Abstract
Analog circuits are essential to electronic systems due to their variety of critical functions. Catastrophic faults, such as short- and open-circuit faults, can stop the circuit from functioning. Meanwhile, parametric faults such as drift due to temperature fluctuations, noise in components, and power supply issues cause the circuit to operate beyond its range. Such faults can harm the circuit and its constituent parts. Therefore, it is crucial to identify and address the issues brought on by these faults. Common traditional fault diagnosis methods that rely on manual testing and visual assessment are lacking in complex electronic systems and faults. Such methods can catch obvious problems but struggle with subtle or rare faults. Herein, AI has emerged as a strong tool in enhancing fault detection processes, providing capabilities for analyzing vast amounts of data, recognizing patterns, and making decisions based on that data with improved accuracy and speed in fault diagnosis. Accordingly, the common emitter circuit-DC configuration was considered with 15 patterns. The first pattern represents normal conditions, whereas the others represent faulty conditions. The faulty patterns included probable fluctuations in collector and emitter resistor values, power supply internal resistance, and operating temperature. A dataset covering the study parameters and circuit patterns was established, considering both simulation and experimental readings. Supervised machine learning, primarily using random forest classifiers, was employed to detect faults. The hybrid dataset model was trained and validated on that basis. The system achieved a 98.7% success rate in the fault detection condition, demonstrating its efficiency and robust performance. To further investigate the physics behind various fault patterns, a comprehensive analytical model was developed and linked to the machine learning results, highlighting the effectiveness of each feature.