Behaviour-based Manufacturing Control with Soft Computing Techniques

Abstract

Esnek Hesaplama yöntemleri, Üretim Yürütme Sistemlerinde (MES) bozulmaların ele alınması ve belirsizlik yönetiminin ortaya koyduğu zorlukları ele almak için son yıllarda yaygın olarak kullanılmaktadır. Bu araştırma makalesinin odak noktası, Davranış Tabanlı Kontroldeki sınıflandırma problemlerine yönelik Esnek Hesaplama yöntemlerinin uygulanmasıdır. Makale, bir üretim sisteminin davranışını belirlemek için sınıflandırma tekniklerinin kullanılmasını önermektedir. Bu, anormal davranışın tespit edilmesini sağladığı ve uygun düzeltici önlemlerin uygulanmasına izin verdiği için önemli bir görevdir. Önerilen sınıflandırma yöntemi, Yapay Sinir Ağları ve Bulanık mantık kullanımına dayanmaktadır. Sinir Ağları, verilerden öğrenme ve kalıplara dayalı tahminler yapma yetenekleri nedeniyle sınıflandırma görevleri için güçlü bir araçtır.

Keywords

• Soft Computing
• Manufacturing Execution Systems
• Behaviour Based Control

Behaviour-based Manufacturing Control with Soft Computing Techniques

Abstract

Soft Computing methods have been widely used in recent years to address the challenges posed by disturbances handling and uncertainty management in Manufacturing Execution Systems (MES). The focus of this research paper is on the application of Soft Computing methods for classification problems in Behaviour Based Control. The paper proposes the use of classification techniques to determine the behavior of a production system. This is an important task as it enables the detection of anomalous behavior and allows for the implementation of appropriate corrective measures. The proposed classification method is based on the use of Neural Networks and Fuzzy logic. Neural Networks are a powerful tool for classification tasks due to their ability to learn from data and make predictions based on patterns. The proposed method uses a feedforward neural network with a single hidden layer to classify the behavior of the production system. The inputs to the network are features extracted from the production system, while the output is the classification result. Fuzzy logic is also used in the proposed classification method to handle uncertainty in the input data. In conclusion, this research paper presents a novel approach to classification problems in Behaviour Based Control using Soft Computing methods. The proposed method shows promising results in handling disturbances and uncertainty in manufacturing systems. Further research in this area could lead to the development of more advanced Soft Computing methods for manufacturing systems, enabling more efficient and effective control and management of production processes.

Keywords

• Soft Computing
• Manufacturing Execution Systems
• Behaviour Based Control.

References

1. Parmenter, D. (2015). Key performance indicators: developing, implementing, and using winning KPIs. John Wiley & Sons.
2. Monostori, L., Kádár, B., Bauernhansl, T., Kondoh, S., Kumara, S., Reinhart, G., Sauer, O., Schuh, G., Sihn, W. & Ueda, K. (2016). Cyber-physical systems in manufacturing. Cirp Annals, 65(2), 621-641.
3. Probabilistic and general regression neural networks [Online]. Available https://www.dtreg.com/solution/probabilistic-and-general-regression-neural-networks
4. Hornyák, O., Erdélyi, F., & Kulcsár, G. (2006, September). Behaviour-based control for uncertainty management in manufacturing execution systems. In Proceedings of the 8th International Conference on The Modern Information Technology in the Innovation Processes of the Industrial Enterprises (pp. 73-79).
5. Lengyel, A. Erdélyi, F., Behaviour Based Combined Approaches to Uncertainty Management in Manufacturing Systems. in IWES 6th International Conference. Tokyo, pp. 77-83., 2016
6. Rouzafzoon, J., & Helo, P. (2016). Developing service supply chains by using agent based simulation. Industrial Management & Data Systems.
7. Mataric, M. J. (1997). Behaviour-based control: Examples from navigation, learning, and group behaviour. Journal of Experimental & Theoretical Artificial Intelligence, 9(2-3), 323-336.
8. Matarić, M. J. (1998). Behavior-based robotics as a tool for synthesis of artificial behavior and analysis of natural behavior. Trends in cognitive sciences, 2(3), 82-86.

9. Kober, J., Bagnell, J. A., & Peters, J. (2013). Reinforcement learning in robotics: A survey. The International Journal of Robotics Research, 32(11), 1238-1274..
10. Grossmann, I. E., Van Den Heever, S. A., & Harjunkoski, I. (2002, March). Discrete optimization methods and their role in the integration of planning and scheduling. In AIChE Symposium Series (pp. 150-168). New York; American Institute of Chemical Engineers; 1998.
11. Kovács, S., & Kóczy, L. T. (2004, July). Application of interpolation-based fuzzy logic reasoning in behaviour-based control structures. In 2004 IEEE international conference on fuzzy systems (IEEE Cat. No. 04CH37542) (Vol. 3, pp. 1543-1548). IEEE.