The increasing need for intelligent and reliable vehicle systems has accelerated the adoption of Digital Twin technology for real-time health monitoring and predictive maintenance. This project presents a Digital Twin–based Vehicle Health Monitoring System developed using a Raspberry Pi 3 B+, which synchronizes a physical vehicle with its virtual model using continuous sensor data for condition monitoring and fault prediction.

The system integrates multiple sensors to monitor key vehicle parameters such as voltage and current (INA219), temperature and humidity (DHT11), pressure and altitude (BMP180), vibration, speed, fuel level, and oil level. Vehicle movement is controlled using an L298 motor driver, with a joystick module provided for manual control during testing and emergency situations. All sensor data is logged every 5 seconds to an SD card and visualized in real time through a web-based dashboard.

The digital twin analyzes both live and historical data using ML algorithm to detect anomalies and predict potential failures in advance. When abnormal conditions are detected, a buzzer alert is triggered and notifications are displayed on the web dashboard for remote monitoring. Compared to manual control, the digital twin approach significantly enhances early fault detection, preventive maintenance, and overall vehicle reliability, offering a cost-effective and scalable solution for smart mobility applications.

        Objectives:

• To develop a Digital Twin–based vehicle health monitoring system using Raspberry Pi 3 B+.
• To continuously monitor key vehicle parameters using multiple sensors.
• To enable real-time data logging and visualization through a web-based dashboard.
• To apply machine learning techniques for anomaly detection and fault prediction.
• To provide early alerts and notifications for preventive maintenance.
• To enhance vehicle reliability and safety through intelligent monitoring.
• To design a cost-effective and scalable solution for smart mobility applications.

          The major building blocks of the project are:  

• Battery power supply.
• LM2596 Buck Converter.
• INA219 (voltage and current) sensor.
• DHT11 (temperature and humidity) sensor.
• BMP180 (pressure and altitude) sensor
• Vibration sensor.
• Speed sensor.
• Fuel Level Sensor (SR04).
• Oil level (SR04)
• DC motors with L298 motor driver.
• Joystick module.
• 20*4 LCD display.
• Buzzer.
• SD card.

          Software’s used:  

• Rasppbian OS.
• Machine learning algorithm.
• Express SCH for Circuit design.

          Block Diagram:        

video: