Fault Diagnosis in Manufacturing Systems Using Machine Vision

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21220%2F21%3A00353844" target="_blank" >RIV/68407700:21220/21:00353844 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/PC52310.2021.9447495" target="_blank" >https://doi.org/10.1109/PC52310.2021.9447495</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/PC52310.2021.9447495" target="_blank" >10.1109/PC52310.2021.9447495</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Fault Diagnosis in Manufacturing Systems Using Machine Vision

Popis výsledku v původním jazyce

This paper describes the design and the verification of the method of fault diagnosis of production systems. A diagnosis system usually uses data obtained from a control loop (sensors, actuators, etc.). Unfortunately, clearly identify the fault is difficult or impossible. One set of symptoms can corresponds to more than one error. The conventional solution is to use additional sensors, however, this approach could lead to a parallel backup of the whole system. Here proposed solution is to use machine vision using OpenCV to obtain additional information about the state of the system, extend the set of symptoms and use them in the diagnostic module. In this work proposed diagnostic system is an extension of the previous designed one. A camera sensor was added. The data from the camera is evaluated and the diagnostic relevant objects are detected. These data are incorporated into the fault diagnostic system. The system was implemented and has been tested at a real simple electro-pneumatic circuit. The fault diagnostic system can detect hardware faults in the drive control loop like an electrical disconnection, low-pressure level, sensor, solenoid or PLC periphery malfunction.

Název v anglickém jazyce

Fault Diagnosis in Manufacturing Systems Using Machine Vision

Popis výsledku anglicky

This paper describes the design and the verification of the method of fault diagnosis of production systems. A diagnosis system usually uses data obtained from a control loop (sensors, actuators, etc.). Unfortunately, clearly identify the fault is difficult or impossible. One set of symptoms can corresponds to more than one error. The conventional solution is to use additional sensors, however, this approach could lead to a parallel backup of the whole system. Here proposed solution is to use machine vision using OpenCV to obtain additional information about the state of the system, extend the set of symptoms and use them in the diagnostic module. In this work proposed diagnostic system is an extension of the previous designed one. A camera sensor was added. The data from the camera is evaluated and the diagnostic relevant objects are detected. These data are incorporated into the fault diagnostic system. The system was implemented and has been tested at a real simple electro-pneumatic circuit. The fault diagnostic system can detect hardware faults in the drive control loop like an electrical disconnection, low-pressure level, sensor, solenoid or PLC periphery malfunction.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 23rd International Conference on Process Control

ISBN

978-1-6654-0330-6

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

313-318

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Štrbské Pleso

Datum konání akce

1. 6. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000723653400053