CN113205127A - Transformer self-diagnosis evaluation device and method based on edge calculation - Google Patents
Transformer self-diagnosis evaluation device and method based on edge calculation Download PDFInfo
- Publication number
- CN113205127A CN113205127A CN202110460696.6A CN202110460696A CN113205127A CN 113205127 A CN113205127 A CN 113205127A CN 202110460696 A CN202110460696 A CN 202110460696A CN 113205127 A CN113205127 A CN 113205127A
- Authority
- CN
- China
- Prior art keywords
- transformer
- data
- diagnosis
- module
- source data
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 46
- 238000004092 self-diagnosis Methods 0.000 title claims abstract description 32
- 238000004364 calculation method Methods 0.000 title claims abstract description 28
- 238000000034 method Methods 0.000 title claims description 33
- 238000007781 pre-processing Methods 0.000 claims abstract description 34
- 230000004927 fusion Effects 0.000 claims abstract description 26
- 238000004458 analytical method Methods 0.000 claims abstract description 5
- 238000013135 deep learning Methods 0.000 claims abstract description 3
- 238000003745 diagnosis Methods 0.000 claims description 32
- 238000004140 cleaning Methods 0.000 claims description 8
- 238000013501 data transformation Methods 0.000 claims description 8
- 230000010354 integration Effects 0.000 claims description 8
- 238000001816 cooling Methods 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 7
- 230000003044 adaptive effect Effects 0.000 claims description 5
- 238000007689 inspection Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical group [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims description 4
- 238000013021 overheating Methods 0.000 claims description 4
- 238000004804 winding Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 3
- 238000009413 insulation Methods 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 2
- 238000013144 data compression Methods 0.000 claims description 2
- 238000003066 decision tree Methods 0.000 claims description 2
- 230000002950 deficient Effects 0.000 claims description 2
- 230000007613 environmental effect Effects 0.000 claims description 2
- 230000006870 function Effects 0.000 claims description 2
- 230000016507 interphase Effects 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 238000012360 testing method Methods 0.000 claims description 2
- 230000009466 transformation Effects 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 7
- 239000013307 optical fiber Substances 0.000 abstract description 3
- 230000008447 perception Effects 0.000 abstract 1
- 238000004891 communication Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000009421 internal insulation Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011208 chromatographic data Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000009545 invasion Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000741 silica gel Substances 0.000 description 1
- 229910002027 silica gel Inorganic materials 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Testing Relating To Insulation (AREA)
- Testing Electric Properties And Detecting Electric Faults (AREA)
- Housings And Mounting Of Transformers (AREA)
Abstract
The invention discloses a transformer self-diagnosis evaluation device based on edge calculation, which comprises a data acquisition module, a data preprocessing module, a data fusion module and a rule reasoning module, wherein signals such as internal temperature, pressure, vibration and partial discharge signals, external visible light images, infrared images, casing medium loss and partial discharge signals of a transformer are comprehensively acquired by means of optical fiber sensing, deep learning, edge calculation, Internet of things and the like, and the state analysis and judgment are carried out on the transformer on site, so that the self-perception, self-diagnosis and self-regulation of the transformer are realized, the intelligent level of the transformer is improved, the monitoring precision is improved, and the real-time perception of the running state of the transformer is realized.
Description
Technical Field
The invention relates to the technical field of electrical equipment intelligence, in particular to a transformer self-diagnosis evaluation device and method based on edge calculation.
Background
The power transformer is one of the most widely applied pivot devices which are the most core of energy transmission and conversion in a power grid, and the stability of the operation of the power transformer is closely related to the safe and reliable operation of a power system, so that the improvement of the reliability and the intelligent level of the operation of the transformer is an important subject of research in the power industry.
The key to improving the reliability of the operation of the transformer is to realize the self-perception, self-diagnosis and evaluation of the state of the transformer and self-adaptive automatic regulation. The prior on-line monitoring device, the electrified detection device, the robot inspection and the like are added after the transformer is installed, are not considered from the beginning of the transformer design and are not fully integrated with the transformer into a whole. At present, the problems that monitoring means of internal working states of a power transformer is lack and monitoring capability is not enough generally exist, the key point of the monitoring of the states of the power transformer is the transformer operating state concerned by operation management personnel and possible faults inside the transformer, and the internal faults mainly comprise three types of insulation faults, overheating faults and mechanical faults in nature. If the transformer can be designed without influencing the internal insulation and the overall structure of the transformer, the comprehensive monitoring of the internal insulation, the mechanical and the overheating states of the transformer can be considered, various state quantity information required in the self-diagnosis process and various devices required by self-regulation are considered, and the transformer has extremely important significance for guaranteeing the safe operation of the transformer.
At present, many artificial intelligent transformer fault analysis algorithms are mainly based on transformer oil chromatographic data, and are partially based on partial discharge data, and are not based on novel optical fiber sensing transformer internal temperature, pressure, vibration and partial discharge detection technologies and on an internet of things technology in transformer electric quantity and non-electric quantity sensing technologies.
Disclosure of Invention
The invention aims to solve the defect that the traditional transformer fault analysis cannot analyze the internal temperature, pressure, vibration and partial discharge detection data of a transformer, and provides a transformer self-diagnosis evaluation device and method based on edge calculation.
In order to achieve the purpose, the transformer self-diagnosis evaluation device based on edge calculation comprises a data acquisition module, a data preprocessing module, a data fusion module and a rule reasoning module, wherein the data acquisition module is used for acquiring and communicating transformer multi-source data, and the transformer multi-source data comprises transformer internal state data, transformer external state data, transformer operation data and transformer basic data; the data preprocessing module is used for preprocessing the transformer multi-source data acquired by the data acquisition module by adopting a data preprocessing method to obtain preprocessed transformer multi-source data, and the preprocessing method comprises data cleaning, data integration, data transformation and data specification; the data fusion module is used for extracting and integrating key parameters of the transformer multi-source data output by the data preprocessing module to obtain fused transformer multi-source data; and the rule reasoning module is combined with the transformer multi-source data output by the data fusion module and applies a fault diagnosis rule to carry out comprehensive fault diagnosis on the transformer fault.
A transformer self-diagnosis evaluation method based on edge calculation is characterized in that: it comprises the following steps:
step 1: the data acquisition module is used for acquiring and communicating transformer multi-source data, wherein the transformer multi-source data comprises transformer internal state data, transformer external state data, transformer operation data and transformer basic data;
step 2: the data preprocessing module is used for preprocessing the transformer multi-source data acquired by the data acquisition module by adopting a data preprocessing method to obtain preprocessed transformer multi-source data, and the preprocessing method comprises data cleaning, data integration, data transformation and data specification;
and step 3: the data fusion module extracts and integrates key parameters of the transformer multi-source data output by the data preprocessing module to obtain fused transformer multi-source data;
and 4, step 4: and the rule reasoning module is combined with the transformer multi-source data output by the data fusion module and applies a fault diagnosis rule to carry out comprehensive fault diagnosis on the transformer fault.
The invention has the beneficial effects that: the method can obtain the information of electric quantity and non-electric quantity of the traditional transformer, and can also obtain the signals of temperature, pressure, vibration and partial discharge in the transformer, and the obtained diagnosis and evaluation results are more accurate than the results obtained by the traditional method; according to the invention, multi-source information such as transformer image data, non-electric quantity data, power frequency electric quantity data and high-frequency electric quantity data is comprehensively analyzed, and information interaction, storage and calculation of local edge data and cloud data are carried out, so that the calculation and data transmission efficiency is improved, and resource waste and economic loss are prevented; according to the intelligent control method, the internal temperature and real-time state sensing data of the transformer are analyzed and researched, and the historical operating data of the cloud equipment with the same model is combined, so that the intelligent control of the transformer cooling system is realized.
Drawings
FIG. 1 is a schematic view of the apparatus of the present invention;
FIG. 2 is a flow chart of the operation of the apparatus of the present invention;
FIG. 3 is a diagram of the relationship between the apparatus of the present invention and a transformer fault diagnosis big data center;
FIG. 4 is a diagram of the relationship between the apparatus of the present invention and other devices connected to the Internet of things;
the system comprises a data acquisition module 1, a data preprocessing module 2, a data fusion module 3, a rule inference module 4, an adaptive adjustment module 5 and a cloud edge coordination module 6.
Detailed Description
The invention is described in further detail below with reference to the following figures and specific examples:
the invention designs a transformer self-diagnosis evaluation device based on edge calculation, which comprises a data acquisition module 1, a data preprocessing module 2, a data fusion module 3 and a rule reasoning module 4, wherein the data acquisition module 1 is used for acquiring and communicating transformer multi-source data, and the transformer multi-source data comprises transformer internal state data, transformer external state data, transformer operation data and transformer basic data; the data preprocessing module 2 is used for preprocessing the transformer multi-source data acquired by the data acquisition module 1 by adopting a data preprocessing method to obtain preprocessed transformer multi-source data, and the preprocessing method comprises data cleaning, data integration, data transformation and data specification; the data fusion module 3 is used for extracting and integrating key parameters of the transformer multi-source data output by the data preprocessing module 2 to obtain fused transformer multi-source data; and the rule reasoning module 4 combines the transformer multi-source data output by the data fusion module 3 and applies a fault diagnosis rule to carry out comprehensive fault diagnosis on the transformer fault.
A transformer self-diagnosis evaluation device based on edge calculation is disclosed, as shown in figure 1, and further comprises an adaptive adjustment module 5 and a cloud edge coordination module 6, wherein the adaptive adjustment module 5 analyzes internal state data of a transformer, and combines historical operation data of cloud equipment with the same model and a dynamic prediction model of overload capacity of the transformer to realize intelligent control of a transformer cooling system; the cloud edge coordination module 6 realizes a data interaction technology between the transformer fault diagnosis big data center and the transformer self-diagnosis and evaluation device through the Internet of things and other communication modes.
In the technical scheme, the data acquisition module 1 supports the uniform access of transformer data of different interface types and supports the existing mainstream field communication network interface; the mainstream field communication network interface comprises RS485, Ethernet, an optical port, ZigBee and WiFi; the internal state data of the transformer comprises internal temperature, pressure, vibration and local discharge signals; the external state data of the transformer comprise external visible light images, infrared images, sleeve dielectric loss and sleeve partial discharge signals; the transformer operation data comprises voltage, current information and environment temperature information during transformer operation; the transformer basic data comprises transformer standing book information and historical operation data.
In the technical scheme, the temperature, pressure, vibration and partial discharge signals in the transformer are acquired by the optical fiber sensor; the infrared and visible light cameras are used for monitoring the states of the transformer body and related parts in real time, self-sensing the appearance state of the transformer in real time, and self-sensing the abnormal operation states of the transformer, such as oil leakage of a transformer box body, damage of parts such as a sleeve and a meter, color change of silica gel of a respirator, corrosion of metal parts, invasion of foreign matters and the like; monitoring dielectric loss, capacitance and partial discharge state parameters of the sleeve by using a transformer sleeve end screen measuring sensor based on a magnetic induction principle; voltage and current information, environment temperature information, ledger information and historical operation data during transformer operation are imported from existing sensors and information systems of the transformer.
In the above technical solution, the data preprocessing method refers to some processing performed on data before main processing. In the whole process of diagnosis and evaluation, a large amount of complex, repeated and incomplete data exists in massive raw data, the execution efficiency of a diagnosis and evaluation algorithm is seriously influenced, and even deviation of a calculation result can be caused.
In the technical scheme, the data cleaning is to delete outlier data, over-range data and repeated data in the multi-source data of the transformer, which are acquired by the data acquisition module 1, and if the multi-source data of the transformer has a missing value, interpolate the missing value to obtain the cleaned multi-source data of the transformer; the data integration is to combine and uniformly store the cleaned multi-source data of the transformer to obtain the integrated multi-source data of the transformer and establish a data warehouse; the data transformation refers to the unit unification of the discharge amplitude of the integrated transformer multi-source data, the coding of the content of the defective component data item of the transformer, the normalization of the vibration stability, the vibration correlation and the energy similarity, and the transformation of the transformer multi-source data is obtained; and the data protocol is used for carrying out data compression on the vibration signals and the partial discharge signals in the transformed transformer multi-source data.
In the above technical solution, the method for extracting the key parameters of the multi-source data of the transformer by the data fusion module 3 specifically includes: firstly, extracting key contents of semi-structured data and structured data, and storing the key contents into a relational database; and secondly, extracting characteristic quantities and key data of the unstructured large-volume data for normalized storage.
In the above technical solution, the method for integrating key parameters of multi-source data of the transformer by the data fusion module 3 specifically includes: analyzing the data of the internal temperature, the internal pressure and the casing medium loss of the transformer by adopting a decision tree to obtain an evaluation result based on the internal temperature, the internal pressure and the casing medium loss, wherein the evaluation result based on the internal temperature, the internal pressure and the casing medium loss is a score between 0 and 100; analyzing vibration and partial discharge signals, external visible light images, infrared images and sleeve partial discharge signals by adopting an artificial neural network algorithm to obtain evaluation results based on the vibration and partial discharge signals, the external visible light images, the infrared images and the sleeve partial discharge signals, wherein the evaluation results based on the vibration and partial discharge signals, the external visible light images and the infrared images are the possibility that the transformer corresponds to each fault, for example, the probability of A-type faults is 80%, the probability of B-type faults is 10%, the probability of C-type faults is 10%, and finally, integrating the evaluation results of each state to obtain the evaluation result of the overall state of the transformer.
In the above technical solution, the method for the rule inference module 4 to perform comprehensive fault diagnosis on the transformer fault specifically includes: establishing a transformer fault tree and a corresponding fault reasoning rule on the basis of expert experience and a case base; on the basis of the acquired multi-source data state quantity of the transformer, a fault reasoning rule is applied to carry out comprehensive fault diagnosis, whether a fault occurs or not is judged on a node of an established fault tree, the probability of which fault occurs is also judged on the whole fault tree, and a diagnosis conclusion is obtained by combining a case library to obtain a final conclusion; if the conclusion is not clear enough, the state quantities of other transformer multi-source data which are not obtained can be input again in the data fusion stage for further diagnosis, and the rule base can be further updated by referring to the result of manual diagnosis, so that the accuracy of subsequent diagnosis is improved.
In the technical scheme, the multi-source data state quantity of the transformer comprises internal temperature, pressure, vibration, partial discharge signals, infrared signals, visible light signals, casing dielectric loss, capacitance and casing partial discharge.
In the above technical solution, the transformer fault includes an internal fault and an external fault; the internal faults comprise inter-phase short circuit, turn-to-turn short circuit, partial discharge, local overheating and insulating oil abnormity; the external faults comprise oil leakage of an oil tank or a sleeve, flashover of the sleeve and faults of a lead-out wire; the internal faults are divided into insulation faults, iron core faults, tap changer faults and winding faults according to common fault prone parts; the transformer fault tree comprises six fault modes of building a winding, an iron core, a sleeve, a cooling system, an on-load tap-changer and non-electric quantity protection.
In the technical scheme, the self-adaptive adjusting module 5 constructs a dynamic prediction model of the overload capacity of the transformer by using the historical operating data of the equipment with the same model of cloud and combining a deep learning technology through the multi-source data state quantity of the transformer, realizes the dynamic prediction function of the overload capacity of the transformer based on edge calculation and cloud data fusion, and realizes the intelligent control of a cooling system of the transformer; the intelligent control is to carry out intelligent analysis and evaluation according to the internal temperature of the transformer, the voltage and current information during operation, the environmental temperature information, the historical operation data of the transformer and the transformer ledger information, and calculate the maximum overload time of the transformer under different overload multiples, so as to automatically adjust the opening number of the coolers according to a strategy.
In the above technical solution, the overload multiple refers to a multiple of a rated load of the transformer. In some cases, the transformer may not be operating at full load, or may be operating at excess load, which may be 0.1, 0.2, …, 2 times the rated load. Under the conditions of high external environment temperature and high load multiple, the heat productivity of the transformer is high, the transformer cannot operate for a long time, and a plurality of groups of coolers need to be started as much as possible. Under the conditions of low external environment temperature and low load multiple, the transformer can run for a long time without starting a plurality of coolers. The method can calculate the longest operation time of starting coolers with different numbers of groups under the load operation of 0.1 time, 0.2 time, … time and 2 times of the transformer under different times. And adjusting according to a strategy of selecting the minimum number of coolers to be started as much as possible under the condition that the transformer can run for a long time.
In the technical scheme, after edge calculation and processing are carried out on the multi-source data state quantity of the transformer by the edge terminal, the multi-source data state quantity is uploaded to a transformer fault diagnosis big data center at the cloud end, and sharing of data is realized, wherein a relational graph of the device and the transformer fault diagnosis big data center is shown in fig. 3; the cloud end combines a large amount of data to train a method for integrating key parameters of the multi-source data of the transformer by the data fusion module 3 and a method for comprehensively diagnosing faults of the transformer by the rule reasoning module 4, so that optimized parameter settings are obtained, and the parameter settings are downloaded to a self-diagnosis and evaluation device of the transformer at the side end, so that updating and sharing of a diagnosis and evaluation algorithm are realized; the transformer self-diagnosis and evaluation device at the side end interacts with other Internet of things equipment such as inspection and test personnel, inspection robots and the like, so that the regional autonomy and the self-diagnosis efficiency of the transformer are improved, and a relation diagram of the device and other Internet of things equipment is shown in fig. 4.
A transformer self-diagnosis evaluation method based on edge calculation, as shown in fig. 2, includes the following steps:
step 1: the data acquisition module 1 is used for acquiring and communicating transformer multi-source data, wherein the transformer multi-source data comprises transformer internal state data, transformer external state data, transformer operation data and transformer basic data;
step 2: the data preprocessing module 2 is used for preprocessing the transformer multi-source data acquired by the data acquisition module 1 by adopting a data preprocessing method to obtain preprocessed transformer multi-source data, and the preprocessing method comprises data cleaning, data integration, data transformation and data specification;
and step 3: the data fusion module 3 extracts and integrates key parameters of the transformer multi-source data output by the data preprocessing module 2 to obtain fused transformer multi-source data;
and 4, step 4: and the rule reasoning module 4 combines the transformer multi-source data output by the data fusion module 3 to apply a fault diagnosis rule to carry out comprehensive fault diagnosis on the transformer fault.
Details not described in this specification are within the skill of the art that are well known to those skilled in the art.
Claims (10)
1. A transformer self-diagnosis evaluation device based on edge calculation is characterized in that: the transformer multi-source data processing system comprises a data acquisition module (1), a data preprocessing module (2), a data fusion module (3) and a rule reasoning module (4), wherein the data acquisition module (1) is used for acquiring and communicating transformer multi-source data, and the transformer multi-source data comprises transformer internal state data, transformer external state data, transformer operation data and transformer basic data; the data preprocessing module (2) adopts a data preprocessing method to preprocess the transformer multi-source data acquired by the data acquisition module (1) to obtain preprocessed transformer multi-source data, and the preprocessing method comprises data cleaning, data integration, data transformation and data specification; the data fusion module (3) is used for extracting and integrating key parameters of the transformer multi-source data output by the data preprocessing module (2) to obtain fused transformer multi-source data; and the rule reasoning module (4) is combined with the transformer multi-source data output by the data fusion module (3) to apply a fault diagnosis rule to carry out comprehensive fault diagnosis on the transformer fault.
2. The transformer self-diagnosis evaluation device based on edge calculation according to claim 1, wherein: the intelligent control system further comprises an adaptive adjustment module (5) and a cloud side coordination module (6), wherein the adaptive adjustment module (5) analyzes the internal state data of the transformer, and combines historical operation data of equipment with the same model at the cloud end and a dynamic prediction model of the overload capacity of the transformer to realize intelligent control of the transformer cooling system; the cloud side cooperation module (6) realizes a data interaction technology between the transformer fault diagnosis big data center and the transformer self-diagnosis and evaluation device through the Internet of things.
3. The transformer self-diagnosis evaluation device based on edge calculation according to claim 1, wherein: the internal state data of the transformer comprises internal temperature, pressure, vibration and local discharge signals; the external state data of the transformer comprise external visible light images, infrared images, sleeve dielectric loss and sleeve partial discharge signals; the transformer operation data comprises voltage, current information and environment temperature information during transformer operation; the transformer basic data comprises transformer standing book information and historical operation data.
The data cleaning is to delete outlier data, over-range data and repeated data in the transformer multi-source data acquired by the data acquisition module (1), and if the transformer multi-source data has a missing value, the missing value is interpolated to obtain the cleaned transformer multi-source data; the data integration is to combine and uniformly store the cleaned multi-source data of the transformer to obtain the integrated multi-source data of the transformer and establish a data warehouse; the data transformation refers to the unit unification of the discharge amplitude of the integrated transformer multi-source data, the coding of the content of the defective component data item of the transformer, the normalization of the vibration stability, the vibration correlation and the energy similarity, and the transformation of the transformer multi-source data is obtained; and the data protocol is used for carrying out data compression on the vibration signals and the partial discharge signals in the transformed transformer multi-source data.
4. The transformer self-diagnosis evaluation device based on edge calculation according to claim 1, wherein: the method for extracting the key parameters of the multi-source data of the transformer by the data fusion module (3) specifically comprises the following steps: firstly, extracting key contents of semi-structured data and structured data, and storing the key contents into a relational database; and secondly, extracting characteristic quantity and key data of the unstructured data for normalized storage.
5. The transformer self-diagnosis evaluation device based on edge calculation according to claim 1, wherein: the method for integrating the key parameters of the multi-source data of the transformer by the data fusion module (3) specifically comprises the following steps: analyzing the data of the internal temperature, the internal pressure and the casing medium loss of the transformer by adopting a decision tree to obtain an evaluation result based on the internal temperature, the internal pressure and the casing medium loss, wherein the evaluation result based on the internal temperature, the internal pressure and the casing medium loss is a score between 0 and 100; analyzing vibration and partial discharge signals, external visible light images, infrared images and sleeve partial discharge signals by adopting an artificial neural network algorithm to obtain evaluation results based on the vibration and partial discharge signals, the external visible light images, the infrared images and the sleeve partial discharge signals, wherein the evaluation results based on the vibration and partial discharge signals, the external visible light images and the infrared images are the possibility that the transformer corresponds to each fault, and finally integrating the evaluation results of each state to obtain the evaluation result of the overall state of the transformer.
6. The transformer self-diagnosis evaluation device based on edge calculation according to claim 1, wherein: the method for the rule reasoning module (4) to carry out comprehensive fault diagnosis on the transformer fault specifically comprises the following steps: establishing a transformer fault tree and a corresponding fault reasoning rule on the basis of expert experience and a case base; and performing comprehensive fault diagnosis by using a fault reasoning rule on the basis of the acquired multi-source data state quantity of the transformer, judging whether the fault occurs on a node of the established fault tree, judging which fault has high possibility on the whole fault tree, and acquiring a diagnosis conclusion by combining with a case library to obtain a final conclusion.
The multi-source data state quantity of the transformer comprises internal temperature, pressure, vibration, partial discharge signals, infrared signals, visible light signals, casing dielectric loss, capacitance and casing partial discharge.
7. The transformer self-diagnosis evaluation device based on edge calculation according to claim 1 or 6, characterized in that: the transformer faults comprise internal faults and external faults; the internal faults comprise inter-phase short circuit, turn-to-turn short circuit, partial discharge, local overheating and insulating oil abnormity; the external faults comprise oil leakage of an oil tank or a sleeve, flashover of the sleeve and faults of a lead-out wire; the internal faults are divided into insulation faults, iron core faults, tap changer faults and winding faults according to common fault prone parts; the transformer fault tree comprises six fault modes of building a winding, an iron core, a sleeve, a cooling system, an on-load tap-changer and non-electric quantity protection.
8. The transformer self-diagnosis evaluation device based on edge calculation according to claim 2, wherein: the self-adaptive adjusting module (5) constructs a dynamic prediction model of the overload capacity of the transformer by using the historical operating data of the cloud equipment with the same model and combining a deep learning technology through the multi-source data state quantity of the transformer, realizes the dynamic prediction function of the overload capacity of the transformer based on edge calculation and cloud data fusion, and realizes the intelligent control of a cooling system of the transformer; the intelligent control is to carry out intelligent analysis and evaluation according to the internal temperature of the transformer, the voltage and current information during operation, the environmental temperature information, the historical operation data of the transformer and the transformer ledger information, and calculate the maximum overload time of the transformer under different overload multiples, so as to automatically adjust the opening number of the coolers according to a strategy.
9. The transformer self-diagnosis evaluation device based on edge calculation according to claim 2, wherein: the edge end carries out edge calculation and processing on the multi-source data state quantity of the transformer and uploads the multi-source data state quantity to a transformer fault diagnosis big data center at the cloud end, and data sharing is achieved; the cloud end combines a large amount of data to train a method for integrating key parameters of the multi-source data of the transformer by the data fusion module (3) and a method for comprehensively diagnosing the transformer fault by the rule reasoning module (4), so that optimized parameter settings are obtained, and the parameter settings are downloaded to a transformer self-diagnosis and evaluation device at the side end, so that the updating and sharing of a diagnosis and evaluation algorithm are realized; the transformer self-diagnosis and evaluation device at the side end interacts with other Internet of things equipment such as inspection and test personnel and inspection robots, and the regional self-diagnosis capability and the self-diagnosis efficiency of the transformer are improved.
10. A transformer self-diagnosis evaluation method based on edge calculation is characterized in that: it comprises the following steps:
step 1: the data acquisition module (1) acquires and communicates transformer multi-source data, wherein the transformer multi-source data comprises transformer internal state data, transformer external state data, transformer operation data and transformer basic data;
step 2: the data preprocessing module (2) adopts a data preprocessing method to preprocess the transformer multi-source data acquired by the data acquisition module (1) to obtain preprocessed transformer multi-source data, and the preprocessing method comprises data cleaning, data integration, data transformation and data specification;
and step 3: the data fusion module (3) extracts and integrates key parameters of the transformer multi-source data output by the data preprocessing module (2) to obtain fused transformer multi-source data;
and 4, step 4: and the rule reasoning module (4) is combined with the transformer multi-source data output by the data fusion module (3) to apply a fault diagnosis rule to carry out comprehensive fault diagnosis on the transformer fault.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110460696.6A CN113205127A (en) | 2021-04-27 | 2021-04-27 | Transformer self-diagnosis evaluation device and method based on edge calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110460696.6A CN113205127A (en) | 2021-04-27 | 2021-04-27 | Transformer self-diagnosis evaluation device and method based on edge calculation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113205127A true CN113205127A (en) | 2021-08-03 |
Family
ID=77029289
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110460696.6A Pending CN113205127A (en) | 2021-04-27 | 2021-04-27 | Transformer self-diagnosis evaluation device and method based on edge calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113205127A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114252110A (en) * | 2022-03-02 | 2022-03-29 | 山东和兑智能科技有限公司 | Intelligent evaluation system and evaluation method for power transformation equipment |
| CN114283821A (en) * | 2021-12-24 | 2022-04-05 | 国网陕西省电力公司铜川供电公司 | Transformer detection method, system and device based on full-sonic wave train and terminal equipment |
| CN114444734A (en) * | 2022-01-27 | 2022-05-06 | 山东电工电气集团有限公司 | Transformer multi-mode fault diagnosis method based on edge calculation |
| CN114705928A (en) * | 2022-03-09 | 2022-07-05 | 天纳能源科技（上海）有限公司 | Transformer data management method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012062037A1 (en) * | 2010-11-12 | 2012-05-18 | 江西省电力科学研究院 | Traveling wave fault location method of transmission line based on electronic transformer |
| CN111650540A (en) * | 2020-06-18 | 2020-09-11 | 国网湖南省电力有限公司 | Main transformer intelligent state monitoring device and method based on multi-source data |
| CN111784026A (en) * | 2020-05-28 | 2020-10-16 | 国网信通亿力科技有限责任公司 | Cloud-side cooperative sensing-based all-dimensional physical examination system for electrical equipment of transformer substation |
| CN112564272A (en) * | 2020-10-22 | 2021-03-26 | 国网浙江省电力有限公司嘉兴供电公司 | Transformer substation health control method integrating multidimensional monitoring and fault information |
-
2021
- 2021-04-27 CN CN202110460696.6A patent/CN113205127A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012062037A1 (en) * | 2010-11-12 | 2012-05-18 | 江西省电力科学研究院 | Traveling wave fault location method of transmission line based on electronic transformer |
| CN111784026A (en) * | 2020-05-28 | 2020-10-16 | 国网信通亿力科技有限责任公司 | Cloud-side cooperative sensing-based all-dimensional physical examination system for electrical equipment of transformer substation |
| CN111650540A (en) * | 2020-06-18 | 2020-09-11 | 国网湖南省电力有限公司 | Main transformer intelligent state monitoring device and method based on multi-source data |
| CN112564272A (en) * | 2020-10-22 | 2021-03-26 | 国网浙江省电力有限公司嘉兴供电公司 | Transformer substation health control method integrating multidimensional monitoring and fault information |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114283821A (en) * | 2021-12-24 | 2022-04-05 | 国网陕西省电力公司铜川供电公司 | Transformer detection method, system and device based on full-sonic wave train and terminal equipment |
| CN114444734A (en) * | 2022-01-27 | 2022-05-06 | 山东电工电气集团有限公司 | Transformer multi-mode fault diagnosis method based on edge calculation |
| CN114252110A (en) * | 2022-03-02 | 2022-03-29 | 山东和兑智能科技有限公司 | Intelligent evaluation system and evaluation method for power transformation equipment |
| CN114705928A (en) * | 2022-03-09 | 2022-07-05 | 天纳能源科技（上海）有限公司 | Transformer data management method and system |
| CN114705928B (en) * | 2022-03-09 | 2023-02-10 | 天纳能源科技（上海）有限公司 | Transformer data management method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113205127A (en) | Transformer self-diagnosis evaluation device and method based on edge calculation | |
| CN112910094B (en) | Remote automatic transformer substation inspection system and method based on ubiquitous power Internet of things | |
| CN111650451B (en) | Converter transformer fault reason identification method and system | |
| CN101149416B (en) | Power cable insulation state monitoring and life span management system | |
| CN116069079B (en) | Intelligent heat dissipation control method and system for intelligent switch cabinet | |
| CN111143447B (en) | Dynamic monitoring early warning decision system and method for weak links of power grid | |
| CN212207592U (en) | Artificial intelligence high voltage circuit breaker on-line monitoring device | |
| CN113656938A (en) | Monitoring method, control device and storage medium for distribution network transformer | |
| CN111898092A (en) | Cable running state evaluation decision analysis method and system | |
| CN113537415A (en) | Convertor station inspection method and device based on multi-information fusion and computer equipment | |
| CN116207845B (en) | Automatic monitoring method and system for protecting power equipment | |
| CN115248402A (en) | Oil immersed transformer on-line monitoring system and method | |
| CN116800199A (en) | Distributed photovoltaic operation electric energy quality monitoring and analyzing method | |
| CN111830438A (en) | Transformer fault detection method and transformer | |
| CN117630543A (en) | Transformer fault state supervision method and system based on Internet of things data | |
| CN112329821A (en) | Intelligent diagnosis system for power transformer and diagnosis method based on decision tree classification | |
| CN116596301A (en) | Cable multi-state variable evaluation model design method and device based on zero-order learning method | |
| CN114720809A (en) | Vehicle-mounted bidirectional charger test system and control method thereof | |
| CN114462692A (en) | Power grid old and old equipment technical improvement strategy optimization and adjustment method | |
| Chen et al. | A transformer vibration amplitude prediction method via fusion of multi-signals | |
| Guo et al. | Construction of Power Equipment Running Status Monitoring System Based on Infrared Temperature Measurement Technology and Big Data Algorithm | |
| CN117791562A (en) | Substation equipment state management method and device, management server and storage medium | |
| Li et al. | On-Line Monitoring and Fault Diagnosis of Box Transformer Substation Based on VPRS-RBFNN | |
| Gao et al. | Construction of intelligent sensing and fault early warning system of large power transformer based on cloud edge cooperation | |
| Zhou et al. | An intelligent monitoring and diagnosis system for 330kV oil-immersed power 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210803 |