CN115452978B - Reliability judging method and device for power transformer insulation system - Google Patents
Reliability judging method and device for power transformer insulation system Download PDFInfo
- Publication number
- CN115452978B CN115452978B CN202211041787.7A CN202211041787A CN115452978B CN 115452978 B CN115452978 B CN 115452978B CN 202211041787 A CN202211041787 A CN 202211041787A CN 115452978 B CN115452978 B CN 115452978B
- Authority
- CN
- China
- Prior art keywords
- model
- evaluation model
- transformer
- constructing
- insulation system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000009413 insulation Methods 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 title claims abstract description 33
- HYBBIBNJHNGZAN-UHFFFAOYSA-N furfural Chemical compound O=CC1=CC=CO1 HYBBIBNJHNGZAN-UHFFFAOYSA-N 0.000 claims abstract description 86
- 238000013210 evaluation model Methods 0.000 claims abstract description 78
- 238000012360 testing method Methods 0.000 claims abstract description 65
- 238000006116 polymerization reaction Methods 0.000 claims abstract description 39
- 230000007613 environmental effect Effects 0.000 claims abstract description 18
- 238000001514 detection method Methods 0.000 claims abstract description 17
- 238000004587 chromatography analysis Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims description 17
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000032683 aging Effects 0.000 claims description 6
- 238000001069 Raman spectroscopy Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000002790 cross-validation Methods 0.000 claims description 3
- 230000007547 defect Effects 0.000 abstract 1
- 239000003921 oil Substances 0.000 description 32
- 239000007789 gas Substances 0.000 description 8
- 230000008439 repair process Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000004215 Carbon black (E152) Substances 0.000 description 1
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008033 biological extinction Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 230000000593 degrading effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010891 electric arc Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 229930195733 hydrocarbon Natural products 0.000 description 1
- 150000002430 hydrocarbons Chemical class 0.000 description 1
- 239000001257 hydrogen Substances 0.000 description 1
- 229910052739 hydrogen Inorganic materials 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 239000002480 mineral oil Substances 0.000 description 1
- 235000010446 mineral oil Nutrition 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000010079 rubber tapping Methods 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N30/00—Investigating or analysing materials by separation into components using adsorption, absorption or similar phenomena or using ion-exchange, e.g. chromatography or field flow fractionation
- G01N30/02—Column chromatography
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/65—Raman scattering
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/26—Oils; Viscous liquids; Paints; Inks
- G01N33/28—Oils, i.e. hydrocarbon liquids
- G01N33/2835—Specific substances contained in the oils or fuels
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Immunology (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Engineering & Computer Science (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Chemical Kinetics & Catalysis (AREA)
- General Chemical & Material Sciences (AREA)
- Oil, Petroleum & Natural Gas (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Housings And Mounting Of Transformers (AREA)
Abstract
The invention provides a reliability judging method and device of a power transformer insulation system, wherein the method comprises the following steps of constructing a frame model of the transformer insulation system; acquiring oil chromatography historical test data and constructing a first evaluation model; under the same test period, acquiring furfural historical test data, and determining a relation between the furfural content and the polymerization degree; taking the ratio of the polymerization degree to the threshold value as a weight, and constructing a second evaluation model by combining the frame model; acquiring line inrush current data and environmental parameters of a transformer; calculating a first weight and a second weight according to the line inrush current data and the environmental parameters, and constructing a joint judgment model by combining the first evaluation model and the second evaluation model; and acquiring detection data of the current power transformer insulation system, inputting the detection data into the joint judgment model, and outputting a reliability index. According to the invention, two types of evaluation models based on different characteristic products are fused, so that the reliability judgment accuracy is improved, and the hysteresis defect of the traditional evaluation model is overcome.
Description
Technical Field
The invention relates to the technical field of power transformer state evaluation, in particular to a reliability judging method and device for an insulation system of a power transformer.
Background
The power transformer is one of electric equipment with important status and high price in the power grid system, plays an indispensable role in the power grid system and plays a central role in the conversion and transmission links of electric energy, so that the safety operation of the power transformer is very necessary.
Insulating oil in an oil-immersed transformer plays a vital role in a transformer insulation system: 1. the heat dissipation and cooling functions are mainly achieved during operation; 2. the winding is kept in a good insulation state, and insulation maintenance effects are achieved; 3. the transformer oil plays an arc extinction role at the contact point of the high-voltage lead and the tapping switch, and corona and arc discharge are prevented from being generated; 4. transformer oil is widely used as a liquid seal in hydraulic safety valves.
At present, the insulating oil of the transformer is generally mineral oil, and when the insulating oil is heated or high-energy discharge and other conditions (mainly line current) occur in oil filling equipment, the insulating oil can be cracked to generate hydrogen or low-molecular hydrocarbon characteristic gases, such as H2, CH4, C2H6, C2H4, C2H2, CO2 and other characteristic gases. Therefore, the analysis of the characteristic gas by the chromatographic on-line monitoring device is an effective means for analyzing the transformer insulating oil, and the faults of equipment can be found in early stages.
Moreover, the insulation system of the transformer is mainly composed of insulation oil and insulation paper, and the insulation paper is cracked and degraded to generate furfural during long-time operation of the transformer, so that the reliability of the insulation system can be deduced by detecting the proportion of furfural dissolved in the insulation oil and furfural adsorbed in the insulation paper. The existing method for estimating the polymerization degree of the insulating paper through the furfural content in the insulating oil so as to infer the reliability of an insulating system is the most common estimation method.
However, in the prior art, based on characteristic products such as dissolved gas in oil or furfural content, the reliability of the transformer insulation system is estimated by processing, calculating and analyzing by using mathematical methods such as a wavelet network method, a neural network method or a Bayesian network classifier, and the like, because only single characteristic data is relied on, the estimation accuracy is easy to be low, and the problems of over repair or no repair and the like are caused. In addition, because factors influencing the reliability of the transformer insulation system include temperature characteristics, line inrush current characteristics, humidity characteristics and the like, different values are available under different environments and meteorological conditions, uncertainty and randomness of influencing factors are not fully considered in the prior art, for example, furfural produced by cracking and degrading of insulation paper can slowly change along with the change of external conditions such as temperature and humidity, but the furfural content at the moment cannot accurately reflect the health state of the insulation paper. Thus, there is a significant hysteresis in the prior art in indirectly inferring insulation system reliability by monitoring the products produced.
Disclosure of Invention
In view of the above problems, the invention provides a reliability judging method and device for an insulation system of a power transformer, which solve the problems that in the prior art, only single characteristic data is relied on, evaluation accuracy is easy to be low, and over repair or no repair is caused, and obvious hysteresis exists.
In order to solve the technical problems, the invention adopts the following technical scheme: the reliability judging method of the power transformer insulation system comprises the following steps of obtaining equipment information of a transformer and constructing a frame model of the transformer insulation system; acquiring oil chromatography historical test data, and constructing a first evaluation model based on a Stacking algorithm; under the same test period, acquiring furfural historical test data, and determining a relation between the furfural content and the polymerization degree; taking the ratio of the polymerization degree to a threshold value as a weight, and constructing a second evaluation model by combining the frame model; under the same test period, obtaining line inrush current data and environmental parameters of the transformer; calculating a first weight and a second weight according to the line inrush current data and the environmental parameters, and constructing a joint judgment model by combining the first evaluation model and the second evaluation model; and acquiring detection data of the current power transformer insulation system, inputting the detection data into the joint judgment model, and outputting a reliability index.
Preferably, the equipment information includes a transformer model and an expected life, and the constructing a frame model of the transformer insulation system includes: assuming the reliability index of the frame model as D, then
In the above, D 0 For the initial moment T of the transformer 0 Is the reliability index of (1), G is the aging rate, T 1 D is the current moment of the transformer t For the reliability index corresponding to the possible fault time of the transformer, T d Is the life expectancy.
Preferably, the oil chromatography historical test data includes concentration of dissolved characteristic gas in oil and corresponding reliability index of the insulation system, and the building the first evaluation model based on the Stacking algorithm includes: dividing the oil chromatography history test data into a training sample and a test sample, and training a primary model of a Stacking model according to a K-fold cross validation method to obtain a new training sample; averaging the test samples to obtain new test samples; and training a secondary model of the Stacking model by using the new training sample, and testing by using the new test sample so as to obtain a first evaluation model.
Preferably, the furfural history test data includes a furfural content and a corresponding polymerization degree thereof, and the determining a relation between the furfural content and the polymerization degree includes:
D P ＝-120·ln Fa+b
in the above formula, dp is the degree of polymerization, fa is the furfural content, b is a constant, and 469 is taken.
Preferably, the constructing a second evaluation model in combination with the frame model includes: setting the threshold value of the polymerization degree as D P0 The insulation system reaches its service life at this time; the calculation formula of the second evaluation model is as follows:
in the above formula, D' is the reliability index of the second evaluation model, lambda is the adjustment coefficient, D P Degree of polymerization, D P0 Is the threshold value of polymerization degree, D is the frame modelReliability index of (c).
Preferably, the calculating a first weight and a second weight according to the line inrush data and the environmental parameter, and constructing a joint judgment model by combining the first evaluation model and the second evaluation model includes: counting the number of line inrush times exceeding a set peak value in a test period, calculating the average number of the number of line inrush times, and taking the ratio of the average number of line inrush times to an inrush time standard value as a first weight; counting the humidity in the test period, calculating the average humidity, and taking the ratio of the average humidity to a humidity standard value as a second weight; the calculation formula of the joint judgment model is as follows:
in the above, k 0 、k 1 、k 2 For correction coefficients, Q is the first evaluation model,n is the average number of the line inrush times 0 Is the standard value of inrush frequency->Average humidity, pw 0 D' is the second evaluation model, epsilon is the error, which is the humidity standard value.
As a preferred solution, an oil chromatograph, a laser raman spectrometer and a humidity detector are installed on the transformer, and the step of obtaining the detection data includes: detecting the concentration of dissolved characteristic gas in the oil by using an oil chromatographic analyzer; detecting the furfural content in a transformer oil tank by using a laser Raman spectrometer; and detecting the ambient humidity around the transformer by using a humidity detector.
The invention also provides a reliability judging device of the power transformer insulation system, which comprises a frame model building module, a power transformer insulation system and a power transformer insulation system, wherein the frame model building module is used for obtaining equipment information of a transformer and building a frame model of the power transformer insulation system; the first evaluation model construction module is used for acquiring oil chromatography historical test data and constructing a first evaluation model based on a Stacking algorithm; the relation determining module is used for acquiring furfural historical test data under the same test period and determining a relation between the furfural content and the polymerization degree; the second evaluation model construction module takes the ratio of the polymerization degree to a threshold value as weight, and constructs a second evaluation model by combining the frame model; the data acquisition module is used for acquiring line inrush current data and environmental parameters of the transformer under the same test period; the joint model construction module is used for calculating a first weight and a second weight according to the line inrush current data and the environmental parameters, and constructing a joint judgment model by combining the first evaluation model and the second evaluation model; and the reliability output module is used for acquiring detection data of the current power transformer insulation system, inputting the detection data into the joint judgment model and outputting a reliability index.
Compared with the prior art, the invention has the beneficial effects that: according to the oil chromatography historical test data, training is carried out by using a layering model integration framework of a Stacking algorithm to construct a first evaluation model, so that the accuracy of the first evaluation model can be remarkably improved; the method comprises the steps of constructing a frame model by using equipment information of a transformer, determining a relation between furfural content and polymerization degree according to furfural historical test data, taking the ratio of the polymerization degree to a threshold value as weight, and constructing a second evaluation model by combining the frame model, so that the aging state of an insulation system can be better obtained; according to the line inrush data and the environment parameters, a first weight and a second weight are calculated, a first evaluation model and a second evaluation model are combined to construct a joint judgment model, and the accuracy of reliability judgment is improved by fusing two types of evaluation models based on different characteristic products.
Drawings
The disclosure of the present invention is described with reference to the accompanying drawings. It is to be understood that the drawings are designed solely for the purposes of illustration and not as a definition of the limits of the invention. In the drawings, like reference numerals are used to refer to like parts. Wherein:
FIG. 1 is a flow chart of a reliability determination method for an insulation system of a power transformer according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a reliability determining device for an insulation system of a power transformer according to an embodiment of the invention.
Detailed Description
It is to be understood that, according to the technical solution of the present invention, those skilled in the art may propose various alternative structural modes and implementation modes without changing the true spirit of the present invention. Accordingly, the following detailed description and drawings are merely illustrative of the invention and are not intended to be exhaustive or to limit the invention to the precise form disclosed.
An embodiment according to the invention is shown in connection with fig. 1. A reliability judging method of an insulation system of a power transformer comprises the following steps:
1) And acquiring equipment information of the transformer, and constructing a frame model of the transformer insulation system.
The equipment information comprises the model number and the expected service life of the transformer, and then a frame model of the transformer insulation system is constructed, comprising: let the reliability index of the frame model be D,
in the above, D 0 For the initial moment T of the transformer 0 Is the reliability index of (1), G is the aging rate, T 1 D is the current moment of the transformer t For the reliability index corresponding to the possible fault time of the transformer, T d Is the life expectancy.
2) And acquiring oil chromatography historical test data, and constructing a first evaluation model based on a Stacking algorithm.
The oil chromatography historical test data comprises the concentration of dissolved characteristic gas in oil and a corresponding insulation system reliability index, and a first evaluation model is built based on a Stacking algorithm, and the method comprises the following steps:
a. dividing the oil chromatography history test data into a training sample and a test sample, and training a primary model of a Stacking model according to a K-fold cross validation method to obtain a new training sample;
b. averaging the test samples to obtain new test samples;
c. and training a secondary model of the Stacking model by using the new training sample, and testing by using the new testing sample so as to obtain a first evaluation model.
3) And under the same test period, acquiring furfural historical test data, and determining a relation between the furfural content and the polymerization degree.
The furfural history test data comprises furfural content and corresponding polymerization degree, and the method comprises the steps of:
D P ＝-120·ln Fa+b
in the above formula, dp is the degree of polymerization, fa is the furfural content, b is a constant, and 469 is taken.
4) And taking the ratio of the polymerization degree to the threshold value as a weight, and constructing a second evaluation model by combining the framework model.
Specifically, constructing a second evaluation model in combination with the framework model includes: let the threshold value of the polymerization degree be D P0 The insulation system reaches its service life at this time; the calculation formula of the second evaluation model is as follows:
in the above formula, D' is the reliability index of the second evaluation model, lambda is the adjustment coefficient, D P Degree of polymerization, D P0 And D is a reliability index of the frame model.
5) And under the same test period, obtaining the line inrush data and the environmental parameters of the transformer, wherein the line inrush data and the environmental parameters are also historical test data.
6) And calculating a first weight and a second weight according to the line inrush current data and the environmental parameters, and constructing a joint judgment model by combining the first evaluation model and the second evaluation model. The method comprises the following steps:
counting the number of line inrush times exceeding a set peak value in a test period, calculating the average number of the number of line inrush times, and taking the ratio of the average number of line inrush times to the standard value of the number of inrush times as a first weight;
counting the humidity in the test period, calculating the average humidity, and taking the ratio of the average humidity to a humidity standard value as a second weight;
the calculation formula of the joint judgment model is as follows:
in the above, k 0 、k 1 、k 2 For correction coefficients, Q is the first evaluation model,n is the average number of the line inrush times 0 Is the standard value of inrush frequency->Average humidity, pw 0 D' is the second evaluation model, epsilon is the error, which is the humidity standard value.
It can be understood that, in the embodiment of the invention, for simplicity and convenience in calculation, humidity is taken as the main external condition affecting the health state of the insulation system, and the temperature and the atmospheric pressure in the external condition can also be taken into consideration to construct the comprehensive weight of the humidity, the temperature and the atmospheric pressure, namely, the sum of the ratio of the three to the standard value is taken as the comprehensive weight to be substituted into the joint judgment model formula, thereby further improving the model precision.
7) And acquiring detection data of the current power transformer insulation system, inputting the detection data into the joint judgment model, and outputting a reliability index. The reliability index is divided into a plurality of levels, such as 4 levels of normal, attention, abnormal, and serious.
In the embodiment of the invention, an oil chromatograph, a laser raman spectrometer and a humidity detector are arranged on a transformer, and then the acquisition step of detection data comprises the following steps: detecting the concentration of dissolved characteristic gas in the oil by using an oil chromatographic analyzer; detecting the furfural content in a transformer oil tank by using a laser Raman spectrometer; and detecting the ambient humidity around the transformer by using a humidity detector.
Referring to fig. 2, the present invention provides a reliability determination device for an insulation system of a power transformer, comprising:
the frame model construction module is used for acquiring equipment information of the transformer and constructing a frame model of the transformer insulation system;
the first evaluation model construction module is used for acquiring oil chromatography historical test data and constructing a first evaluation model based on a Stacking algorithm;
the relation determining module is used for acquiring furfural historical test data under the same test period and determining a relation between the furfural content and the polymerization degree;
the second evaluation model construction module takes the ratio of the polymerization degree to the threshold value as weight, and constructs a second evaluation model by combining with the frame model;
the data acquisition module is used for acquiring line inrush current data and environmental parameters of the transformer under the same test period;
the joint model construction module is used for calculating a first weight and a second weight according to the line inrush current data and the environmental parameters and constructing a joint judgment model by combining the first evaluation model and the second evaluation model;
and the reliability output module is used for acquiring detection data of the current power transformer insulation system, inputting the detection data into the joint judgment model and outputting a reliability index.
In summary, the beneficial effects of the invention include: according to the oil chromatography historical test data, training is carried out by using a layering model integration framework of a Stacking algorithm to construct a first evaluation model, so that the accuracy of the first evaluation model can be remarkably improved; the frame model is built by utilizing the equipment information of the transformer, then the relation between the furfural content and the polymerization degree is determined according to the furfural historical test data, the ratio of the polymerization degree to the threshold value is used as the weight, and the second evaluation model is built by combining the frame model, so that the aging state of the insulation system can be better obtained; according to the line inrush data and the environment parameters, a first weight and a second weight are calculated, a first evaluation model and a second evaluation model are combined to construct a joint judgment model, and the accuracy of reliability judgment is improved by fusing two types of evaluation models based on different characteristic products.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
It should be appreciated that the integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The technical scope of the present invention is not limited to the above description, and those skilled in the art may make various changes and modifications to the above-described embodiments without departing from the technical spirit of the present invention, and these changes and modifications should be included in the scope of the present invention.
Claims (4)
1. The reliability judging method of the power transformer insulation system is characterized by comprising the following steps of:
acquiring equipment information of a transformer, and constructing a frame model of the transformer insulation system;
acquiring oil chromatography historical test data, and constructing a first evaluation model based on a Stacking algorithm;
under the same test period, acquiring furfural historical test data, and determining a relation between the furfural content and the polymerization degree;
taking the ratio of the polymerization degree to a threshold value as a weight, and constructing a second evaluation model by combining the frame model;
under the same test period, obtaining line inrush current data and environmental parameters of the transformer;
calculating a first weight and a second weight according to the line inrush current data and the environmental parameters, and constructing a joint judgment model by combining the first evaluation model and the second evaluation model;
acquiring detection data of a current power transformer insulation system, inputting the detection data into the joint judgment model, and outputting a reliability index;
wherein, the furfural history test data includes a furfural content and a corresponding polymerization degree thereof, and the determining a relation between the furfural content and the polymerization degree includes:
；
in the formula, dp is the polymerization degree, fa is the furfural content, b is a constant, and 469 is taken;
constructing a second assessment model in conjunction with the framework model, comprising: setting the threshold value of the polymerization degree asThe insulation system reaches its service life at this time; the calculation formula of the second evaluation model is as follows:
；
in the above-mentioned method, the step of,for the reliability index of the second evaluation model, +.>To adjust the coefficient +.>For degree of polymerization->Is threshold value of polymerization degree, ++>Is a reliability index of the frame model;
calculating a first weight and a second weight according to the line inrush data and the environmental parameter, and constructing a joint judgment model by combining a first evaluation model and a second evaluation model, wherein the joint judgment model comprises: counting the number of line inrush times exceeding a set peak value in a test period, calculating the average number of the number of line inrush times, and taking the ratio of the average number of line inrush times to an inrush time standard value as a first weight; counting the humidity in the test period, calculating the average humidity, and taking the ratio of the average humidity to a humidity standard value as a second weight; the calculation formula of the joint judgment model is as follows:
；
in the above-mentioned method, the step of,for correction factor +.>For the first evaluation model, +.>For the average number of line inrush times, +.>Is the standard value of inrush frequency->Average humidity>Is the standard value of humidity, and is->For the second evaluation model, +.>Is an error;
the equipment information includes a transformer model and life expectancy, and the constructing a frame model of the transformer insulation system includes: assuming the reliability index of the frame model as D, then
；
In the above-mentioned method, the step of,for the initial moment +.>G is the aging rate, < >>For the current moment of the transformer, < >>To become asReliability index corresponding to the possible failure moment of the press, +.>Is the life expectancy.
2. The method for determining reliability of an insulation system of a power transformer according to claim 1, wherein the oil chromatography history test data includes concentration of dissolved characteristic gas in oil and corresponding insulation system reliability index, the constructing a first evaluation model based on a Stacking algorithm includes:
dividing the oil chromatography history test data into a training sample and a test sample, and training a primary model of a Stacking model according to a K-fold cross validation method to obtain a new training sample;
averaging the test samples to obtain new test samples;
and training a secondary model of the Stacking model by using the new training sample, and testing by using the new test sample so as to obtain a first evaluation model.
3. The method according to claim 1, wherein the step of acquiring the detection data includes: detecting the concentration of dissolved characteristic gas in the oil by using an oil chromatographic analyzer; detecting the furfural content in a transformer oil tank by using a laser Raman spectrometer; and detecting the ambient humidity around the transformer by using a humidity detector.
4. A power transformer insulation system reliability determination device, comprising:
the frame model construction module is used for acquiring equipment information of the transformer and constructing a frame model of the transformer insulation system;
the first evaluation model construction module is used for acquiring oil chromatography historical test data and constructing a first evaluation model based on a Stacking algorithm;
the relation determining module is used for acquiring furfural historical test data under the same test period and determining a relation between the furfural content and the polymerization degree;
the second evaluation model construction module takes the ratio of the polymerization degree to a threshold value as weight, and constructs a second evaluation model by combining the frame model;
the data acquisition module is used for acquiring line inrush current data and environmental parameters of the transformer under the same test period;
the joint model construction module is used for calculating a first weight and a second weight according to the line inrush current data and the environmental parameters, and constructing a joint judgment model by combining the first evaluation model and the second evaluation model;
the reliability output module is used for acquiring detection data of the current power transformer insulation system, inputting the detection data into the joint judgment model and outputting a reliability index;
wherein, the furfural history test data includes a furfural content and a corresponding polymerization degree thereof, and the determining a relation between the furfural content and the polymerization degree includes:
；
in the formula, dp is the polymerization degree, fa is the furfural content, b is a constant, and 469 is taken;
constructing a second assessment model in conjunction with the framework model, comprising: setting the threshold value of the polymerization degree asThe insulation system reaches its service life at this time; the calculation formula of the second evaluation model is as follows:
；
in the above-mentioned method, the step of,for the reliability index of the second evaluation model, +.>To adjust the coefficient +.>For degree of polymerization->Is threshold value of polymerization degree, ++>Is a reliability index of the frame model;
calculating a first weight and a second weight according to the line inrush data and the environmental parameter, and constructing a joint judgment model by combining a first evaluation model and a second evaluation model, wherein the joint judgment model comprises: counting the number of line inrush times exceeding a set peak value in a test period, calculating the average number of the number of line inrush times, and taking the ratio of the average number of line inrush times to an inrush time standard value as a first weight; counting the humidity in the test period, calculating the average humidity, and taking the ratio of the average humidity to a humidity standard value as a second weight; the calculation formula of the joint judgment model is as follows:
；
in the above-mentioned method, the step of,for correction factor +.>For the first evaluation model, +.>For the average number of line inrush times, +.>Is the standard value of inrush frequency->Average humidity>Is the standard value of humidity, and is->For the second evaluation model, +.>Is an error;
the equipment information includes a transformer model and life expectancy, and the constructing a frame model of the transformer insulation system includes: assuming the reliability index of the frame model as D, then
；
In the above-mentioned method, the step of,for the initial moment +.>G is the aging rate, < >>For the current moment of the transformer, < >>For the reliability index corresponding to the possible failure time of the transformer, < >>Is the life expectancy.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211041787.7A CN115452978B (en) | 2022-08-29 | 2022-08-29 | Reliability judging method and device for power transformer insulation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211041787.7A CN115452978B (en) | 2022-08-29 | 2022-08-29 | Reliability judging method and device for power transformer insulation system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115452978A CN115452978A (en) | 2022-12-09 |
| CN115452978B true CN115452978B (en) | 2024-04-12 |
Family
ID=84301562
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211041787.7A Active CN115452978B (en) | 2022-08-29 | 2022-08-29 | Reliability judging method and device for power transformer insulation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115452978B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117250456B (en) * | 2023-11-20 | 2024-01-30 | 山东海鲲数控设备有限公司 | Transformer insulation state monitoring system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110297167A (en) * | 2019-07-17 | 2019-10-01 | 国网浙江省电力有限公司电力科学研究院 | A kind of transformer ageing state evaluation method based on Multi-source Information Fusion |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110297141A (en) * | 2019-07-01 | 2019-10-01 | 武汉大学 | Fault Locating Method and system based on multilayer assessment models |
-
2022
- 2022-08-29 CN CN202211041787.7A patent/CN115452978B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110297167A (en) * | 2019-07-17 | 2019-10-01 | 国网浙江省电力有限公司电力科学研究院 | A kind of transformer ageing state evaluation method based on Multi-source Information Fusion |
Non-Patent Citations (7)
| Title |
|---|
| 变压器状态及寿命的分层评估模型及应用;余华兴 等;电工技术(第2期);第28-31页 * |
| 基于Stacking元学习策略的变压器故障诊断;汪凤 等;水电能源科学;第31卷(第8期);第196-199页 * |
| 基于多信息融合的变压器故障诊断;袁海满 等;高压电器;第54卷(第9期);第103-110页 * |
| 基于多特征指标综合评价的油纸绝缘热老化程度研究;连鸿松 等;绝缘材料;第51卷(第3期);第64-69页 * |
| 基于油中溶解产物分析的油纸绝缘寿命预测模型;颜海俊 等;广西电力;第43卷(第4期);第1-6+23页 * |
| 基于耐久度的油浸绝缘电气主设备状态评估模型;徐铬 等;电气应用;第36卷(第3期);第24-30页 * |
| 李瑞福.工厂供配电技术.电子科技大学出版社,2016,第120页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115452978A (en) | 2022-12-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1085534B1 (en) | Intelligent analysis system and method for fluid-filled electrical equipment | |
| US10001518B2 (en) | System and method for power transmission and distribution asset condition prediction and diagnosis | |
| CN104730378B (en) | Inside transformer complex defect fuzzy diagnosis method based on oil dissolved gas | |
| EP2735011B1 (en) | Method and system for estimating transformer remaining life | |
| KR101160775B1 (en) | System and method for evaluating integrity of power transformer | |
| JP5494034B2 (en) | Reliability evaluation apparatus, reliability evaluation program, and reliability evaluation method | |
| Hillary et al. | A tool for estimating remaining life time of a power transformer | |
| EP1085635A2 (en) | Fluid-filled electrical equipment intelligent analysis system and method | |
| CN115452978B (en) | Reliability judging method and device for power transformer insulation system | |
| KR101046752B1 (en) | Transformer life assessment method | |
| Shutenko | Method for detection of developing defects in high-voltage power transformers by results of the analysis of dissolved oil gases | |
| Jian et al. | The new developed health index for power transformer condition assessment | |
| Gautam et al. | Identifying transformer oil criticality using fuzzy logic approach | |
| CN105468911A (en) | Transformer state evaluation method based on analytic hierarchy process and rough set | |
| CN116990621B (en) | Dynamic fault monitoring system for electric power safety tools | |
| CN116862478A (en) | Transformer health assessment method based on layered architecture and dynamic weighting | |
| Patil et al. | An Integrated Fuzzy based Online Monitoring System for Health Index and Remnant Life Computation of 33 kV Steel Mill Transformer | |
| Ghazali et al. | TNB experience in condition assessment and life management of distribution power transformers | |
| Paul et al. | Bivariate modelling of normalized energy intensity of oil and paper for accessing the fault severity of transformer and reactors | |
| JP2023547017A (en) | Judging the status of electrical equipment using fluctuations in diagnostic parameter prediction errors | |
| Pickster | Determination of probability of failure of power transformers using statistical analysis | |
| Schreiter et al. | Investigation of Transformer Oil Properties with advanced Multidimensional Methods | |
| Herath et al. | Long term dga trend evaluation of transmission power transformers | |
| KR20230077369A (en) | Apparatus and method for calculating diagnostic cycle of analyzing gas in transformer | |
| Ansari et al. | Assessing the moisture content of oil‐impregnated paper bushings with a simple and fast method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |