Analysis for the angular deformation of steel plates in a high-frequency induction forming process with a triangle heating technique

A triangle heating technique with the use of a heat source of high-frequency induction heating to make a steel plate deformed into a curved shape was modeled and analyzed using the numerical analysis of the finite element method in order to predict the angular deformation of the steel plate formed by the technique. For the analysis of the deformation, heat generation by an electromagnetic field was first analyzed with consideration of the preheat effect, and heat flow using the heat generated from the plate as the heat source was then analyzed. Thermal history of the plate predicted by numerical analysis was compared with that measured in an experiment of triangle heating on a steel plate. Deformations of the plates were then analyzed with changes of heating parameters including heating dimensions and plate thickness. The analyses were also verified with a series of experiments. In order to derive a simplified equation to readily predict deformation from the triangle heating technique, deformations predicted by numerical analyses and measured by the experiments were synthesized in association with the heating parameters using a statistical method of recursion analysis. The equation was verified to be able to predict the deformations conversely and expected to be practically used in the industry to select the heating parameters for the desired shapes of curved plates.

Forming Complicated Surface in Shipyard Using Neural Network System

Determining the positions of triangle heating in and parameters of heating process are important for deforming the concave surfaces in shipyard, as well as airplane. The objective of this study was to develop an artificial neural network (ANN) model to predict positions of induction heating and parameters of heating process based on analytical solutions. This model of ANN can help manufacturers determine the positions of induction heating lines and their heating parameters to form a desired shape of plate. The backpropagation neural network systems for determining line-heating positions from object shape of plate are presented in this paper. An artificial neural network model is developed with the relationship between the desired shape of plate and the paths of induction heating. The input data are vertical displacements of plate and the output data are selected heating lines composed by the areas. The outputs of the models were positions of induction heating on plate as well as their parameters. Simulated values obtained with neural network correspond closely to the experimental results.

A Study of Transverse Shrinkage and Vertical Displacement in Induction Triangle Heating

Deformations including transverse shrinkage and vertical displacement of induction triangle heating play an important role in shipyard. However, the deformations and behaviors of plate after heating are complex, the analysis of this process consumes much time and expensive. The objective of this paper was to develop an analytical solution to determine transverse shrinkage and vertical displacement in induction triangle heating based on laminated plate theory. The plastic region in the analytical solution of the angular deformation and shrinkage of a steel plate is obtained from the thermal analysis of the plate with the heat input calculated from the electro-magnetic analysis of the induction heating process. Calculated values obtained with analytical solution correspond closely to the experimental results.

Analysis of triangle heating technique using high frequency induction heating in forming process of steel plate

Triangle heating technique using a gas flame is used to deform steel plate in ship construction. However, in the flame heating process, the heat source is often difficult to control and parts cannot be deformed efficiently. In this study, a numerical model is developed to study the triangle heating technique with the more controllable heat source of high-frequency induction heating and to analyze the deformation of steel plate in the heating process. To simplify the many complex trajectories of the triangle heating technique, a rotational path of inductor is suggested and then a 2-dimensional circular heat input model is proposed. The heat flow and transverse shrinkage in steel plate during triangle heating with the induction heat are analyzed. The results of the analyses are compared with those of experiments to show the good agreement. The heat source and thermo-mechanical analysis models proposed in this study were effective and efficient for simulating the triangle heating technique in the forming of steel plate in shipbuilding.

곡가공 프로세스를 고려한 곡판 분류 알고리즘

In general, the forming process of the curved hull plates consists of sub tasks, such as roll bending, line heating, and triangle heating. In order to complement the automated curved hull forming system, it is necessary to develop an algorithm to classify the curved hull plates of a ship into standard shapes with respect to the techniques of forming task, such as the roll bending, the line heating, and the triangle heating. In this paper, the curved hull plates are classified by four standard shapes and the combination of them, or saddle, convex, flat, cylindrical shape, and the combination of them, that are related to the forming tasks necessary to form the shapes. In preprocessing, the Gaussian curvature and the mean curvature at the mid-point of a mesh of modeling surface by Coon's patch are calculated. Then the nearest neighbor method to classify the input plate type is applied. Tests to verify the developed algorithm with sample plates of a real ship data have been performed.

Analysis of Bending Deformation in Triangle Heating of Steel Plates with Induction Heating Process Using Laminated Plate Theory#

The steel-forming process in shipyards is considered an important stage with respect to productivity and precision of curved plates. The induction heating process has been of interest to steel formation because the power and its distribution are easier to control and reproduce. Besides, induction heating equipment can be easily integrated with a robotic system for automation. The heating process usually utilizes line heating or triangle heating methods to form hull plates. Even though a number of studies on the line heating method have been performed, there have been few studies on the triangle heating method. In this study, using a simplified elasto-plastic model and laminated plate theory, an analytic means of predicting the bending deformation in triangle heating of steel plates is derived. For the purpose of this, the induction heating process is modeled in advance, with numerical heat flux and heat flow analyses to determine the plastic region. The plastic region is considered as an inclusion that has eigenstrains in the laminated plate. The analytic solution is applied to predict deformations to verify its exactness. The results of the analytic solution are quite good compared with those of the triangle heating experiment, revealing the effectiveness of the analytic solution.

The Determination of Heating Shapes and Locations for Triangle Heating

Thermal forming is a method to form a curved plate by inducing local shrinkage and angular distortion through heating and cooling. In this approach, two different methods are available: line heating and triangle heating. Among them, this paper discusses triangle heating and presents algorithms for determining heating shapes and locations. The heating shape is determined by using the in-plane strain distributions, which are calculated by nonlinear kinematics analysis between the designed and initial shapes, field survey results, and mechanics based on the neutral axis. To predict the angular distortion and shrinkage in various heating conditions, a functional relation of residual deformations is formulated. For the formulation, multivariate analysis and multiple regression techniques are used with data obtained from experiments of unit triangle heating and numerical analysis. Using the determined heating shapes and the functional relation for the residual deformations, a correct triangle heating position is determined by an algorithm, which can predict qualitatively correct angular distortion and shrinkage in the interior and quantitatively correct distortion values on the edge. Finally, analytic verification of the proposed method has been done by applying the method to a convex type plate used in the field. The proposed work can be used for automation of curved plate fabrication in the shipyards.

고유변형도법을 이용한 삼각가열에 의한 판 변형의 시뮬레이션

고유변형도법을 이용한 삼각가열에 의한 판 변형의 시뮬레이션

Prediction of steel plate deformation due to triangle heating using the inherent strain method

In a shipyard, line heating and triangle heating are two major processes carried out by skilled workers to form curved plates in various shapes under various heating conditions. There have been many studies on line heating, but triangle heating has rarely been studied owing to its complicated heating process with irregular multiheating paths and highly concentrated heat input. Triangle heating is the most labor-intensive job. Hence, it is essential for most shipyards to study the automation, as well as the improvement, of the triangle heating process in order to increase hull-forming productivity. In this study, a pioneering attempt to simulate triangle heating was made. A circular disk-spring model is proposed as an analysis model for the elastoplastic procedure of triangle heating, and the inherent strain method is also used to analyze the deformation of plates. The results of the simulation were compared with those of experiments and showed good agreement. It is shown that the present approach and the model used in this study are effective and efficient for simulating triangle heating for the steel plate forming process in shipbuilding.

Effect of line heating factors on transverse shrinkage generated by triangle heating

For automatization of the line heating work that is a basic technology in making curved surfaces of ships it needs to evaluate transverse shrinkage generated by triangle heating quantitatively. In this paper, techniques were examined in triangle heating tests and an estimation method using FEM analyses were developed in the first place. Secondly numerical simulations of triangle heating discussed effects of line heating factors that were curvature radius in the transverse direction, water-cooling and heating length. It was concluded that curvature radius in the transverse direction had least effect in transverse shrinkage and water cooling following the heating touch led to efficient shrinkage. And as the parameter value of heat input in the panel end part was increasing with varying travel speed, transverse shrinkage generated lager, so that it was approximately proportional to the parameter value. The maximum shrinkage was achieved when heating length was from 0.3 to 0.4 times as long as plate width.