Morphology and autowave metric on CNN applied to Bubble-Debris classification

István Szatmári, Abraham Schultz, Csaba Rekeczky, Tibor Kozek, T. Roska, Leon O. Chua

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

In this study, we present the initial results of cellular neural network (CNN)-based autowave metric to high-speed pattern recognition of gray-scale images, the application is to a problem involving separation of metallic wear deris particles from air bubbles. This problem arises in an optical-based system for determination of mechanical wear. This paper focuses on distinguishing debris particles suspended in the oil flow from air bubbles and aims to employ CNN technology to create an online fault monitoring system. For the class of engines of interest bubbles occur much more often than debris particles and the goal is to develop a classification system with an extremely low false alarm rate for missclassififed bubbles. The designed analogic CNN algorithm detects and classifies single ubbles and bubble groups using inary morphology and autowave metric. The debris particles are separated based on autowave distances computed btween bubble models and the unknown objects. Initial experiments indicate that the proposed algorithm is robust and noise tolerant and when implemented on a CNN universal chip it provides a solution in real time.

Original languageEnglish
Pages (from-to)1385-1393
Number of pages9
JournalIEEE Transactions on Neural Networks
Volume11
Issue number6
DOIs
Publication statusPublished - 2000

Fingerprint

Cellular neural networks
Cellular Networks
Debris
Bubble
Neural Networks
Metric
Wear of materials
Air
Pattern recognition
False Alarm Rate
Network Algorithms
Engines
Monitoring System
Pattern Recognition
Monitoring
High Speed
Fault
Engine
Chip
Classify

Keywords

  • Autowave metric
  • Cellular neural networks (CNNs)
  • Hamming and Hausdorff distances
  • Model-based classification

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Theoretical Computer Science
  • Electrical and Electronic Engineering
  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Hardware and Architecture

Cite this

Morphology and autowave metric on CNN applied to Bubble-Debris classification. / Szatmári, István; Schultz, Abraham; Rekeczky, Csaba; Kozek, Tibor; Roska, T.; Chua, Leon O.

In: IEEE Transactions on Neural Networks, Vol. 11, No. 6, 2000, p. 1385-1393.

Research output: Contribution to journalArticle

Szatmári, István ; Schultz, Abraham ; Rekeczky, Csaba ; Kozek, Tibor ; Roska, T. ; Chua, Leon O. / Morphology and autowave metric on CNN applied to Bubble-Debris classification. In: IEEE Transactions on Neural Networks. 2000 ; Vol. 11, No. 6. pp. 1385-1393.
@article{486dd60cb9f64031a0a25aa10d4d5630,
title = "Morphology and autowave metric on CNN applied to Bubble-Debris classification",
abstract = "In this study, we present the initial results of cellular neural network (CNN)-based autowave metric to high-speed pattern recognition of gray-scale images, the application is to a problem involving separation of metallic wear deris particles from air bubbles. This problem arises in an optical-based system for determination of mechanical wear. This paper focuses on distinguishing debris particles suspended in the oil flow from air bubbles and aims to employ CNN technology to create an online fault monitoring system. For the class of engines of interest bubbles occur much more often than debris particles and the goal is to develop a classification system with an extremely low false alarm rate for missclassififed bubbles. The designed analogic CNN algorithm detects and classifies single ubbles and bubble groups using inary morphology and autowave metric. The debris particles are separated based on autowave distances computed btween bubble models and the unknown objects. Initial experiments indicate that the proposed algorithm is robust and noise tolerant and when implemented on a CNN universal chip it provides a solution in real time.",
keywords = "Autowave metric, Cellular neural networks (CNNs), Hamming and Hausdorff distances, Model-based classification",
author = "Istv{\'a}n Szatm{\'a}ri and Abraham Schultz and Csaba Rekeczky and Tibor Kozek and T. Roska and Chua, {Leon O.}",
year = "2000",
doi = "10.1109/72.883456",
language = "English",
volume = "11",
pages = "1385--1393",
journal = "IEEE Transactions on Neural Networks and Learning Systems",
issn = "2162-237X",
publisher = "IEEE Computational Intelligence Society",
number = "6",

}

TY - JOUR

T1 - Morphology and autowave metric on CNN applied to Bubble-Debris classification

AU - Szatmári, István

AU - Schultz, Abraham

AU - Rekeczky, Csaba

AU - Kozek, Tibor

AU - Roska, T.

AU - Chua, Leon O.

PY - 2000

Y1 - 2000

N2 - In this study, we present the initial results of cellular neural network (CNN)-based autowave metric to high-speed pattern recognition of gray-scale images, the application is to a problem involving separation of metallic wear deris particles from air bubbles. This problem arises in an optical-based system for determination of mechanical wear. This paper focuses on distinguishing debris particles suspended in the oil flow from air bubbles and aims to employ CNN technology to create an online fault monitoring system. For the class of engines of interest bubbles occur much more often than debris particles and the goal is to develop a classification system with an extremely low false alarm rate for missclassififed bubbles. The designed analogic CNN algorithm detects and classifies single ubbles and bubble groups using inary morphology and autowave metric. The debris particles are separated based on autowave distances computed btween bubble models and the unknown objects. Initial experiments indicate that the proposed algorithm is robust and noise tolerant and when implemented on a CNN universal chip it provides a solution in real time.

AB - In this study, we present the initial results of cellular neural network (CNN)-based autowave metric to high-speed pattern recognition of gray-scale images, the application is to a problem involving separation of metallic wear deris particles from air bubbles. This problem arises in an optical-based system for determination of mechanical wear. This paper focuses on distinguishing debris particles suspended in the oil flow from air bubbles and aims to employ CNN technology to create an online fault monitoring system. For the class of engines of interest bubbles occur much more often than debris particles and the goal is to develop a classification system with an extremely low false alarm rate for missclassififed bubbles. The designed analogic CNN algorithm detects and classifies single ubbles and bubble groups using inary morphology and autowave metric. The debris particles are separated based on autowave distances computed btween bubble models and the unknown objects. Initial experiments indicate that the proposed algorithm is robust and noise tolerant and when implemented on a CNN universal chip it provides a solution in real time.

KW - Autowave metric

KW - Cellular neural networks (CNNs)

KW - Hamming and Hausdorff distances

KW - Model-based classification

UR - http://www.scopus.com/inward/record.url?scp=0006191061&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0006191061&partnerID=8YFLogxK

U2 - 10.1109/72.883456

DO - 10.1109/72.883456

M3 - Article

C2 - 18249862

AN - SCOPUS:0006191061

VL - 11

SP - 1385

EP - 1393

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

SN - 2162-237X

IS - 6

ER -