Abstract

Robotic automation systems includes higher production rates and increased productivity, more efficient use of materials, better product quality, improved safety, and reduced factory lead times. Higher output and increased productivity have been two of the biggest reasons in justifying the use of automation. Despite the claims of high quality from good workmanship by humans, automated systems typically perform the manufacturing process with less variability than human workers, resulting in greater control and consistency of product quality. Also, increased process control makes more efficient use of materials, resulting in less scrap. Despite all these advantages, the final product control is still carried out by workers. In this study, it is planned to prevent quality problems with a video processing that integrates with the robotic automation line in order to solve the final quality problem. This system, which controls the movements of the worker in the predetermined motion routes with the signals coming from the line. It aims to ensure that the products going to the customer are completely error free.

References

[1]https://medium.com/t%C3%BCrkiye/yapay-zekan%C4%B1n-tarih%C3%A7esi-vegeli%C5%9Fim-s%C3%BCreci-cb4c73deb01d

[2] https://techy.works/genel/yapay-zeka-nedir/

[3] Kızrak, M. ve Bolat, B., (2018),"Derin Öğrenme ile Kalabalık Analizi Üzerine Detaylı Bir Araştırma", Bilişim Teknolojileri Dergisi, c.11, no.11, s. 263-286.

[4] https://www.wipo.int/edocs/pubdocs/en/wipo_pub_1055/2019.pdf 

[5] Şeker, B. ve Diri, B. ve Balık, H., (2017),"Derin Öğrenme Yöntemleri ve Uygulamaları Hakkında Bir İnceleme", Gazi Mühendislik Bilimleri Dergisi, c.3, no.3, s 47-64.

[6] Keskenler, M., Keskenler, E., (2017),"Geçmişten Günümüze Yapay Sinir Ağları ve Tarihçesi", Takvim-i Vekayi Dergisi, c.5, no.2, s.8-18.

[7] https://yapayzeka.ai/yapay-sinir-aglarinin-calisma-prensibi/2018/1/

[8] https://pjreddie.com/darknet/yolo/

[9] https://docs.python.org/3/

[10] https://docs.opencv.org/4.4.0/

[11] Cassidy, A. P.; Deviney, F. A. Calculating Feature Importance in Data Streams with Concept Drift Using Online Random Forest. 2014 IEEE International Conference on Big Data (Big Data), 2014.

[12]https://stanford.edu/~shervine/l/tr/teaching/cs-230/cheatsheet-convolutional-neuralnetworks

[13]https://towardsdatascience.com/r-cnn-fast-r-cnn-faster-r-cnn-yolo-object-detectionalgorithms-36d53571365e