Location

Brunswick, ME

Start Date

1-1-1992 12:00 AM

Description

This paper describes the application of a neural network which was developed to perform a complex mapping [1]. The network utilizes phase quadrature information by, essentially, embedding the impedance plane representation in a network structure. The focus is on the implementation of the network in an automated inspection environment for the detection and classification of defects in the presence of severe deterministic noise arising from grain boundaries, machining grooves, and geometric discontinuities. We then go on to describe the possible use of chaotic oscillations for enhanced defect detection and the eventual marriage of chaotic oscillator phase plane data and the neural network for automated pattern recognition.

Book Title

Review of Progress in Quantitative Nondestructive Evaluation

Volume

11A

Chapter

Chapter 3: Interpretive Signal Processing and Image Reconstruction

Section

Neural Networks

Pages

733-740

DOI

10.1007/978-1-4615-3344-3_94

Language

en

File Format

application/pdf

Share

COinS
 
Jan 1st, 12:00 AM

The Use of Phase Quadrature Information for the Automated Detection and Classification of Defects in the Presence of Deterministic Noise

Brunswick, ME

This paper describes the application of a neural network which was developed to perform a complex mapping [1]. The network utilizes phase quadrature information by, essentially, embedding the impedance plane representation in a network structure. The focus is on the implementation of the network in an automated inspection environment for the detection and classification of defects in the presence of severe deterministic noise arising from grain boundaries, machining grooves, and geometric discontinuities. We then go on to describe the possible use of chaotic oscillations for enhanced defect detection and the eventual marriage of chaotic oscillator phase plane data and the neural network for automated pattern recognition.