Consistent and minimal springback using a stepped binder force trajectory and neural network control

Article Abstract:

Results show that the neural network determines the high binder force and punch displacement percentage of the stepped binder force trajectory controlling springback and maximum strain in Aluminum channel forming process.

United States, Statistical Data Included, Computer networks, Testing, Binders (Materials), Sheet-metal, Sheet metal

---

Effective models for prediction of springback in flanging

Article Abstract:

Meshfree Method using the Reproducing Kernel Particle Methods is used for prediction of springback angle in a straight flanging operation. The isotropic law is unable to predict the springback as well as material property described by the kinematic hardening law.

Kernel functions, Mechanics, Engineering mechanics, Material facts (Law)

---

Experimental implementation of neural network springback control metal forming

Article Abstract:

The controlling of the springback of a steel channel forming process using an artificial neural network and a stepped binder force trajectory is presented. It concluded that the neural network control algorithm is able to effectively capture the non-linear relationships and interactions of the process parameters.

Steel, Mechanical properties, Neural network

Similar abstracts:

• Abstracts: Conservation is key to preventing water exports from the Great Lakes, IJC concludes. Flooded with U.S. hazardous waste imports, Canada rethinks its rules
• Abstracts: Numerical analysis of welding residual stress and its verification using neutron diffraction measurement. Residual stress reduction and fatigue strength improvement by controlling welding pass sequences

This website is not affiliated with document authors or copyright owners. This page is provided for informational purposes only. Unintentional errors are possible.