CN116973498A - Transformer bushing safety monitoring system based on artificial intelligence - Google Patents
Transformer bushing safety monitoring system based on artificial intelligence Download PDFInfo
- Publication number
- CN116973498A CN116973498A CN202310675250.4A CN202310675250A CN116973498A CN 116973498 A CN116973498 A CN 116973498A CN 202310675250 A CN202310675250 A CN 202310675250A CN 116973498 A CN116973498 A CN 116973498A
- Authority
- CN
- China
- Prior art keywords
- gas
- fault
- data
- time
- oil
- 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.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 34
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 28
- 238000003745 diagnosis Methods 0.000 claims abstract description 24
- 238000001514 detection method Methods 0.000 claims abstract description 16
- 230000000007 visual effect Effects 0.000 claims abstract description 16
- 238000010586 diagram Methods 0.000 claims abstract description 13
- 238000000926 separation method Methods 0.000 claims abstract description 10
- 238000011208 chromatographic data Methods 0.000 claims abstract description 4
- 230000003993 interaction Effects 0.000 claims abstract description 4
- 239000007789 gas Substances 0.000 claims description 126
- 230000008859 change Effects 0.000 claims description 16
- 238000000034 method Methods 0.000 claims description 16
- 238000004891 communication Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 12
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 6
- 239000012159 carrier gas Substances 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 4
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000013500 data storage Methods 0.000 claims description 3
- 238000007872 degassing Methods 0.000 claims description 3
- 230000007774 longterm Effects 0.000 claims description 3
- 229910052757 nitrogen Inorganic materials 0.000 claims description 3
- 239000001301 oxygen Substances 0.000 claims description 3
- 229910052760 oxygen Inorganic materials 0.000 claims description 3
- 230000003449 preventive effect Effects 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000009413 insulation Methods 0.000 description 6
- 239000004020 conductor Substances 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004868 gas analysis Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Classifications
-
- 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
- G06F16/248—Presentation of query results
-
- 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
- G01N30/86—Signal analysis
- G01N30/8693—Models, e.g. prediction of retention times, method development and validation
-
- 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
- G01N30/88—Integrated analysis systems specially adapted therefor, not covered by a single one of the groups G01N30/04 - G01N30/86
-
- 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
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/041—Abduction
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/30—Prediction of properties of chemical compounds, compositions or mixtures
-
- 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
- G01N30/88—Integrated analysis systems specially adapted therefor, not covered by a single one of the groups G01N30/04 - G01N30/86
- G01N2030/8809—Integrated analysis systems specially adapted therefor, not covered by a single one of the groups G01N30/04 - G01N30/86 analysis specially adapted for the sample
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Pathology (AREA)
- Mathematical Physics (AREA)
- Immunology (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Biochemistry (AREA)
- Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Crystallography & Structural Chemistry (AREA)
- Evolutionary Computation (AREA)
- Probability & Statistics with Applications (AREA)
- Fuzzy Systems (AREA)
- Housings And Mounting Of Transformers (AREA)
Abstract
The invention discloses a transformer bushing safety monitoring system based on artificial intelligence, which mainly comprises a fault diagnosis expert system and a transformer oil chromatographic online analysis system, wherein the fault diagnosis expert system comprises a transformer bushing electrical knowledge base, an SQLServer database, an inference engine, a man-machine interaction interface and a built-in controller; the transformer oil chromatographic online analysis system comprises an air source module, an oil-gas separation module, a gas detection module and a chromatographic data acquisition and processing module. According to the relevance between every two gas generation, a gas concentration distribution map is formed, triangles are formed by connecting every two concentration values, and S-t curves of the areas of the triangles are counted; the gas concentration distribution diagram and the S-t curve are matched for diagnosis, so that the visual degree of various fault diagnoses is greatly improved, and the analysis speed of faults is greatly improved; and statistics is carried out on the data of a period of time before the fault, thus providing a new idea for real-time fault monitoring.
Description
Technical Field
The invention relates to the technical field of transformer safety management, in particular to a transformer bushing safety monitoring system based on artificial intelligence.
Background
The transformer is a heart center of a transformer substation, and in the operation process, the working is required to be reliable, if the faults are light, equipment is damaged seriously, and the fire is caused to endanger normal safety in the station, so that the transformer is required to be subjected to thermal defect detection timely and effectively to prevent safety accidents.
Along with the high-speed development of artificial intelligence technology, the intelligent terminal of the transformer and the fault diagnosis expert system gradually replace the traditional manual overhaul system, such as a recently developed intelligent transformer on-line monitoring system, integrate data maintenance management with analysis diagnosis, establish a systematic, multi-level and visual fault diagnosis expert system, realize the real-time on-line monitoring of the running condition of the transformer, realize the remote management of monitoring data through a network communication technology, and ensure that the safety operation of a power grid lays a foundation for establishing the intelligent power grid for the state.
The online monitoring unit for the dissolved gas in the transformer oil is used as one of important components of an online monitoring system for the intelligent transformer, and online monitoring analysis of the content of the dissolved gas in the insulating oil is an effective method for finding and diagnosing potential faults in the transformer.
The key point of the existing intelligent transformer online monitoring system is a core algorithm, the key point of the core algorithm is how to carry out visual processing on analysis data of dissolved gas in transformer oil, common visual processing comprises a David triangle method, an IEC three-ratio method and a fuzzy mathematical reasoning method, but after information integration, the results of various visual processing are still combined modes of numerical values and data charts, when information is fed back to a fault diagnosis expert system, an expert still needs to carry out full comparison through artificial experience and knowledge reserve to obtain a specific diagnosis conclusion, and although the system has a larger progress than a manual maintenance system, multiple data integration and maintenance demonstration are still needed, meanwhile, the data statistics is disordered, the visual degree is still difficult to meet the timeliness and effectiveness of the existing intelligent management science, and improvement is needed.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides an artificial intelligence-based transformer bushing safety monitoring system.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
the transformer bushing safety monitoring system based on artificial intelligence mainly comprises a fault diagnosis expert system and a transformer oil chromatographic online analysis system,
the fault diagnosis expert system of the first part includes:
the transformer bushing electrical knowledge base is used for storing historical data of the transformer bushing and integrating possible faults, reasons, judging methods and characteristic data caused by transformer oil into an experience data packet for calling according to diagnostic reports obtained by historical data experts;
the SQL Server database comprises a transformer comprehensive information database, a conventional electric test database and an oil solution gas composition database, and provides a data storage and feedback platform;
the inference engine stores a mathematical inference algorithm, analyzes the component data of the solution gas in the transformer oil, analyzes the real-time concentration value and the concentration change rate, and compares the real-time concentration value and the concentration change rate with historical data to obtain fault data corresponding to the matching of the experience data packet, thereby obtaining fault diagnosis;
the man-machine interaction interface monitors the data by adopting a data table and an image format, and calls real-time data and relevant historical data thereof at any time to obtain a visual fault report;
the controller is used for connecting various components and servers, forwarding a fault report to a client on site, providing early warning information and timely overhauling;
the transformer oil chromatographic online analysis system of the second part comprises:
the gas source module comprises a gas generating unit, a gas storage unit, a purifying unit, a pressure control and alarm unit and the like and is used for providing carrier gas for driving gas to flow;
the oil-gas separation module comprises an oil sample circulation acquisition unit, an oil sample quantifying unit, an oil sample treatment return unit, a degassing and gas collecting unit and the like and is used for separating dissolved gas in the transformer oil;
the gas detection module comprises a gas separation unit, a constant temperature and constant current control unit, a gas detection unit and the like and is used for collecting and removing nitrogen and oxygen, purifying each fault gas and detecting and analyzing;
the chromatographic data acquisition processing module comprises a data acquisition unit, a field control processing unit, a communication control unit, a communication unit and the like, and is used for acquiring analysis data and outputting signals, and if the data and the alarm signals are directly uploaded without the communication unit, a computer and monitoring software can be installed in a main control room, and the running state of equipment can be directly monitored in the main control room;
the auxiliary unit comprises a transformer interface, an oil pipe, a communication cable, a power cable and the like.
Preferably, the transformer oil chromatographic online analysis system works as follows: firstly, carrying out oil circuit circulation by utilizing an oil sample collecting unit, treating dead oil of a connecting pipeline, and then quantifying an oil sample; the oil-gas separation unit is used for rapidly separating dissolved gas in oil, conveying the dissolved gas into a quantitative pipe of the six-way valve and automatically sampling; under the pushing of carrier gas, sample gas is separated by a chromatographic column and sequentially enters a gas detection unit; the data acquisition unit is used for completing the conversion and acquisition of AD data, the embedded processing unit is used for storing, calculating and analyzing the acquired data, uploading the data to the data processing server (installed in a main control room) through an Ethernet interface, and finally, the data processing and fault analysis are carried out by XS-DGA-03 monitoring and early warning software.
Further, the monitoring and early warning software divides the faults into a plurality of levels according to the gas concentration value, namely a general fault, a serious fault and a critical fault, the critical fault needs immediate field processing, the serious fault is deeply analyzed according to the combination of time limit, other electrical detection reports and expert judgment, the general fault is taken as the preventive condition of the serious fault and the critical fault to be summarized, and a regular diagnosis report archive is formed for standby, so that long-term data processing and fault analysis are facilitated.
Preferably, the mathematical reasoning algorithm in the reasoning machine is as follows:
according to the relativity between every two gas generation, forming a gas concentration distribution map with a certain sequence, forming triangles through connection of every two concentration values, counting the areas of the triangles, and comparing to obtain the difference between the concentration of two gases and the concentration of other gases, so that the fault type can be judged through quick observation.
Further, the mathematical reasoning algorithm in the reasoning engine also comprises the following processes: by comparing the areas of the triangles, the ratio of S1 to S6 needs to be calculated for C (6, 2) =15 times, and the expression ratio corresponding to the areas of the triangles in various fault types is as follows if S5 > S1 in the 'oil overheat' fault: S5/S1 > 1, while the other S2/S1S 3/S1S 4/S1S 6/S1 0; comparing the area ratios tested in real time with the inherent performance ratios of the fault types, the fault types can be immediately obtained, wherein the faults of partial discharge in oil paper insulation and arc in oil and paper are referred to by the sum of S1-S6, namely the fixed sum value of the sum of the triangular areas of the faults, the real-time sum value of the real-time detection S1-S6 is compared with the fixed sum value, and the real-time sum value/the fixed sum value = 0.7-1.3 can be regarded as corresponding fault matched state; through the comparison operation of the two ratios, the diagnosis of the fault type can be rapidly determined.
Still further, the mathematical reasoning algorithm in the reasoning engine further comprises the following process: meanwhile, according to the time statistics of the two gas concentrations and the time-varying curves, namely the visual effect of the S-t curves, the time-varying curves can be changed from a coordinate system, which area or areas in each S-t curve is at a high value and which area or areas are at a low value, and the gas concentration variation of some faults before the occurrence can be monitored and early-warned in real time, so that system support can be provided for the realization of a fault early-warning mechanism.
More importantly, the method of constructing the gas concentration profile is as follows:
1) According to the empirical data in the database, the concentration value of a certain gas in which a certain fault occurs in the transformer bushing is arranged and then averaged, and the averaged value is multiplied by 3 to be used as the valueThe limiting value of the gas concentration is calculated in turn to H 2 、C 2 H 2 、CH 4 、C 2 H 4 、CO 2 And CO, and multiplying the six limit values by a different ratio K 1 -κ 6 Enlarging or reducing to the same value, forming a six-axis polar coordinate system by using six polar coordinate axes with an origin O and the six polar coordinate axes being distributed annularly at equal angles, wherein the endpoints correspond to the limit values, and adjacent endpoints are connected to form a hexagon;
2) The real-time concentration value obtained by the test is multiplied by the proportion kappa 1 -κ 6 Multiplying 3 by a corresponding proportion value in the coordinate to obtain a mark value in the coordinate;
3) Automatically connecting the marking values of adjacent polar coordinate axes, constructing a triangle with the two marking values and an origin O, outputting a graph, calculating the area of each triangle in each six-axis polar coordinate system through graph identification calculation, and setting H 2 Polar axis and C 2 H 2 The triangle area between the polar coordinate axes is S1, H 2 The triangle area between the polar coordinate axis and the CO polar coordinate axis is S2, and other CO and CO 2 、C 2 H 4 、CH 4 And C 2 H 2 The triangular areas between the two polar coordinate axes are sequentially S3, S4, S5 and S6, so that a gas concentration distribution diagram capable of recording concentration in real time is obtained, and the distribution diagram is shown in figure 2;
4) According to the test time sequence, the change of the area of each triangle related to six gases along with time is counted, an S-t curve of a period of time is obtained after linear fitting, whether the state of oil in a transformer sleeve is abnormal or not can be observed in real time, the change trend of the gas concentration in a period of time before and when a certain fault occurs can be observed in real time, and the possibility of rule summarization is provided for subsequent fault early warning, so that the S-t curve provides a new thought for fault real-time monitoring.
Compared with the prior art, the invention has the beneficial effects that:
1. aiming at the defect of low visual processing degree of the existing various intelligent transformer online monitoring systems, the invention discovers that the possibility of single fault gas is almost not existed when a fault happens according to the prompt of the three-ratio method in the existing visual processing and the gas composition analysis experience summary when the actual transformer sleeve fails, and at least two gases are often generated simultaneously when the fault happens; according to the component analysis report, a certain set rule exists between the occurrence frequency and the concentration of nine gases when faults occur.
2. According to the correlation between every two gas generation, a gas concentration distribution map is formed in a certain sequence, a triangle is formed by connecting every two concentration values, and the areas of the triangles are counted and compared to obtain the difference between the concentration of two gases and the concentration of the other gases, so that the fault type can be judged through quick observation;
3. the gas concentration distribution diagram is used as a novel visual interface, wherein a six-axis polar coordinate system can timely acquire gas concentration data detected in real time and obtain a marked value, the marked values of adjacent polar coordinate axes form triangles, and the area of each triangle in the six-axis polar coordinate system is calculated through image recognition, so that the gas concentration distribution diagram capable of recording concentration in real time is obtained;
4. according to the invention, through counting the change of the area of each triangle related to six gases along with time according to the test time sequence, an S-t curve of a period of time is obtained after linear fitting, whether the state of oil in a transformer sleeve is abnormal or not can be observed in real time, the change trend of the gas concentration in a period of time before and when a certain fault occurs can be observed in real time, and the possibility of rule summarization is provided for subsequent fault early warning;
5. the visual degree of various fault diagnoses is greatly improved through the matching diagnosis of the gas concentration distribution diagram and the S-t curve, namely, the pre-characteristic assignment of each fault is displayed and contrasted according to the interface of the gas concentration distribution diagram and the S-t curve (the assignment can be displayed in the coordinate system of the gas concentration distribution diagram and the S-t curve), and the analysis speed of the fault is greatly improved; and statistics is carried out on the data of a period of time before the fault so as to obtain the occurrence rule of the fault, thereby providing a new idea for real-time monitoring of the fault.
Drawings
FIG. 1 is a schematic diagram of an artificial intelligence based transformer bushing safety monitoring system according to the present invention;
FIG. 2 is a gas analysis comparison chart of the safety monitoring system of the transformer bushing based on artificial intelligence;
FIG. 3 is a graph (S-t plot) of the interference area of the detected gas concentration over time obtained from the gas analysis comparison graph of FIG. 2.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.
1. System architecture
The transformer bushing safety monitoring system based on artificial intelligence mainly comprises a fault diagnosis expert system and a transformer oil chromatographic online analysis system:
the fault diagnosis expert system of the first part includes:
the transformer bushing electrical knowledge base is used for storing historical data of the transformer bushing and integrating possible faults, reasons, judging methods and characteristic data caused by transformer oil into an experience data packet for calling according to diagnostic reports obtained by historical data experts;
the SQL Server database comprises a transformer comprehensive information database, a conventional electric test database and an oil solution gas composition database, and provides a data storage and feedback platform;
the inference engine stores a mathematical inference algorithm, analyzes the component data of the solution gas in the transformer oil, analyzes the real-time concentration value and the concentration change rate, and compares the real-time concentration value and the concentration change rate with historical data to obtain fault data corresponding to the matching of the experience data packet, thereby obtaining fault diagnosis;
the man-machine interaction interface monitors the data by adopting a data table and an image format, and calls real-time data and relevant historical data thereof at any time to obtain a visual fault report;
the controller is used for connecting various components and servers, forwarding a fault report to a client on site, providing early warning information and timely overhauling;
the transformer oil chromatographic online analysis system of the second part comprises:
the gas source module comprises a gas generating unit, a gas storage unit, a purifying unit, a pressure control and alarm unit and the like and is used for providing carrier gas for driving gas to flow;
the oil-gas separation module comprises an oil sample circulation acquisition unit, an oil sample quantifying unit, an oil sample treatment return unit, a degassing and gas collecting unit and the like and is used for separating dissolved gas in the transformer oil;
the gas detection module comprises a gas separation unit, a constant temperature and constant current control unit, a gas detection unit and the like and is used for collecting and removing nitrogen and oxygen, purifying each fault gas and detecting and analyzing;
the chromatographic data acquisition processing module comprises a data acquisition unit, a field control processing unit, a communication control unit, a communication unit and the like, and is used for acquiring analysis data and outputting signals, and if the data and the alarm signals are directly uploaded without the communication unit, a computer and monitoring software can be installed in a main control room, and the running state of equipment can be directly monitored in the main control room;
the auxiliary unit comprises a transformer interface, an oil pipe, a communication cable, a power cable and the like.
Specifically, the working process of the transformer oil chromatographic online analysis system is as follows:
firstly, carrying out oil circuit circulation by utilizing an oil sample collecting unit, treating dead oil of a connecting pipeline, and then quantifying an oil sample; the oil-gas separation unit is used for rapidly separating dissolved gas in oil, conveying the dissolved gas into a quantitative pipe of the six-way valve and automatically sampling; under the pushing of carrier gas, sample gas is separated by a chromatographic column and sequentially enters a gas detection unit; the data acquisition unit is used for completing the conversion and acquisition of AD data, the embedded processing unit is used for storing, calculating and analyzing the acquired data, uploading the data to the data processing server (installed in a main control room) through an Ethernet interface, and finally, the data processing and fault analysis are carried out by XS-DGA-03 monitoring and early warning software.
Further, the monitoring and early warning software divides the faults into a plurality of levels according to the gas concentration values, namely a general fault, a serious fault and a critical fault respectively:
"critical faults" require immediate field handling;
the serious fault is combined with other electrical detection reports and expert judgment to carry out deep analysis according to time limit;
the general faults are summarized as the preventive situations of serious faults and critical faults, and regular diagnosis reports are formed for archiving, so that long-term data processing and fault analysis are facilitated.
2. Algorithm improvement of visualization processing:
1) According to the prompt of the three-ratio method in the existing visualization processing and according to the gas composition analysis experience summary of the actual transformer bushing fault, the single fault gas is found to be almost impossible when the fault occurs, and at least two gases are often generated simultaneously when the fault occurs; according to the component analysis report, a certain set rule exists between the occurrence frequency and the concentration of nine gases when faults occur.
2) Based on the analysis, the invention forms a gas concentration distribution diagram with a certain sequence according to the relativity between every two gas generation, forms triangles through connection of every two concentration values, counts the areas of the triangles and compares the areas to obtain the difference between the concentration of two gases and the concentration of other gases, thereby judging the fault type through quick observation, and referring to FIG. 2;
3) The ratio of S1 to S6 is calculated by comparing the areas of the triangles, wherein the ratio of S1 to S6 is calculated by C (6, 2) =15 times, and the ratio corresponds to the expression ratio of the areas of the triangles in various fault types;
if S5 > S1 in the "oil over temperature" fault, the expression ratio is: S5/S1 is more than 1, other S2/S1 is approximately equal to S3/S1 is approximately equal to S4/S1 is approximately equal to S6/S1 is approximately equal to 0, and the real-time test area ratios are compared with the inherent performance ratios of the fault types, so that the fault types can be immediately obtained;
the partial discharge in the oil paper insulation of the fault and the inherent performance ratio of the arc in the oil and paper of the fault are similar, so that the sum of S1-S6, namely the fixed sum value of the sum of the areas of each triangle of each fault, the real-time sum value of S1-S6 detected in real time is referred to, the real-time sum value is compared with the fixed sum value, and the real-time sum value/the fixed sum value = 0.7-1.3 can be considered as corresponding to the matched state of the fault;
the diagnosis of the fault type can be rapidly determined through the comparison operation of the two ratios, and is specifically shown in the table 1;
TABLE 1 Transformer bushing failure analysis Table based on gas composition speculation
It should be noted that, the fault arc is a failure of insulation between conductors with different electric potentials, such as phase conductors, to ground, and no metal connection is formed, and a short circuit is formed by the arc. Partial discharge is a deterioration of local insulation, an excessive local field strength (such as a tip), an ionization of air at a local insulation surface, etc., and an arc may be generated. However, the arc does not penetrate other conductors, and is therefore called a "partial" discharge. The partial discharge may be an air-ionized corona discharge or an arc-flash discharge along the insulating surface, but not conducted to other conductors. Under the condition that S1 is approximately equal to S3 and is more than S5, the difference of the total content of fault gases needs to be analyzed, namely the total concentration of the fault gases generated by partial discharge faults in the oil paper insulation is obviously smaller than the total concentration of the fault gases generated by arc faults in the oil and paper (compared with the fault gas range of historical data), so that the display area of an S-t curve also needs to display various fault gas concentration values and the total concentration values of the fault gases generated by various faults, thereby facilitating quick judgment by manual expert comparison and quick determination of fault types after comparison operation of a later intelligent expert system.
4) Meanwhile, according to the time statistics of the two gas concentrations and the time-varying curves, namely the visual effect of the S-t curves, which one or more areas in each S-t curve are located at a high value and which one or more areas are located at a low value can be changed along with the time in a coordinate system, and the gas concentration variation of some faults before the occurrence can be monitored and early-warned in real time, so that system support can be provided for the realization of a fault early-warning mechanism, and the system can be referred to as figure 3.
3. Construction of a gas concentration profile:
the construction method of the gas concentration distribution map is as follows:
1) According to the empirical data in the database, the concentration value of a certain gas in which a certain fault occurs in the transformer bushing is arranged and then averaged, the average value is multiplied by 3 and then used as the limiting value of the gas concentration, and H is calculated in sequence 2 、C 2 H 2 、CH 4 、C 2 H 4 、CO 2 And CO, and multiplying the six limit values by a different ratio K 1 -κ 6 Enlarging or reducing to the same value, forming a six-axis polar coordinate system by using six polar coordinate axes with an origin O and the six polar coordinate axes being distributed annularly at equal angles, wherein the endpoints correspond to the limit values, and adjacent endpoints are connected to form a hexagon;
2) The real-time concentration value obtained by the test is multiplied by the proportion kappa 1 -κ 6 Multiplying 3 by a corresponding proportion value in the coordinate to obtain a mark value in the coordinate;
3) Automatically connecting the marking values of adjacent polar coordinate axes, constructing a triangle with the two marking values and an origin O, outputting a graph, calculating the area of each triangle in each six-axis polar coordinate system through graph identification calculation, and setting H 2 Polar axis and C 2 H 2 The triangle area between the polar coordinate axes is S1, H 2 The triangle area between the polar coordinate axis and the CO polar coordinate axis is S2, and other CO and CO 2 、C 2 H 4 、CH 4 And C 2 H 2 The triangular areas between the two polar coordinate axes are sequentially S3, S4, S5 and S6, so that a gas concentration distribution diagram capable of recording concentration in real time is obtained, and the distribution diagram is shown in figure 2;
4) According to the test time sequence, the change of the area of each triangle related to six gases along with time is counted, an S-t curve of a period of time is obtained after linear fitting, whether the state of oil in the transformer bushing is abnormal or not can be observed in real time,the change trend of the gas concentration in a period of time before and during the occurrence of a certain fault can be observed in real time, the possibility of summarizing the rules is provided for the subsequent fault early warning, as shown in figure 3, which is a dynamic graph of curve change in 24 hours before and during the occurrence of the fault spark discharge in oil, S1 shows sudden increase change, S2-S5 fluctuates around 0 value (actually is the fluctuation of the electric signal of the detection limit of gas detection), and S6 shows larger fluctuation, namely CH before the occurrence of the fault 4 The concentration has certain fluctuation, S6 tends to be gentle when faults occur, and the fact that discharge has a certain small amount of electric arcs but does not cause actual short circuit heat release is proved, other faults (such as electric arcs in oil) are not deduced in practice, and the faults are in accordance with the types of the faults in actual tests and the possibility and complexity of mutual conversion, so that the S-t curve provides a new thought for fault real-time monitoring.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should make equivalent substitutions or modifications according to the technical scheme of the present invention and the inventive concept thereof, and should be covered by the scope of the present invention.
Claims (7)
1. The transformer bushing safety monitoring system based on artificial intelligence mainly comprises a fault diagnosis expert system and a transformer oil chromatographic online analysis system, and is characterized in that the fault diagnosis expert system comprises:
the transformer bushing electrical knowledge base is used for storing historical data of the transformer bushing and integrating possible faults, reasons, judging methods and characteristic data caused by transformer oil into an experience data packet for calling according to diagnostic reports obtained by historical data experts;
the SQL Server database comprises a transformer comprehensive information database, a conventional electric test database and an oil solution gas composition database, and provides a data storage and feedback platform;
the inference engine stores a mathematical inference algorithm, analyzes the component data of the solution gas in the transformer oil, analyzes the real-time concentration value and the concentration change rate, and compares the real-time concentration value and the concentration change rate with historical data to obtain fault data corresponding to the matching of the experience data packet, thereby obtaining fault diagnosis;
the man-machine interaction interface monitors the data by adopting a data table and an image format, and calls real-time data and relevant historical data thereof at any time to obtain a visual fault report;
the controller is used for connecting various components and servers, forwarding a fault report to a client on site, providing early warning information and timely overhauling;
the transformer oil chromatographic online analysis system comprises:
the gas source module comprises a gas generating unit, a gas storage unit, a purifying unit and a pressure control and alarm unit and is used for providing carrier gas for driving gas to flow;
the oil-gas separation module comprises an oil sample circulation acquisition unit, an oil sample quantifying unit, an oil sample treatment return unit and a degassing and gas collecting unit and is used for separating dissolved gas in the transformer oil;
the gas detection module comprises a gas separation unit, a constant temperature and constant current control unit and a gas detection unit and is used for collecting and removing nitrogen and oxygen, purifying each fault gas and detecting and analyzing;
the chromatographic data acquisition processing module comprises a data acquisition unit, a field control processing unit, a communication control unit and a communication unit and is used for acquiring analysis data and outputting signals;
the auxiliary unit comprises a transformer interface, an oil pipe and a communication and power cable.
2. The artificial intelligence based transformer bushing safety monitoring system of claim 1, wherein the transformer oil chromatographic online analysis system works as follows: firstly, carrying out oil circuit circulation by utilizing an oil sample collecting unit, treating dead oil of a connecting pipeline, and then quantifying an oil sample; the oil-gas separation unit is used for rapidly separating dissolved gas in oil, conveying the dissolved gas into a quantitative pipe of the six-way valve and automatically sampling; under the pushing of carrier gas, sample gas is separated by a chromatographic column and sequentially enters a gas detection unit; the data acquisition unit is used for completing the conversion and acquisition of AD data, the embedded processing unit is used for storing, calculating and analyzing the acquired data, uploading the data to the data processing server through the Ethernet interface, and finally carrying out data processing and fault analysis by the monitoring and early warning software.
3. The transformer bushing safety monitoring system based on artificial intelligence according to claim 2, wherein the monitoring and early warning software divides the faults into a plurality of levels according to the gas concentration values, namely "general faults", "serious faults" and "critical faults", the critical faults "need immediate field processing, the" serious faults "are deeply analyzed according to time limit and combined with other electrical detection reports and expert judgment, and the" general faults "are summarized as the preventive conditions of the" serious faults "and the" critical faults ", so as to form a regular diagnosis report archive for long-term data processing and fault analysis.
4. The artificial intelligence based transformer bushing safety monitoring system of claim 1, wherein the mathematical reasoning algorithm in the reasoning engine flows as follows:
according to the relativity between every two gas generation, forming a gas concentration distribution map with a certain sequence, forming triangles through connection of every two concentration values, counting the areas of the triangles, and comparing to obtain the difference between the concentration of two gases and the concentration of other gases, so that the fault type can be judged through quick observation.
5. The artificial intelligence based transformer bushing safety monitoring system of claim 4, wherein the mathematical reasoning algorithm in the reasoning engine further comprises the process of: by comparing the areas of the triangles, calculating the ratio of S1 to S6 by two to obtain the ratio C (6, 2) =15 times, and comparing the real-time tested area ratio with the inherent performance ratio of each fault type corresponding to the performance ratio of each triangle area in each fault type; referring to the sum of S1-S6, i.e. the fixed sum value of the sum of the areas of the triangles of each fault, comparing the real-time sum value of S1-S6 detected in real time with the fixed sum value, and determining that the real-time sum value/fixed sum value=0.7-1.3 is the "corresponding fault matched state"; the diagnosis of the fault type is rapidly determined through the comparison operation of the two ratios.
6. The artificial intelligence based transformer bushing safety monitoring system of claim 5, wherein the mathematical reasoning algorithm in the reasoning engine further comprises the process of: according to the time statistics of the two gas concentrations and the time-varying curves, namely the visual effect of the S-t curves, the time-varying areas or areas in the S-t curves are located at high values and the time-varying areas or areas are located at low values are observed from a coordinate system, and the gas concentration variation of some faults before occurrence is monitored and early warned in real time.
7. The artificial intelligence based transformer bushing safety monitoring system of claim 4, wherein the gas concentration profile is constructed as follows:
1) According to the empirical data in the database, the concentration value of a certain gas in which a certain fault occurs in the transformer bushing is arranged and then averaged, the average value is multiplied by 3 and then used as the limiting value of the gas concentration, and H is calculated in sequence 2 、C 2 H 2 、CH 4 、C 2 H 4 、CO 2 And CO, and multiplying the six limit values by a different ratio K 1 -κ 6 Enlarging or reducing to the same value, forming a six-axis polar coordinate system by using six polar coordinate axes with an origin O and the six polar coordinate axes being distributed annularly at equal angles, wherein the endpoints correspond to the limit values, and adjacent endpoints are connected to form a hexagon;
2) The real-time concentration value obtained by the test is multiplied by the proportion kappa 1 -κ 6 Multiplying 3 by a corresponding proportion value in the coordinate to obtain a mark value in the coordinate;
3) Coordinate axes of adjacent polesThe mark values of (2) are automatically connected, two mark values and an origin O form a triangle, a graph is output, the area of each triangle in each six-axis polar coordinate system is calculated through graph identification calculation, and H is set 2 Polar axis and C 2 H 2 The triangle area between the polar coordinate axes is S1, H 2 The triangle area between the polar coordinate axis and the CO polar coordinate axis is S2, and other CO and CO 2 、C 2 H 4 、CH 4 And C 2 H 2 The triangular areas between the two polar coordinate axes are sequentially S3, S4, S5 and S6, and a gas concentration distribution diagram of the concentration is recorded in real time;
4) According to the test time sequence, the change of the area of each triangle related to six gases along with time is counted, an S-t curve of a period of time is obtained after linear fitting, whether the state of oil in a transformer sleeve is abnormal or not is observed in real time, and the change trend of the gas concentration in a period of time before and when a certain fault occurs is observed in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310675250.4A CN116973498A (en) | 2023-06-08 | 2023-06-08 | Transformer bushing safety monitoring system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310675250.4A CN116973498A (en) | 2023-06-08 | 2023-06-08 | Transformer bushing safety monitoring system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116973498A true CN116973498A (en) | 2023-10-31 |
Family
ID=88483924
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310675250.4A Pending CN116973498A (en) | 2023-06-08 | 2023-06-08 | Transformer bushing safety monitoring system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116973498A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117405284A (en) * | 2023-12-15 | 2024-01-16 | 南京中鑫智电科技有限公司 | Pressure early warning method and system for sleeve oil hole plug assembly |
-
2023
- 2023-06-08 CN CN202310675250.4A patent/CN116973498A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117405284A (en) * | 2023-12-15 | 2024-01-16 | 南京中鑫智电科技有限公司 | Pressure early warning method and system for sleeve oil hole plug assembly |
| CN117405284B (en) * | 2023-12-15 | 2024-03-01 | 南京中鑫智电科技有限公司 | Pressure early warning method and system for sleeve oil hole plug assembly |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111650451B (en) | Converter transformer fault reason identification method and system | |
| Dukarm | Transformer oil diagnosis using fuzzy logic and neural networks | |
| CN104990629B (en) | A kind of electrical equipment fault automatic early-warning system of infrared imaging temperature measuring | |
| CN108761228A (en) | Measure the Operation Condition of Power Transformers appraisal procedure under big data | |
| CN108051709A (en) | Transformer state online evaluation analysis method based on artificial intelligence technology | |
| CN116973498A (en) | Transformer bushing safety monitoring system based on artificial intelligence | |
| CN116187593B (en) | Power distribution network fault prediction processing method, device, equipment and storage medium | |
| CN116593495B (en) | Operation and maintenance intelligent control system and method for flue gas online monitoring equipment | |
| CN116308285A (en) | Intelligent terminal safety supervision system based on data processing | |
| CN106646014A (en) | Transformer fault diagnosis method | |
| CN110879586A (en) | Phase modulator fault diagnosis and state monitoring method and system | |
| CN112966990A (en) | Comprehensive state evaluation method for power transformation equipment | |
| CN110808856A (en) | Big data operation and maintenance method and system based on data center | |
| CN115248402A (en) | Oil immersed transformer on-line monitoring system and method | |
| CN117368644A (en) | Sensor cable detection method | |
| CN114519382A (en) | Nuclear power plant key operation parameter extraction and abnormity monitoring method | |
| CN110674240B (en) | GIS-based distributed multistage intelligent fault diagnosis system for power equipment | |
| CN117409526A (en) | Electrical fire extremely early warning and monitoring system and fire extinguishing method | |
| CN110488125B (en) | Method and system for realizing active early warning processing based on state information quantity of circuit breaker | |
| CN111766475A (en) | Disconnection fault positioning matrix algorithm | |
| CN113537658A (en) | Equipment risk assessment and maintenance system and method | |
| CN116628544A (en) | Fault diagnosis method based on hydraulic winch state on-line monitoring | |
| CN114925867A (en) | Internet of things maintenance prediction system for key equipment in seamless steel tube production | |
| CN112379196B (en) | Power transmission and transformation equipment state monitoring and analyzing method based on Internet of things technology | |
| CN112285631A (en) | Judgment method and system for active early warning of current transformer |
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 |