High resolution measurement of translucent plastic wall thicknesses by computerized tomography and neural networks.

Thomas Lee Hemminger, R. E. Farrell

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

Today there is a great deal of interest in the field of plastics design. Several methods can be employed to create plastic products such as injection molding, compression and transfer molding, and blow molding. This paper is concerned with blow molding which is a procedure employed to create hollow plastic containers such as those used to contain liquids and solids in the wholesale and retail markets. An important aspect of blow molding is the measurement of the wall thickness of semi-liquid plastic before the molding procedure has been initiated. Minimization of waste is rapidly becoming a critical consideration within the plastics community due to the cost of raw polymers. Unfortunately, it is also an extremely difficult task to measure the thickness considering the high temperatures and elasticity of the polymers in question. This paper presents initial research on a non-invasive approach for wall thickness measurements of semi-liquid plastics through the utilization of computerized tomography and neural networks. The work described here is based on simulations and on modeling data obtained through experimental means. This technique can be extended to other fields of research as well, such as those related to the development of glass and ceramic products.

Original languageEnglish (US)
Pages (from-to)317-324
Number of pages8
JournalInternational Journal of Neural Systems
Volume8
Issue number3
DOIs
StatePublished - Jan 1 1997

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'High resolution measurement of translucent plastic wall thicknesses by computerized tomography and neural networks.'. Together they form a unique fingerprint.

Cite this