A New Approach to Preform Design in Metal Forging Processes Based on the Convolution Neural Network

This study presents an innovative methodology for preform design in metal forging processes based on the convolution neural network (CNN) algorithm. The proposed approach extracts the features of inputted forging product geometries and utilizes them to derive the corresponding preform shapes by employing weight arrays (filters) determined during the convolutional operations. The filters are progressively updated during the training process, emulating the learning steps of a process engineer responsible for the design of preform shapes for the forging processes. The design system is composed of multiple three-dimensional (3D) CNN sub-models, which can automatically derive individual 3D preform design candidates. It also implies that the 3D surfaces of preforms are easily acquired, which is important for the forging industry. The proposed preform design methodology was validated by applying it to two-dimensional (2D) axisymmetric shapes, one-quarter plane-symmetric 3D shapes, and two other industrial cases. In all the considered cases, the design methodology achieved substantial reductions in the forging load without forging defects, proving its reliability and effectiveness for application in metal forging processes.

Variable-thickness design of CFRP B-pillar reinforcement considering draping

An integrated optimization method that comprehensively considers draping factors such as fiber reorientations and cutting of layers is proposed for designing CFRP B-pillar reinforcement with a variable thickness. A laminate parameterization scheme, the local shared layer parameterization scheme (LSL-PS), is developed to parameterize the physical composition of laminates with variable-thickness. Kinematic draping simulations and preform designs are introduced to evaluate fiber reorientations and eliminate manufacturing defects. The optimization design of the B-pillar reinforcement is integrated with a LSL-PS, draping-simulation and preform-design, a RBF surrogate model and GA. At the same time, a comparative optimization without the consideration of draping factors is performed in parallel. The comparison results show that considering draping not only helps designers eliminate manufacturing defects but also helps to obtain a further weight reduction of 13.33% because fiber reorientations are fully utilized to improve the structural performance.

Preform design in axial hot closed die forging by isothermal surface method. Part 3. Preform design of industrial cases

The isothermal surfaces method for preform design is proposed. The procedure for determining of the preform shape is given. The features in using of the method for forgings with various shapes are considered. The method is illustrated by industrial examples. The design algorithm uses the QForm metal forming simulation software to build isothermal surfaces and check the quality of the designed die geometry by finite element modeling, as well as specially developed version of the QFormDirect CAD based on SpaceClaimтм.

Preform design in axial hot closed die forging by isothermal surface method. Part 1. Overview of preform design methods. Theoretical aspects and algorithm of preform shape design

Methods of preform design in hot-die forging are analyzed. It is noted that despite numerous works in this fi eld, preform design is still often based on the trial-and-error method. The isothermal surfaces method for preform design is proposed and its mathematical basis is considered. The procedure for determining of the preform shape is given. The design algorithm uses the QForm metal forming simulation software to build isothermal surfaces and check in the quality of the designed die geometry by finite element modeling, as well as specially developed version of the QFormDirect CAD based on SpaceClaim™.

Preform design in axial hot closed die forging by isothermal surface method. Part 2. Application of isothermal surfaces method for complex shape forgings

The isothermal surfaces method for preform design is proposed. The procedure for determining of the preform shape is given. The features in using of the method for forgings with various shapes are considered. The method is illustrated by industrial examples. The design algorithm uses the QForm metal forming simulation software to build isothermal surfaces and check the quality of the designed die geometry by finite element modeling, as well as specially developed version of the QFormDirect CAD based on SpaceClaimтм.

Optimization of Preform Design in Tadeusz Rut Forging of Heavy Crankshafts

Tadeusz Rut (TR) forging is a widely used forging method to create heavy, solid crankshafts for marine or power-generating engines. The preform of a TR forging is forged into a crank throw by simultaneously applying both a vertical and a horizontal deformation. It is necessary to optimize the preform design, since a conventional analytical design for the preform gives various choices for the geometric variables. The purpose of the current study is to optimize the preform design in TR forging for heavy crankshafts in order to improve the dimensional accuracy of a forged shape using a limited material volume. A finite element (FE) model for TR forging was developed and validated by comparing with experimental results. Parametric FE analyses were used to evaluate the effects of the geometric variables of the preform on the final dimensions of the forged product. The geometric variables of the preform were optimized by a response-surface method (RSM) to obtain the results of parametric FE analyses. The volume allocation between the pin and the web of the preform is the dominant factor that affects the desirability of the final forged shape. A multi-objective optimization is employed to consider the mutually exclusive changes of local machining allowances of the final forged product. Optimization using a response-surface method is a useful tool to reach the large and uniform machining allowances that are required for the preform necessary for a TR forging.