Predictive Vehicle Maintenance using Deep Neural Networks
Neil F. Johnson, Vinodh Ewards, Salaja Silas, G. Jaspher W. Kathrine
Abstract
The integration of smart sensors and Internet of Things (IoT) devices within vehicles is transforming the automotive industry, generating a wealth of data with immense potential for predictive maintenance systems. This research study explores a subset of these sensors such as, engine temperature, oil pressure, battery voltage, fuel level, odometer reading, tier pressure, brake fluid level, air filter status, transmission fluid level, and coolant level. This study proposes a novel predictive vehicle health maintenance system that leverages real-time sensor data to predict potential issues and optimize servicing schedules, minimize breakdowns, and enhance the overall vehicle reliability. Using a sample of a dataset with readings and states of the mentioned sensors, a deep neural network was trained and the results show a prediction accuracy of 97%.