Fault Diagnosis Based on Data Mining: A Case Study in Nanjing

Nowadays, metro is playing an important role in our life all over the world. People like travelling or going to work by metro for its advantages such as avoiding traffic jam and saving money, but there are many accidents every year, so the fault diagnosis of the metro is very important because it is closely related to the safety of passengers. And the fault diagnosis of the door control system is the most important among the metro systems because it will injure passengers most if the door has some faults. In this paper, we will attempt to apply the data mining to get fault diagnosis of the door control system online. Firstly, we will give one method for association analysis based on the characteristics of the door control system, and then apply it online to predict the fault of the door control system. Lastly, the experiments show the efficiency of the proposed algorithm.