AVTOMOBIL DVIGATELLARI MAP VA YONILG‘I BOSIMI SENSORLARI NOSOZLIKLARINI MACHINE LEARNING ALGORITMLARI YORDAMIDA DIAGNOSTIKA QILISH

A.SH.Qosimov

Farg‘ona davlat texnika universiteti

S.U.Xujamqulov

Farg‘ona davlat texnika universiteti


Abstract

Annotatsiya: Ushbu maqolada zamonaviy avtomobil dvigatellarining barqaror ishlashini ta’minlovchi MAP (Manifold Absolute Pressure) va yonilg‘i bosimi sensorlari o‘rtasidagi funksional bog‘liqlik tadqiq etiladi. Tadqiqotning maqsadi — an’anaviy diagnostika usullari aniqlay olmaydigan “yashirin” nosozliklarni Machine Learning (ML) algoritmlari yordamida erta bosqichda aniqlash metodikasini ishlab chiqishdir. Maqolada regressiya va anomaliyalarni aniqlash modellari yordamida sensorlar ko‘rsatkichlaridagi o‘zaro korrelyatsiya tahlil qilingan. Natijalar shuni ko‘rsatadiki, ML algoritmlarini qo‘llash diagnostika aniqligini 90-95% dan oshirish imkonini beradi.

Kalit so‘zlar: MAP sensori, yonilg‘i bosimi, Machine Learning, diagnostika, regressiya tahlili, UzAuto Motors, ECM, anomaliyalarni aniqlash.

Abstract. This article examines the functional relationship between the MAP (Manifold Absolute Pressure) sensor and fuel pressure sensors, which ensure the stable operation of modern automobile engines. The purpose of the study is to develop a methodology for the early detection of “hidden” faults that cannot be identified by conventional diagnostic methods using Machine Learning (ML) algorithms. The article analyzes the inter-correlation of sensor readings through regression and anomaly detection models. The results show that the application of ML algorithms makes it possible to increase diagnostic accuracy to more than 90–95%.

Keywords: MAP sensor, fuel pressure, Machine Learning, diagnostics, regression analysis, UzAuto Motors, ECM, anomaly detection.


References

1. Heywood, J. B. (2018). Internal Combustion Engine Fundamentals. McGraw-Hill Education.

2. Jardine, A. K., Lin, D., & Banjevic, D. (2006). "A review on machinery diagnostics and prognostics implementing condition-based maintenance". Mechanical Systems and Signal Processing.

3. Denton, T. (2017). Advanced Automotive Fault Diagnosis. Routledge.

4. Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer.

5. GMD (General Motors Daewoo) Technical Manual. Engine Control Systems and Sensors.

6. Zhou, Z. H. (2021). Machine Learning. Springer Nature.

7. Chen, J., & Li, P. (2020). "Predictive maintenance system for automotive production line based on Big Data". Journal of Manufacturing Systems.

8. Mobed, M., et al. (2021). "Anomaly detection in automotive engine sensors using deep learning". IEEE Transactions on Vehicular Technology.

9. Schmidt, B., & Wang, L. (2019). "Cloud-based predictive maintenance: A case study in automotive industry". Procedia CIRP.

10. Isermann, R. (2011). Fault-Diagnosis Applications: Model-Based Condition Monitoring. Springer.

Most read articles by the same author(s)