Zero Defect Manufacturing Using Digital Numerical Control

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F22%3A10253821" target="_blank" >RIV/61989100:27240/22:10253821 - isvavai.cz</a>

Výsledek na webu

<a href="https://journals.pan.pl/dlibra/publication/142383/edition/124578/content" target="_blank" >https://journals.pan.pl/dlibra/publication/142383/edition/124578/content</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.24425/mper.2022.142383" target="_blank" >10.24425/mper.2022.142383</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Zero Defect Manufacturing Using Digital Numerical Control

Popis výsledku v původním jazyce

This paper proposes the application of the digital numerical control (DNC) technique to con-nect the smart meter to the inspection system and evaluate the total harmonic distortion (THD) value of power supply voltage in IEEE 519 standard by measuring the system. Ex-perimental design by the Taguchi method is proposed to evaluate the compatibility factors to choose Urethane material as an alternative to SS400 material for roller fabrication at the machining center. Computer vision uses artificial intelligence (AI) technique to identify object iron color in distinguishing black for urethane material and white for SS400 material, color recognition results are evaluated by measuring system, system measurement is locked when the object of identification is white material SS400. Computer vision using AI technology is also used to recognize facial objects and control the layout of machining staff positions according to their respective skills. The results obtained after the study are that the surface scratches in the machining center are reduced from 100% to zero defects and the surface polishing process is eliminated, shortening production lead time, and reducing 2 employees. The total operating cost of the processing line decreased by 5785 USD per year. Minitab 18.0 software uses statistical model analysis, experimental design, and Taguchi technical analysis to evaluate the process and experimentally convert materials for roller production. MATLAB 2022a runs a computer vision model using artificial intelligence (AI) to recognize color ob-jects to classify Urethane and SS400 materials and recognize the faces of people who control employee layout positions according to their respective skills.

Název v anglickém jazyce

Zero Defect Manufacturing Using Digital Numerical Control

Popis výsledku anglicky

This paper proposes the application of the digital numerical control (DNC) technique to con-nect the smart meter to the inspection system and evaluate the total harmonic distortion (THD) value of power supply voltage in IEEE 519 standard by measuring the system. Ex-perimental design by the Taguchi method is proposed to evaluate the compatibility factors to choose Urethane material as an alternative to SS400 material for roller fabrication at the machining center. Computer vision uses artificial intelligence (AI) technique to identify object iron color in distinguishing black for urethane material and white for SS400 material, color recognition results are evaluated by measuring system, system measurement is locked when the object of identification is white material SS400. Computer vision using AI technology is also used to recognize facial objects and control the layout of machining staff positions according to their respective skills. The results obtained after the study are that the surface scratches in the machining center are reduced from 100% to zero defects and the surface polishing process is eliminated, shortening production lead time, and reducing 2 employees. The total operating cost of the processing line decreased by 5785 USD per year. Minitab 18.0 software uses statistical model analysis, experimental design, and Taguchi technical analysis to evaluate the process and experimentally convert materials for roller production. MATLAB 2022a runs a computer vision model using artificial intelligence (AI) to recognize color ob-jects to classify Urethane and SS400 materials and recognize the faces of people who control employee layout positions according to their respective skills.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20201 - Electrical and electronic engineering

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2022

Kód důvěrnosti údajů

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

Název periodika

Management and Production Engineering Review

ISSN

2080-8208

e-ISSN

2082-1344

Svazek periodika

13

Číslo periodika v rámci svazku

3

Stát vydavatele periodika

PL - Polská republika

Počet stran výsledku

14

Strana od-do

61-74

Kód UT WoS článku

000874550600006

EID výsledku v databázi Scopus

—