Preventive Diagnostics of Internal Combustion Engines Based on Setpoint-to-Actual Deviation Using Artificial Intelligence and a Standardized 3/5/7 Data-Collection Protocol

Edmond Gevorkyan

Edmond Gevorkyan Automotive Electronics Specialist, President of CODIAG Nancy, France

Keywords: preventive diagnostics, internal combustion engines, setpoint-to-actual deviation, OBD-II data, artificial intelligence, predictive maintenance, diagnostic trouble codes, residual analysis, 3/5/7 protocol, engine health monitoring

Abstract

Preventive engine diagnostics needs a signal that appears before a diagnostic trouble code and remains interpretable across engine types. This article proposes a conceptual and methodological framework for internal combustion engines in which the diagnostic primitive is the deviation between the electronic control unit setpoint and the actual realized value across regulated loops. The aim is to define how this deviation can support early fault recognition when engineers combine it with artificial intelligence and a standardized 3/5/7 data-collection protocol covering idle, urban, and highway phases. The study uses a structured review of ten recent sources on OBD-II analytics, fault detection, predictive maintenance, residual diagnostics, and explainable AI. The analytical part substantiates the diagnostic value of setpoint-to-actual deviation, specifies the data collection logic, and outlines validation through detection lead time. The framework supports workshops and fleets seeking traceable pre-DTC monitoring without proprietary software details and with field validation reserved for later studies.

References

Cummins, L., Sommers, A., Ramezani, S. B., Mittal, S., Jabour, J., Seale, M., & Rahimi, S. (2024). Explainable predictive maintenance: A survey of current methods, challenges and opportunities. IEEE Access, 12, 57574–57602. https://doi.org/10.1109/ACCESS.2024.3391130
Jung, D., Frisk, E., & Krysander, M. (2024). The LiU-ICE benchmark: An industrial fault diagnosis case study. arXiv. https://doi.org/10.48550/ARXIV.2408.13269
Mahale, Y., Kolhar, S., & More, A. S. (2025). A comprehensive review on artificial intelligence driven predictive maintenance in vehicles: Technologies, challenges and future research directions. Discover Applied Sciences, 7(4), 243. https://doi.org/10.1007/s42452-025-06681-3
Mercorelli, P. (2024). Recent advances in intelligent algorithms for fault detection and diagnosis. Sensors, 24(8), 2656. https://doi.org/10.3390/s24082656
Michailidis, E. T., Panagiotopoulou, A., & Papadakis, A. (2025). A review of OBD-II-based machine learning applications for sustainable, efficient, secure, and safe vehicle driving. Sensors, 25(13), 4057. https://doi.org/10.3390/s25134057
Navali, N., Vanajakshi, L., & Bullock, D. M. (2023). Application of on-board diagnostics (OBD) data for vehicle trajectory prediction. In L. Devi, M. Errampalli, A. Maji, & G. Ramadurai (Eds.), Proceedings of the Sixth International Conference of Transportation Research Group of India (Vol. 273, pp. 319–328). Springer Nature Singapore. https://doi.org/10.1007/978-981-19-4204-4_19
Srinivaas, A., Sakthivel, N. R., & Nair, B. B. (2025a). Cross domain fault diagnosis in internal combustion engines using multisensor data with transfer federated and transformer based federated transfer learning. Scientific Reports, 15(1), 36775. https://doi.org/10.1038/s41598-025-20692-5
Srinivaas, A., Sakthivel, N. R., & Nair, B. B. (2025b). Machine learning approaches for fault detection in internal combustion engines: A review and experimental investigation. Informatics, 12(1), 25. https://doi.org/10.3390/informatics12010025
Torres, N. N. S., Maciel, J. N., Lima, T. L. D. V., Gazziro, M., Filho, A. C. L., Carmo, J. P. P. D., & Ando Junior, O. H. (2025). Fault diagnosis in internal combustion engines using artificial intelligence predictive models. Applied System Innovation, 8(5), 147. https://doi.org/10.3390/asi8050147
Ucar, A., Karakose, M., & Kırımça, N. (2024). Artificial intelligence for predictive maintenance applications: Key components, trustworthiness, and future trends. Applied Sciences, 14(2), 898. https://doi.org/10.3390/app14020898