Automotive Experiences

Articles

Integrating Synthetic Data with Deep Learning for Predictive Modelling and Optimization of Diesel Engine Performance on Waste Plastic Oil Blends

Fitra Hidiyanto , Rizqon Fajar , Fauzi Dwi Setiawan , Sigit Tri Atmaja , Heru Priyanto , Muhammad Samsul Maarif , Yaaro Telaumbanua

Published
February 6, 2026

Vol. 9 No. 1 (2026)
Pages 9-26

DOI

Open Access
Share

Abstract

The scarcity of experimental data for diesel engines fueled by waste plastic oil (WPO) is a critical obstacle to optimizing engine performance. In this study, only 42 experimental data points covering six blend ratios and seven load conditions were available. To overcome this limitation, 121 synthetic data points were generated by training a suite of machine‑learning models—Random Forest, Gradient Boosting, and AdaBoost—on the original dataset and then predicting outputs across a grid of WPO blend ratios (0–50% in 5% increments) and engine loads (0–100% in 10% increments). The synthetic data were rigorously validated using Kolmogorov–Smirnov tests, kernel density estimation, and principal component analysis to ensure statistical similarity with the original measurements. Subsequently, a Multi‑Input Multi‑Output (MIMO) deep neural network was trained on the combined real and synthetic dataset to predict four key performance metrics—power, torque, specific fuel consumption (SFC) and brake thermal efficiency (BTE)—and its hyperparameters were fine‑tuned using Bayesian optimization via Optuna, achieving coefficients of determination (R²) above 0.95. Optimization analysis indicated that a 17% WPO blend at 82% load delivers the best trade‑off between power, efficiency and fuel consumption for non‑road applications. This integrated framework demonstrates how synthetic data generation, rigorous validation and deep‑learning modelling can effectively mitigate data scarcity and provide actionable insights for performance optimization of plastic pyrolysis oil in diesel engines.


 

Keywords

Waste plastic oil; Pyrolysis; Diesel engine performance; Synthetic data generation; Engine optimization; Deep learning modelling

References

  1. [1] W. Arjharn, P. Liplap, S. Maithomklang, K. Thammakul, S. Chuepeng, and E. Sukjit, “Distilled Waste Plastic Oil as Fuel for a Diesel Engine: Fuel Production, Combustion Characteristics, and Exhaust Gas Emissions,” ACS Omega, vol. 7, no. 11, pp. 9720–9729, 2022, doi: 10.1021/acsomega.1c07257.
  2. [2] K. Wathakit et al., “Characterization and impact of waste plastic oil in a variable compression ratio diesel engine,” Energies, vol. 14, no. 8, 2021, doi: 10.3390/en14082230.
  3. [3] A. Pumpuang, N. Klinkaew, K. Wathakit, A. Sukhom, and E. Sukjit, “The influence of plastic pyrolysis oil on fuel lubricity and diesel engine performance,” RSC Advances, vol. 14, no. 14, pp. 10070–10087, 2024, doi: 10.1039/D3RA08150H.
  4. [4] M. J. Szwaja and A. Szymanek, “Combustion comparative analysis of pyrolysis oil and diesel fuel under constant-volume conditions,” Combustion Engines, vol. 195, no. 4, pp. 90–96, Aug. 2023, doi: 10.19206/CE-169805.
  5. [5] J. Senthil, M. Prabhahar, C. Thiagarajan, S. Prakash, and M. S. Kumar, “Evaluating Diesel Engine Performance with Blended Fuels from Low-Density Plastic Pyrolysis Oil: A Sustainable Approach to Diesel Engine Operation,” International Journal of Mechanical Engineering, vol. 10, no. 10, pp. 26–36, Oct. 2023, doi: 10.14445/23488360/IJME-V10I10P103.
  6. [6] H. Yaqoob, H. M. Ali, U. Sajjad, and K. Hamid, “Investigating the potential of plastic pyrolysis oil-diesel blends in diesel engine: Performance, emissions, thermodynamics and sustainability analysis,” Results in Engineering, vol. 24, no. October, p. 103336, Dec. 2024, doi: 10.1016/j.rineng.2024.103336.
  7. [7] S. Maithomklang, E. Sukjit, J. Srisertpol, N. Klinkaew, and K. Wathakit, “Pyrolysis Oil Derived from Plastic Bottle Caps: Characterization of Combustion and Emissions in a Diesel Engine,” Energies, vol. 16, no. 5, 2023, doi: 10.3390/en16052492.
  8. [8] A. K. Panda, S. K. Rout, and A. K. Das, “Optimization of diesel engine performance and emission using waste plastic pyrolytic oil by ANN and its thermo-economic assessment,” Environmental Science and Pollution Research, vol. 31, no. 27, pp. 38893–38907, Apr. 2023, doi: 10.1007/s11356-023-26891-9.
  9. [9] S. Şen and M. Bahattin Çelik, “Modeling the effect of plastic oil obtained from XLPE cable waste on diesel engine performance and emission parameters with the response surface method,” Science and Technology for Energy Transition, vol. 79, p. 58, Aug. 2024, doi: 10.2516/stet/2024059.
  10. [10] M. Gillioz, G. Dubuis, and P. Jacquod, “A large synthetic dataset for machine learning applications in power transmission grids,” Scientific Data , vol. 12, no. 1, pp. 1–17, 2025, doi: 10.1038/s41597-025-04479-x.
  11. [11] J. Werheid, S. He, A. Gannouni, A. Abdelrazeq, and R. H. Schmitt, “A Synthetic Data Pipeline for Supporting Manufacturing SMEs in Visual Assembly Control,” in 2025 2nd International Generative AI and Computational Language Modelling Conference (GACLM), Sep. 2025, pp. 1–7. doi: 10.48550/arXiv.2509.13089.
  12. [12] S. Hong, Y. Kwon, D. Shin, J. Park, and N. Kang, “DeepJEB: 3D Deep Learning-Based Synthetic Jet Engine Bracket Dataset,” Journal of Mechanical Design, vol. 147, no. 4, Apr. 2025, doi: 10.1115/1.4067089.
  13. [13] C. Picard, J. Schiffmann, and F. Ahmed, “Dated: Guidelines for Creating Synthetic Datasets for Engineering Design Applications,” in Volume 3A: 49th Design Automation Conference (DAC), American Society of Mechanical Engineers, Aug. 2023, pp. 1–13. doi: 10.1115/DETC2023-111609.
  14. [14] S. Maithomklang, K. Wathakit, E. Sukjit, B. Sawatmongkhon, and J. Srisertpol, “Utilizing Waste Plastic Bottle-Based Pyrolysis Oil as an Alternative Fuel,” ACS Omega, vol. 7, no. 24, pp. 20542–20555, Jun. 2022, doi: 10.1021/acsomega.1c07345.
  15. [15] A. Wiangkham, N. Klinkaew, P. Aengchuan, P. Liplap, A. Ariyarit, and E. Sukjit, “Experimental and optimization study on the effects of diethyl ether addition to waste plastic oil on diesel engine characteristics,” RSC Advances, vol. 13, no. 36, pp. 25464–25482, 2023, doi: 10.1039/d3ra04489k.
  16. [16] M. S. Aswathanrayan et al., “Prediction of performance and emission features of diesel engine using alumina nanoparticles with neem oil biodiesel based on advanced ML algorithms,” Scientific Reports, vol. 15, no. 1, p. 12683, Apr. 2025, doi: 10.1038/s41598-025-97092-2.
  17. [17] D. Huri and T. Mankovits, “Automotive Rubber Product Design Using Response Surface Method,” Periodica Polytechnica Transportation Engineering, vol. 50, no. 1, pp. 28–38, Dec. 2021, doi: 10.3311/PPtr.16280.
  18. [18] M. Sheyyab, P. T. Lynch, E. K. Mayhew, and K. Brezinsky, “Optimized synthetic data and semi-supervised learning for Derived Cetane Number prediction,” Combustion and Flame, vol. 259, p. 113184, Jan. 2024, doi: 10.1016/j.combustflame.2023.113184.
  19. [19] M. G. De Giorgi, S. Campilongo, and A. Ficarella, “A diagnostics tool for aero-engines health monitoring using machine learning technique,” Energy Procedia, vol. 148, pp. 860–867, Aug. 2018, doi: 10.1016/j.egypro.2018.08.109.
  20. [20] I. Pan, L. Mason, and O. Matar, “Data-Centric Engineering: integrating simulation, machine learning and statistics. Challenges and Opportunities,” Chemical Engineering Science, vol. 249, p. 117271, Nov. 2021, doi: 10.1016/j.ces.2021.117271.
  21. [21] J. W. Anderson, M. Ziolkowski, K. Kennedy, and A. W. Apon, “Synthetic Image Data for Deep Learning,” arXiv preprint arXiv:2212.06232, Dec. 2022, doi: 10.48550/arXiv.2212.06232.
  22. [22] M. Stenger, R. Leppich, I. Foster, S. Kounev, and A. Bauer, “Evaluation is key: a survey on evaluation measures for synthetic time series,” Journal of Big Data, vol. 11, no. 1, p. 66, May 2024, doi: 10.1186/s40537-024-00924-7.
  23. [23] M. Chaibi, E. M. Benghoulam, L. Tarik, M. Berrada, and A. El Hmaidi, “Machine Learning Models Based on Random Forest Feature Selection and Bayesian Optimization for Predicting Daily Global Solar Radiation,” International Journal of Renewable Energy Development, vol. 11, no. 1, pp. 309–323, Feb. 2022, doi: 10.14710/ijred.2022.41451.
  24. [24] P. Whig, K. Gupta, N. Jiwani, H. Jupalle, S. Kouser, and N. Alam, “A novel method for diabetes classification and prediction with Pycaret,” Microsystem Technologies, vol. 29, no. 10, pp. 1479–1487, 2023, doi: 10.1007/s00542-023-05473-2.
  25. [25] S. Sunaryo, P. A. Sesotyo, E. Saputra, and A. P. Sasmito, “Performance and Fuel Consumption of Diesel Engine Fueled by Diesel Fuel and Waste Plastic Oil Blends: An Experimental Investigation,” Automotive Experiences, vol. 4, no. 1, pp. 20–26, 2021, doi: 10.31603/ae.3692.
  26. [26] F. Marin, A. Rohatgi, and S. Charlot, “WebPlotDigitizer, a polyvalent and free software to extract spectra from old astronomical publications: application to ultraviolet spectropolarimetry,” arXiv preprint arXiv:1708.02025, Aug. 2017, doi: 10.48550/arXiv.1708.02025.
  27. [27] M. Cicala, V. Festa, and A. Marrone, “Data extraction from vintage well sonic log graphs in the ViDEPI project (offshore the Apulia, southern Italy): A multi-useful dataset,” Data in Brief, vol. 46, p. 108814, Feb. 2023, doi: 10.1016/j.dib.2022.108814.
  28. [28] A. Dashti, A. H. Navidpour, F. Amirkhani, J. L. Zhou, and A. Altaee, “Application of machine learning models to improve the prediction of pesticide photodegradation in water by ZnO-based photocatalysts,” Chemosphere, vol. 362, no. January, p. 142792, Aug. 2024, doi: 10.1016/j.chemosphere.2024.142792.
  29. [29] Z. Dobesova, “Evaluation of Orange data mining software and examples for lecturing machine learning tasks in geoinformatics,” Computer Applications in Engineering Education, vol. 32, no. 4, 2024, doi: 10.1002/cae.22735.
  30. [30] Á. Palma, M. Antunes, J. Bernardino, and A. Alves, “Multi-Class Intrusion Detection in Internet of Vehicles: Optimizing Machine Learning Models on Imbalanced Data,” Future Internet, vol. 17, no. 4, pp. 1–14, 2025, doi: 10.3390/fi17040162.
  31. [31] J. H. Friedman, “Greedy function approximation: A gradient boosting machine.,” The Annals of Statistics, vol. 29, no. 5, pp. 1189–1232, Oct. 2001, doi: 10.1214/aos/1013203451.
  32. [32] S. Patnaik, N. Khatri, and E. R. Rene, “Artificial neural networks-based performance and emission characteristics prediction of compression ignition engines powered by blends of biodiesel derived from waste cooking oil,” Fuel, vol. 370, p. 131806, Aug. 2024, doi: 10.1016/j.fuel.2024.131806.
  33. [33] K. Sunil Kumar et al., “Performance, Combustion, and Emission analysis of diesel engine fuelled with pyrolysis oil blends and n-propyl alcohol-RSM optimization and ML modelling,” Journal of Cleaner Production, vol. 434, p. 140354, Jan. 2024, doi: 10.1016/j.jclepro.2023.140354.
  34. [34] F. Hidiyanto and A. Halim, “KNN Methods with Varied K, Distance and Training Data to Disaggregate NILM with Similar Load Characteristic,” in Proceedings of the 3rd Asia Pacific Conference on Research in Industrial and Systems Engineering 2020, New York, NY, USA: ACM, Jun. 2020, pp. 93–99. doi: 10.1145/3400934.3400953.
  35. [35] D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation,” PeerJ Computer Science, vol. 7, p. e623, Jul. 2021, doi: 10.7717/peerj-cs.623.
  36. [36] J. Xiong, O. Fink, J. Zhou, and Y. Ma, “Controlled physics-informed data generation for deep learning-based remaining useful life prediction under unseen operation conditions,” Mechanical Systems and Signal Processing, vol. 197, 2023, doi: 10.1016/j.ymssp.2023.110359.
  37. [37] S. M. Aithal and P. Balaprakash, “MaLTESE: Large-Scale Simulation-Driven Machine Learning for Transient Driving Cycles,” in Lecture Notes in Computer Science, 2019, pp. 186–205. doi: 10.1007/978-3-030-20656-7_10.
  38. [38] L. Hansen, A. Petrovic, N. Seedat, and M. Van Der Schaar, “Reimagining Synthetic Tabular Data Generation through Data-Centric AI: A Comprehensive Benchmark,” in Advances in Neural Information Processing Systems 36, San Diego, California, USA: Neural Information Processing Systems Foundation, Inc. (NeurIPS), Oct. 2023, pp. 33781–33823. doi: 10.52202/075280-1466.
  39. [39] J. Heine, E. E. E. Fowler, A. Berglund, M. J. Schell, and S. Eschrich, “Techniques to produce and evaluate realistic multivariate synthetic data,” Scientific Reports, vol. 13, no. 1, pp. 1–28, 2023, doi: 10.1038/s41598-023-38832-0.
  40. [40] J. Siswanto et al., “Short-Term Prediction of Bus Station Fleet Number Using a Combination of BiLSTM Models,” Automotive Experiences, vol. 8, no. 1, pp. 205–215, Apr. 2025, doi: 10.31603/ae.13402.
  41. [41] S. Alabdulwahab, Y. T. Kim, and Y. Son, “Privacy-Preserving Synthetic Data Generation Method for IoT-Sensor Network IDS Using CTGAN,” Sensors, vol. 24, no. 22, pp. 1–18, 2024, doi: 10.3390/s24227389.
  42. [42] I. E. Livieris, N. Alimpertis, G. Domalis, and D. Tsakalidis, “An Evaluation Framework for Synthetic Data Generation Models,” IFIP Advances in Information and Communication Technology, vol. 713 IFIPAI, pp. 320–335, 2024, doi: 10.1007/978-3-031-63219-8_24.
  43. [43] S. Dutta, M. N. U. Khan, and M. E. Hoque, “An Artificial Neural Network-based Model for Predicting Diesel Engine Performance and Emissions using Pyrolytic Plastic Oil Blend with Diesel Fuel,” SSRN Electronic Journal, no. December, pp. 1–6, 2024, doi: 10.2139/ssrn.4859475.
  44. [44] M. Zhang, N. Tsoulakos, P. Kujala, and S. Hirdaris, “A deep learning method for the prediction of ship fuel consumption in real operational conditions,” Engineering Applications of Artificial Intelligence, vol. 130, p. 107425, Apr. 2024, doi: 10.1016/j.engappai.2023.107425.
  45. [45] S. Watanabe, “Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performance,” arXiv preprint arXiv:2304.11127, pp. 1–74, 2023, doi: 10.48550/arXiv.2304.11127.
  46. [46] K. P. K. K. Mohamad Zaim Awang Pon, “Hyperparameter Tuning of Deep learning Models in Keras,” Sparklinglight Transtions on Artificial Intelligence and Quantum Computing(STAIQC), vol. 1, no. 2021, pp. 36–40, doi: 10.55011/staiqc.2021.1104.
  47. [47] S. Tao, P. Peng, Y. Li, H. Sun, Q. Li, and H. Wang, “Supervised contrastive representation learning with tree-structured parzen estimator Bayesian optimization for imbalanced tabular data,” Expert Systems with Applications, vol. 237, no. November 2022, 2024, doi: 10.1016/j.eswa.2023.121294.
  48. [48] S. Watanabe and F. Hutter, “c-TPE: Tree-Structured Parzen Estimator with Inequality Constraints for Expensive Hyperparameter Optimization,” IJCAI International Joint Conference on Artificial Intelligence, vol. 2023-Augus, pp. 4371–4379, 2023, doi: 10.24963/ijcai.2023/486.
  49. [49] S. Sieradzki and J. Mańdziuk, “Modified Adaptive Tree-Structured Parzen Estimator for Hyperparameter Optimization,” arXiv preprint arXiv:2502.00871, pp. 1–21, Feb. 2025, doi: 10.48550/arXiv.2502.00871.
  50. [50] L. Qiao, X. Li, Q. Umer, and P. Guo, “Deep learning based software defect prediction,” Neurocomputing, vol. 385, pp. 100–110, 2020, doi: 10.1016/j.neucom.2019.11.067.
  51. [51] A. M. Abdullah, R. S. A. Usmani, T. R. Pillai, M. Marjani, and I. A. T. Hashem, “An Optimized Artificial Neural Network Model using Genetic Algorithm for Prediction of Traffic Emission Concentrations,” International Journal of Advanced Computer Science and Applications, vol. 12, no. 6, pp. 797–807, 2021, doi: 10.14569/IJACSA.2021.0120693.
  52. [52] D. Bouabdallaoui, T. Haidi, M. Derri, I. Hbiak, and M. El Jaadi, “Multi-temporal forecasting of wind energy production using artificial intelligence models,” International Journal of Renewable Energy Development, vol. 14, no. 3, pp. 505–517, 2025, doi: 10.61435/ijred.2025.61086.
  53. [53] J. Castresana, G. Gabiña, L. Martin, A. Basterretxea, and Z. Uriondo, “Marine diesel engine ANN modelling with multiple output for complete engine performance map,” Fuel, vol. 319, no. March, 2022, doi: 10.1016/j.fuel.2022.123873.
  54. [54] I. Tyass, T. Khalili, M. Rafik, B. Abdelouahed, A. Raihani, and K. Mansouri, “Wind Speed Prediction Based on Statistical and Deep Learning Models,” International Journal of Renewable Energy Development, vol. 12, no. 2, pp. 288–299, 2023, doi: 10.14710/ijred.2023.48672.
  55. [55] C. Kaewbuddee et al., “Effects of Alcohol-Blended Waste Plastic Oil on Engine Performance Characteristics and Emissions of a Diesel Engine,” Energies, vol. 16, no. 3, 2023, doi: 10.3390/en16031281.
  56. [56] R. T. Marler and J. S. Arora, “The weighted sum method for multi-objective optimization: New insights,” Structural and Multidisciplinary Optimization, vol. 41, no. 6, pp. 853–862, 2010, doi: 10.1007/s00158-009-0460-7.
  57. [57] M. Zhang, N. Tsoulakos, P. Kujala, and S. Hirdaris, “A deep learning method for the prediction of ship fuel consumption in real operational conditions,” Engineering Applications of Artificial Intelligence, vol. 130, no. October 2023, p. 107425, 2024, doi: 10.1016/j.engappai.2023.107425.
  58. [58] K. Sunil Kumar et al., “Performance, Combustion, and Emission analysis of diesel engine fuelled with pyrolysis oil blends and n-propyl alcohol-RSM optimization and ML modelling,” Journal of Cleaner Production, vol. 434, no. December 2023, p. 140354, 2024, doi: 10.1016/j.jclepro.2023.140354.
  59. [59] D. Beltrán and M. L. L. Dantas, “CACHAI’s First Module: A Fully Customizable Chord Diagram for Astronomy and Beyond,” Research Notes of the AAS, vol. 9, no. 8, p. 216, 2025, doi: 10.3847/2515-5172/adf8df.
  60. [60] R. Hao, Y. Wang, and W. Zhang, “Gene expression profiling of extraocular muscles in primary inferior oblique overaction,” PeerJ, vol. 13, pp. 1–17, 2025, doi: 10.7717/peerj.19474.
  61. [61] A. A. Zimta, A. B. Tigu, C. Braicu, C. Stefan, C. Ionescu, and I. Berindan-Neagoe, “An Emerging Class of Long Non-coding RNA With Oncogenic Role Arises From the snoRNA Host Genes,” Frontiers in Oncology, vol. 10, no. April, 2020, doi: 10.3389/fonc.2020.00389.
  62. [62] M. Goyal and Q. H. Mahmoud, “A Systematic Review of Synthetic Data Generation Techniques Using Generative AI,” Electronics, vol. 13, no. 17, p. 3509, Sep. 2024, doi: 10.3390/electronics13173509.
  63. [63] V. K. Kaimal and P. Vijayabalan, “A study on synthesis of energy fuel from waste plastic and assessment of its potential as an alternative fuel for diesel engines,” Waste management, vol. 51, pp. 91–96, 2016, doi: 10.1016/j.wasman.2016.03.003.
  64. [64] H. Yaqoob, H. M. Ali, U. Sajjad, and K. Hamid, “Investigating the potential of plastic pyrolysis oil-diesel blends in diesel engine: Performance, emissions, thermodynamics and sustainability analysis,” Results in Engineering, vol. 24, no. November, 2024, doi: 10.1016/j.rineng.2024.103336.
Article Metrics
47
Views
35
Downloads

SCITE

DIMENSIONS

Publication Information
Published February 6, 2026
Section Articles
Copyright Copyright (c) 2026 Fitra Hidiyanto, Rizqon Fajar, Fauzi Dwi Setiawan, Sigit Tri Atmaja, Heru Priyanto, Muhammad Samsul Maarif, Yaaro Telaumbanua
Keywords
  • Waste plastic oil
  • Pyrolysis
  • Diesel engine performance
  • Synthetic data generation
  • Engine optimization
  • Deep learning modelling