Prediction of Transport Fuel Consumption by Artificial Neural Network: A Case Study of Land Reclamation Trucks in the Southern Border Provinces, Thailand
Keywords:
PerformanceAbstract
The purpose of this research is to compare the transport fuel prediction performance by an artificial neural network with the MAPE. The monthly transportation fuel consumption data from 2013 to 2017 were used to estimate fuel consumption using three transfer functions: sigmoid, bipolar sigmoid, and hyperbolic-tangent. Each transfer function will divide the neural network into 9 structures, namely, input layer (12 nodes), hidden layer (between 4 to 12 nodes), and output (layer 1 node) that is related to time series data, totaling 27 structures to be used to assess the MAPE for fuel consumption predicted. The learning rate was 0.05, the momentum was 0.5, and the number of iterations was 100,000. It was found that an ANN (12-8-1) neural network with a hyperbolic-tangent transfer function has the lowest as 0.03 percent of MAPE. The study's findings may be used to create case studies for businesses wishing to enhance their fuel economy. This includes using the suggestions from this study to increase the accuracy of predicting data of relevance in other sectors.
References
Affan, M. F., Abdullah, A. G., & Surya, W. (2019). Forecasting of wind speed using exponential smoothing and artificial neural networks (ANN). Journal of Physics: Conference Series, 1402(3), 033082. IOP Publishing.
Akarslan, E., & Hocaoglu, F. O. (2018). Electricity demand forecasting of a micro grid using ANN. 2018 9th International Renewable Energy Congress (IREC), 1–5. IEEE.
Badyalina, B., Mokhtar, N. A., Azimi, A. I. F., Majid, M., Ramli, M. F., & Yaa’coob, F. F. (2022). Data-driven models for wind speed forecasting in malacca state. MATEMATIKA: Malaysian Journal of Industrial and Applied Mathematics, 125–139.
Bangkokbiznews. (2022). Thailand imported more than 1 million barrels of fuel in January 2022, an increase of 9.9%. Retrieved from https://www.bangkokbiznews.com/business/
(in Thai)
Farooque, A. A., Zaman, Q. U., Nguyen-Quang, T., Groulx, D., Schumann, A. W., & Chang, Y. K. (2016). Development of a predictive model for
wild blueberry harvester fruit losses during harvesting using artificial neural network. Applied Engineering in Agriculture, 32(6), 725–738.
Fauziah, F. N., Gunaryati, A., & Sari, R. T. K. (2017). Comparison forecasting with double exponential smoothing and artificial neural network to predict the price of sugar. Int. J. Simul. Syst. Sci. Technol, 18(4), 1-8.
Hyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: Principles and practice. OTexts.
Ibrahim, N. N. A. N., Razak, I. A. W. A., & Bohari, Z. H. (2018). Electricity price forecasting using artificial neural network: Activation function selection. Proceedings of Symposium on Electrical, Mechatronics and Applied Science 2018 (SEMA’18), 151–152.
Ireri, A. M. (2014). A Data Mining approach to private healthcare services demand forecast in Nairobi County (PhD Thesis).
Johnson, D., & King, M. (1988). BASIC forecasting techniques Butterworths. London.
Le, L. T., Lee, G., Park, K.-S., & Kim, H. (2020). Neural network-based fuel consumption estimation for container ships in Korea. Maritime Policy & Management, 47(5), 615–632.
Mostafaeipour, A., Goli, A., & Qolipour, M. (2018). Prediction of air travel demand using a hybrid artificial neural network (ANN) with bat and
firefly algorithms: a case study. The Journal of Supercomputing, 74(10), 5461–5484.
Piyanuch Sathapongpakdee. (2022). Industry Outlook 2022-2024: Road Freight Transportation Service.Retrieved from https://www.krungsri.com/th/research/industry/industry-outlook/logistics/road-freight-transportation/IO/road-freight-transportation-2022-
(in Thai)
Siami-Irdemoosa, E., & Dindarloo, S. R. (2015). Prediction of fuel consumption of mining dump trucks: A neural networks approach. Applied Energy, 151, 77–84.
Southern Border Provinces Administration Centre. (2022). Sentiment Index for Southern Border Provinces Retrieved from https://www.sbpac.go.th/wp-content/uploads/2020/08/
Sukpan, C., Chopaiad, C., & Chooduang, S.. (2015). Price Forecasting of Ribbed Smoked Rubber Sheet No.3 in the Agricultural Futures Market by Leading Indicators and Artificial Neural Networks. Thaksin University Journal, 18(1), 32–40. (in Thai).
TPS.pdf. (in Thai)
Wysocki, O., Deka, L., & Elizondo, D. (2019). Heavy duty vehicle fuel consumption modeling using artificial neural networks. 2019 25th International Conference on Automation and Computing (ICAC), 1–6. IEEE.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Graduate Studies Nakhon Si Thammarat Rajabhat Univeristy
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
