This Final Year Project proposes the development of an AI-powered OBD-II diagnostic and maintenance ecosystem that integrates a mobile application, a backend server, machine learning models, and a web dashboard to provide real-time vehicle health monitoring and predictive maintenance insights. The system leverages OBD-II data from the vehicle to identify faults, monitor live sensor readings, maintain service records. The mobile application (Flutter-based) will serve as the primary interface for drivers. It will display real-time parameters such as engine RPM, vehicle speed, coolant temperature, while also showing active fault codes in both English and Urdu, with integrated voice assistance for improved accessibility. The app will also feature CRUD functionality for maintaining a digital service history, generate oil change reminders, and provide trip logs with GPS-based tracking.
Objectives
Develop real-time OBD-II data acquisition and visualization for sensors like RPM, speed, temperature, and fuel.
Integrate machine learning for anomaly detection and crash detection.
Provide accident detection using smartphone accelerometer data to identify sudden impacts
and trigger alerts.
Provide Urdu and English voice accessibility.
Implement role-based access control for Drivers, Mechanics, and Admins to ensure secure
data handling.
Enable CRUD operations for service history with automated reminders based on
mileage/time.
Incorporate trip logging with GPS integration for location tracking and performance metrics.
Set up notifications and reminders for faults, predictions, maintenance, and accidents.
Create a backend for data ingestion, storage (using Supabase PostgreSQL and
TimescaleDB), and API connections.
Display live sensor readings and fault codes with Urdu & voice support.
Maintain CRUD-based vehicle service history.
Store detailed log history in backend with GPS-based trip tracking.
Provide oil change and maintenance reminders.
Enable mechanics to view user cars, logs, and provide recommendations.
Enable web-based dashboards for admin and mechanics.
Socio-Economic Benefit
Providing precise Diagnostic Trouble Codes (DTCs) eliminates guesswork, helping users understand their car's issues and preventing unnecessary repairs or overcharging by dishonest repair shops.
Increased Road Safety: Real-time insights into vehicle health, such as steering position malfunctions or low brake fluid, can alert drivers to unsafe conditions before they result in a roadside breakdown or accident.
Methodologies
Agile
Outcome
Fully Functional Mobile Application: A complete, deployable front-end interface that allows users to seamlessly navigate through vehicle health dashboards, trip logs, and diagnostic reports.
Reliable Hardware-Software Integration: A stable, secure connection protocol established between the mobile application and standard OBD2 hardware (via Bluetooth or Wi-Fi) for real-time data extraction.
Real-Time Telemetry Dashboard: The ability for the user to monitor live vehicle metrics (e.g., engine RPM, coolant temperature, vehicle speed, fuel trim) with minimal latency.
Smart Diagnostics & Troubleshooting: A feature that not only reads and clears check engine light codes but provides actionable step-by-step repair guidance or severity warnings based on AI analysis.
Historical Data Logging: A database implementation that records past trips, recurring errors, and performance trends over time, enabling users to track vehicle health history.
