Automobiles have become an integral aspect of daily life worldwide, offering convenient transportation for work, school, and essential journeys. Their adaptability allows people to explore remote areas, connect with family, and engage in recreational pursuits by providing reliable and efficient trans-portation. Amid hectic lifestyles, vehicle maintenance often takes a back seat, leading to increased demand for repairs and contributing to resource depletion. Employing machine learning techniques offers a solution to mitigate these challenges. Our research, titled “Predictive maintenance for two-wheeler vehicles using XGBoost”, utilizes the XGBoost algorithm to predict the optimal condition of a vehicle. XGBoost is employed for its ability to handle complex, non-linear relationships in the input parameters and enhancing the accuracy of predictions. Key parameters include vehicle type, process temperature, air temperature, torque, tool wear,and rotational speed, they offer insights into specific mechanical and operational aspects like thermal conditions, mechanical stress, and wear, allowing for accurate predictions of potential failures. This predictive model aims to empower users with insights into their vehicle's health, contributing to sustainable automotive practices.
Predictive Maintenance for Two-Wheeler Vehicles Using XGBoost
14.03.2024
447800 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Controlling Vehicles in Response to Two-Wheeler Vehicles
Europäisches Patentamt | 2020
|Six-wheeler vehicles for passenger transport
Engineering Index Backfile | 1928
|Execution of CNG on Two-Wheeler Vehicles
Springer Verlag | 2023
|