With the continuous progress of ship technology, the detection and diagnosis of circuit faults has become particularly important, but traditional methods often rely on manual experience, resulting in long fault response time and low diagnostic accuracy. The purpose of this paper is to use machine learning algorithms to improve the efficiency and accuracy of ship circuit fault detection and diagnosis. Firstly, this study collects historical fault data of ship circuits, including sensor readings, voltage, current, etc., and performs data preprocessing to remove noise and missing values. Subsequently, this study employs feature selection methods to extract key features and utilizes various machine learning models (random forest and support vector machine) for training and validation. The experimental results show that the accuracy rate of the random forest model on the test set has reached 92%, while the accuracy rate of the support vector machine is 88%. The conclusion shows that the fault detection and diagnosis method based on machine learning can significantly improve the speed and accuracy of identifying ship circuit faults, and provide effective technical support for the safe operation of ships.