SavedAdd your journal

Journals / Politeknik Dergisi / 2017 / Cilt: 20 - Sayı: 1

Dynamic Weight Estimation Application with Artificial Neural Networks

Yapay Sinir Ağları ile Dinamik Ağırlık Tahmin Uygulaması

MEHMET YUMURTACI
İSMAİL YABANOVA
Pages
37–41
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)

When the results were assessed, it has been determined that the weight prediction could be made successfully with the artificial neural networks in the dynamic measurement systems.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In our day when the capacities of manufacturing have increased rapidly, also the speedy weighting of manufactured products has become an important subject.
📊
Key Findings & Data:The artificial neural network was trained with the weight data taken from the measurement system and then, performance of the network was evaluated with the test data.
💡
Conclusion & Impact:When the results were assessed, it has been determined that the weight prediction could be made successfully with the artificial neural networks in the dynamic measurement systems.
🔬Design:Research Article
📍Scope:Comprehensive Sample
⚙️Variables:Dinamik Tartım · Yapay Sinir Ağları · Yük Hücresi

Abstract

In our day when the capacities of manufacturing have increased rapidly, also the speedy weighting of manufactured products has become an important subject. Because of this speed requirement, the products must be weighted on the weighing platform without being stopped. The weighting process of products in motion on the weighting platform without being stopped is called as dynamic weighting. However, in the dynamic weighting systems, the measurement signal is noisy as the weighted product is in motion and various methods must be used to determine the weight of product within a definite period of time. In this study, artificial neural networks were used to predict the weights of the weighted products in motion. The artificial neural network was trained with the weight data taken from the measurement system and then, performance of the network was evaluated with the test data. When the results were assessed, it has been determined that the weight prediction could be made successfully with the artificial neural networks in the dynamic measurement systems.

Özet

Üretim kapasitelerinin hızla arttığı günümüzde üretilen ürünlerin hızlı bir şekilde tartımı önemli bir konu haline gelmiştir. Bu hız ihtiyacından dolayı da ürünlerin tartım platformu üzerinde durdurulmadan tartılması gerekmektedir. Ürünlerin tartım platformu üzerinde durdurulmadan hareket halinde iken tartılması işlemine dinamik tartım denmektedir. Ancak dinamik tartım sistemlerinde tartılan ürünün hareketli olmasından dolayı ölçüm sinyali gürültülü olmaktadır. Ürünün ağırlığının belirli bir süre içerisinde tespit edilebilmesi için çeşitli yöntemlerin kullanılması gerekmektedir. Bu çalışmada hareket halinde tartılan ürünlerin ağırlıklarının tahminini gerçekleştirmek için yapay sinir ağları kullanılmıştır. Ölçüm sisteminden alınan ağırlık verileri ile yapay sinir ağı eğitilmiş ve daha sonra ağın performansı test verileri ile değerlendirilmiştir. Sonuçlar değerlendirildiğinde dinamik ölçüm sistemlerinde ağırlık tahmininin yapay sinir ağları ile başarılı bir şekilde yapılabileceği görülmektedir.

🔖

Cite This Article

YUMURTACI, M., YABANOVA, İ. (2017). Dynamic Weight Estimation Application with Artificial Neural Networks. Politeknik Dergisi, Cilt: 20 - Sayı: 1, 37–41. https://ajindex.com/articles/306551

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (13)

  1. Niedźwiecki, M. and Wasilewski, A., “Application of adaptive filtering to dynamic weighing of vehicles”, Control Engineering Practice, 4(5): 635-644, (1996)
  2. Yamazaki, T., Sakurai, Y., Ohnishi, H., Kobayashi, M. and Kurosu, S., “Continuous mass measurement in checkweighers and conveyor belt scales”, Proceedings of the 41st SICE Annual Conference, Osaka, 470-474, (2002)
  3. Boschetti, G., Caracciolo, R., Richiedei, D. and Trevisani, A., “Model-based dynamic compensation of load cell response in weighing machines affected by environmental vibrations”, Mechanical Systems and Signal Processing, 34(1-2): 116-130, (2013)
  4. Pietrzak, P., Meller, M. and Niedźwiecki, M., “Dynamic mass measurement in checkweighers using a discrete time-variant low-pass filter”, Mechanical Systems and Signal Processing, 48(1-2): 67-76, (2014)
  5. Jafaripanah, M., Al-Hashimi, B.M. and White, N.M., “Dynamic sensor compensation using analogue adaptive filter compatible with digital technology”, in Circuits, Devices and Systems, IEE Proceedings, 152(6): 745-751, (2005)
  6. Halimic, M., and Balachandran, W., “Kalman filter for dynamic weighing system”, in Industrial Electronics, 1995. ISIE '95., Proceedings of the IEEE International Symposium on, Athens, 2: 786-791, (1995)
  7. Jian, X., and Bin, M., “Investigation of discrete wavelet transform for signal de-noising in weight-in-motion system”, Future Computer and Communication (ICFCC), 2010 2nd International Conference on, Wuhan, 2: 769-772, (2010)
  8. Xiao, J. and Lv, P., “Application of wavelet transform in weigh-in-motion”, Intelligent Systems and Applications, 2009. ISA 2009. International Workshop on, Wuhan, 1- 4 (2009)
  9. Bin, M. and Xinguo, Z., “Discrete wavelet transform for signal processing in weight-in-motion system”, Electrical and Control Engineering (ICECE), 2010 International Conference on, Wuhan, 4668-4671, (2010)
  10. Zhang, Y. and Fu, H., “Dynamic weighing signalbprocessing by system identification”, in Industrial Mechatronics and Automation (ICIMA), 2010 2nd International Conference on, Wuhan, 2: 203-206, (2010)
  11. Almodarresi Yasin, S.M.T. and White, N.M., “Application of artificial neural networks to intelligent weighing systems”, in Science, Measurement and Technology, IEE Proceedings, 146(6): 265-269, (1999)
  12. Bahar, H.B. and Horrocks, D.H., “Dynamic weight estimation using an artificial neural network”, Artificial Intelligence in Engineering, 12 (1–2): 135-139, (1998)
  13. Halimic, M., B