Since the smart charging piles are generally deployed in complex environments and prone to failure, it is significant to perform efficient fault diagnosis and timely maintenance for them.
If a fault is not cleared in a charging pile, it could not work normally after started a second time. After settlement completion, faults are warned and reset, and the charging pile enters a standby state. Only after the fault has been cleared can the charging pile work by restarting.
In case of a fault, the charging pile will display the related fault code on the charging fault record page, the fault light will be on, and the output of the charging pile will be cut off. Faults in charging piles can be reset by swiping the card. After the settlement is completed, faults will be warned and reset, and the charging pile will enter the standby state.
Abstract: With the application of the Internet of Things (IoT), smart charging piles, which are important facilities for new energy electric vehicles (NEVs), have become an important part of the smart grid.
In this article, a real-time fault prediction method combining cost-sensitive logistic regression (CS-LR) and cost-sensitive support vector machine classification (CS-SVM) is proposed. CS-LR is first used to classify the fault data of smart charging piles, then the CS-SVM is adopted to predict the faults based on the classified data.
CS-LR is first used to classify the fault data of smart charging piles, then the CS-SVM is adopted to predict the faults based on the classified data. The feasibility of the proposed model is illustrated through the case study on fault prediction of real-world smart charging piles.