Platform for Intelligent Manufacturing Systems with Elements of Knowledge Discovery

Mączka, Tomasz; Żabiński, Tomasz

doi:10.5772/35095

Cited by 4 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The obtained rules indicate machines for which the difficulty in maintaining stable production occurs. Further details can be found in [11]. The experiments described in this paper are a continuation of applying CI methods for discovering knowledge from the production events.…”

Section: Platform For Intelligent Manufacturingmentioning

confidence: 97%

See 1 more Smart Citation

Computational Intelligence application in fasteners manufacturing

Mączka

Żabiński

Kluska

2012

2012 IEEE 13th International Symposium on Computational Intelligence and Informatics (CINTI)

View full text Add to dashboard Cite

The paper describes the application of Computational Intelligence (CI) methods for knowledge discovery from data collected in manufacturing execution system (MES) operating in a fasteners manufacturing company. The purpose of the research is to find factors causing decrease in the efficiency of the fasteners production process. The structure and preparation phase of analyzed data, concerning daily work data of pushing machines for cold forging are presented. Chosen methodology, i.e. classification algorithms is briefly described. Experiments of finding relationships between production speed, material and product type in the form of if-then rules were performed. The results received a positive opinion of the company management board and give promising prospects for the CI methods implementation in the factory. It is planned to use the CI methods as a continuously working part of a platform for Intelligent Manufacturing System (IMS), which has been implemented in the factory.

show abstract

Section: Platform For Intelligent Manufacturingmentioning

confidence: 97%

“…Data for experiments was prepared in the form of intervals built from production events, like in experiment with association rules described in [11]. A Python script for data preparation was developed in order to transfer events into production intervals and attach additional attributes from the company ERP system.…”

Section: Data Preparationmentioning

confidence: 99%