Oil-immersed power transformer defect early warning method based on hidden Markov model
A power transformer and hidden Markov technology, which is applied in the field of oil-immersed power transformer defect early warning based on hidden Markov model, can solve the problem of reducing the universality of field samples, difficult to find transformers, affecting the generalization ability and diagnosis of models. issues of accuracy
Active Publication Date: 2019-08-30
HUAQIAO UNIVERSITY
View PDF4 Cites 8 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The main problems in identifying the operating status of transformers are as follows: 1) There are many factors affecting the insulation degradation of transformers, such as environment, materials, service age, etc. Individual differences caused by various influencing factors make it difficult to find universal standards or 2) The mapping relationship between external observations (changes in the concentration of dissolved gas in oil) and internal defects of transformers is relatively complex, and it is difficult to accurately quantify and identify based on some existing experience
Due to the difficulty in obtaining sample data of typical conditions on site, the difficulty of model establishment is increased; and, as analyzed above, since the insulation degradation process of transformers is greatly affected by insulation materials, operating environment and operating years, the model used in the modeling process There may be large differences between the sample transformer and the actual transformer to be diagnosed in terms of insulation material, insulation structure, service life and operating environment, which will reduce the universality of the obtained field samples, which affects the generalization of the established model Capability and diagnostic accuracy
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0060] see figure 1 As shown, the transformer used in this embodiment is a 3×277MVA 515 / 22KV single-phase transformer group manufactured by British Alstom Company (now AREVA Company). The main transformer is an open transformer with no diaphragm and capsule in the oil conservator. The transformer insulating oil uses Nytro 10GBN hydrogenated light naphthenic mineral oil from NYNAS Company in Sweden. Table 1 shows the different characteristic gases produced by the fault and the amount of abnormal gas when the fault occurs (because the experimental sample does not have CO 2 measurement data, so some of them contain the fault characteristic gas CO 2 The amount of abnormal gas in the fault decreases accordingly). Take G=1, g=5, take MATLAB as the working platform to carry out the simulation description of the present invention. Select 3 groups of chromatographic data of 50 sampling points in each group before the primary alarm state of C-phase chromatogram of the main transform...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an oil-immersed power transformer defect early warning method based on a hidden Markov model, and the method comprises the steps: training the hidden Markov model through the time sequence data of the change of the concentration of dissolved gas in the oil of a transformer to be monitored, and obtaining a probability model about the abnormal change condition of the concentration of the dissolved gas in the oil; and calculating the probability of abnormal gas concentration change of the transformer to be detected at the current moment based on the probability model, andfurther detecting an early warning signal appearing in transformer abnormal state transition to realize dynamic early warning of the transformer operation state. Early warning signals appearing in transformer state transition are constructed and detected through dissolved gas data in oil monitored by an oil chromatography on-line monitoring system of a transformer to be diagnosed, typical sample data do not need to be collected in the modeling process, and the data are easy to obtain; and the built model uses the data of the transformer to be diagnosed, so that the generalization problem doesnot exist, and early defect early warning and identification of the transformer are facilitated.
Description
technical field [0001] The invention relates to the technical field of early warning and fault diagnosis of oil-immersed power transformer defects, in particular to a defect early warning method for oil-immersed power transformers based on a hidden Markov model. Background technique [0002] The oil-immersed power transformer is the most basic and important power grid equipment in the power system. At the same time, it is also a kind of equipment that is prone to accidents. Defect early warning and fault diagnosis for the transformer are important to ensure the stable operation of the power system. Among them, monitoring and The analysis of dissolved gas (DGA) in oil plays an important role in ensuring the safe and stable operation of transformers. [0003] The main problems in identifying the operating status of transformers are as follows: 1) There are many factors affecting the insulation degradation of transformers, such as environment, materials, service age, etc. Indiv...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & AuthorityApplications(China)
IPC IPC(8): G06F17/10G01R31/00G01R31/02G01N30/00G01N33/28
CPCG06F17/10G01R31/00G01N30/00G01N33/2841G01R31/62Y04S10/50
Inventor方瑞明张燕
OwnerHUAQIAO UNIVERSITY