Diagnosis of a Chopper Controlled DC Motor by Boosting

This paper proposes a methodology to diagnose a transient state of a dynamic system using boosting. The methodology is composed by two steps: one off-line process and another on-line process. The off-line phase begins gathering data from the system, both when it is running free of fault and when the system is running in each fault mode. A segmentation and normalization algorithm is used to reduce the large amount of gathered data. The final step is the generation of a decision tree by a classification tool. The boosting technique is used with the aim of improving the classification results. The on-line process of the methodology consists of evaluating a new reading of the system sensors with the generated decision trees. The diagnosis of the system is the result of this evaluation which has very low computational cost due to the simplicity of the decision trees. Also, the implementation cost is very low due to this simplicity