The traction and braking control systems of trains are primarily managed by the controller, a critical electrical control device within rail transportation systems, ensuring the safety and stability of trains during operation. With the development of rail transportation, the demand for efficient maintenance of these controllers has become increasingly urgent. Traditional maintenance methods heavily rely on manual inspection, which not only leads to low maintenance efficiency but also presents challenges such as insufficient precision, long maintenance cycles, and incomplete data records. These issues are especially prominent in confined working environments, where the limitations of traditional maintenance methods become more apparent. This study proposes an integrated diagnostic system for controllers based on high-precision electrical testing and visual inspection technologies. By combining visual measurement techniques with electrical performance testing, the system innovatively enables the automated detection of various parameters of the controllers. Furthermore, through a self-learning algorithm, the diagnostic model is continuously optimized, enhancing fault prediction accuracy, reducing manual intervention, and significantly improving detection efficiency and precision. This system provides a novel solution for the intelligent maintenance of controllers.