Conventional resource conservation for automotive traction and its utilization to maximize efficiency is not only important but also essential for climate change. Diesel engine lubricating oil is one such component, which has enough potential considering the current methods of servicing. Present work is focused on developing/validating a process, which can predict critical properties of oil at any given instance. This prediction is independent of vehicle operating conditions and vehicle mileage. As the process is independent of above two parameters, even the oil quality after a top up can be identified. Experimental setup consisted of single cylinder stationary engine (Kirloskar - TV1) delivering 5.2kW power @1500 RPM is tested for detailed analysis of the oil characteristics such as Kinematic viscosity, Acid number, Base number and Carbon residue with respect to different engine parameters.Test run was conducted for 150 hrs and the said characteristics for samples were critically analysed at fixed intervals. A ML model was built using data obtained from the test to classify oil quality and predict the remaining mileage. This model was validated with different oil samples (fresh, intermediate and deteriorated). While this model was deployed over raspberry pi for live computations, the results (classification - ok/not ok and mileage) were relayed to a mobile application to simulate end user real time monitoring. The future work will focus on real time testing of a heavy diesel engine integrating both experimental and ML approaches to predict the life of lubricating oil coupled with dynamic scenarios and potential oil failure modes.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    IC Engine Dynamic oil Life Prediction Using Machine Learning Approach


    Weitere Titelangaben:

    Sae Technical Papers



    Kongress:

    10TH SAE India International Mobility Conference ; 2022



    Erscheinungsdatum :

    2022-10-05




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Print


    Sprache :

    Englisch




    Dynamic Automatic Transmission Oil Life Prediction Using Machine Learning

    Badiger, Aishwaryalaxmi / Bhat, Goutam / Priyadarshi, Priyamvad | SAE Technical Papers | 2024


    Vibration Rating Prediction Using Machine Learning in a Dynamic Skip Fire Engine

    Mandal, Aditya / Arvanitis, Anastasios / Chien, Li-Chun et al. | SAE Technical Papers | 2019


    Engine Knock Evaluation Using a Machine Learning Approach

    Ricci, Federico / Mariani, Francesco / petrucci, Luca et al. | SAE Technical Papers | 2020


    Personalized dynamic route prediction using machine learning: A review

    Sudhanva, M G / Kishore, S / Dixit, Sunanda | IEEE | 2017