TR
Avrasya Ekonometri �statistik ve Ampirik Ekonomi DergisiYl:2015 Say: 2 Alan: statistik-Saysal Yntemler-Ekonometri

ebnem KOLTAN YILMAZ, M. Mustafa YCEL
Do?rusal Vektr Kuantizasyon modeli kullan?larak yapay sinir a?lar?yla beton bas?n dayan?m? kontrol ?emalar?nda rnt tan?ma
 
Bu almada ama, iletmenin kalite amalarnn yerine getirilmesi olarak tanmlanan srete ortaya kan ya da gelecekte meydana gelebilecek hatalar tespit etmek ve bunlar iyiletirmek iin Yapay Zeka (YZ) tekniklerinden biri olan Yapay Sinir Alarnn (YSA) uygulanabilirliini gstermektir. Bylece kalite dzeyini ykseltmek, iletme maliyetlerini azaltmak, zaman tasarrufu, alanlar motive etmek, mteri ikayetlerini azaltmak gibi kalite kontrolnn gerekleri olan temel amalara katk salanabilecektir. Bu kapsamda, hazr beton reten bir iletmenin en nemli kalite gstergelerinden biri olan basn dayanm ortalamalar kullanlmtr. YSA modeli olan Dorusal Vektr Kuantizasyon (DVK) modeli kullanlarak kontrol emalarna ilikin kalite karakteristii gzlem deerleri ve kontrol emalarna ilikin parametrelerle iki model kurulmu, modeller karlatrldnda kalite karakteristii gzlem deerleriyle oluturulan modelin kontrol emalarna ilikin parametrelerle oluturulan modele gre daha baarl sonular verdii ortaya konmutur.

Anahtar Kelimeler: Kontrol emalarnda rnt Tanma (KT), Yapay Sinir Alar, Dorusal Vektr Kuantizasyon (DVK), Beton Basn Dayanm, Beton Kalite.


Concrete strength control charts pattern recognition based on Linear Vector Quantization neural networks
 
The objective in this study is to detect the errors that occur or may occur in the future during the process in which the companys quality objectives are fulfilled and to show the applicability of the Artificial Neural Networks (ANN) which is one of the Artificial Intelligence (AI) techniques. Thus, it will be able to contribute to the main purposes which make quality control necessary such as to raise the level of quality, reduce operating costs, time savings, raising employees motivation and reducing customer complaints. For this purpose, average compressive strength, one of the most important quality indicators, of a company that produces ready-mixed concrete has been used. Linear Vector Quantization (LVQ) type ANN model has been established by using the quality characteristics observation values related to control charts and the parameters related to control charts, and when these two models are compared, it has been found out that the model whose quality characteristics have been constructed using the observation values result in more successful results than that constructed with the model's control charts.

Keywords: Pattern Recognition in Control Charts (CCPR), Neural Networks, Linear Vector Quantization (LVQ), Concrete Strength, Concrete Quality.


Detay

ÇERK