Abstract
Dissolved gas analysis (DGA) is an important method of predicting transformer faults, and the accuracy of DGA measurements is of great significance to the evaluation of the transformer state in grid edge systems. In actual situations, it is difficult to regularly calibrate online DGA monitoring devices in a uniform way. Therefore, this paper proposes a method based on B-EMD and DBN to evaluate the validity of online DGA monitoring data and optimize the corresponding calibration plan. An analysis of actual DGA signals shows that the method proposed in this paper can effectively diagnose faults and improve the reliability of DGA online monitoring devices.
Highlights
Power transformers are one of the most important pieces of equipment in a power system, and their operation reliability is directly related to the safety of the power system
At present, dissolved gas analysis (DGA) for transformer oil is an effective method of diagnosing transformer defects [1]–[3] and has been widely used to monitor the state of power transformers
According to the corresponding fault type of training samples and the feature vectors extracted by the model, the health status of a DGA online monitoring device is defined as follows: (1) dangerous: when the fault confidence coefficient is above 90%, repair and maintenance are necessary; (2) alarming: when the fault confidence coefficient ranges from 80% to 90%, the device should be included in the repair and maintenance plan; (3) hidden danger: the fault confidence coefficient ranges from 70% to 80%; (4) potential hidden danger: the fault confidence coefficient ranges from 60% to 70%; and (5) safe: the fault confidence coefficient is below 60%
Summary
Power transformers are one of the most important pieces of equipment in a power system, and their operation reliability is directly related to the safety of the power system. This paper proposes a method based on B-EMD and DBN to evaluate the validity of online DGA monitoring data and optimize the calibration scheme. An analysis of actual DGA signals shows that the method proposed in this paper can effectively diagnose the faults of DGA online monitoring devices and improve device reliability. Perform three spline interpolations for the maximum/ minimum sequences x+(t) and x−(t) separately before obtaining the upper/lower envelope curves of the original input signal x(t), which are expressed as e+(t) and e−(t).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
