TY  - BOOK
AU  - Akbar Naqvi, Syed Muhammad Ali 
AU  - Supervisor Dr. Shibli Nisar
TI  - AI-Based Fault Diagnosis of Car Engines Using Multi-Sensor Data Fusion
U1  - 621.382,NAQ 
PY  - 2024///
CY  - MCS, NUST 
PB  - Rawalpindi 
KW  - UG EE Project
KW  - BEE-57
N1  - Modern automobiles rely on sophisticated Engine Control Units (ECUs) to manage various performance aspects. However, in an Internal Combustion engine, a small fault can lead to bigger and multiple problems, resulting in unexpected breakdowns and high repair costs. To address this issue, this paper presents an AI-based fault diagnostic system that integrates multiple sensors to predict and identify engine faults, such as Misfires, Piston knocks, and Starting/Stability Malfunctions. By leveraging neural networks for multi-sensor data fusion, the system enables real-time analysis of sensor data, improving fault prediction accuracy and adaptability to evolving fault patterns. The integration of neural networks with sensor data fusion represents a significant advancement in automotive diagnostics, supporting our commitment to delivering efficient fault diagnostic solutions. This AI-based early detection system aims to minimize repair costs and inconvenience for vehicle owners, highlighting the importance of predictive maintenance in ensuring vehicle reliability and performance
ER  -