Experimental Data-Based ANN Modeling for Injection Flow Rate Prediction in Common Rail Fuel Systems Considering Fuel Temperature Effects
Received: 6 January 2026 | Revised: 31 January 2026, 6 April 2026, 10 April 2026, and 17 April 2026 | Accepted: 18 April 2026 | Online: 25 April 2026
Corresponding author: Nguyen Tuan Nghia
Abstract
In this study, an Artificial Neural Network (ANN) model is developed to predict the main injection flow rate of an electronically controlled injector in a Common Rail fuel injection system. Experimental data were collected using a Common Rail injector test bench equipped with an integrated temperature control unit, allowing the fuel temperature to be maintained at fixed values during testing. Two experimental datasets were obtained at fuel temperatures of 25 °C and 35 °C, each consisting of 344 data points, resulting in a total of 688 samples for model development and evaluation. The ANN model was trained using 80% of the dataset (550 samples), whereas the remaining 20% (138 samples) were used for testing. The predictive performance of the model was evaluated using the coefficient of determination (R²), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). The results show that the ANN achieved high prediction accuracy on the training dataset, with R² = 0.9861, MAE = 0.0561, and RMSE = 0.0833. On the testing dataset, the model maintained strong predictive capability, yielding R² = 0.9814, MAE = 0.0624, and RMSE = 0.0872. The small differences between the training and testing performance indicators demonstrate good generalization ability. The results confirm that ANN is an effective and reliable tool for predicting injection flow rate in Common Rail systems under different fixed fuel temperature conditions. The proposed approach enables simultaneous processing of multiple experimental datasets with high accuracy, contributing to reduced experimental time and operating costs, and offering significant potential for modeling, prediction, and optimization of electronically controlled fuel injection systems.
Keywords:
Artificial Neural Networks (ANNs), injection flow rate, Common Rail, fixed temperatureDownloads
References
M. A. Costagliola, M. Costabile, and M. V. Prati, "Impact of road grade on real driving emissions from two Euro 5 diesel vehicles," Applied Energy, vol. 231, pp. 586–593, Dec. 2018.
J. Schommers et al., "Potential of Common Rail Injection System for Passenger Car DI Diesel Engines," SAE International, SAE World Congress, Detroit, MI, USA, SAE Technical Paper 2000-01–0944, Mar. 2000.
Z. Gao, G. Li, H. Li, C. Xu, and Y. Kang, "Experiment investigation of injection parameters effects on injection stability of a high pressure common rail system," Science Progress, vol. 104, no. 1, Jan. 2021, Art. no. 0036850420983625.
R. Xu, F. Ma, L. Li, W. Yang, and Y. Zhang, "Research on fuel injection characteristics of common rail system based on high pressure pipeline integration and matching," Energy Science & Engineering, vol. 12, no. 4, pp. 1446–1461, Apr. 2024.
V. Dragan, I. Malael, and B. Gherman, "A Comparative Analysis Between Optimized and Baseline High Pressure Compressor Stages Using Tridimensional Computational Fluid Dynamics," Engineering, Technology & Applied Science Research, vol. 6, no. 4, pp. 1103–1108, Aug. 2016.
C. Mata, V. Rojas-Reinoso, and J. A. Soriano, "Experimental determination and modelling of fuel rate of injection: A review," Fuel, vol. 343, July 2023, Art. no. 127895.
T. Žvirblis, K. Čižiūnienė, and J. Matijošius, "Application of Machine Learning for Fuel Consumption and Emission Prediction in a Marine Diesel Engine Using Diesel and Waste Cooking Oil," Journal of Marine Science and Engineering, vol. 13, no. 7, July 2025, Art. no. 1328.
C. Guan, Y. Duan, J. Zhai, and D. Han, "Hydraulic dynamics in split fuel injection on a common rail system and their artificial neural network prediction," Fuel, vol. 255, Nov. 2019, Art. no. 115792.
I. Veza et al., "Review of artificial neural networks for gasoline, diesel and homogeneous charge compression ignition engine," Alexandria Engineering Journal, vol. 61, no. 11, pp. 8363–8391, Nov. 2022.
B. Liu, H. Fei, L. Wang, L. Fan, and X. Yang, "Real-time estimation of fuel injection rate and injection volume in high-pressure common rail systems," Energy, vol. 298, July 2024, Art. no. 131386.
M. S. P, G. V, P. P, G. A, and D. G, "Prediction efficiency of artificial neural network for CRDI engine output parameters," Transportation Engineering, vol. 3, Mar. 2021, Art. no. 100041.
D. Babu, V. Thangarasu, and A. Ramanathan, "Artificial neural network approach on forecasting diesel engine characteristics fuelled with waste frying oil biodiesel," Applied Energy, vol. 263, Apr. 2020, Art. no. 114612.
Downloads
How to Cite
License
Copyright (c) 2026 Nguyen Xuan Khoa, Nguyen Tuan Nghia, Nguyen Thanh Vinh, Le Dinh Manh, Chu Duc Hung, Le Huu Chuc, Trinh Duy Hung
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
