Yapay zeka tabanlı araç koltuğu tanıma sisteminin geliştirilmesi
Yükleniyor...
Dosyalar
Tarih
2023
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Bursa Teknik Üniversitesi, Lisansüstü Eğitim Enstitüsü
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
Motorlu taşıtların tasarlandığı, üretildiği ve pazarlanarak satıldığı iş alanına otomotiv sektörü denilmektedir. Sektörün yaklaşık %70'inde otomobil imalatları yer almaktadır. Otomobili oluşturan bir çok parça bulunmaktadır. Motor, tekerlek, metal gövde ve kapılar, koltuk, plastik paneller gibi yaklaşık 5.000 parçadan oluşur. Her parçayı imal eden yan sanayiler de sektörde önemli role sahiptir. Bu çalışmada, koltuk üreten bir yan sanayi firmasındaki bir araç modeline ait koltuk tipleri incelenmiştir. Otomotiv sektöründe, senelik yaklaşık 300.000 adet sadece bir modele ait araç üretimi gerçekleşmektedir. Her bir aracın ön sırasında bir adet sürücü koltuğu ve bir adet yolcu koltuğu olmak üzere, toplam iki adet koltuk bulunmaktadır. Koltukların kumaş tiplerine göre ayırım yapıldığında, altı farklı model bulunmaktadır. Koltuk üreten yan sanayi firmalarında, senelik her model için ortalama 600.000 adet koltuk imalatı gerçekleşmektedir. Derin öğrenme temelli bilgisayar görüsü teknolojisinin gelişmesiyle birlikte üretilen koltukların modellerine göre otomatik tanımlanması, stoklanması için uygulama ihtiyacı ortaya çıkmıştır. Yüksek stok maliyetleri, hatalı üretim ve etiket, otomotiv firmalarının en büyük problemleri arasındadır. Endüstri 4.0 ile birlikte akıllı makineler sayesinde akıllı üretimler ve kontroller yapılabilmektedir. Hızlı, yüksek doğruluk oranı ve düşük maliyetler ile yüksek maliyetli problemlerden uzaklaşılmıştır. Yapay zeka teknolojilerinin kullanıldığı akıllı makineler sayesinde, akıllı üretim teknolojileri geliştirilmiştir. Yüksek çözünürlüklü kameralar, hassasiyeti yüksek algılayıcı sensörler, otomasyon taşıyıcı sistemler ile üretilen ürünler daha hızlı ve doğru olmaktadır. Bu çalışmada, otomobil modeline ait farklı versiyon koltuklarını üreten bir otomotiv yan sanayi firmasında, stok alanı ve üretim öncesi ile sonrası koltuk modellerinin otomatik ayrılması amaçlanmıştır. Bu çalışmada daha önce üretim alanlarında ve stok bölgelerinde konumlandırılmış olan araba koltukları kullanılarak otomatik nesne (koltuk) tespitinin yapılması için yapay zeka yönteminden yararlanılmıştır. Koltuk tiplerine göre eğitim ve test verileri oluşturulmuştur. Her bir koltuğa ait modelin fotoğrafları farklı ortamlarda çekilmiştir. Fotoğraflar model tipine göre tek tek etiketlenerek, test ve eğitim verileri oluşturulmuştur. Faster R-CNN, RetineNEt ve EfficientDet modelleri ile yapılan eğitmler sonucunda, Tensorflow Faster R-CNN modelinde yüksek oranda test sonuçları elde edilmiştir.
The area of business in which motor vehicles are designed, produced and marketed is called the automotive industry. Automobile manufacturing takes place in approximately 70% of this industry. There are many parts that make up the car. It consists of about 5,000 parts such as engine, wheel, metal body and doors, seat, plastic panels. The sub-industries that manufacture each part also have an important role in the sector. In this study, seat types belonging to a vehicle model in a sub-industry company that produces seats were examined. In the automotive sector, approximately 300,000 vehicles belonging to only one model are produced annually. There are a total of two seats in the front row of each vehicle, one for the driver and one for the passenger. There are six different models when the seats are differentiated according to the fabric types. In the sub-industry companies that produce seats, an average of 600,000 seats are produced for each model annually. With the development of deep learning-based computer vision technology, the need for an application has emerged for the automatic identification and stocking of the seats produced according to their models. High inventory costs, faulty production and labels are among the biggest problems of automotive companies. With Industry 4.0, smart productions and controls can be made thanks to smart machines. High cost problems are avoided with fast, high accuracy rate and low costs. Thanks to smart machines in which artificial intelligence technologies are used, smart production technologies have been developed. Products produced with high-resolution cameras, high-sensitivity sensors, automation carrier systems are faster and more accurate. In this study, it is aimed to automatically separate the stock area and pre-production and post-production seat models in an automotive supplier industry company that produces different version seats of the automobile model. In this study, artificial intelligence method was used for automatic object (seat) detection by using car seats that were previously located in production areas and stock areas. Training and test data were created according to seat types at different environments. Test and training data were created by labeling the photographs one by one according to the model type. As a result of the trainings conducted with Faster R-CNN, RetineNEt and EfficientDet models, high test results were obtained in the Tensorflow Faster R-CNN model.
The area of business in which motor vehicles are designed, produced and marketed is called the automotive industry. Automobile manufacturing takes place in approximately 70% of this industry. There are many parts that make up the car. It consists of about 5,000 parts such as engine, wheel, metal body and doors, seat, plastic panels. The sub-industries that manufacture each part also have an important role in the sector. In this study, seat types belonging to a vehicle model in a sub-industry company that produces seats were examined. In the automotive sector, approximately 300,000 vehicles belonging to only one model are produced annually. There are a total of two seats in the front row of each vehicle, one for the driver and one for the passenger. There are six different models when the seats are differentiated according to the fabric types. In the sub-industry companies that produce seats, an average of 600,000 seats are produced for each model annually. With the development of deep learning-based computer vision technology, the need for an application has emerged for the automatic identification and stocking of the seats produced according to their models. High inventory costs, faulty production and labels are among the biggest problems of automotive companies. With Industry 4.0, smart productions and controls can be made thanks to smart machines. High cost problems are avoided with fast, high accuracy rate and low costs. Thanks to smart machines in which artificial intelligence technologies are used, smart production technologies have been developed. Products produced with high-resolution cameras, high-sensitivity sensors, automation carrier systems are faster and more accurate. In this study, it is aimed to automatically separate the stock area and pre-production and post-production seat models in an automotive supplier industry company that produces different version seats of the automobile model. In this study, artificial intelligence method was used for automatic object (seat) detection by using car seats that were previously located in production areas and stock areas. Training and test data were created according to seat types at different environments. Test and training data were created by labeling the photographs one by one according to the model type. As a result of the trainings conducted with Faster R-CNN, RetineNEt and EfficientDet models, high test results were obtained in the Tensorflow Faster R-CNN model.
