CN117330910A - Intelligent analysis and diagnosis system for transformer substation oil products based on big data - Google Patents
Intelligent analysis and diagnosis system for transformer substation oil products based on big data Download PDFInfo
- Publication number
- CN117330910A CN117330910A CN202311240387.3A CN202311240387A CN117330910A CN 117330910 A CN117330910 A CN 117330910A CN 202311240387 A CN202311240387 A CN 202311240387A CN 117330910 A CN117330910 A CN 117330910A
- Authority
- CN
- China
- Prior art keywords
- data
- oil
- transformer substation
- intelligent
- detection
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 41
- 238000001514 detection method Methods 0.000 claims abstract description 91
- 238000000034 method Methods 0.000 claims abstract description 22
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 21
- 238000012549 training Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 17
- 239000007789 gas Substances 0.000 claims description 71
- HSFWRNGVRCDJHI-UHFFFAOYSA-N alpha-acetylene Natural products C#C HSFWRNGVRCDJHI-UHFFFAOYSA-N 0.000 claims description 11
- 125000002534 ethynyl group Chemical group [H]C#C* 0.000 claims description 11
- 239000001257 hydrogen Substances 0.000 claims description 11
- 229910052739 hydrogen Inorganic materials 0.000 claims description 11
- 230000004927 fusion Effects 0.000 claims description 10
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 abstract description 11
- 238000007689 inspection Methods 0.000 description 14
- 238000012544 monitoring process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 2
- 238000007499 fusion processing Methods 0.000 description 2
- 150000002431 hydrogen Chemical class 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000004090 dissolution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1227—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials
- G01R31/1263—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation
- G01R31/1281—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation of liquids or gases
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/62—Testing of transformers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Power Engineering (AREA)
- Housings And Mounting Of Transformers (AREA)
Abstract
The application provides a transformer substation oil intelligent analysis diagnosis system based on big data, the system that shows includes: the detection module is used for detecting the concentration of dissolved gas in the insulating oil product and obtaining detection data; the sample module is used for calculating the speed increase of the gas concentration during each data acquisition, and correlating the speed increase with the service time of the insulating oil in the transformer substation to obtain sample data; the training module is used for training a preset convolutional neural network according to the sample data to obtain an oil intelligent analysis model; the diagnosis module is used for collecting the detection data of the oil products in the transformer substation in real time, inputting the detection data into the intelligent oil product analysis model, and obtaining an intelligent oil product analysis diagnosis result according to the detection data and the service time of the insulating oil. Through big data processing, the method can accurately diagnose the oil product change into a future trend, and has higher application value for oil product diagnosis and analysis.
Description
Technical Field
The application claims a transformer substation oil product diagnosis technology, especially relates to a transformer substation oil product intelligent analysis diagnosis system based on big data. The application also relates to an intelligent analysis and diagnosis method for the transformer substation oil based on big data.
Background
In a transformer substation, insulating oil plays a vital role in the insulativity of the whole transformer substation, so that the analysis and detection of the insulating state of the insulating oil are very important to timely obtain the oil parameters of the insulating oil.
The oil product change of the insulating oil in the transformer substation is mainly caused by gas dissolution, and the gas is regulated in the 'transmission and transformation equipment state overhaul test procedure', wherein the analysis qualification range of the dissolved gas in the insulating oil is as follows: acetylene is less than or equal to 5uL/L; hydrogen is less than or equal to 150uL/L, and if the measured value exceeds the standard, the fault of the insulating state of the transformer can be predicted.
In the prior art, the detection of the state of dissolved gas in insulating oil mainly comprises:
1. the oil sample is obtained from the oil sample valve reserved on the transformer body in a manual mode, the oil sample valve is tested and detected in a laboratory by using a chromatograph, the quality of the insulating oil is monitored on line, and the method plays a great role in the detection of the state of power grid equipment.
2. And detecting the monitoring equipment in an on-line monitoring mode in real time.
The problems with the first approach include: test data of the running state of dissolved gas in the transformer insulating oil cannot be obtained in time.
The second method has the problems that the monitoring equipment in an on-line monitoring mode is complex in construction and installation in aspects of remote communication, equipment power supply and the like, the function of remote monitoring can be realized only by arranging corresponding cables, and the daily maintenance workload is large.
Disclosure of Invention
In order to solve the problems in the prior art, the application provides an intelligent analysis and diagnosis system for transformer substation oil products based on big data. The application also relates to an intelligent analysis and diagnosis method for the transformer substation oil based on big data.
The application provides a transformer substation oil intelligent analysis diagnostic system based on big data, include:
the detection module is used for detecting the concentration of dissolved gas in the insulating oil product to obtain detection data, wherein the gas at least comprises acetylene and hydrogen;
the sample module is used for arranging the detection data according to a time sequence, calculating the speed increase of the gas concentration during each data acquisition, and correlating the speed increase with the service time of the insulating oil in the transformer substation to obtain sample data;
the training module is used for training a preset convolutional neural network according to the sample data to obtain an oil intelligent analysis model;
the diagnosis module is used for collecting the detection data of the oil products in the transformer substation in real time, inputting the detection data into the intelligent oil product analysis model, and obtaining an intelligent oil product analysis diagnosis result according to the detection data and the service time of the insulating oil.
Optionally, the acquisition module includes:
the timing unit is used for setting the data acquisition time according to a preset mode and comprises an acquisition time interval and an acquisition interval.
Optionally, the sample module includes:
and the historical data unit is used for storing historical data corresponding to the detection data.
Optionally, the training module includes:
the preprocessing unit is used for processing the data formats and unifying the formats of the data with different formats.
Optionally, the convolutional neural network includes:
the first convolution layer, the second convolution layer, the third convolution layer and the fusion layer.
The application also provides a substation oil intelligent analysis and diagnosis method based on big data, which comprises the following steps:
detecting the concentration of dissolved gas in an insulating oil product to obtain detection data, wherein the gas at least comprises acetylene and hydrogen;
arranging the detection data according to a time sequence, calculating the speed increase of the gas concentration during each data acquisition, and correlating the speed increase with the service time of the insulating oil in the transformer substation to obtain sample data;
training a preset convolutional neural network according to the sample data to obtain an oil intelligent analysis model;
and acquiring the detection data of the oil product in the transformer substation in real time, inputting the detection data into the intelligent oil product analysis model, and obtaining an intelligent oil product analysis and diagnosis result by the intelligent oil product analysis model according to the detection data and the service time of the insulating oil.
Optionally, the detecting the concentration of the dissolved gas in the insulating oil product includes:
and setting the data acquisition time according to a preset mode, wherein the data acquisition time comprises an acquisition time interval and an acquisition interval.
Optionally, the method comprises the following steps:
and storing historical data corresponding to the detection data.
Optionally, the arranging the detection data in time sequence includes:
the data format is processed, and the data with different formats are subjected to format unification.
Optionally, the convolutional neural network includes:
the first convolution layer, the second convolution layer, the third convolution layer and the fusion layer.
Compared with the prior art, the application has the advantages that:
the application provides a transformer substation oil intelligent analysis diagnostic system based on big data, include: the detection module is used for detecting the concentration of dissolved gas in the insulating oil product to obtain detection data, wherein the gas at least comprises acetylene and hydrogen; the sample module is used for arranging the detection data according to a time sequence, calculating the speed increase of the gas concentration during each data acquisition, and correlating the speed increase with the service time of the insulating oil in the transformer substation to obtain sample data; the training module is used for training a preset convolutional neural network according to the sample data to obtain an oil intelligent analysis model; the diagnosis module is used for collecting the detection data of the oil products in the transformer substation in real time, inputting the detection data into the intelligent oil product analysis model, and obtaining an intelligent oil product analysis diagnosis result according to the detection data and the service time of the insulating oil. Through big data processing, the method can accurately diagnose the oil product change into a future trend, and has higher application value for oil product diagnosis and analysis.
Drawings
Fig. 1 is a schematic diagram of a substation oil intelligent analysis and diagnosis system based on big data in the application.
Fig. 2 is a model training flow chart in the present application.
Fig. 3 is a flowchart of a substation oil intelligent analysis and diagnosis method based on big data in the application.
Detailed Description
The following are examples of specific implementation provided for the purpose of illustrating the technical solutions to be protected in this application in detail, but this application may also be implemented in other ways than described herein, and one skilled in the art may implement this application by using different technical means under the guidance of the conception of this application, so this application is not limited by the following specific embodiments.
The application provides a transformer substation oil intelligent analysis diagnostic system based on big data, include: the detection module is used for detecting the concentration of dissolved gas in the insulating oil product to obtain detection data, wherein the gas at least comprises acetylene and hydrogen; the sample module is used for arranging the detection data according to a time sequence, calculating the speed increase of the gas concentration during each data acquisition, and correlating the speed increase with the service time of the insulating oil in the transformer substation to obtain sample data; the training module is used for training a preset convolutional neural network according to the sample data to obtain an oil intelligent analysis model; the diagnosis module is used for collecting the detection data of the oil products in the transformer substation in real time, inputting the detection data into the intelligent oil product analysis model, and obtaining an intelligent oil product analysis diagnosis result according to the detection data and the service time of the insulating oil. Through big data processing, the method can accurately diagnose the oil product change into a future trend, and has higher application value for oil product diagnosis and analysis.
Fig. 1 is a schematic diagram of a substation oil intelligent analysis and diagnosis system based on big data in the application.
Referring to fig. 1, a detection module 101 is configured to detect a concentration of a gas dissolved in an insulating oil product to obtain detection data, where the gas at least includes acetylene and hydrogen;
the detecting module at least comprises a setting unit, a timing unit, a detecting unit and a data processing unit, wherein the setting unit is used for setting the mode of detecting data by the detecting module, namely setting data formats, detecting frequency and the like, the timing unit is used for setting the time of data acquisition according to a preset mode, the timing unit comprises an acquisition time interval, the acquisition time interval controls the opening and closing of the detecting unit, the detecting unit is used for detecting the gas concentration in insulating oil, and the data processing unit is used for processing the detecting signals of the detecting unit to generate concentration values.
The oil product of the insulating oil is related to the concentration of the gas in the insulating oil, and the gas mainly comprises acetylene and hydrogen, but the gas can be set to detect other gases, and the change can be set to different gases according to actual conditions.
The detection specifically means detecting the concentration of the gas in the insulating oil, and when the detection unit sends out a detection signal according to the concentration of the gas in the insulating oil, the data processing unit generates detection data with a gas concentration value according to the detection signal and sends out the detection data.
Referring to fig. 1, a sample module 102 is configured to arrange the detection data in time sequence, calculate a speed increase of the gas concentration during each data acquisition, and correlate the speed increase with a usage time of the insulating oil in the transformer substation to obtain sample data;
after the detection data is sent to the sample module, the detection data is converted into sample data, and specifically, the sample data further comprises historical data. In another real-time manner, the sample data may be generated entirely from the historical data.
Specifically, the sample module includes a history data unit, where the history data unit is used to store history data corresponding to the detection data.
After the sample module acquires the inspection data, the gas concentration label in the inspection data searches the data of the corresponding gas concentration label from the historical data unit, and the data is called out and is generated together with the inspection data.
In this application, the gas concentration tag is mainly a digital tag marked by the data processing unit according to the type of the inspection unit, and the tag is used for marking the type of the inspection data, such as the gas type, etc.
The sample data also includes time data, which is a time point when each of the inspection units generates a detection signal.
Next, the data are ordered in a time sequence and a time concentration curve is generated from the time versus concentration, and derivatives, i.e. the rate of concentration, at each of the time points on the curve.
And respectively reading the rate and the time corresponding to the rate for association, and taking the rate, the time and the association relationship as sample data.
Referring to fig. 1, a training module 103 is configured to train a preset convolutional neural network according to the sample data to obtain an oil intelligent analysis model;
the system at least further comprises a preprocessing module, wherein the preprocessing module is used for checking and unifying formats of the sample data.
After the unification of the formats is completed, the sample data are input into the convolutional neural network to train the intelligent analysis model of the oil product.
The convolutional neural network comprises a first convolutional layer, a second convolutional layer, a third convolutional layer and a fusion layer, wherein the first convolutional layer, the second convolutional layer and the third convolutional layer respectively process data three times in the same mode, and then the processed data are input into the fusion layer to generate result data.
Fig. 2 is a model training flow chart in the present application.
Referring to fig. 2, the convolution process of S201 data is shown.
The convolution processing of the data refers to transmitting the data to the convolution layers (including a first convolution layer, a second convolution layer and a third convolution layer) for data screening.
Specifically, after the sample data of the sample group is input to the first convolution layer, the layer is firstly divided into two sample groups according to the time of the sample data, including a sample group of the detection data sample combination historical data, and each sample group refers to a number of oil product change periods.
And respectively generating graphs based on the speed and time based on the sample group, and judging the fluctuation degree in the graphs.
The determination formula of the fluctuation degree can be expressed as follows:
wherein p is the waviness, said M i At the rate of the ith time point, the N i Is the ith time point, the N max -N min Refers to the detection time length, M max -M min Refers to the degree of rate change, M 1 Refers to the rate of increase of the gas concentration of the new insulating oil.
After the first convolution layer obtains the p, comparing the p with a preset threshold value, and when the p is larger than the preset threshold value, the rate at the time point is a first pseudo rate, and removing the M i 。
The second convolution layer removes the second pseudo-rate at a different predetermined threshold and the third convolution layer removes the third pseudo-rate.
S202, fusion processing of data.
And inputting the curve graph with the pseudo rate removed into a fusion layer, and fusing the curve graph of the detection data with the curve graph of the historical data to generate result data.
And carrying out parameter adjustment on the convolutional neural network model according to the result data to finally obtain the result data which accords with the expectation, and completing the training of the convolutional neural network.
Referring to fig. 1, a diagnostic module 104 is configured to collect the detection data of the oil product in the transformer substation in real time, input the detection data to the intelligent oil product analysis model, and obtain an intelligent oil product analysis and diagnosis result according to the detection data and the service time of the insulating oil.
At this time, the detection module acquires the inspection data in real time, and the result data obtained by the detection data is a curve of the rate of increase of the gas concentration of the oil product with time.
The gas concentration value in the insulating oil is detected, and the increasing speed of the gas in the insulating oil can be predicted according to the working time of the insulating oil during detection, so that the time of the gas concentration critical value can be obtained by accurately judging the time variation diagram of the gas concentration in the insulating oil.
The application also provides an intelligent analysis and diagnosis method for the transformer substation oil product based on the big data, and the method predicts the change of the gas content in the oil gas through the big data, so that the oil product can be accurately estimated.
Fig. 3 is a flowchart of a substation oil intelligent analysis and diagnosis method based on big data in the application.
Referring to fig. 3, S301 detects the concentration of dissolved gas in the insulating oil product to obtain detection data, where the gas at least includes acetylene and hydrogen;
the detecting module at least comprises a setting unit, a timing unit, a detecting unit and a data processing unit, wherein the setting unit is used for setting the mode of detecting data by the detecting module, namely setting data formats, detecting frequency and the like, the timing unit is used for setting the time of data acquisition according to a preset mode, the timing unit comprises an acquisition time interval, the acquisition time interval controls the opening and closing of the detecting unit, the detecting unit is used for detecting the gas concentration in insulating oil, and the data processing unit is used for processing the detecting signals of the detecting unit to generate concentration values.
The oil product of the insulating oil is related to the concentration of the gas in the insulating oil, and the gas mainly comprises acetylene and hydrogen, but the gas can be set to detect other gases, and the change can be set to different gases according to actual conditions.
The detection specifically means detecting the concentration of the gas in the insulating oil, and when the detection unit sends out a detection signal according to the concentration of the gas in the insulating oil, the data processing unit generates detection data with a gas concentration value according to the detection signal and sends out the detection data.
Referring to fig. 3, S302 arranges the detection data in time sequence, calculates the acceleration of the gas concentration during each data acquisition, and correlates the acceleration with the usage time of the insulating oil in the transformer substation to obtain sample data;
after the detection data is sent to the sample module, the detection data is converted into sample data, and specifically, the sample data further comprises historical data. In another real-time manner, the sample data may be generated entirely from the historical data.
Specifically, the sample module includes a history data unit, where the history data unit is used to store history data corresponding to the detection data.
After the sample module acquires the inspection data, the gas concentration label in the inspection data searches the data of the corresponding gas concentration label from the historical data unit, and the data is called out and is generated together with the inspection data.
In this application, the gas concentration tag is mainly a digital tag marked by the data processing unit according to the type of the inspection unit, and the tag is used for marking the type of the inspection data, such as the gas type, etc.
The sample data also includes time data, which is a time point when each of the inspection units generates a detection signal.
Next, the data are ordered in a time sequence and a time concentration curve is generated from the time versus concentration, and derivatives, i.e. the rate of concentration, at each of the time points on the curve.
And respectively reading the rate and the time corresponding to the rate for association, and taking the rate, the time and the association relationship as sample data.
Referring to fig. 3, S303 trains a preset convolutional neural network according to the sample data to obtain an oil intelligent analysis model;
the system at least further comprises a preprocessing module, wherein the preprocessing module is used for checking and unifying formats of the sample data.
After the unification of the formats is completed, the sample data are input into the convolutional neural network to train the intelligent analysis model of the oil product.
The convolutional neural network comprises a first convolutional layer, a second convolutional layer, a third convolutional layer and a fusion layer, wherein the first convolutional layer, the second convolutional layer and the third convolutional layer respectively process data three times in the same mode, and then the processed data are input into the fusion layer to generate result data.
Fig. 2 is a model training flow chart in the present application.
Referring to fig. 2, the convolution process of S201 data is shown.
The convolution processing of the data refers to transmitting the data to the convolution layers (including a first convolution layer, a second convolution layer and a third convolution layer) for data screening.
Specifically, after the sample data of the sample group is input to the first convolution layer, the layer is firstly divided into two sample groups according to the time of the sample data, including a sample group of the detection data sample combination historical data, and each sample group refers to a number of oil product change periods.
And respectively generating graphs based on the speed and time based on the sample group, and judging the fluctuation degree in the graphs.
The determination formula of the fluctuation degree can be expressed as follows:
wherein p is the waviness, said M i At the rate of the ith time point, the N i Is the ith time point, the N max -N min Refers to the detection time length, M max -M min Refers to the degree of rate change, M 1 Refers to the rate of increase of the gas concentration of the new insulating oil.
After the first convolution layer obtains the p, comparing the p with a preset threshold value, and when the p is larger than the preset threshold value, the rate at the time point is a first pseudo rate, and removing the M i 。
The second convolution layer removes the second pseudo-rate at a different predetermined threshold and the third convolution layer removes the third pseudo-rate.
S202, fusion processing of data.
And inputting the curve graph with the pseudo rate removed into a fusion layer, and fusing the curve graph of the detection data with the curve graph of the historical data to generate result data.
And carrying out parameter adjustment on the convolutional neural network model according to the result data to finally obtain the result data which accords with the expectation, and completing the training of the convolutional neural network.
Referring to fig. 3, S304 acquires the detection data of the oil product in the transformer substation in real time, inputs the detection data into the intelligent oil product analysis model, and obtains an intelligent oil product analysis and diagnosis result according to the detection data and the service time of the insulating oil.
At this time, the detection module acquires the inspection data in real time, and the result data obtained by the detection data is a curve of the rate of increase of the gas concentration of the oil product with time.
The gas concentration value in the insulating oil is detected, and the increasing speed of the gas in the insulating oil can be predicted according to the working time of the insulating oil during detection, so that the time of the gas concentration critical value can be obtained by accurately judging the time variation diagram of the gas concentration in the insulating oil.
While embodiments of the present invention have been shown and described in the foregoing of this application, it will be appreciated by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the invention, the scope of which is defined by the claims and their equivalents.
Claims (10)
1. Intelligent analysis and diagnosis system of transformer substation oil based on big data, characterized by comprising:
the detection module is used for detecting the concentration of dissolved gas in the insulating oil product to obtain detection data, wherein the gas at least comprises acetylene and hydrogen;
the sample module is used for arranging the detection data according to a time sequence, calculating the speed increase of the gas concentration during each data acquisition, and correlating the speed increase with the service time of the insulating oil in the transformer substation to obtain sample data;
the training module is used for training a preset convolutional neural network according to the sample data to obtain an oil intelligent analysis model;
the diagnosis module is used for collecting the detection data of the oil products in the transformer substation in real time, inputting the detection data into the intelligent oil product analysis model, and obtaining an intelligent oil product analysis diagnosis result according to the detection data and the service time of the insulating oil.
2. The intelligent analysis and diagnosis system for transformer substation oil based on big data according to claim 1, wherein the acquisition module comprises:
the timing unit is used for setting the data acquisition time according to a preset mode and comprises an acquisition time interval and an acquisition interval.
3. The intelligent analysis and diagnosis system for transformer substation oil based on big data according to claim 1, wherein the sample module comprises:
and the historical data unit is used for storing historical data corresponding to the detection data.
4. The intelligent analysis and diagnosis system for transformer substation oil based on big data according to claim 1, wherein the training module comprises:
the preprocessing unit is used for processing the data formats and unifying the formats of the data with different formats.
5. The intelligent analysis and diagnosis system for transformer substation oil based on big data according to claim 1, wherein the convolutional neural network comprises:
the first convolution layer, the second convolution layer, the third convolution layer and the fusion layer.
6. The intelligent analysis and diagnosis method for the transformer substation oil based on the big data is characterized by comprising the following steps of:
detecting the concentration of dissolved gas in an insulating oil product to obtain detection data, wherein the gas at least comprises acetylene and hydrogen;
arranging the detection data according to a time sequence, calculating the speed increase of the gas concentration during each data acquisition, and correlating the speed increase with the service time of the insulating oil in the transformer substation to obtain sample data;
training a preset convolutional neural network according to the sample data to obtain an oil intelligent analysis model;
and acquiring the detection data of the oil product in the transformer substation in real time, inputting the detection data into the intelligent oil product analysis model, and obtaining an intelligent oil product analysis and diagnosis result by the intelligent oil product analysis model according to the detection data and the service time of the insulating oil.
7. The intelligent analysis and diagnosis method for transformer substation oil based on big data according to claim 6, wherein the detecting the dissolved gas concentration in the insulating oil comprises:
and setting the data acquisition time according to a preset mode, wherein the data acquisition time comprises an acquisition time interval and an acquisition interval.
8. The intelligent analysis and diagnosis method for the transformer substation oil based on big data according to claim 6, comprising the following steps:
and storing historical data corresponding to the detection data.
9. The intelligent analysis and diagnosis method for the transformer substation oil based on big data according to claim 6, wherein the arranging the detection data in time sequence comprises:
the data format is processed, and the data with different formats are subjected to format unification.
10. The intelligent analysis and diagnosis method for transformer substation oil based on big data according to claim 6, wherein the convolutional neural network comprises:
the first convolution layer, the second convolution layer, the third convolution layer and the fusion layer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311240387.3A CN117330910A (en) | 2023-09-25 | 2023-09-25 | Intelligent analysis and diagnosis system for transformer substation oil products based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311240387.3A CN117330910A (en) | 2023-09-25 | 2023-09-25 | Intelligent analysis and diagnosis system for transformer substation oil products based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117330910A true CN117330910A (en) | 2024-01-02 |
Family
ID=89282223
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311240387.3A Pending CN117330910A (en) | 2023-09-25 | 2023-09-25 | Intelligent analysis and diagnosis system for transformer substation oil products based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117330910A (en) |
-
2023
- 2023-09-25 CN CN202311240387.3A patent/CN117330910A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110647133B (en) | Rail transit equipment state detection maintenance method and system | |
| CN110672332B (en) | Gas turbine fault early warning system based on SARIMA model | |
| CN115566804B (en) | Electric power monitoring system based on distributed optical fiber sensing technology | |
| CN104390657A (en) | Generator set operating parameter measuring sensor fault diagnosis method and system | |
| CN112173636B (en) | Method for detecting faults of belt conveyor carrier roller by inspection robot | |
| CN111679176A (en) | Circuit fault monitoring system for power saving | |
| CN116523506A (en) | Circuit fault prediction analysis system based on digital twin transformer station technology | |
| CN112379621A (en) | Power station house environment monitoring system and method | |
| CN118130984B (en) | Cable partial discharge fault real-time monitoring method based on data driving | |
| CN104615121A (en) | Method and system for train fault diagnosis | |
| CN203037628U (en) | Gas chromatography on-line monitoring device for insulating oil of operating transformer | |
| CN117368644A (en) | Sensor cable detection method | |
| CN116388383A (en) | Electric power IT equipment monitored control system based on intelligence fortune dimension | |
| CN116029699A (en) | Power information system based on data twinning and operation and maintenance method | |
| CN109285331B (en) | Power cable temperature early warning system based on data analysis and temperature prediction | |
| CN111556111A (en) | Pipe gallery equipment fault remote diagnosis system based on Internet of things | |
| CN113374582B (en) | Device and method for evaluating running state of gas turbine | |
| WO2022001289A1 (en) | Power distribution network partial discharge ultrasonic test method and system | |
| CN118038295A (en) | Real-time online identification system for defects of power transmission line | |
| CN117330910A (en) | Intelligent analysis and diagnosis system for transformer substation oil products based on big data | |
| CN117538240A (en) | Magnetic material equipment pipeline corrosion on-line monitoring system | |
| CN107274112B (en) | Diagnostic algorithm model for improving dissolved gas in oil | |
| CN115034408A (en) | Internet of things maintenance prediction system for key equipment in seamless steel tube production | |
| CN205941719U (en) | Removal operation management end that power equipment detected | |
| CN114925867A (en) | Internet of things maintenance prediction system for key equipment in seamless steel tube production |
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 |