Title :
Advanced sensor and diagnostic technologies for development of intelligent substations
Author :
Shoureshi, Rahmat ; Norick, Tim ; Permana, Virdiansyah ; Work, John
Author_Institution :
Sch. of Eng. & Comput. Sci., Denver Univ., CO, USA
Abstract :
An essential step toward the development of an intelligent substation is to provide self-diagnosing capability at the equipment level transformers, circuit breakers and other substation equipment should be enabled to detect their potential failures and make life expectancy prediction without human interference. For this to happen, sensors, data storage and transmittal, data analysis, fault detection, and health assessment must be interconnected in a distributed system. This paper details development of an advanced predictive maintenance and diagnostic system that can be used to monitor the health of the transformer and other substation equipment. An artificial intelligent architecture utilizing neuro-fuzzy techniques is used for non-linear system identification, output estimation, and fault detection. An on-line portable diagnostic module, which collects the temperature, current, and vibration data for analysis, is designed and implemented. The development of an optical sensor for use in the diagnostic system is also presented. Experimental results from application of this system to three single-phase 166 MVA are presented. Preliminary indications show the system to work effectively at identifying developing failures in transformers.
Keywords :
circuit breakers; fault location; fuzzy neural nets; maintenance engineering; nonlinear systems; power system interconnection; power transformers; sensors; substation automation; advanced predictive maintenance; advanced sensor; circuit breakers; data analysis; data storage; diagnostic technologies; distributed system interconnection; equipment level transformers health monitoring; fault detection; health assessment; human interference; intelligent substations; life expectancy prediction; neurofuzzy techniques; nonlinear system identification; self-diagnosing capability; Circuit breakers; Data analysis; Electrical fault detection; Humans; Intelligent sensors; Interference; Memory; Sensor systems; Substations; Transformers;
Conference_Titel :
Power Engineering Society General Meeting, 2004. IEEE
Print_ISBN :
0-7803-8465-2
DOI :
10.1109/PES.2004.1372912