An apparatus, system, and method of forming a mold insert for an injection molding operation, comprising: providing a design of an injection mold part; analyzing, by a predictive model, the design to determine a conformal cooling arrangement for a mold insert for forming the injection mold part; and forming the mold insert including the conformal cooling arrangement.

An adhesion prediction method of predicting adhesion of metal particles in a workpiece to a die in a forging process using an aluminum-based material as the workpiece includes: a cumulative friction work amount calculation step of calculating a cumulative friction work amount generated between the workpiece and the die; a metal diffusion analysis step of analyzing a diffusion state of the metal particles between the workpiece and the die; and an adhesion prediction determination step of predicting a state of occurrence of the adhesion of the metal particles to the die, considering the cumulative friction work amount calculated in the cumulative friction work amount calculation step, the diffusion state analyzed in the metal diffusion analysis step, and a film thickness of a lubricating film provided on a surface of the die that comes into contact with the workpiece.

A method includes two or more reference strain gradient information being a relationship between the strain at the hole edge and a strain gradient along a radial direction. Hole expansion forming is performed on the evaluation metal sheet under the same forming conditions as respective forming conditions corresponding to at least two pieces of the reference strain gradient information to obtain at least two limit hole expansion ratios at a hole expansion limit of the evaluation metal sheet. A formable region of the evaluation metal sheet is obtained from the at least two pieces of the reference strain gradient information and the obtained at least two limit hole expansion ratios at the hole expansion limit. Stretch flange cracking at the sheared end face of the evaluation metal sheet is evaluated by the obtained formable region.

A software-implemented method is described for processing results of a simulation carried out with finite element analysis software, the software being adapted to simulate a filling process of a molded piece in a mold by a molten material injected into it, wherein: results are taken from a file of simulation results, a computer Database containing technical specifications of injection molding machines is accessed and a search is performed in the Database comparing the results read from the file with technical specifications stored in the Database and associated with each press to determine whether or not one or each press of the Database is able to perform the process.

Deep learning approaches and systems are described to control the process of casting physical objects. A neural network, operating on one or more processors of a server or distributed computing resources and maintained in one or more data storage devices, is trained to recognize relationships between the target digital representation and the resulting metal parts that are cast, and a number of specific approaches are described herein to overcome technical issues in relation to misalignments between reference points, among others. These deep learning approaches are then used for generation of command or control signals which modify how the casting process is conducted. Command or control signals can be used to modify how a cast mold is made, to modify environmental variables, to modify manufacturing parameters, and combinations thereof.

A system may include an access engine and a foam part generation engine. The access engine may be configured to access a computer-aided design (CAD) seat surface that represents a seat surface of a seat design and access seat parameters for the seat design. The foam part generation engine may be configured to construct a CAD foam part for the seat design based on the CAD seat surface and the seat parameters.

A computer-implemented method, computer program, system and apparatus for computing a thermal thickness and providing pre-manufacturing feedback on a design of a three-dimensional physical object that is to be formed by solidification of a fluid in a mold. An equation is solved, representing heat release through the cavity-mold interface when the object is formed. The thermal thickness and its uniformity provide insight in the manufacturability of the object, and may be used to automatically generate pre-manufacturing feedback. The thermal thickness and pre-manufacturing feedback are transmitted or displayed to a user.

The present disclosure provides a method for collecting parameters for casting solidification simulation and a gridded design method for a pouring and riser system, comprising calculating thermodynamic parameters of a superalloy; obtaining cooling curves of the superalloy with different thickness; measuring a linear expansion coefficient of the superalloy as a function of temperature; the design method comprising: simulating a solidification process with tubular features of different thickness, and determining a feeding distance of the features of different thickness; establishing a gridded pouring and riser system, dividing the casting into a plurality of modules according to the thickness, and dividing a cell inside each module, and ensuring that a size of the cell is less than the feeding distance with the thickness; simulating filling and solidification of castings and the gridded pouring and riser system, and analyzing simulation results of defects.

Disclosed is a learning method for performing virtual-actual correction by machine learning-assisted simulation of a pressure numerical value, the method including: in a pre-step: obtaining actual production data of executing a process parameter by a production device; in a first extraction step: analyzing the actual production data using an autoencoder to obtain a plurality of first features; in a simulation step: executing simulated production data of the process parameter using a production prediction model; in a second extraction step: analyzing the simulated production data using the autoencoder to obtain a plurality of second features; and in a training step: training the plurality of first features and the plurality of second features using a multilayer perceptron (MLP) to obtain a correction model, wherein the correction model can be provided for the MLP to correct the simulated production data into the corresponding actual production data.

A measuring apparatus of bulk viscosity includes a temperature-controlling cylinder having a test chamber for holding a molding material and at least one piston configured to seal an opening of the temperature-controlling cylinder. The temperature-controlling cylinder and the at least one piston are configured for measuring pressures, specific volumes and temperatures (PVT) of the molding material by applying a plurality of cooling rates to the molding material inside the testing chamber under an isobaric environment, or applying a plurality of mechanical pressures to the molding material inside the testing chamber under an isothermal environment. The measuring apparatus further includes a process module configured for deriving a plurality of parameters in relation to the pressures, specific volumes and temperatures (PVT) of the molding material based on the measurement; deriving an equilibrium pressure based on the plurality of parameters obtained from a first slowest cooling rate among the plurality of cooling rates.