A Method for Power System Data Visualization and Fault Condition Diagnosis Based on the Common Information Model

With the increasing complexity of power systems, the need for system data visualization and fault condition recognition has become increasingly important. This study proposes a method for power system data visualization and condition recognition based on the Common Information Model (CIM), aiming to enhance the intelligent management and fault diagnosis accuracy of power systems. The method extracts structural information from the CIM model to construct a visual representation of the power system and generates a data set of the power system through a power system topology traversal algorithm. Furthermore, the study combines the Kmeans clustering algorithm and the K-Nearest Neighbor(KNN) classification algorithm to develop a fault condition recognition method. By analyzing historical fault condition data, the method trains and validates a fault condition recognition model, achieving accurate identification of the power system's working state. Case analysis of the IEEE 3-machine 9-node system verifies the effectiveness of the proposed method, showing that it can significantly improve the accuracy and efficiency of power system fault diagnosis and has important practical application value for the intelligent maintenance of power systems.