A new intelligent hierarchical fault diagnosis system [for power networks]

As a part of a substation-level decision support system, a new intelligent hierarchical fault diagnosis system for the online fault diagnosis of power systems is presented in this paper. The proposed diagnosis system divides the fault diagnosis process into two phases. Using time-stamped information of relays and breakers, phase I identifies the possible fault sections through the group method of data handling (GMDH) networks, and phase II recognizes the types and detailed situations of the faults identified in phase I by using a fast bit-operation logical inference mechanism. The diagnosis system has been practically verified by testing on a typical Taiwan power secondary transmission system. Test results show that rapid and accurate diagnosis can be obtained with flexibility and portability for fault diagnosis purpose of diverse substations.