Development of a Vehicle Sensor Fault Diagnosis Device Using Artificial Intelligence Techniques to Improve Diagnostic Accuracy

Abstract

The rapid evolution of automotive technology has heightened the reliance on electronic sensors for real-time monitoring and diagnostics. However, accurately identifying sensor faults remains a significant challenge due to the increasing complexity of modern vehicles. This paper presents the design and development of an intelligent diagnostic device that employs artificial intelligence (AI) techniques specifically Artificial Neural Networks (ANNs) to enhance the precision of fault detection. The system integrates signal acquisition, preprocessing, and classification modules within a low-cost embedded platform based on Arduino. It processes data from various simulated automotive sensors, distinguishing between normal and faulty conditions with high accuracy. Experimental evaluations demonstrate the device’s superior diagnostic performance compared to conventional tools. In addition, an economic feasibility analysis confirms the device’s potential for widespread adoption, particularly in resource-constrained markets. The proposed solution offers a cost-effective, accurate, and scalable approach to vehicle sensor diagnostics, promising improvements in maintenance efficiency, cost reduction, and overall road safety.