Line Balancing Based on Error Rate Estimation with Artificial Neural Networks in Assembly Line Operations

Kenan Özden; Atakan Tahsin

Makale detayları

Line Balancing Based on Error Rate Estimation with Artificial Neural Networks in Assembly Line Operations

Yazarlar:

Kenan Özden | Atakan Tahsin

Yayıncı:

İstanbul Gelisim University

Ana Başlıklar:

Endüstri Mühendisliği | Teknoloji Yönetimi ve İş Modelleri

Dergi:

İstanbul Gelişim Üniversitesi Sosyal Bilimler Dergisi Vol.10 Issue 1, pp.16-32

Belge Tipi:

Makale

Yayın Tarihi:

3/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001287153

pISSN:

2148-4287

Anahtar kelimeler:

Özet:

 In this study, in the assembly line systems consisting of the operations in interaction with each other; To reduce the number of faulty products, to prevent poor quality and to reduce the production time, Error Ratio Estimation with Artificial Neural Networks and probabilistic Line Balancing method have been performed. The error rate estimation provides information on which jeans models should be applied in the improvement work to eliminate existing errors in place. In the study, using the Levenberg - Marquardt Learning Algorithm, machine learning was determined by the experimental design method. At the same time, it has been used as an artificial intelligence algorithm in the multi-directional decision making stages, estimation and line balancing parts. In Assembly Line Equilibration, it has been aimed to re-stabilize the unbalanced line with the influence of post-forecasting process recovery. The Probabilistic Line Balancing method has been used because the processing times are stochastic variable and statistical data and mathematical algorithms digital algorithms can be created. When the results are examined, a successful forecasting process has been carried out for two different five-pocket jeans models which has been selected and it has been seen that the work components of the probabilistic line balancing method enable it to be precisely assigned to work stations. And it has given reliable results.

 In this study, in the assembly line systems consisting of the operations in interaction with each other; To reduce the number of faulty products, to prevent poor quality and to reduce the production time, Error Ratio Estimation with Artificial Neural Networks and probabilistic Line Balancing method have been performed. The error rate estimation provides information on which jeans models should be applied in the improvement work to eliminate existing errors in place. In the study, using the Levenberg - Marquardt Learning Algorithm, machine learning was determined by the experimental design method. At the same time, it has been used as an artificial intelligence algorithm in the multi-directional decision making stages, estimation and line balancing parts. In Assembly Line Equilibration, it has been aimed to re-stabilize the unbalanced line with the influence of post-forecasting process recovery. The Probabilistic Line Balancing method has been used because the processing times are stochastic variable and statistical data and mathematical algorithms digital algorithms can be created. When the results are examined, a successful forecasting process has been carried out for two different five-pocket jeans models which has been selected and it has been seen that the work components of the probabilistic line balancing method enable it to be precisely assigned to work stations. And it has given reliable results.

 In this study, in the assembly line systems consisting of the operations in interaction with each other; To reduce the number of faulty products, to prevent poor quality and to reduce the production time, Error Ratio Estimation with Artificial Neural Networks and probabilistic Line Balancing method have been performed. The error rate estimation provides information on which jeans models should be applied in the improvement work to eliminate existing errors in place. In the study, using the Levenberg - Marquardt Learning Algorithm, machine learning was determined by the experimental design method. At the same time, it has been used as an artificial intelligence algorithm in the multi-directional decision making stages, estimation and line balancing parts. In Assembly Line Equilibration, it has been aimed to re-stabilize the unbalanced line with the influence of post-forecasting process recovery. The Probabilistic Line Balancing method has been used because the processing times are stochastic variable and statistical data and mathematical algorithms digital algorithms can be created. When the results are examined, a successful forecasting process has been carried out for two different five-pocket jeans models which has been selected and it has been seen that the work components of the probabilistic line balancing method enable it to be precisely assigned to work stations. And it has given reliable results.

 Bu çalışmada birbiri ile etkileşim halinde olan operasyonlardan oluşan montaj hattı sistemlerinde; Hatalı ürün sayısını azaltmak, kalitesizliği önlemek ve üretim süresini azaltmak için Yapay Sinir Ağları ile Hata Oranı Tahmini ve olasılıksal Hat Dengeleme yöntemi yapılmıştır. Hata oranı tahmini, mevcut hataları yerinde gidermek için iyileştirme çalışmasında hangi kot modellerinin uygulanması gerektiği hakkında bilgi verir. LevenbergMarquardt Öğrenme Algoritması kullanılarak yapılan çalışmada deneysel tasarım yöntemiyle makine öğrenmesi belirlenmiştir. Aynı zamanda çok yönlü karar verme aşamalarında, tahmin ve hat dengeleme kısımlarında yapay zekâ algoritması olarak kullanılmıştır. Montaj Hattı Dengeleme de, tahmin sonrası süreç iyileştirme etkisi ile dengesiz hattın yeniden dengelenmesi amaçlanmıştır. İşlem süreleri stokastik değişken ve istatistiksel veriler ve matematiksel algoritmalar dijital algoritmalar oluşturulabilir olduğu için Probabilistic Hat dengeleme yöntemi kullanılmıştır. Sonuçlar incelendiğinde seçilen iki farklı beş cepli kot pantolon modeli için başarılı bir tahmin süreci gerçekleştirilmiş ve olasılıksal hat dengeleme yönteminin iş bileşenlerinin iş istasyonlarına tam olarak atanmasını sağladığı ve güvenilir sonuçlar görülmüştür.

Makale detayları

Line Balancing Based on Error Rate Estimation with Artificial Neural Networks in Assembly Line Operations

Yazarlar:

Kenan Özden | Atakan Tahsin

Yayıncı:

İstanbul Gelisim University

Ana Başlıklar:

Endüstri Mühendisliği | Teknoloji Yönetimi ve İş Modelleri

Dergi:

İstanbul Gelişim Üniversitesi Sosyal Bilimler Dergisi Vol.10 Issue 1, pp.16-32

Belge Tipi:

Makale

Yayın Tarihi:

3/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001287153

pISSN:

2148-4287

Assembly Line Balancing

Artificial Neural Networks

Multilayer Perception Model Probability

Levenberg-Marquardt Learning Algorithm

Probabilistic Line Balancing Method

Apparel Department in Textile

Artificial Intelligence application example to increase Efficiency and Quality

Montaj Hattı Dengeleme

Yapay Sinir Ağları

Çok Katmanlı Algı Modeli Olasılık

Levenberg-Marquardt Öğrenme Algoritması

Olasılık Hattı Dengeleme Yöntemi

Tekstilde Konfeksiyon Bölümü

Üretim Verimliliğini ve Kaliteyi Artırmak için Yapay Zeka uygulama örneği

Sayı

Makale detayları

Yazarlar: Kenan Özden | Atakan Tahsin

Yayıncı: İstanbul Gelisim University

Ana Başlıklar: Endüstri Mühendisliği | Teknoloji Yönetimi ve İş Modelleri

Dergi: İstanbul Gelişim Üniversitesi Sosyal Bilimler Dergisi Vol.10 Issue 1, pp.16-32

Belge Tipi: Makale

Yayın Tarihi: 3/2023

Belge Dili: İngilizce

Document ID (Org No.): 2001287153

pISSN: 2148-4287

Sayı

Yazarlar:

Kenan Özden | Atakan Tahsin

Yayıncı:

İstanbul Gelisim University

Ana Başlıklar:

Endüstri Mühendisliği | Teknoloji Yönetimi ve İş Modelleri

Dergi:

İstanbul Gelişim Üniversitesi Sosyal Bilimler Dergisi Vol.10 Issue 1, pp.16-32

Belge Tipi:

Makale

Yayın Tarihi:

3/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001287153

pISSN:

2148-4287