Kasislerin Yakıt Tüketimine Etkisinin RNN, LSTM, GRU Tekrarlayan Derin Öğrenme Algoritmaları ile Tespiti
Yıl 2023,
Cilt: 6 Sayı: 1, 12 - 23, 15.03.2023
Mustafa Fatih Tosun
,
Ali Şentürk
Öz
Bu çalışmada, trafiği düzenlemek için kullanılan kasislerde, araçların yavaşlama ve hızlanmasının yakıt tüketimine etkisinin belirlenmesi amaçlanmıştır. Bunun için, kasis bulunan güzergâhlarda kullanılan aracın OBD-II portundan Arduino ile gerçek zamanlı hız ve yakıt tüketimi verileri alınmıştır. Alınan veriler ön işleme tabi tutulmuştur. Yakıt tüketimini tahmin etmek için Tekrarlayan Sinir Ağları (RNN), Uzun Kısa Süreli Bellek (LSTM), Geçitli Tekrarlayan Birim (GRU) tekrarlayan derin öğrenme modelleri geliştirilmiştir. Ön işlemden geçen veriler modellerin eğitiminde kullanılmıştır. Geliştirilen modellerde hiperparametre optimizasyonu yapılmıştır. Böylece katman sayısı, katmanlardaki hücre sayısı, hücrelerin aktivasyon fonksiyonları ve öğrenme oranı belirlenmiştir. Doğrulama setinde en düşük ‰63 ortalama kare hatası elde edilmiştir. Geliştirilen modeller kullanılarak farklı kasisler ve hız senaryolarının yakıt tüketimine olan etkileri tahmin edilmeye çalışılmıştır. Kasislerden geçiş için belirlenen hız ve zaman verileri kullanılarak yakıt tüketiminin kasis etkisi boyunca %16,30 ile %31,03 arasında arttırdığı sonucuna ulaşılmıştır.
Teşekkür
Çalışmada yer alan derin öğrenme hesaplamaları TÜBİTAK ULAKBİM, Yüksek Başarım ve Grid Hesaplama Merkezi’nde (TRUBA kaynaklarında) gerçekleştirilmiştir.
Kaynakça
- Amarasinghe, M., Kottegoda, S., Arachchi, A. L., Muramudalige, S., Bandara, H. M. N. D., Azeez, A., 2015. “Cloud-based driver monitoring and vehicle diagnostic with OBD-II telematics”. 2015 Fifteenth International Conference on Advances in ICT for Emerging Regions (ICTer), 243–249. https://doi.org/10.1109/ICTER.2015.7377695
- Coşkun, U. 2008. “Controller Area Network Uygulaması”. Yüksek Lisans Tezi, Gebze Teknik Üniversitesi, Yüksek Teknoloji Enstitüsü
- Cueva-Fernandez, G., Espada, J. P., García-Díaz, V., García, C. G., Garcia-Fernandez, N., 2014. “Vitruvius: An expert system for vehicle sensor tracking and managing application generation”. Journal of Network and Computer Applications, 42, 178–188. https://doi.org/https://doi.org/10.1016/j.jnca.2014.02.013
- Fu, Y., Lou, F., Meng, F., Tian, Z., Zhang, H., Jiang, F., 2018. “An Intelligent Network Attack Detection Method Based on RNN”. 2018 IEEE Third International Conference on Data Science in Cyberspace (DSC), 483–489. https://doi.org/10.1109/DSC.2018.00078
- Kowalik, B. 2018. “Introduction to car failure detection system based on diagnostic interface”. In 2018 International Interdisciplinary PhD Workshop (IIPhDW (pp. 4-7). IEEE.
- Kowalik, B., Szpyrka, M. 2019. “Online environment for data acquisition from car sensors”. Automatyka/Automatics, 23(1), 7-7.
- Lokman, S.-F., Othman, A. T., Abu-Bakar, M.-H., 2019. “Intrusion detection system for automotive Controller Area Network (CAN) bus system: a review”. EURASIP Journal on Wireless Communications and Networking, 2019(1), 184. https://doi.org/10.1186/s13638-019-1484-3
- Meseguer, J., E., Calafate, C., T., Cano, J., C., Manzoni, P., 2015. “Assessing the Impact of Driving Behavior on Instantaneous Fuel Consumption”. 12th Annual IEEE Consumer Communications and Networking Conference (CCNC), 443–448. https://doi.org/10.1109/CCNC.2015.7158016
- Perrotta, F., Parry, T., Neves, L. C., 2017. “Application of machine learning for fuel consumption modelling of trucks”. 2017 IEEE International Conference on Big Data (Big Data), 3810–3815. https://doi.org/10.1109/BigData.2017.8258382
- Somuncu, E., Atasoy, N., 2021. “Evrişimli tekrarlayan sinir ağı ile metin görüntüleri üzerinde karakter tanıma uygulaması gerçekleştirilmesi”. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, 37 (1), 17-28. DOI: 10.17341/gazimmfd.866552
- Syahputra, R., 2016. “Applıcatıon of neuro-fuzzy method for predıctıon of vehıcle fuel consumptıon”. Journal of Theoretical and Applied Information Technology, 86(1).
- Şen, B., 2020. “Estimating instant fuel consumption by machine learning and improving fuel consumption”. Yüksek Lisans Tezi, Galatasaray Üniversitesi Fen Bilimleri Enstitüsü
- Uyanık, T., Karatuğ, Ç., Arslanoğlu, Y., 2020. “Machine learning approach to ship fuel consumption: A case of container vessel”. Transportation Research Part D: Transport and Environment, 84, 102389. https://doi.org/https://doi.org/10.1016/j.trd.2020.102389
- Vilgenoğlu, E., 2019. “Real-time vehicle monitoring and on-board diagnostic system”. Yüksek Lisans Tezi, Dokuz Eylül Üniversitesi Fen Bilimleri Enstitüsü
- Wang, J., Du, Y., Wang, J., 2020. “LSTM based long-term energy consumption prediction with periodicity. Energy”, 197, 117197. https://doi.org/10.1016/j.energy.2020.117197
- Wang, W., Liu, H., Lin, W., Chen, Y., Yang, J.-A., 2020. “Investigation on Works and Military Applications of Artificial Intelligence”. IEEE Access, 8, 131614–131625.
- Wickramanayake, S., Bandara, D., 2016. “Fuel consumption prediction of fleet vehicles using Machine Learning: A comparative study”. 2nd International Moratuwa Engineering Research Conference, MERCon 2016, 90–95. https://doi.org/10.1109/MERCon.2016.7480121
- Zhang, D., Kabuka, M, R., 2018. “Combining weather condition data to predict traffic flow: a GRU‐based deep learning approach IET Intelligent Transport Systems”, 12(7), 578-585.
The Detection of the Effect of Bumpers on Fuel Consumption with RNN, LSTM, GRU Recurrent Deep Learning Algorithms
Yıl 2023,
Cilt: 6 Sayı: 1, 12 - 23, 15.03.2023
Mustafa Fatih Tosun
,
Ali Şentürk
Öz
This study is aimed to determine the effect of vehicle deceleration and acceleration on fuel consumption in the bumps which are used to regulate traffic. For this, real-time fuel consumption and speed data are acquired with Arduino from the OBD-II port of the vehicle drived on routes with bumps. Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) deep learning models are developed to predict fuel consumption. The preprocessed data is used to train the models. Hyperparameter optimization is conducted in the developed models. Thus, the number of layers and the units in the layers, the activation functions and the learning rate is specified. The lowest mean square error is obtained as 63‰ in the validation set. The effects of different speed scenarios on fuel consumption are predicted by using the models. In conclusion, fuel consumption increased between 16.30% and 31.03% during the impact of the bumps, by using the speed and time calculated for the bumps.
Kaynakça
- Amarasinghe, M., Kottegoda, S., Arachchi, A. L., Muramudalige, S., Bandara, H. M. N. D., Azeez, A., 2015. “Cloud-based driver monitoring and vehicle diagnostic with OBD-II telematics”. 2015 Fifteenth International Conference on Advances in ICT for Emerging Regions (ICTer), 243–249. https://doi.org/10.1109/ICTER.2015.7377695
- Coşkun, U. 2008. “Controller Area Network Uygulaması”. Yüksek Lisans Tezi, Gebze Teknik Üniversitesi, Yüksek Teknoloji Enstitüsü
- Cueva-Fernandez, G., Espada, J. P., García-Díaz, V., García, C. G., Garcia-Fernandez, N., 2014. “Vitruvius: An expert system for vehicle sensor tracking and managing application generation”. Journal of Network and Computer Applications, 42, 178–188. https://doi.org/https://doi.org/10.1016/j.jnca.2014.02.013
- Fu, Y., Lou, F., Meng, F., Tian, Z., Zhang, H., Jiang, F., 2018. “An Intelligent Network Attack Detection Method Based on RNN”. 2018 IEEE Third International Conference on Data Science in Cyberspace (DSC), 483–489. https://doi.org/10.1109/DSC.2018.00078
- Kowalik, B. 2018. “Introduction to car failure detection system based on diagnostic interface”. In 2018 International Interdisciplinary PhD Workshop (IIPhDW (pp. 4-7). IEEE.
- Kowalik, B., Szpyrka, M. 2019. “Online environment for data acquisition from car sensors”. Automatyka/Automatics, 23(1), 7-7.
- Lokman, S.-F., Othman, A. T., Abu-Bakar, M.-H., 2019. “Intrusion detection system for automotive Controller Area Network (CAN) bus system: a review”. EURASIP Journal on Wireless Communications and Networking, 2019(1), 184. https://doi.org/10.1186/s13638-019-1484-3
- Meseguer, J., E., Calafate, C., T., Cano, J., C., Manzoni, P., 2015. “Assessing the Impact of Driving Behavior on Instantaneous Fuel Consumption”. 12th Annual IEEE Consumer Communications and Networking Conference (CCNC), 443–448. https://doi.org/10.1109/CCNC.2015.7158016
- Perrotta, F., Parry, T., Neves, L. C., 2017. “Application of machine learning for fuel consumption modelling of trucks”. 2017 IEEE International Conference on Big Data (Big Data), 3810–3815. https://doi.org/10.1109/BigData.2017.8258382
- Somuncu, E., Atasoy, N., 2021. “Evrişimli tekrarlayan sinir ağı ile metin görüntüleri üzerinde karakter tanıma uygulaması gerçekleştirilmesi”. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, 37 (1), 17-28. DOI: 10.17341/gazimmfd.866552
- Syahputra, R., 2016. “Applıcatıon of neuro-fuzzy method for predıctıon of vehıcle fuel consumptıon”. Journal of Theoretical and Applied Information Technology, 86(1).
- Şen, B., 2020. “Estimating instant fuel consumption by machine learning and improving fuel consumption”. Yüksek Lisans Tezi, Galatasaray Üniversitesi Fen Bilimleri Enstitüsü
- Uyanık, T., Karatuğ, Ç., Arslanoğlu, Y., 2020. “Machine learning approach to ship fuel consumption: A case of container vessel”. Transportation Research Part D: Transport and Environment, 84, 102389. https://doi.org/https://doi.org/10.1016/j.trd.2020.102389
- Vilgenoğlu, E., 2019. “Real-time vehicle monitoring and on-board diagnostic system”. Yüksek Lisans Tezi, Dokuz Eylül Üniversitesi Fen Bilimleri Enstitüsü
- Wang, J., Du, Y., Wang, J., 2020. “LSTM based long-term energy consumption prediction with periodicity. Energy”, 197, 117197. https://doi.org/10.1016/j.energy.2020.117197
- Wang, W., Liu, H., Lin, W., Chen, Y., Yang, J.-A., 2020. “Investigation on Works and Military Applications of Artificial Intelligence”. IEEE Access, 8, 131614–131625.
- Wickramanayake, S., Bandara, D., 2016. “Fuel consumption prediction of fleet vehicles using Machine Learning: A comparative study”. 2nd International Moratuwa Engineering Research Conference, MERCon 2016, 90–95. https://doi.org/10.1109/MERCon.2016.7480121
- Zhang, D., Kabuka, M, R., 2018. “Combining weather condition data to predict traffic flow: a GRU‐based deep learning approach IET Intelligent Transport Systems”, 12(7), 578-585.