SavedAdd your journal

Journals / Anadolu Üniversitesi Bilim ve Teknoloji Dergisi :A-Uygulamalı Bilimler ve Mühendislik / 2001 / Cilt: 2 - Sayı: 1

A minimizing total completion time based neural network approach for job shop scheduling

Atölye tipi üretim ortamında işlerin çizelgelenmesinde toplam tamamlanma zamanının en küçüklenmesine dayalı bir sinirsel ağ yaklaşımı

A. Sermet ANAGÜN
Ümit Ali ÖZKAZANÇ
Pages
125–136
Publication Date
2022-10-11
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The proposed framework has been tested on example problems consisting of different numbers of jobs and machines.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Neural networks, one of the promising approaches of artificial intelligence techniques, due to having the ability of learning, generalizing from situations and especially characteristic of parallel distributed processing, have become an alternative approach for solving the class of NP-hard optimization problems.
📊
Key Findings & Data:In this study, job shop scheduling problem, considered as a NP-hard optimizatoin problem, has been mapped onto Hopfıeld neural network.
💡
Conclusion & Impact:The proposed framework has been tested on example problems consisting of different numbers of jobs and machines.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters

Abstract

Neural networks, one of the promising approaches of artificial intelligence techniques, due to having the ability of learning, generalizing from situations and especially characteristic of parallel distributed processing, have become an alternative approach for solving the class of NP-hard optimization problems. In this study, job shop scheduling problem, considered as a NP-hard optimizatoin problem, has been mapped onto Hopfıeld neural network. Basically, problem has been defined by an energy function satisfying the objective of the minimizing the total completion time of all jobs and other related constraints. The aim is to form an acceptable possible schedules in a fast way by using the ability of parallel processing. The proposed framework has been tested on example problems consisting of different numbers of jobs and machines.

Özet

Yapay zeka tekniklerinden olan sinirsel ağlar, öğrenme, durumlardan çıkarsamalar yapabilme yetenekleri ve özellikle de bilginin paralel işlenebilmesi niteliği sayesinde çoğu NP-zor kapsamına giren eniyileme problemlerinin çözümü için bir alternatif yaklaşım olmuştur. Bu çalışmada, NP-zor sınıfına giren atölye tipi üretim ortamında işlerin çizelgelenmesi problemi Hopfield sinirsel ağı üzerinde yapılandırılmıştır. Problem, tüm işlerin toplam tamamlanma zamanını en küçükleyecek ve ilgili kısıtları sağlayacak biçimde bir enerji fonksiyonu ile tanımlanmıştır. Amaç, hızlı bir şekilde paralel dağıtılmış işleme yeteneklerinden yararlanarak kabul edilebilir olası çizelgeler oluşturmaktır. Önerilen yapı, iş ve makine sayısı yönüyle farklı örnek problemler üzerinde yapılandırılmış ve çözüm aranmıştır.

🔖

Cite This Article

ANAGÜN, A. S., ÖZKAZANÇ, Ü. A. (2022). A minimizing total completion time based neural network approach for job shop scheduling. Anadolu Üniversitesi Bilim ve Teknoloji Dergisi :A-Uygulamalı Bilimler ve Mühendislik, Cilt: 2 - Sayı: 1, 125–136. https://ajindex.com/articles/438516

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (13)

  1. Aiyer, S.V.B., Niranjan, M. ve Fallside, F. (1990). A Theoretical Investigation into the Performance of the Hopfield Model. IEEE Trans. Neural Networks, 1(2), 204-215.
  2. Anagün, A.S. (1999). Bilgi Güvenliğinin Sağlanmasında Kullanıcı Özelliklerine Dayalı Bir Yapay Sinirsel Ağ Yaklaşımı. Endüstri Mühendisliği, 10(4), 3-11.
  3. Cichocki, A. ve Unbehauen, R. (1993). Neural Networks for Optimization and Signal Processing. Wiley and Sons, Chichester. Cheung, J. Y. (1994). Scheduling. Artificial Neural Networks for Intelligent Manufacturing, edited by Cihan H. Dagli, Chapmann and Hall, Londra. Dagli, C. H. ve Poshyanonda, P. (1994). Basic Artificial Neural Networks Architectures. Artificial Neural Networks for Intelligent Manufacturing, edited by Cihan H. Dagli, Chapmann and Hall, Londra. Freeman, J.A. ve Skapura, D.M. (1991). Neural Networks: Algorithms, Applications arul Programming Techniques. Addison Wesley Publishing. Foo, S.Y. ve Takefuji, Y. (1988a). Stochastic Neural Networks for Solving Job Shop Scheduling Part 1.Problem Presentation. Proc. Int. Conf. Neural Networks, 2,275-282.
  4. Foo, S.Y. ve Takefuji, Y. (1988b). Stochastic Neural Networks for Solving Job Shop Scheduling Part 2. Architecture and Simulations. Proc. Int. Conf. Neural Networks. 2, 283-290.
  5. Foo, S.Y., Takefuji, Y. ve Szu, H. (1995). Scaling Properties of Neural Networks for Job Shop Scheduling. Neurocomputing, 8(1), 79-91.
  6. Grossberg, S. (1988). Nonlinear Neural Networks: Principles. Mechanisms and Architectures. Neural Networks. 1, 17-61.
  7. Haykin, S., (1994). Neural Networks: A Comprehensive Foundation. Prentice Hall. Hopfield, J. J. ve Tank, D. W. (1986). Computing with Neural Circuits: A Model. Science, 233,625-639.
  8. Hopfield, J. J. ve Tank, D. W. (1985). Neural Computation of Decisions in Optimization Problems. Biological Cybernetics, 52, 141-152.
  9. Hopfield, J. J. (1984). Neurons with Graded Response have Collective Computational Properties like those of Two-State Neurons. Proc. Natl. Acad. Sci., 81, 3088-3092.
  10. Hopfield, J. J. (1982). Neural Networks and Physical Systems with Emergent Collective Computational Abilities. Proc. Natl. Acad. Sci., 79, 2554-2558.
  11. Jain, A. S. ve Meeran, S. (1998). Job Shop Scheduling Using Neural Networks. International Journal of Production Research, 36(5), 1249-1272.
  12. Knapp, G.M. ve Wang, H.-P. (1992). Machine Fault Classification: A Neural Network Approach. International Journal of Production Research, 30(4), 881-823.
  13. Looi, C.K. (1992). Neural Network Methods in Comb