An Artificial Intelligence Approach to Predict the Hybrid Nanofluids based Application for Radiators

This study addresses renewable energy concerns through the utilization of nanotechnology in automotive cooling systems, focusing on hybrid nanofluids for radiator applications. Employing a specific nanoparticle incorporation technique, the research aims to enhance radiator efficiency crucial for robust engine performance. In light of potential radiator malfunctions, the study introduces an innovative approach for fault detection using Artificial Neural Network (ANN) algorithms, classifying faults into six categories: normal operation, radiator door failure, blocked tubes, fan blockage, disconnected fins and tubes, and coolant leaks. Results indicate the successful implementation of AI-based fault detection, demonstrating high accuracy in categorizing radiator faults. The research not only establishes a foundation for integrating AI into automotive maintenance but also contributes to sustainable practices by fortifying engine efficiency through nanotechnology-enhanced cooling. The implications extend to proactive fault resolution and optimal vehicle performance, marking a significant stride in the intersection of nanotechnology and AI within the automotive sector. Future directions involve refining AI algorithms, expanding fault categories, and exploring further applications of nanotechnology for continued advancements in automotive systems.