Application of deep learning in quality inspection of casting products
2022
Аутори
Perišić, NatalijaJovanović, Radiša
Остала ауторства
Spasojević Brkić, VesnaMisita, Mirjana
Bugarić, Uglješa
Конференцијски прилог (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
In this paper artificial neural network is proposed as a method to classify defective and non-defective casting products in order to improve quality inspection process. Three different models of convolutional neural networks are trained and tested on dataset of submersible pump impeller images which has uneven number of image samples in each class. In order to inspect if slightly imbalanced classes have impact on result, two experiments are done. All of the models are ImageNet pre-trained networks, InceptionV3, Xception and MobileNetV2, where transfer learning method is applied with fine-tuning. Stochastic gradient descent algorithm is implemented for optimization. Obtained results of all models are presented and comparison is made.
Кључне речи:
Artificial intelligence / Convolutional neural networks / Quality inspection / Deep learning / Pump impeller dataset / Transfer learningИзвор:
8th International Conference of Industrial Engineering SIE 2022 : Proceedings, 29th-30th September, 2022, Belgrade, Serbia, 2022, 148-151Издавач:
- Belgrade: University of Belgrade Faculty of Mechanical Engineering
Финансирање / пројекти:
- Министарство науке, технолошког развоја и иновација Републике Србије, институционално финансирање - 200105 (Универзитет у Београду, Машински факултет) (RS-MESTD-inst-2020-200105)
- MISSION4.0 - Deep Machine Learning and Swarm Intelligence-Based Optimization Algorithms for Control and Scheduling of Cyber-Physical Systems in Industry 4.0 (RS-ScienceFundRS-AI-6523109)
Колекције
Институција/група
Mašinski fakultetTY - CONF AU - Perišić, Natalija AU - Jovanović, Radiša PY - 2022 UR - https://machinery.mas.bg.ac.rs/handle/123456789/4498 AB - In this paper artificial neural network is proposed as a method to classify defective and non-defective casting products in order to improve quality inspection process. Three different models of convolutional neural networks are trained and tested on dataset of submersible pump impeller images which has uneven number of image samples in each class. In order to inspect if slightly imbalanced classes have impact on result, two experiments are done. All of the models are ImageNet pre-trained networks, InceptionV3, Xception and MobileNetV2, where transfer learning method is applied with fine-tuning. Stochastic gradient descent algorithm is implemented for optimization. Obtained results of all models are presented and comparison is made. PB - Belgrade: University of Belgrade Faculty of Mechanical Engineering C3 - 8th International Conference of Industrial Engineering SIE 2022 : Proceedings, 29th-30th September, 2022, Belgrade, Serbia T1 - Application of deep learning in quality inspection of casting products EP - 151 SP - 148 UR - https://hdl.handle.net/21.15107/rcub_machinery_4498 ER -
@conference{ author = "Perišić, Natalija and Jovanović, Radiša", year = "2022", abstract = "In this paper artificial neural network is proposed as a method to classify defective and non-defective casting products in order to improve quality inspection process. Three different models of convolutional neural networks are trained and tested on dataset of submersible pump impeller images which has uneven number of image samples in each class. In order to inspect if slightly imbalanced classes have impact on result, two experiments are done. All of the models are ImageNet pre-trained networks, InceptionV3, Xception and MobileNetV2, where transfer learning method is applied with fine-tuning. Stochastic gradient descent algorithm is implemented for optimization. Obtained results of all models are presented and comparison is made.", publisher = "Belgrade: University of Belgrade Faculty of Mechanical Engineering", journal = "8th International Conference of Industrial Engineering SIE 2022 : Proceedings, 29th-30th September, 2022, Belgrade, Serbia", title = "Application of deep learning in quality inspection of casting products", pages = "151-148", url = "https://hdl.handle.net/21.15107/rcub_machinery_4498" }
Perišić, N.,& Jovanović, R.. (2022). Application of deep learning in quality inspection of casting products. in 8th International Conference of Industrial Engineering SIE 2022 : Proceedings, 29th-30th September, 2022, Belgrade, Serbia Belgrade: University of Belgrade Faculty of Mechanical Engineering., 148-151. https://hdl.handle.net/21.15107/rcub_machinery_4498
Perišić N, Jovanović R. Application of deep learning in quality inspection of casting products. in 8th International Conference of Industrial Engineering SIE 2022 : Proceedings, 29th-30th September, 2022, Belgrade, Serbia. 2022;:148-151. https://hdl.handle.net/21.15107/rcub_machinery_4498 .
Perišić, Natalija, Jovanović, Radiša, "Application of deep learning in quality inspection of casting products" in 8th International Conference of Industrial Engineering SIE 2022 : Proceedings, 29th-30th September, 2022, Belgrade, Serbia (2022):148-151, https://hdl.handle.net/21.15107/rcub_machinery_4498 .