CN114252724B - Intelligent detection method and detection system for transformer - Google Patents
Intelligent detection method and detection system for transformer Download PDFInfo
- Publication number
- CN114252724B CN114252724B CN202210194722.XA CN202210194722A CN114252724B CN 114252724 B CN114252724 B CN 114252724B CN 202210194722 A CN202210194722 A CN 202210194722A CN 114252724 B CN114252724 B CN 114252724B
- Authority
- CN
- China
- Prior art keywords
- transformer
- subsystem
- characteristic
- parameters
- acquisition
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
Abstract
The invention provides an intelligent detection method and system for a transformer. The detection system comprises a first external high-speed acquisition subsystem, a second external high-speed acquisition subsystem and a detection subsystem, wherein the first external high-speed acquisition subsystem is used for acquiring external environment operation parameters; the second internal low-speed acquisition subsystem is used for acquiring internal multi-characteristic gas parameters and has a plurality of acquisition modes; the third data characteristic analysis subsystem is used for generating a data characteristic analysis result after data characteristic analysis is carried out on the collected external environment operation parameters; and the fourth intelligent switching subsystem switches the acquisition mode of the second internal low-speed acquisition subsystem based on the data characteristic analysis result. The detection method comprises the step of starting a global acquisition mode for acquiring characteristic parameters of all characteristic gases in the transformer and switching the acquisition mode. According to the technical scheme, the internal parameter acquisition mode can be automatically switched based on the change of the external environment parameters, so that the blindness of data acquisition and monitoring is avoided, and the intelligent detection of the state of the transformer is realized.
Description
Technical Field
The invention belongs to the technical field of transformer state detection, and particularly relates to an intelligent transformer detection method and system and a computer readable storage medium for realizing the method.
Background
Once a fault occurs, the transformer, which is one of the most important devices in the power grid, will cause immeasurable damage to the operation of the power equipment, and it is very important to ensure the safe and stable operation of the power equipment. With implementation of a smart grid plan and gradual improvement of aspects such as sensor technology, computer processing, signal communication and various optimization algorithms, the intelligent transformer system can not only timely perform fault feedback and fault early warning, but also record and store data and upload a higher-level central system.
The transformer on-line monitoring and diagnosing system is based on advanced digital measurement technology, obtains information quantity representing equipment state in real time or at regular time, uploads the information quantity to a fault analysis module through various communication technologies, analyzes the information through intelligent diagnosis software by simultaneously combining related historical records and related data such as regulations and systems, evaluates whether the equipment running state is normal, judges whether the equipment has faults, and provides basic information for equipment maintenance decision based on the information.
The Chinese patent application CN113567393A discloses an online monitoring system for dissolved gas in laser spectrum oil, which can continuously monitor the operating condition of operating power equipment on line and obtain information capable of reflecting the change of the operating condition at any time; after data obtained by on-line monitoring is analyzed and processed, the running state of the equipment is diagnosed, and necessary maintenance is arranged according to the diagnosis result; the running state of the transformer can be mastered in time, latent faults of the transformer can be found, and the utilization rate of power equipment such as the transformer is improved to the maximum extent.
However, the inventor finds that, in the prior art, when the dissolved gas is used as the characteristic signal for diagnosis, all possible situations need to be considered, and after a plurality of possible gas content values are needed, fault judgment is performed according to the existing rules, so that not only the corresponding type of gas sensor needs to be arranged, but also corresponding content monitoring software and data analysis software are needed, and the energy consumption is extremely high in the utilization of hardware resources.
Disclosure of Invention
In order to solve the technical problems, the invention provides an intelligent detection method and an intelligent detection system for a transformer.
The detection system comprises a first external high-speed acquisition subsystem, a second external high-speed acquisition subsystem and a detection subsystem, wherein the first external high-speed acquisition subsystem is used for acquiring external environment operation parameters; the second internal low-speed acquisition subsystem is used for acquiring internal multi-characteristic gas parameters and has a plurality of acquisition modes; the third data characteristic analysis subsystem is used for generating a data characteristic analysis result after data characteristic analysis is carried out on the collected external environment operation parameters; and the fourth intelligent switching subsystem switches the acquisition mode of the second internal low-speed acquisition subsystem based on the data characteristic analysis result.
The detection method comprises the following step of starting a global acquisition mode to acquire characteristic parameters of all characteristic gases in the transformer and then subsequently executing acquisition mode switching.
According to the technical scheme, the internal parameter acquisition mode can be automatically switched based on the change of the external environment parameters, so that the blindness of data acquisition and monitoring is avoided, and the intelligent detection of the state of the transformer is realized.
Specifically, the technical solution of the present invention can be implemented as the following aspects:
in a first aspect of the present invention, an intelligent transformer detection system is provided, which includes a first external high-speed acquisition subsystem, a second internal low-speed acquisition subsystem, a third data characteristic analysis subsystem, and a fourth intelligent switching subsystem;
the first external high-speed acquisition subsystem is used for acquiring external environment operation parameters of the transformer, and the external environment operation parameters comprise external environment parameters of the transformer and operation state parameters of a local power grid of the transformer;
the second internal low-speed acquisition subsystem is used for acquiring various characteristic gas parameters inside the transformer, the second internal low-speed acquisition subsystem has various acquisition modes, and the types of the characteristic gases acquired in different acquisition modes are not completely the same;
the third data characteristic analysis subsystem performs data characteristic analysis on the external environment operation parameters acquired by the first external high-speed acquisition subsystem to generate a data characteristic analysis result;
and the fourth intelligent switching subsystem switches the acquisition mode of the second internal low-speed acquisition subsystem based on the data characteristic analysis result.
In specific implementation, the external environment parameters of the transformer comprise an external temperature value, an external noise value and a partial discharge signal value of the environment where the transformer is located;
the operation state parameters of the local power grid in which the transformer is located include an output power value, an output voltage value, and a plurality of phase angle (phase angle) change values of the local power grid.
Furthermore, the fourth intelligent switching subsystem comprises a preset mode switching database;
the preset mode switching database comprises a three-ratio mode switching database and a grand satellite trigonometry mode switching database.
The fourth intelligent switching subsystem switches the acquisition mode of the second internal low-speed acquisition subsystem based on the data feature analysis result, and specifically includes:
and searching a limit area corresponding to the potential fault characteristic in the grand satellite trigonometry mode switching database based on the potential fault characteristic of the transformer determined by the data characteristic analysis result, and determining the acquisition mode of the second internal low-speed acquisition subsystem based on the limit area.
The characteristic gas comprises C2H4、CH4、C2H2、C2H6And H2；
At least one characteristic gas is collected in any collection mode.
In a second aspect of the present invention, a transformer intelligent detection method is provided, which includes the following steps:
s1: acquiring external environment operation parameters of the transformer, wherein the external environment operation parameters comprise external environment parameters of the transformer and operation state parameters of a local power grid of the transformer;
s2: performing data characteristic analysis on the acquired external environment operation parameters to generate a data characteristic analysis result;
s3: determining an updating acquisition mode of the characteristic gas in the transformer based on the data characteristic analysis result;
s4: switching the current collection mode of the characteristic gas in the transformer to the updated collection mode, and returning to the step S1;
wherein, the types of the characteristic gases collected under different collection modes are not completely the same.
Before the step S1, the method further includes a step S0:
s0: starting a global acquisition mode, wherein the global acquisition mode is used for acquiring characteristic parameters of all characteristic gases in the transformer, and all the characteristic gases are C2H4、CH4、C2H2、C2H6And H2。
The data characteristic analysis result is used for representing potential fault characteristics of the transformer, and the potential fault characteristics comprise partial discharge, low-energy discharge, high-energy discharge, low-temperature overheat, high-temperature overheat and medium-temperature overheat.
In a third aspect of the present invention, a terminal device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the steps of the transformer intelligent detection method are implemented.
In a fourth aspect of the present invention, a computer-readable storage medium is provided, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the steps of the transformer intelligent detection method.
Compared with the method for monitoring and acquiring all internal possible characteristic signals of the transformer state in the prior art, the technical scheme of the invention firstly carries out data characteristic analysis on the basis of external environment operation parameters and then generates a data characteristic analysis result so as to determine the potential fault characteristics of the transformer; on the basis, the existing internal parameter acquisition mode is updated, so that the acquisition of internal characteristic signals is more targeted; meanwhile, as all possible characteristic signals do not need to be identified, the identification and judgment speed is higher, and the detection mode tends to be intelligent.
Further advantages of the invention will be apparent in the detailed description section in conjunction with the drawings attached hereto.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a diagram of an intelligent transformer detection system according to an embodiment of the present invention;
FIG. 2 is a general operational schematic diagram of the detection system of FIG. 1 implementing transformer fault signature identification;
FIG. 3 is a schematic diagram illustrating logic for implementing internal acquisition mode switching in the detection system of FIG. 1;
FIG. 4 is a schematic diagram of the judgment rule of the prior art (David triangulation) according to the embodiment of the present invention;
FIG. 5 is a flowchart of a transformer intelligent detection method according to an embodiment of the present invention;
FIG. 6 is a schematic flow diagram of a further preferred embodiment of the method of FIG. 5;
fig. 7 is a schematic diagram of a computer electronic device implementing the method of fig. 5 or 6.
Detailed Description
The invention is further described with reference to the following drawings and detailed description.
Before describing the various embodiments of the present invention, some basic knowledge regarding transformer condition monitoring and fault identification is introduced. It should be noted that these basic knowledge parts are directly derived from the prior art documents and will be introduced as part of the technical solution of the present invention; moreover, in addition to the basic knowledge, part of the knowledge relating to the improvements of the present invention is also incorporated herein by reference, so as to introduce the applicant's motivation to discover related technical problems and to introduce related improvements of the present invention.
DL/T722-2014 dissolved gas analysis and judgment guide in transformer oil states that in the current large environment of the domestic power system, the gas analysis method in oil is still one of the most reliable and stable modes for monitoring oil-filled equipment, the working principle of the method is based on the meteorological chromatographic analysis technology, the dissolved gas in oil is removed through a degasser, corresponding analysis is carried out, and the latent fault of the oil-immersed transformer is diagnosed by using the analysis result.
The traditional diagnosis method is generally obtained by induction of a large number of transformer operation parameters, a three-ratio method is proposed by the international electrotechnical commission in 1977, and an improved three-ratio method, a David triangle method, a cubic graph method and the like are proposed by foreign scholars on the basis of the three-ratio method.
The conventional experiment project of the oil-immersed transformer is more than 32 items, including separation and analysis of oil and gas, various inspections before delivery and during operation, and the like, according to the preventive test regulations of power equipment revised in 2006.
The related prior art is introduced as follows:
gas analysis, diagnosis and fault detection in transformer oil [ M ]. beijing, china electric power agency, 2005.
Youchen Wang, Jiandong Wu, Zhe Li, et al. Research on a Practical De-noising and the Characterization of Partial Discharge UHF Signals[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2014, 21(5): 2206-2216。
The inventor finds that in practical application, the detailed regulation can effectively prevent various faults of the transformer, but various parameters which are too complicated are difficult to obtain comprehensively, and a large amount of manpower and material resources are consumed; in addition, in practical application, the corresponding degree of a plurality of parameters to the same fault is low, and a plurality of parameters can only reflect a single fault in fact, which is a great waste to resources.
Taking the three-ratio method as an example, the conventional three-ratio method needs to identify C at the same time2H4、CH4、C2H2、C2H6And H2The content of 5 characteristic gases is counted, and then C is formed by combining the characteristic gases in pairs2H2/C2H4、CH4/ H2And C2H4/ C2H6And the three ratios are used for coding the proportional intervals of the three ratios and correspond to the fault types of the transformer.
David's triangle rule needs to be based on CH4、C2H4、C2H2The combination of different components of (a) yields 6 possible combinations of states.
Meanwhile, a single detection method may cause erroneous judgment, and in practical application, one or more methods need to be combined for comprehensive judgment, which also causes the characteristic gas to be acquired more comprehensively.
However, the transformer actually has only one fault state at a certain moment, and generally more than two fault states cannot occur at the same time; in addition, the transformer which is qualified to leave a factory is actually operated in a normal state most of the time, and the fault state is only a local short-time fault caused in a few extreme cases or an external unstable state.
The inventor considers that the fault detection technology of the prior art has the defects that even if local short-time faults are faced, all time intervals must be monitored in real time, namely, parameter acquisition and identification are carried out for a long time; even if only one fault state can happen at a certain moment, all characteristic parameters are collected at the same time, so that all parameter values are combined one by one to obtain corresponding identification indexes for judgment.
Obviously, the processing mode wastes hardware resources and increases energy consumption, and great problems need to be improved.
Therefore, the inventor specially provides a corresponding technical scheme of the invention. According to the technical scheme, all parameters are not detected blindly under all conditions, and data characteristic analysis results are generated after data characteristic analysis is carried out on the basis of external environment operation parameters so as to determine potential fault characteristics of the transformer; on the basis, the existing internal parameter acquisition mode is updated, so that the acquisition of internal characteristic signals is more targeted; meanwhile, as all possible characteristic signals do not need to be identified, the identification and judgment speed is higher, and the detection mode tends to be intelligent.
To achieve the above technical effects, reference is first made to fig. 1.
Fig. 1 is a diagram of an intelligent transformer detection system according to an embodiment of the present invention.
In fig. 1, the intelligent detection system includes a first external high-speed acquisition subsystem, a second internal low-speed acquisition subsystem, a third data characteristic analysis subsystem, and a fourth intelligent switching subsystem.
The specific implementation functions of each subsystem are as follows:
the first external high-speed acquisition subsystem is used for acquiring the external environment operation parameters of the transformer, and the second internal low-speed acquisition subsystem is used for acquiring various characteristic gas parameters inside the transformer.
It should be noted that "external environment of the transformer" and "inside the transformer" are relative concepts.
The external environment where the transformer is located refers to the condition that the transformer to be detected is taken as a whole, and the external environment operation parameters are collected from the environment outside the whole.
Specifically, the external environment operation parameters include external environment parameters of the transformer itself and operation state parameters of a local power grid in which the transformer is located.
As a further example, the external environment parameters of the transformer itself include an external temperature value, an external noise value, and a partial discharge signal value of an environment in which the transformer itself is located;
the operation state parameters of the local power grid in which the transformer is located comprise an output power value, an output voltage value and a plurality of phase angle change values of the local power grid.
"inside the transformer" refers to the environment inside the "whole" after the transformer is viewed as a whole. Taking an oil-immersed transformer as an example, the oil-immersed transformer is to immerse a transformer core, a winding and the like into a transformer tank filled with oil, at this time, the "inside of the transformer" refers to the transformer tank, and various characteristic gases can be detected from the space of the transformer tank.
Preference is given toThe characteristic gas comprises C2H4、CH4、C2H2、C2H6And H2；
Further, by way of more complete description of the characteristic gas, the characteristic gas also includes O2、CO、CO2And H in gaseous or liquid state2O, and the like.
As previously mentioned, in the prior art, it is often necessary to acquire C simultaneously2H4、CH4、C2H2、C2H6、H2、O2、CO、CO2And H in gaseous or liquid state2And O, taking the specific content, proportion and the like of the components as the judgment basis of the working condition of the transformer.
To this end, as a first improvement of the present invention, in the embodiment of fig. 1, the second internal low-speed acquisition subsystem has a plurality of acquisition modes, the types of characteristic gases acquired in different acquisition modes are not completely the same, and at least one characteristic gas is acquired in any acquisition mode.
That is, in various embodiments of the present invention, most of the time, it is not necessary to simultaneously acquire C2H4、CH4、C2H2、C2H6、H2、O2、CO、CO2And H in gaseous or liquid state2And O, switching the collection mode according to the situation, and collecting only one or a few (but not all) characteristic gases when appropriate.
Specifically, the third data characteristic analysis subsystem performs data characteristic analysis on the external environment operating parameters acquired by the first external high-speed acquisition subsystem to generate a data characteristic analysis result;
and the fourth intelligent switching subsystem switches the acquisition mode of the second internal low-speed acquisition subsystem based on the data characteristic analysis result.
It should be noted that, in the present invention, the external environment operation parameters adopt a high-speed acquisition mode to rapidly respond to the external changes, and the internal multi-characteristic gas acquisition adopts a low-speed acquisition mode to reflect the accuracy. The selection of different acquisition speeds meets the requirement of subsequent statistical data acquisition.
On the basis of fig. 1, see fig. 2. Fig. 2 is an overall working schematic diagram of the detection system in fig. 1 for realizing transformer fault feature identification.
In fig. 2, after the third data characteristic analysis subsystem performs data characteristic analysis on the external environment operating parameters acquired by the first external high-speed acquisition subsystem, a data characteristic analysis result is generated, which specifically includes:
the third data characteristic analysis subsystem analyzes a first threshold range of the external environment parameter values, and matches a first potential transformer state corresponding to the first threshold range in a preset statistical database based on the first threshold range;
the third data characteristic analysis subsystem analyzes a second variation range of the operation state parameters of the local power grid where the transformer is located, and matches a second transformer evolution state corresponding to the second variation range in a preset statistical database based on the second variation range;
and determining potential fault characteristics of the transformer as the data characteristic analysis result based on the first potential transformer state and the second transformer evolution state.
The preset statistical database is a statistical database which establishes a corresponding relation with the current external environment operation parameters of the transformer in advance according to the historical diagnosed fault state of the transformer.
As described above, the external environment parameters of the transformer itself include an external temperature value, an external noise value, and a partial discharge signal value of the environment where the transformer itself is located;
the statistical database stores the corresponding transformer fault states under different external environment parameter values.
As an illustrative and non-limiting example, the statistical database stores the correspondence between external temperature values and external noise values to transformer fault conditions as follows:
if the external temperature value is greater than 550 ℃ & & the external noise value is greater than 35db, it is determined with a 95% confidence that the transformer has a "high temperature overheat" fault state (first transformer potential state);
an external noise value > 35db & & partial discharge frequency is greater than 2500Mhz, a "high energy discharge" fault condition (first transformer potential condition) of the transformer is determined to be present with a 90% confidence level;
as mentioned above, the operating state parameters of the local power grid in which the transformer is located include an output power value, an output voltage value, and a plurality of phase angle change values of the local power grid.
The statistical database stores the corresponding transformer fault status under different operating status parameter values.
By way of illustrative and non-limiting example, the statistical database maintains output power values, output voltage values, and a plurality of phase angle change values versus transformer fault conditions as follows:
if the similarity between the output power curve and the output voltage value curve in the preset time period exceeds a first standard value, the confidence coefficient of the transformer fault in low-energy discharge (second transformer evolution state) is more than 85%, and the confidence coefficient of the transformer fault in high-energy discharge is lower than 15% (second transformer evolution state);
the maximum change value in the plurality of phase angle change values is an integer multiple of 90 degrees (90 degrees to 180 degrees to 270 degrees to 360 degrees), but the output power value is continuously lower than a second standard value, the confidence that the transformer fault is high-energy discharge (the second transformer evolution state) is more than 85 percent;
……
obviously, the actual corresponding relationship of the statistical database needs a person skilled in the art to obtain a fitting statistic based on statistical principles after a large amount of historical statistical data is gathered according to the model, the field installation environment and the like of an actual transformer, different corresponding relationships can be obtained for different transformers and installation environments, but under a set confidence, the corresponding relationships can be popularized to the intelligent detection process of other transformers in the same environment and the intelligent detection process of transformers of the same model in different installation environments.
In short, the technical problem of the present application can be solved as long as the preset statistical database is a statistical database that establishes a corresponding relationship with the current transformer external environment operating parameters in advance according to the historical diagnosed transformer fault state.
On the basis of the above description, see fig. 3. Fig. 3 is a schematic diagram of logic determination for implementing internal acquisition mode switching in the detection system of fig. 1.
And determining potential fault characteristics of the transformer as the data characteristic analysis result based on the first potential transformer state and the second transformer evolution state.
The latent fault feature here is the determined latent fault type of the transformer under the specified confidence statistic condition that is greater than the threshold value, such as the states of high-temperature overheating, high-energy discharging, low-energy discharging and the like mentioned above.
Of course, the latent fault features may also (broadly) include partial discharge, low energy discharge, high energy discharge, low temperature superheat, high temperature superheat, medium temperature superheat.
In fig. 3, the fourth intelligent switching subsystem comprises a preset mode switching database;
the preset mode switching database comprises a three-ratio mode switching database and a grand triangle mode switching database.
In one aspect, the fourth intelligent switching subsystem switches the acquisition mode of the second internal low-speed acquisition subsystem based on the data feature analysis result, and specifically includes:
and searching a code value corresponding to the potential fault feature in the three-ratio mode switching database based on the potential fault feature of the transformer determined by the data feature analysis result, and determining the acquisition mode of the second internal low-speed acquisition subsystem based on the code value.
The three-ratio method mode switching database is an encoding database established by adopting reverse thinking based on the existing three-ratio method.
Specifically, the three-ratio method mode switching database is a fault type-code correspondence table established after removing the same codes in the same type of fault types and retaining different codes based on the existing code relationship (code-fault type) table corresponding to the three-ratio method.
In the prior art, the conventional three-ratio method needs to identify C simultaneously2H4、CH4、C2H2、C2H6And H2The content of 5 characteristic gases is counted, and then C is formed by combining the characteristic gases in pairs2H2/C2H4、CH4/ H2And C2H4/ C2H6And the three ratios are used for coding the proportional intervals of the three ratios and correspond to the fault types of the transformer.
For example, if all three ratios are below 0.1, C is2H2/C2H4、CH4/ H2And C2H4/ C2H6The codes corresponding to the three ratios are 0-1-0; if the three ratio ranges are within [0.1, 1 ]]Then C is2H2/C2H4、CH4/ H2And C2H4/ C2H6The codes corresponding to the three ratios are 1-0-0; if the three ratio ranges are E [1, 3 ]]Then C is2H2/C2H4、CH4/ H2And C2H4/ C2H6The codes corresponding to the three ratios are 1-2-1; if the three ratio ranges are E [3, 1]Then C is2H2/C2H4、CH4/ H2And C2H4/ C2H6The codes corresponding to the three ratios are 2-2-2;
by analogy, three code values with different ratios in different ranges can be obtained, and then different fault states can be determined according to the combination of the three code values, for example, when C2H2/C2H4、CH4/ H2To therebyAnd C2H4/ C2H6When the code combination corresponding to the three ratios is 0-0-0, the fault type is judged to be low-temperature overheating below 150 ℃, and when C is used2H2/C2H4、CH4/ H2And C2H4/ C2H6When the code combination corresponding to the three ratios is 0-2-0, the fault type is judged to be low-temperature overheating at the temperature of 150-300 ℃.
It can be seen that, in any case, the prior art needs to identify C at the same time when using the three-ratio method2H4、CH4、C2H2、C2H6And H2The content of 5 characteristic gases in total causes unnecessary data acquisition resource waste.
For this reason, as an improvement, in this embodiment, based on the existing three-ratio method, the three-ratio method mode switching database established by using the reverse thinking is specifically as follows:
for the fault type of "low temperature overheating", the corresponding code is 2, but is no longer 0-0-0 and 0-2-0, that is, if the potential fault feature of the transformer determined by the data feature analysis result is "low temperature overheating", the corresponding code value is found to be 2 in the three-ratio mode switching database.
At this time, an acquisition mode of the second internal low-speed acquisition subsystem may be determined based on the encoded value.
Specifically, the code value is 2 at this time, which means that only CH needs to be acquired at this time4And H2The contents of two characteristic gases without continuously collecting the contents of other characteristic gases.
Therefore, at this time, the acquisition mode of the second internal low-speed acquisition subsystem is switched to the first partial acquisition mode in which only CH is acquired4And H2The contents of two characteristic gases without continuously collecting the contents of other characteristic gases.
Similarly, in the three-ratio mode-switching database, the "low-energy discharge" corresponds to a code value of 2, instead of 2The existing three-ratio method, three codes (2-0/1-0/1/2; 2-2-0/1/2), does not need to monitor all C2H4、CH4、C2H2、C2H6、H2、O2、CO、CO2And H in gaseous or liquid state2O。
It is worth noting that the existing three-ratio method has the correspondence relationship: the coding combination corresponds to the fault type, namely after all characteristic gases are collected, coding values corresponding to the three ratios are obtained, and then the coding combination is searched to determine the fault type;
as shown in the following table:
the method adopts reverse thinking, namely firstly determining the potential fault type higher than the preset confidence coefficient based on the external environment parameter value or the running state parameter value, then taking the potential fault characteristic as the data characteristic analysis result, then searching the corresponding coding value from the three-ratio method mode switching database, and then determining which characteristic gas or which two characteristic gases should be monitored or collected, thereby avoiding the resource waste caused by collecting all characteristic gas signals.
In summary, the code values in the three-ratio method mode switching database are obtained by removing the same code combination from the corresponding relationship between the existing three-ratio method code combination and the fault type and leaving different code combinations;
based on the above table, the code values in the three-ratio mode switching database can be summarized as follows:
low temperature superheat-code value (2) -acquisition mode: CH (CH)4、 H2；
Medium temperature superheat-encoding value (2, 1) -acquisition mode: CH (CH)4、 H2，H6，C2H4；
……
Low energy discharge-coded value (2, 0, 1) -acquisition mode:H4、 H2，H6，C2H4；
and so on.
Of course, the function of the three-ratio mode switching database is to define different characteristic gases, and therefore, other encoding modes are possible, and the above example is only illustrative.
In another aspect, the fourth intelligent switching subsystem switches the acquisition mode of the second internal low-speed acquisition subsystem based on the data feature analysis result, and specifically includes:
and searching a limit area corresponding to the potential fault characteristic in the grand satellite trigonometry mode switching database based on the potential fault characteristic of the transformer determined by the data characteristic analysis result, and determining the acquisition mode of the second internal low-speed acquisition subsystem based on the limit area.
Similarly, similar to the three-ratio method in the prior art, the existing grand satellite triangulation method also needs to collect multiple characteristic gases at the same time, and then search for the region limit in the grand satellite triangulation method by calculating the ratio.
See fig. 6 for the judgment rules of grand satellite trigonometry.
Wherein, the first and the second end of the pipe are connected with each other,
PD-partial discharge;
d1-low energy discharge;
d2-high energy discharge;
t1-thermal failure, T < 300 ℃;
t2-thermal failure, T < 700 ℃ at 300 ℃;
t3-thermal failure, T > 700 ℃.
According to the proportional value of the characteristic signal, the corresponding limit region rule is as follows:
similar to the establishment method of the three-ratio mode switching database, in this embodiment, the grand satellite trigonometry mode switching database is also established by reverse thinking, that is, after determining the potential fault type higher than the predetermined confidence based on the external environment parameter value or the operating state parameter value, the potential fault characteristic is used as the data characteristic analysis result, then the corresponding coding value is searched from the grand satellite trigonometry mode switching database, and then which characteristic gas or which two characteristic gases should be monitored or collected is determined, thereby avoiding the waste of resources caused by collecting all characteristic gas signals.
The large satellite trigonometry mode switching database is an encoding database established by adopting reverse thinking based on the existing large satellite trigonometry.
Specifically, the grand satellite trigonometry mode switching database is a fault type-code correspondence table established after the same codes in the same fault type are removed and different codes are reserved based on the existing coding relationship (code-fault type) table corresponding to the grand satellite trigonometry.
For example, the encoding rules of the grand triangle schema switching database are as follows:
if the potential fault type is partial discharge, the code is 1, and the corresponding acquisition mode is CH4I.e. only CH needs to be collected at this time4；
If the potential fault type is low-energy discharge, the code is 2-3, and the corresponding acquisition mode is C2H4And C2H2I.e. only C has to be collected at this time2H4And C2H2；
And so on.
It can be understood that, in the technical solution of the present invention, the latent fault feature in the form of confidence is used as the data feature analysis result, and a certain uncertainty and inaccuracy also exists in the latent fault feature itself, for example, it is determined that the current latent fault feature is partial discharge, but after the acquisition mode is switched, the acquired CH is acquired4The contents and proportions of (a) do not conform to the existing rules, at this time, the confidence value needs to be further adjusted, or the external environment operation parameters continue to be collected, or the statistical database is updated, and the like, but in any case, in each subsequent collection mode, only part of the characteristic gas needs to be collected, but not all of the characteristic gas needs to be collected.
Of course, this situation occurs with less probability according to practical and statistical principles.
However, the present invention also provides a further preferred embodiment, and after the switching of the collection mode is described, if the content and the ratio of the collected characteristic gases do not conform to the existing rules, the global collection mode is recovered, where the global collection mode is used to collect the characteristic parameters of all the characteristic gases inside the transformer, and the characteristic gases are C2H4、CH4、C2H2、C2H6And H2。
Based on the structure and principle of fig. 1-4, reference is next made to fig. 5 and 6.
FIG. 5 is a flowchart of a transformer intelligent detection method according to an embodiment of the present invention; fig. 6 is a schematic flow diagram of a further preferred embodiment of the method illustrated in fig. 5.
In fig. 5, a transformer intelligent detection method is shown, the method comprising steps S1-S6:
s1: acquiring external environment operation parameters of the transformer, wherein the external environment operation parameters comprise external environment parameters of the transformer and operation state parameters of a local power grid of the transformer;
s2: performing data characteristic analysis on the acquired external environment operation parameters to generate a data characteristic analysis result;
s3: determining an updating acquisition mode of the characteristic gas in the transformer based on the data characteristic analysis result;
s4: switching the current collection mode of the characteristic gas in the transformer to the updated collection mode, and returning to the step S1;
wherein, the types of the characteristic gases collected under different collection modes are not completely the same.
Referring to fig. 6, before the step S1, the method further includes a step S0:
s0: starting a global acquisition mode for acquiring data inside the transformerCharacteristic parameter of all characteristic gases, wherein all characteristic gases are C2H4、CH4、C2H2、C2H6And H2。
In the above embodiment, preferably, the data characteristic analysis result is used to characterize potential fault characteristics of the transformer, where the potential fault characteristics include partial discharge, low energy discharge, high energy discharge, low temperature overheat, high temperature overheat, and medium temperature overheat.
The method further comprises the following steps:
before the step S0, a preset statistical database and a preset mode switching database are established, where the preset mode switching database includes a three-ratio method mode switching database and a grand satellite triangle method mode switching database.
The preset statistical database is a statistical database which establishes a corresponding relation with the current external environment operation parameters of the transformer in advance according to the historical diagnosed fault state of the transformer.
As described above, the external environment parameters of the transformer itself include an external temperature value, an external noise value, and a partial discharge signal value of an environment where the transformer itself is located;
the statistical database stores the corresponding transformer fault states under different external environment parameter values.
The actual corresponding relation of the statistical database needs a person skilled in the art to obtain a fitting statistic based on a statistical principle after a large amount of historical statistical data are gathered according to the model, the field installation environment and the like of an actual transformer, different corresponding relations can be obtained for different transformers and installation environments, but under a set confidence coefficient, the corresponding relations can be popularized to the intelligent detection process of other transformers in the same environment and the intelligent detection process of transformers in the same model in different installation environments.
In short, the technical problem of the present application can be solved as long as the preset statistical database is a statistical database which establishes a corresponding relationship with the current transformer external environment operation parameters in advance according to the historical diagnosed transformer fault state.
For the establishment and introduction of the three-ratio method mode switching database and the grand satellite trigonometry mode switching database, reference is made to the foregoing embodiment, and details are not repeated here.
In step S1, the external environment parameters of the transformer itself include an external temperature value, an external noise value, and a partial discharge signal value of an environment where the transformer itself is located;
the operation state parameters of the local power grid in which the transformer is located comprise an output power value, an output voltage value and a plurality of phase angle change values of the local power grid.
In step S2, analyzing a first threshold range of the external environment parameter value, and matching a first potential transformer state corresponding to the first threshold range in a preset statistical database based on the first threshold range;
analyzing a second variation range of the operation state parameter of the local power grid where the transformer is located, and matching a second transformer evolution state corresponding to the second variation range in a preset statistical database based on the second variation range;
and determining potential fault characteristics of the transformer as the data characteristic analysis result based on the first potential transformer state and the second transformer evolution state.
The step S3 includes:
and searching for a code value corresponding to the potential fault feature in the three-ratio mode switching database based on the potential fault feature of the transformer determined by the data feature analysis result, and determining the updating acquisition mode based on the code value.
And/or the presence of a gas in the atmosphere,
and searching a limit area corresponding to the potential fault feature in the great satellite trigonometry mode switching database based on the potential fault feature of the transformer determined by the data feature analysis result, and determining the updating acquisition mode based on the limit area.
It should be noted that the steps shown in fig. 5 or fig. 6, or the method and process, can be implemented automatically by computer program instructions. Thus, referring to fig. 7, there is provided an electronic computer device comprising a bus, a processor, and a memory for storing a computer program comprising program instructions, the processor for executing the program instructions stored by the computer storage medium.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 7. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement the steps of the aforementioned method examples. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing power secondary apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing power secondary device to cause a series of operational steps to be performed on the computer or other programmable power secondary device to produce a computer implemented process such that the instructions which execute on the computer or other programmable power secondary device provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Practice proves that compared with the method for monitoring and acquiring all internal possible characteristic signals of the transformer in the prior art, the technical scheme of the invention firstly carries out data characteristic analysis on the basis of external environment operating parameters and then generates a data characteristic analysis result so as to determine potential fault characteristics of the transformer; on the basis, the existing internal parameter acquisition mode is updated, so that the acquisition of internal characteristic signals is more targeted; meanwhile, as all possible characteristic signals do not need to be identified, the identification and judgment speed is higher, and the detection mode tends to be intelligent; in addition, the statistical database can be optimized and updated according to actual conditions, the intelligent degree of the statistical database is higher and higher along with the gradual long-term use of the technical scheme, the statistical database is more and more suitable for various conditions, a closed-loop self-learning process is formed, and the universality of the technical scheme is enhanced.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
The present invention is not limited to the specific module configuration described in the related art. The prior art mentioned in the background section can be used as part of the invention to understand the meaning of some technical features or parameters. The scope of the present invention is defined by the claims.
Claims (3)
1. An intelligent detection system for a transformer comprises a first external high-speed acquisition subsystem, a second internal low-speed acquisition subsystem, a third data characteristic analysis subsystem and a fourth intelligent switching subsystem;
the method is characterized in that:
the first external high-speed acquisition subsystem is used for acquiring external environment operation parameters of the transformer, and the external environment operation parameters comprise external environment parameters of the transformer and operation state parameters of a local power grid of the transformer;
the second internal low-speed acquisition subsystem is used for acquiring various characteristic gas parameters inside the transformer, the second internal low-speed acquisition subsystem has various acquisition modes, and the types of the characteristic gas acquired in different acquisition modes are not completely the same;
the third data characteristic analysis subsystem analyzes a first threshold range of external environment parameter values, and matches a first potential transformer state corresponding to the first threshold range in a preset statistical database based on the first threshold range;
the third data characteristic analysis subsystem analyzes a second variation range of the operation state parameters of the local power grid where the transformer is located, and matches a second transformer evolution state corresponding to the second variation range in a preset statistical database based on the second variation range;
determining potential fault characteristics of the transformer as data characteristic analysis results based on the first transformer potential state and the second transformer evolution state;
the fourth intelligent switching subsystem comprises a preset mode switching database;
the preset mode switching database comprises a grand triangle method mode switching database and a three-ratio method mode switching database;
the fourth intelligent switching subsystem searches a code value corresponding to the potential fault feature in a three-ratio mode switching database based on the potential fault feature of the transformer determined by the data feature analysis result, and determines the acquisition mode of the second internal low-speed acquisition subsystem based on the code value;
the fourth intelligent switching subsystem searches a limit area corresponding to the potential fault characteristic in a great satellite trigonometry mode switching database based on the potential fault characteristic of the transformer determined by the data characteristic analysis result, and determines the acquisition mode of the second internal low-speed acquisition subsystem based on the limit area;
the three-ratio mode switching database is an encoding database established by adopting reverse thinking based on the existing three-ratio method, is an encoding relation table corresponding to the existing three-ratio method, removes the same codes in the same fault types, and reserves the corresponding relation table about the fault types-codes established after different codes are reserved;
the grand satellite trigonometry mode switching database is an encoding database established by adopting reverse thinking based on the existing grand satellite trigonometry, is an encoding relation table corresponding to the existing grand satellite trigonometry, removes the same encoding in the same fault type, and maintains a corresponding relation table about fault type-encoding established after different encoding;
and after the acquisition mode is switched, if the content and the proportion value of the acquired characteristic gas do not accord with the existing rule, recovering the global acquisition mode, wherein the global acquisition mode is used for acquiring the characteristic parameters of all the characteristic gases in the transformer.
2. The intelligent transformer detection system of claim 1, wherein:
the external environment parameters of the transformer comprise an external temperature value, an external noise value and a partial discharge signal value of the environment where the transformer is located;
the operation state parameters of the local power grid in which the transformer is located comprise an output power value, an output voltage value and a plurality of phase angle change values of the local power grid.
3. An intelligent transformer detection method, which is implemented based on the intelligent transformer detection system of claim 1 or 2, and is characterized by comprising the following steps:
s0: starting a global acquisition mode, wherein the global acquisition mode is used for acquiring characteristic parameters of all characteristic gases in the transformer, and all the characteristic gases are C2H4、CH4、C2H2、C2H6And H2；
S1: acquiring external environment operation parameters of the transformer, wherein the external environment operation parameters comprise external environment parameters of the transformer and operation state parameters of a local power grid of the transformer;
s2: performing data characteristic analysis on the acquired external environment operation parameters to generate a data characteristic analysis result;
the data characteristic analysis result is used for representing potential fault characteristics of the transformer, and the potential fault characteristics comprise partial discharge, low-energy discharge, high-energy discharge, low-temperature overheat, high-temperature overheat and medium-temperature overheat;
s3: determining an updating acquisition mode of the characteristic gas in the transformer based on the data characteristic analysis result;
s4: switching the current collection mode of the characteristic gas in the transformer to the updated collection mode, and returning to the step S1;
wherein, the types of the characteristic gases collected under different collection modes are not completely the same.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210194722.XA CN114252724B (en) | 2022-03-02 | 2022-03-02 | Intelligent detection method and detection system for transformer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210194722.XA CN114252724B (en) | 2022-03-02 | 2022-03-02 | Intelligent detection method and detection system for transformer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114252724A CN114252724A (en) | 2022-03-29 |
| CN114252724B true CN114252724B (en) | 2022-06-17 |
Family
ID=80800155
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210194722.XA Active CN114252724B (en) | 2022-03-02 | 2022-03-02 | Intelligent detection method and detection system for transformer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114252724B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104569666A (en) * | 2014-12-25 | 2015-04-29 | 重庆大学 | Power transformer fault prediction method based on electricity-graph model |
| CN111856169A (en) * | 2019-04-22 | 2020-10-30 | 宁波奥克斯高科技有限公司 | Transformer fault detection method and system |
| CN112486057A (en) * | 2020-11-03 | 2021-03-12 | 江苏核电有限公司 | Dry-type transformer multi-information-quantity online comprehensive monitoring method and system |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103207950B (en) * | 2013-04-16 | 2016-08-10 | 郑州航空工业管理学院 | A kind of intelligent method of transformer fault diagnosis based on RBF neural |
| CN104655948A (en) * | 2013-11-21 | 2015-05-27 | 国家电网公司 | Novel multistage fault diagnosis method for power transformer |
| CN106682081A (en) * | 2016-11-23 | 2017-05-17 | 云南电网有限责任公司电力科学研究院 | Multi-model based comprehensive transformer performance analysis system |
| CN206505010U (en) * | 2017-02-16 | 2017-09-19 | 四方特变电工智能电气有限公司 | Gases Dissolved in Transformer Oil on-Line Monitor Device based on optoacoustic spectroscopy |
| CN107014437A (en) * | 2017-04-20 | 2017-08-04 | 国网江苏省电力公司无锡供电公司 | The intelligent data acquisition method of transformer station's multisensor syste |
| CN107884647A (en) * | 2017-11-06 | 2018-04-06 | 南京力通达电气技术有限公司 | Transformer fault early warning system based on data mining |
| CN108051709A (en) * | 2017-11-30 | 2018-05-18 | 南京力通达电气技术有限公司 | Transformer state online evaluation analysis method based on artificial intelligence technology |
| CN111784175A (en) * | 2020-07-10 | 2020-10-16 | 西南石油大学 | Distribution transformer risk assessment method and system based on multi-source information |
| CN112269151A (en) * | 2020-10-15 | 2021-01-26 | 芜湖金牛电气股份有限公司 | Method for diagnosing gas fault in transformer oil |
| CN114123518B (en) * | 2022-01-25 | 2022-04-22 | 山东和兑智能科技有限公司 | Digital intelligent detection method and monitoring system for transformer |
-
2022
- 2022-03-02 CN CN202210194722.XA patent/CN114252724B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104569666A (en) * | 2014-12-25 | 2015-04-29 | 重庆大学 | Power transformer fault prediction method based on electricity-graph model |
| CN111856169A (en) * | 2019-04-22 | 2020-10-30 | 宁波奥克斯高科技有限公司 | Transformer fault detection method and system |
| CN112486057A (en) * | 2020-11-03 | 2021-03-12 | 江苏核电有限公司 | Dry-type transformer multi-information-quantity online comprehensive monitoring method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114252724A (en) | 2022-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103197177B (en) | A kind of transformer fault diagnosis analytical approach based on Bayesian network | |
| CN105044499A (en) | Method for detecting transformer state of electric power system equipment | |
| CN110866331A (en) | Evaluation method for quality defects of power transformer family | |
| CN114386537A (en) | Lithium battery fault diagnosis method and device based on Catboost and electronic equipment | |
| Basuki | Online dissolved gas analysis of power transformers based on decision tree model | |
| CN109142830A (en) | Stealing detection method based on power information acquisition system big data | |
| Tong et al. | Online monitoring data processing method of transformer oil chromatogram based on association rules | |
| CN114252724B (en) | Intelligent detection method and detection system for transformer | |
| CN108845285B (en) | Electric energy metering device detection method and system | |
| CN117394529A (en) | SCADA-based auxiliary decision method and system for main distribution network loop-closing reverse power supply control conditions | |
| CN111929579B (en) | Generator online fault diagnosis method and device and computer device | |
| CN112183610A (en) | Transformer fault prediction method and transformer fault prediction device | |
| CN104360194A (en) | Fault diagnosis method for smart power grid | |
| Zhang et al. | Anomalous state detection of dissolved gases in transformer oil based on the canopy hyper sphere model | |
| CN117074852A (en) | Power distribution network electric energy monitoring and early warning management method and system | |
| CN111240306A (en) | Self-adaptive distribution transformer fault diagnosis system and diagnosis method thereof | |
| Pan et al. | Study on intelligent anti–electricity stealing early-warning technology based on convolutional neural networks | |
| Wang et al. | A fault diagnosis method for transformer integrating rough set with fuzzy rules | |
| Huang et al. | Research on accident inversion and analysis method of the oil and gas pipeline SCADA system | |
| Li et al. | Nonparametric kernel density estimation model of transformer health based on dissolved gases in oil | |
| CN114252110B (en) | Intelligent evaluation system and evaluation method for power transformation equipment | |
| Liang et al. | Power transformer abnormal state recognition model based on improved K-Means clustering | |
| Wang et al. | Health status diagnosis of distribution transformers based on big data mining | |
| Hu et al. | Power equipment status information parallel fault diagnosis of based on MapReduce | |
| Zhou et al. | Interval fuzzy probability method for power transformer multiple fault diagnosis |
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 |