Research Papers: Materials and Fabrication

An Artificial Neural Network Model to Predict Material Characteristics From the Results of Miniature Disk Bending Tests

[+] Author and Article Information
A. K. Ghosh

Trombay, Maharastra,
Mumbai 85, India
e-mail: ashok.ghosh@gmail.com

Vishnu Verma

Scientific Officer
Maharastra, Mumbai 85, India
e-mail: vishnuv@barc.gov.in

G. Behera

Scientific Assistant
Maharastra, Mumbai 85, India
e-mail: gourahar@barc.gov.in

1Corresponding author.

Contributed by the Pressure Vessel and Piping Division of ASME for publication in the JOURNAL OF PRESSURE VESSEL TECHNOLOGY. Manuscript received November 20, 2013; final manuscript received March 27, 2014; published online October 13, 2014. Assoc. Editor: Osamu Watanabe.

J. Pressure Vessel Technol 137(1), 011404 (Oct 13, 2014) (7 pages) Paper No: PVT-13-1195; doi: 10.1115/1.4027320 History: Received November 20, 2013; Revised March 27, 2014

The inverse problem of evaluating mechanical properties of material from the observed values of load and deflection of a miniature disk bending specimen is discussed in this paper. It involves analysis of large amplitude, elasto-plastic deformation considering contact and friction. The approach in this work is to first generate—by a finite element (FE) solution—a large database of load-displacement (P-w) records for varying material properties. An artificial neural network (ANN) is trained with some of these data. The errors in the various values of the parameters during testing with additional known data were found to be reasonably small.

Copyright © 2015 by ASME
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Fig. 1

Schematic drawing of setup for miniature disk bending test; specimen thickness (h) = 0.25 mm; d1 = 1 mm; d2 = 1.5 mm; R = 0.2 mm

Grahic Jump Location
Fig. 2

FE model of MDBT simulation (axisymmetric)

Grahic Jump Location
Fig. 3

Finite element simulations with different boundary condition and comparison with analytical and experimental results of MDBT

Grahic Jump Location
Fig. 4

Values of total resultant strain in the specimen at a load of 360 N

Grahic Jump Location
Fig. 5

Load versus deflection for varying: 5(a)-E; 5(b)-σy; 5(c)-m; 5(d)-A0 (other parameters at the base values)

Grahic Jump Location
Fig. 6

ANN scheme for evaluating material properties from load–displacement records

Grahic Jump Location
Fig. 7

Details of the ANN in Fig. 6. (Note: The outward connection from all the neurons have not been shown.)

Grahic Jump Location
Fig. 8

Load versus deflection—base case: (a) direct FEM with base values of parameters and (b) FEM with ANN predicted parameters

Grahic Jump Location
Fig. 9

Error in ANN-predicted values of Sy for all 81 cases




Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In