CN117330137B - Intelligent identification and fault detection method and system for transformer inspection image - Google Patents
Intelligent identification and fault detection method and system for transformer inspection image Download PDFInfo
- Publication number
- CN117330137B CN117330137B CN202311631212.5A CN202311631212A CN117330137B CN 117330137 B CN117330137 B CN 117330137B CN 202311631212 A CN202311631212 A CN 202311631212A CN 117330137 B CN117330137 B CN 117330137B
- Authority
- CN
- China
- Prior art keywords
- transformer
- data
- fault
- value
- equal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 30
- 238000001514 detection method Methods 0.000 title claims description 85
- 238000000034 method Methods 0.000 claims abstract description 41
- 238000012544 monitoring process Methods 0.000 claims description 137
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 51
- 230000008859 change Effects 0.000 claims description 33
- 238000001035 drying Methods 0.000 claims description 21
- 238000012937 correction Methods 0.000 claims description 20
- 238000004458 analytical method Methods 0.000 claims description 13
- 238000012423 maintenance Methods 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 238000011282 treatment Methods 0.000 claims description 7
- 238000007405 data analysis Methods 0.000 claims description 6
- 238000011418 maintenance treatment Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 description 8
- 238000001816 cooling Methods 0.000 description 4
- 230000000630 rising effect Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Testing Electric Properties And Detecting Electric Faults (AREA)
Abstract
The invention relates to the technical field of transformers, and discloses a method and a system for intelligently identifying and detecting faults of a transformer inspection image.
Description
Technical Field
The invention relates to the technical field of transformers, in particular to a method and a system for intelligent identification and fault detection of a transformer inspection image.
Background
A transformer is an electrical device for changing an alternating voltage. It is possible to convert a voltage from one voltage level to another without changing the magnitude of the current (in an ideal case). Transformers are commonly used in power transmission, electronics, and various applications to meet different voltage requirements.
The transformer generates heat during operation, which causes an increase in internal temperature. When the temperature starts to drop after the transformer stops running, moisture in the surrounding air can condense into water in the cooling process so as to remain on the transformer, and the long-term accumulated condensed water easily causes problems of corrosion, insulation performance drop and the like of the transformer, so that the transformer needs to be monitored periodically.
Traditional carry out comdenstion water to the transformer and detect, generally adopt the mode that temperature detection humidification degree detected to go on, through carrying out a lot of to the temperature variation and the humidity variation of transformer and detect, through the size of its difference, judge whether its inside has the comdenstion water, but the mode external disturbance that this kind of combination of temperature humidification degree detected is great, because the transformer temperature variation rate is faster, produced temperature is higher, monitors from the change of temperature and humidity value alone, causes great detection misarea easily to influence maintenance work.
Disclosure of Invention
The invention provides an intelligent identification and fault detection method for a transformer inspection image, which has the beneficial effects that condensed water detection is carried out by combining a texture value, a humidity value and a sound wave value, and solves the problems that the external interference of the combined detection mode of temperature and humidity mentioned in the background art is large, the temperature change rate of a transformer is high, the generated temperature is high, and a large detection error area is easily caused by monitoring the change of the temperature and the humidity value.
The invention provides the following technical scheme: a method for intelligent identification and fault detection of a transformer inspection image comprises the following specific steps:
s1, determining the position of a target transformer, and deploying acquisition equipment around the target transformer by adopting a uniform interval distribution method; establishing a three-dimensional model, simulating the position of the transformer, and obviously marking the geographic coordinates of the transformer and the coordinates of the acquisition equipment in the three-dimensional model;
s2, acquiring initial monitoring data and secondary monitoring data of the acquisition equipment, respectively preprocessing the initial monitoring data and the secondary monitoring data, and respectively establishing a first data set and a second data set based on the processed initial monitoring data and the processed secondary monitoring data;
s3, establishing a digital twin model, and respectively analyzing a first data set and a second data set, wherein the first data set comprises a first texture value WL1, a first humidity value SD1 and a first sound wave value SB1, and the second data set comprises a second texture value WL2, a second humidity value SD2 and a second sound wave value SB2;
s4, comparing the first data set with the second data set through a digital twin model, and further respectively obtaining a texture difference coefficient WLX, a humidity difference coefficient SDX and an acoustic wave difference coefficient SBC;
s5, inputting a texture difference coefficient WLX, a humidity difference coefficient SDX and an acoustic wave difference coefficient SBC into a digital twin model, and calculating to obtain a fault resolution coefficient GZX through the model, wherein the fault resolution coefficient GZX is obtained through the calculation of the following formula:
GZX＝(WLX*a1+SDX*a2+SBC*a3/a1+a2+a3)+A；
wherein: WLX is a texture difference coefficient, SDX is a humidity difference coefficient, SBC is an acoustic wave difference coefficient, a1, a2 and a3 are weight values, a1 is more than or equal to 0.25 and less than or equal to 0.35,0.45, a2 is more than or equal to 0.55,0.4 and less than or equal to a3 is more than or equal to 0.45, a1+a2+a3 is more than or equal to 1.1, A is a correction constant, and the values of a1, a2, a3 and A are adjusted and set by a customer or are generated by fitting an analysis function;
s6, calculating and obtaining a fault resolution coefficient GZX according to the step S5, comparing the obtained fault resolution coefficient GZX with a fault threshold GYZ, if the fault resolution coefficient GZX is larger than or equal to the fault threshold GYZ, representing that the transformer breaks down, and if the fault resolution coefficient GZX is smaller than the fault threshold GYZ, representing that the transformer does not break down.
As an alternative scheme of the intelligent identification and fault detection method for the transformer inspection image, the invention comprises the following steps: the collection devices are divided into three categories: the intelligent humidity sensor comprises a plurality of infrared cameras, a plurality of humidity sensors and a plurality of sound wave sensors, wherein various acquisition devices are not in the same circuit with a transformer;
the infrared camera is used for detecting the change condition of the texture value when the temperature of the outer shell of the transformer changes, wherein the detection of the outer shell of the transformer before the transformer is started is recorded as initial detection, and the detection of the outer shell of the transformer after the transformer is started is recorded as secondary detection;
the humidity sensor is used for detecting the humidity value change condition of the outer transformer shell, wherein the detection of the outer transformer shell before the transformer is started is recorded as initial detection, and the detection of the outer transformer shell after the transformer is started is recorded as secondary detection;
the sound wave sensor is used for detecting the sound wave value change condition of the outer transformer shell, wherein the detection of the outer transformer shell before the transformer is started is recorded as initial detection, and the detection of the outer transformer shell after the transformer is started is recorded as secondary detection.
As an alternative scheme of the intelligent identification and fault detection method for the transformer inspection image, the invention comprises the following steps: the infrared cameras are uniformly distributed around the transformer, so that the monitoring range of the cameras covers the shell of the transformer;
meanwhile, the parallel interval between the infrared cameras is less than or equal to 0.15 meter, and the vertical interval is less than or equal to 0.25 meter;
the transformer is continuously monitored by the plurality of infrared cameras for a long time, so that initial monitoring data and secondary monitoring data of the temperature rise of the transformer shell body are respectively obtained, namely a first texture value WL1 under initial monitoring and a second texture value WL2 under secondary monitoring.
As an alternative scheme of the intelligent identification and fault detection method for the transformer inspection image, the invention comprises the following steps: the texture difference coefficient WLX is obtained by combining and calculating the first texture data WL1 and the second texture data WL2, and the specific calculation formula is as follows:
WLX＝(WL1-WL2/WL1)+B；
wherein: WL1 is the first texture data, WL2 is the second texture data, B is the correction constant, and the value of B is set by the customer adjustment or generated by an analytical function fit.
As an alternative scheme of the intelligent identification and fault detection method for the transformer inspection image, the invention comprises the following steps: the humidity sensors are uniformly arranged at the top of the transformer outer shell, so that the monitoring range of the humidity sensors covers the top of the transformer;
meanwhile, the horizontal distance between the humidity sensors is less than or equal to 0.1 meter, and the distance between the humidity sensors and the transformer is less than or equal to 0.15 meter;
the transformer is continuously monitored by the humidity sensors for a long time, so that the data of initial monitoring of the air humidity at the upper end of the transformer shell body and the data of secondary monitoring of the transformer are respectively obtained, namely a first humidity value SD1 under initial monitoring and a second humidity value SD2 under secondary monitoring.
As an alternative scheme of the intelligent identification and fault detection method for the transformer inspection image, the invention comprises the following steps: the humidity difference coefficient SDX is obtained through calculation according to the following formula:
SDX＝((SD1-SD2)/SD1)+C；
wherein: SD1 is a first humidity value, SD2 is a second humidity value, C is a correction constant, and the value of C is set by a customer adjustment or generated by an analytical function fit.
As an alternative scheme of the intelligent identification and fault detection method for the transformer inspection image, the invention comprises the following steps: the sound wave sensors are symmetrically arranged at the top and the bottom of the transformer, so that the monitoring range of the sound wave sensors covers the transformer, and the sound change inside the transformer is monitored;
the plurality of acoustic wave sensors are used for continuously monitoring the transformer for a long time, so that data of the initial monitoring of the transformer and data of the secondary monitoring of the transformer of the acoustic wave change in the outer shell of the transformer are respectively obtained, namely a first acoustic wave value SB1 under the initial monitoring and a second acoustic wave value SB2 under the secondary monitoring.
As an alternative scheme of the intelligent identification and fault detection method for the transformer inspection image, the invention comprises the following steps: the acoustic wave difference coefficient SBC is obtained through calculation according to the following formula:
SBC＝((SB1-SB2)/SB1)+D；
wherein: SB1 is the first acoustic value, SB2 is the second acoustic value, D is the correction constant, and the value of D is set by the customer adjustment or generated by an analytical function fit.
As an alternative scheme of the intelligent identification and fault detection method for the transformer inspection image, the invention comprises the following steps: comparing the fault resolution coefficient GZX with a fault threshold GYZ to obtain a comparison result:
when the fault resolution coefficient GZX is more than or equal to the fault threshold GYZ, the condensed water in the transformer exceeds a safety range, and the transformer is in a fault state and needs to be overhauled;
when the fault resolution coefficient GZX is less than or equal to the fault threshold GYZ, the condensed water in the transformer does not exceed the safety range, and maintenance is not needed;
combining and calculating the fault resolution coefficient GZX and the fault threshold GYZ to obtain a comparison difference BXZ, and performing secondary comparison on the comparison difference and the fault threshold to obtain a comparison result:
BXZ/GYZ is less than or equal to 5 percent, represents that the condensate water of the transformer is in a first-stage fault state, and is subjected to shutdown drying treatment, wherein the drying time is less than or equal to 20 minutes and less than or equal to 40 minutes, and the drying temperature is more than or equal to 80 degrees and less than or equal to 120 degrees;
5% < BXZ/GYZ less than or equal to 15%, wherein the transformer condensate water is in a secondary fault state, the shutdown maintenance treatment is set, the shutdown time is less than or equal to 30 minutes and less than or equal to 50 minutes, so as to determine the source of the condensate water and whether the refrigerating system has a water leakage phenomenon, if the refrigerating system does not have the water leakage phenomenon, the drying treatment is carried out, the drying time is less than or equal to 30 minutes and less than or equal to 50 minutes, and the drying temperature is less than or equal to 100 degrees and less than or equal to 120 degrees;
BXZ/GYZ is more than 15%, which represents that the condensed water of the transformer is in a three-level fault state, disassembly and inspection are carried out, and professional overhaul equipment is used for detecting all unit parts in the transformer;
wherein the comparison difference BXZ is obtained by calculation by the following formula:
BXZ＝GZX-GYZ；
wherein: GZX is the failure resolution coefficient and GYZ is the failure threshold.
The invention also provides the following technical scheme: the intelligent identification and fault detection system for the transformer inspection image comprises any one of the intelligent identification and fault detection methods for the transformer inspection image, and the intelligent identification and fault detection method comprises the following steps: the system comprises a monitoring module, a three-dimensional modeling module, a data processing module, a data analysis module, a data comparison module and an execution module:
the monitoring module monitors condensed water in the transformer through the infrared camera, the humidity sensor and the acoustic wave sensor under the monitoring module so as to acquire initial monitoring data and secondary monitoring data;
the three-dimensional modeling module is used for obviously marking the geographic coordinates of the transformer and the coordinates of the acquisition equipment;
the data processing module is used for preprocessing the acquired initial monitoring data and the secondary monitoring data, dividing the processed initial monitoring data and the processed secondary monitoring data into a first data set and a second data set, wherein the first data set comprises a first texture value WL1, a first humidity value SD1 and a first sound wave value SB1, and the second data set comprises a second texture value WL2, a second humidity value SD2 and a second sound wave value SB2;
the data analysis module is used for carrying out combination calculation on the first data set and the second data set so as to obtain a fault resolution coefficient GZX;
the data comparison module is used for comparing the acquired fault resolution coefficient GZX with a fault threshold GYZ, if the fault resolution coefficient GZX is more than or equal to the fault threshold GYZ, the fault of the transformer is represented, and if the fault resolution coefficient GZX is less than the fault threshold GYZ, the fault of the transformer is represented;
and the execution module is used for executing the corresponding overhaul flow according to the comparison result of the data comparison module.
The invention has the following beneficial effects:
1. the intelligent identification and fault detection method for the transformer inspection image realizes intelligent monitoring and fault detection of the state of the transformer, improves the reliability and safety of the operation of the transformer, is different from the traditional detection mode of temperature and humidity, adopts texture value change in the temperature rising process to replace the conventional temperature detection so as to improve the detection accuracy, and simultaneously adds sound wave detection to detect condensed water in the transformer in a deeper way, thereby detecting the inside of the transformer in a deep way while further eliminating external interference, and being beneficial to timely finding and processing potential faults.
2. According to the intelligent identification and fault detection method for the transformer inspection image, comprehensive monitoring and maintenance decision of transformer condensate water problems are realized through calculation of a fault resolution coefficient, comparison with a fault threshold value and further analysis of a poor comparison value. The method is favorable for timely finding and solving the cooling problem in the transformer, improves the usability and stability of the power system, and reduces the maintenance cost and the downtime.
Drawings
FIG. 1 is a schematic diagram of the method steps of the present invention.
FIG. 2 is a schematic flow chart of the system of the present invention.
Fig. 3 is a schematic diagram of the composition structure of the monitoring module of the present invention.
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. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1 to 3, a method for intelligently identifying and detecting faults of a transformer inspection image specifically includes the following steps:
s1, determining the position of a target transformer, and deploying acquisition equipment around the target transformer by adopting a uniform interval distribution method; establishing a three-dimensional model, simulating the position of the transformer, and obviously marking the geographic coordinates of the transformer and the coordinates of the acquisition equipment in the three-dimensional model;
s2, acquiring initial monitoring data and secondary monitoring data of the acquisition equipment, respectively preprocessing the initial monitoring data and the secondary monitoring data, and respectively establishing a first data set and a second data set based on the processed initial monitoring data and the processed secondary monitoring data;
s3, establishing a digital twin model, and respectively analyzing a first data set and a second data set, wherein the first data set comprises a first texture value WL1, a first humidity value SD1 and a first sound wave value SB1, and the second data set comprises a second texture value WL2, a second humidity value SD2 and a second sound wave value SB2;
s4, comparing the first data set with the second data set through a digital twin model, and further respectively obtaining a texture difference coefficient WLX, a humidity difference coefficient SDX and an acoustic wave difference coefficient SBC;
s5, inputting a texture difference coefficient WLX, a humidity difference coefficient SDX and an acoustic wave difference coefficient SBC into a digital twin model, and calculating to obtain a fault resolution coefficient GZX through the model, wherein the fault resolution coefficient GZX is obtained through the calculation of the following formula:
GZX＝(WLX*a1+SDX*a2+SBC*a3/a1+a2+a3)+A；
wherein: WLX is a texture difference coefficient, SDX is a humidity difference coefficient, SBC is an acoustic wave difference coefficient, a1, a2 and a3 are weight values, a1 is more than or equal to 0.25 and less than or equal to 0.35,0.45, a2 is more than or equal to 0.55,0.4 and less than or equal to a3 is more than or equal to 0.45, a1+a2+a3 is more than or equal to 1.1, A is a correction constant, and the values of a1, a2, a3 and A are adjusted and set by a customer or are generated by fitting an analysis function;
s6, calculating and obtaining a fault resolution coefficient GZX according to the step S5, comparing the obtained fault resolution coefficient GZX with a fault threshold GYZ, if the fault resolution coefficient GZX is larger than or equal to the fault threshold GYZ, representing that the transformer breaks down, and if the fault resolution coefficient GZX is smaller than the fault threshold GYZ, representing that the transformer does not break down.
In this embodiment: the position of the transformer is simulated by establishing a three-dimensional model, acquisition equipment is deployed around the transformer, and the geographic coordinates of the transformer and the coordinates of the acquisition equipment are marked obviously, so that a visual monitoring environment is established, accurate positioning of the target transformer is facilitated, and a foundation is provided for subsequent monitoring and analysis.
By acquiring the primary monitoring data and the secondary monitoring data and preprocessing them, a first data set and a second data set are established. The data sets comprise texture value, humidity value, sound wave value and other information related to the state of the transformer, and powerful data support is provided for subsequent analysis and comparison.
The model is used to analyze the first data set and the second data set. The model can help us to understand the monitoring data deeply and recognize the correlation between the data, so that whether the transformer has condensed water or not can be found better.
And comparing the first data set with the second data set through the digital twin model, and calculating a texture difference coefficient, a humidity difference coefficient and an acoustic wave difference coefficient, wherein the difference coefficients reflect the change condition of the monitoring data and are helpful for judging whether condensed water exists in the transformer.
And calculating a fault resolution coefficient by using the calculated difference coefficient and a certain weight value and a correction constant. This coefficient is a key indicator, and by comparing with the fault threshold, it can be accurately determined whether the transformer has failed.
The method comprises the steps of accurately positioning a target transformer, effectively acquiring monitoring data, establishing a digital twin model for deep analysis, calculating a fault resolution coefficient and comparing the fault resolution coefficient with a fault threshold value, so that intelligent monitoring and fault detection of the state of the transformer are realized, the reliability and safety of the operation of the transformer are improved, meanwhile, the method is different from a traditional temperature and humidity detection mode, the conventional temperature detection is replaced by texture value change in the temperature rising process, the detection accuracy is improved, and meanwhile, sound wave detection is added to detect condensed water in the transformer in a deeper way, so that the internal of the transformer is detected in a depth way while external interference is further removed, and potential faults are found and processed timely.
Example 2
Referring to fig. 1 to 3, the collection devices are classified into three types: the intelligent humidity sensor comprises a plurality of infrared cameras, a plurality of humidity sensors and a plurality of sound wave sensors, wherein various acquisition devices are not in the same circuit with a transformer;
the infrared camera is used for detecting the change condition of the texture value when the temperature of the outer shell of the transformer changes, wherein the detection of the outer shell of the transformer before the transformer is started is recorded as initial detection, and the detection of the outer shell of the transformer after the transformer is started is recorded as secondary detection;
the humidity sensor is used for detecting the humidity value change condition of the outer transformer shell, wherein the detection of the outer transformer shell before the transformer is started is recorded as initial detection, and the detection of the outer transformer shell after the transformer is started is recorded as secondary detection;
the sound wave sensor is used for detecting the sound wave value change condition of the outer transformer shell, wherein the detection of the outer transformer shell before the transformer is started is recorded as initial detection, and the detection of the outer transformer shell after the transformer is started is recorded as secondary detection.
In this embodiment: the equipment adopting the infrared camera can monitor the temperature change of the outer shell of the transformer in real time, capture the data of the temperature rising texture change of the outer shell from the initial monitoring to the secondary monitoring process, and find out whether the temperature rising rate is different from other areas due to the existence of condensed water and water stains on the outer shell.
The humidity sensor is used for monitoring the change of the air humidity value in the working process of the transformer, so that whether condensate water exists in the transformer is judged through the change of the humidity value.
The sound wave sensor is used for monitoring the change of the noise value of the transformer in the working process, so that whether condensate water exists in the transformer is judged through the change of the noise value.
The state of the transformer can be comprehensively monitored by adopting a plurality of different types of acquisition equipment, so that the accuracy and the reliability of fault detection are improved. This helps to discover potential problems in time, prevents faults from occurring, and reduces the cost of maintenance and repair of the power equipment.
Example 3
Referring to fig. 1 to 3, the plurality of infrared cameras are uniformly distributed around the transformer, so that the monitoring range of the cameras covers the shell of the transformer;
meanwhile, the parallel interval between the infrared cameras is less than or equal to 0.15 meter, and the vertical interval is less than or equal to 0.25 meter;
the transformer is continuously monitored by the plurality of infrared cameras for a long time, so that initial monitoring data and secondary monitoring data of the temperature rise of the transformer shell body are respectively obtained, namely a first texture value WL1 under initial monitoring and a second texture value WL2 under secondary monitoring.
The texture difference coefficient WLX is obtained by combining and calculating the first texture data WL1 and the second texture data WL2, and the specific calculation formula is as follows:
WLX＝(WL1-WL2/WL1)+B；
wherein: WL1 is the first texture data, WL2 is the second texture data, B is the correction constant, and the value of B is set by the customer adjustment or generated by an analytical function fit.
In this embodiment: the cameras are evenly distributed around the transformer, ensuring that their monitoring range covers the entire transformer housing. Furthermore, the parallel and vertical spacing between cameras is limited to within 0.15 meters and 0.25 meters, which configuration helps to obtain comprehensive and accurate surface temperature data of the transformer housing. Meanwhile, the infrared camera is used for continuously monitoring the transformer for a long time, from initial monitoring to secondary monitoring, the heating data of the outer shell are recorded, and a first texture value WL1 under the initial monitoring and a second texture value WL2 under the secondary monitoring are respectively obtained.
The texture difference coefficient WLX is obtained by combining the first texture data WL1 and the second texture data WL2, and the calculation formula includes a correction constant B, and the value of B may be set by a user adjustment or generated by fitting an analysis function. This flexibility allows the method to be tailored to the characteristics and requirements of different transformers, improving the applicability and customizability of the method.
The reasonably configured infrared cameras ensure accurate monitoring of the temperature change of the transformer housing, while calculating the texture difference coefficient WLX provides important data for analysis of the temperature change. The method is not only helpful for timely detecting the rationality of the change of the texture value when the temperature of the transformer rises, but also has the capability of customizing the client, so that the method is suitable for various transformers with different types, and the purposes of improving the monitoring precision and the fault detection efficiency of the transformer are achieved.
Example 4
Referring to fig. 1 to 3, a plurality of humidity sensors are uniformly arranged on the top of the transformer outer shell, so that the monitoring range of the humidity sensors covers the top of the transformer;
meanwhile, the horizontal distance between the humidity sensors is less than or equal to 0.1 meter, and the distance between the humidity sensors and the transformer is less than or equal to 0.15 meter;
the transformer is continuously monitored by the humidity sensors for a long time, so that the data of initial monitoring of the air humidity at the upper end of the transformer shell body and the data of secondary monitoring of the transformer are respectively obtained, namely a first humidity value SD1 under initial monitoring and a second humidity value SD2 under secondary monitoring.
The humidity difference coefficient SDX is obtained through calculation according to the following formula:
SDX＝((SD1-SD2)/SD1)+C；
wherein: SD1 is a first humidity value, SD2 is a second humidity value, C is a correction constant, and the value of C is set by a customer adjustment or generated by an analytical function fit.
In this embodiment: the sensors are uniformly positioned on top of the transformer housing to ensure that the monitoring range covers the entire top surface of the transformer. Meanwhile, the horizontal spacing between the sensors is limited to be within 0.1 meter, and the spacing between the sensors and the transformer is also limited to be within 0.15 meter. This arrangement ensures accurate monitoring of the air humidity at the upper end of the transformer housing.
The humidity sensor is used for continuously monitoring the transformer for a long time, and data of the upper air humidity are recorded in the initial monitoring and the secondary monitoring stages respectively, so that a first humidity value SD1 under the initial monitoring and a second humidity value SD2 under the secondary monitoring are obtained.
The humidity difference coefficient SDX is obtained by combining the first humidity value SD1 and the second humidity value SD2, where the calculation formula includes a correction constant C, and the value of C may be set by a user adjustment or may be generated by fitting an analysis function. The flexibility enables the method to be adjusted according to the characteristics and requirements of different transformers, and improves the applicability and the customizability of the method.
The reasonably configured humidity sensor ensures accurate monitoring of the change in humidity of the air at the upper end of the transformer, while calculating the humidity difference coefficient SDX provides important data for analysis of the change in humidity. The method is not only helpful for timely detecting the existence of condensed water in the transformer, but also has the capability of customizing the transformer, so that the method is suitable for transformers of different types, and the purposes of improving the monitoring precision and the fault detection efficiency of the transformer are achieved. By these features, the method facilitates better maintenance and management of the transformer by power plant operators.
Example 5
Referring to fig. 1 to 3, a plurality of acoustic wave sensors are symmetrically arranged at the top and the bottom of the transformer, so that the monitoring range of the acoustic wave sensors covers the transformer, thereby monitoring the sound change inside the transformer;
the plurality of acoustic wave sensors are used for continuously monitoring the transformer for a long time, so that data of the initial monitoring of the transformer and data of the secondary monitoring of the transformer of the acoustic wave change in the outer shell of the transformer are respectively obtained, namely a first acoustic wave value SB1 under the initial monitoring and a second acoustic wave value SB2 under the secondary monitoring.
The acoustic wave difference coefficient SBC is obtained through calculation according to the following formula:
SBC＝((SB1-SB2)/SB1)+D；
wherein: SB1 is the first acoustic value, SB2 is the second acoustic value, D is the correction constant, and the value of D is set by the customer adjustment or generated by an analytical function fit.
In this embodiment: the acoustic wave sensors are symmetrically arranged at the top and bottom of the transformer, ensuring that their monitoring range covers the whole transformer interior. This configuration allows the acoustic wave sensor to monitor the sound changes inside the transformer, providing important information on the internal operating conditions. And a part of acoustic wave sensors are used for continuously monitoring the transformer for a long time, data of acoustic wave changes in the outer shell of the transformer are recorded in the initial monitoring and the secondary monitoring stages respectively, and a first acoustic wave value SB1 under the initial monitoring and a second acoustic wave value SB2 under the secondary monitoring are obtained.
The acoustic wave difference coefficient SBC is obtained by combining the first acoustic wave value SB1 and the second acoustic wave value SB2, and the calculation formula includes a correction constant D, where the value of D may be set by a customer adjustment or may be generated by fitting an analysis function. The flexibility enables the method to be adjusted according to the characteristics and requirements of different transformers, and improves the applicability and the customizability of the method.
The application of the acoustic wave sensor increases the monitoring capability of the acoustic wave sensor to the internal sound change of the transformer, and is helpful for timely identifying the interference of mechanical vibration or condensed water. By calculating the acoustic wave difference coefficient SBC, the method can provide key data for analyzing sound variations. The method is not only helpful for timely finding out internal mechanical faults or loosening problems, but also has the capability of customizing the transformer, so that the method is suitable for transformers of different types, and the purposes of improving the monitoring precision and fault detection efficiency of the transformer are achieved. By these features, the method facilitates better maintenance and management of the transformer by power plant operators.
Example 6
Referring to fig. 1 to 3, comparing the fault resolution coefficient GZX with the fault threshold GYZ to obtain a comparison result:
when the fault resolution coefficient GZX is more than or equal to the fault threshold GYZ, the condensed water in the transformer exceeds a safety range, and the transformer is in a fault state and needs to be overhauled;
when the fault resolution coefficient GZX is smaller than the fault threshold GYZ, the condensate water in the transformer does not exceed the safety range, and maintenance is not needed;
combining and calculating the fault resolution coefficient GZX and the fault threshold GYZ to obtain a comparison difference BXZ, and performing secondary comparison on the comparison difference and the fault threshold to obtain a comparison result:
BXZ/GYZ is less than or equal to 5 percent, represents that the condensate water of the transformer is in a first-stage fault state, and is subjected to shutdown drying treatment, wherein the drying time is less than or equal to 20 minutes and less than or equal to 40 minutes, and the drying temperature is more than or equal to 80 degrees and less than or equal to 120 degrees;
5% < BXZ/GYZ less than or equal to 15%, wherein the transformer condensate water is in a secondary fault state, the shutdown maintenance treatment is set, the shutdown time is less than or equal to 30 minutes and less than or equal to 50 minutes, so as to determine the source of the condensate water and whether the refrigerating system has a water leakage phenomenon, if the refrigerating system does not have the water leakage phenomenon, the drying treatment is carried out, the drying time is less than or equal to 30 minutes and less than or equal to 50 minutes, and the drying temperature is less than or equal to 100 degrees and less than or equal to 120 degrees;
BXZ/GYZ is more than 15%, which represents that the condensed water of the transformer is in a three-level fault state, disassembly and inspection are carried out, and professional overhaul equipment is used for detecting all unit parts in the transformer;
wherein the comparison difference BXZ is obtained by calculation by the following formula:
BXZ＝GZX-GYZ；
wherein: GZX is the failure resolution coefficient and GYZ is the failure threshold.
In this embodiment: by comparing the fault resolution coefficient GZX with the fault threshold GYZ, the method can accurately judge the state of the transformer. When the fault resolution coefficient GZX is greater than or equal to the fault threshold value GYZ, it indicates that the condensed water in the transformer exceeds the safety range, which means that the transformer is in a fault state and needs to be overhauled. This helps to find potential cooling system problems in time, preventing further damage to the transformer.
When the fault resolution coefficient GZX is smaller than or equal to the fault threshold GYZ, the condensed water in the transformer does not exceed the safety range, and maintenance is not needed. This result provides maintenance personnel with clear information about the state of the transformer, avoiding unnecessary interventions and outages.
By further calculating the comparison difference BXZ of the fault resolution coefficient GZX and the fault threshold GYZ, the method can evaluate the severity of the condensate water problem in more detail. The process may be formulated with different operating schemes based on different percentages of BXZ/GYZ.
Through calculation of the fault resolution coefficient, comparison with a fault threshold value and further analysis of a comparison poor value, comprehensive monitoring and maintenance decision of the transformer condensate water problem are realized. The method is favorable for timely finding and solving the cooling problem in the transformer, improves the usability and stability of the power system, and reduces the maintenance cost and the downtime.
The invention also provides the following technical scheme: the intelligent identification and fault detection system for the transformer inspection image comprises any one of the intelligent identification and fault detection methods for the transformer inspection image, and the intelligent identification and fault detection method comprises the following steps: the system comprises a monitoring module, a three-dimensional modeling module, a data processing module, a data analysis module, a data comparison module and an execution module:
the monitoring module monitors condensed water in the transformer through the infrared camera, the humidity sensor and the acoustic wave sensor under the monitoring module so as to acquire initial monitoring data and secondary monitoring data;
the three-dimensional modeling module is used for obviously marking the geographic coordinates of the transformer and the coordinates of the acquisition equipment;
the data processing module is used for preprocessing the acquired initial monitoring data and the secondary monitoring data, dividing the processed initial monitoring data and the processed secondary monitoring data into a first data set and a second data set, wherein the first data set comprises a first texture value WL1, a first humidity value SD1 and a first sound wave value SB1, and the second data set comprises a second texture value WL2, a second humidity value SD2 and a second sound wave value SB2;
the data analysis module is used for carrying out combination calculation on the first data set and the second data set so as to obtain a fault resolution coefficient GZX;
the data comparison module is used for comparing the acquired fault resolution coefficient GZX with a fault threshold GYZ, if the fault resolution coefficient GZX is more than or equal to the fault threshold GYZ, the fault of the transformer is represented, and if the fault resolution coefficient GZX is less than the fault threshold GYZ, the fault of the transformer is represented;
and the execution module is used for executing the corresponding overhaul flow according to the comparison result of the data comparison module.
Examples:
first texture value WL1:15.2, first humidity value SD1:45%, first acoustic wave value SB1:72dB;
second texture value WL2:15.1, second humidity value SD2:47%, second sound value SB2:75dB;
texture difference coefficient wlx= (WL 1-WL 2)/WL 1, correction constant B is 0.02;
texture difference coefficient wlx= (15.2-15.1)/15.2+0.02= 0.0658;
humidity difference coefficient sdx= (SD 1-SD 2)/SD 1, correction constant C is 0.01; humidity difference coefficient sdx= (45% -47%)/45% + 0.01= -0.0444;
acoustic wave difference coefficient sbc= (SB 1-SB 2)/SB 1, correction constant D is 0.03;
the acoustic wave difference coefficient sbc= (72 dB-75 dB)/72db+0.03= -0.0417;
a weight a1=0.3, a weight a2=0.5, a weight a3=0.4, and a correction constant a is 0.05;
fault resolution gzx= (WLX 0.3+sdx 0.5+sbc 0.4)/(0.3+0.5+0.4) +0.05;
fault resolution gzx= (0.0658 x 0.3-0.0444 x 0.5-0.0417 x 0.4)/(0.3+0.5+0.4) +0.05=0.0229;
fault threshold GYZ is 0.02;
since the failure resolution coefficient GZX (0.0229) is greater than the failure threshold value GYZ (0.02), the transformer is required to be overhauled when a failure occurs.
The comparison difference BXZ =gzx-gyz=0.0229-0.02=0.0029;
comparison difference BXZ/gyz=0.0029/0.02≡0.145;
as BXZ/GYZ meets the standard of 5% < BXZ/GYZ less than or equal to 15%, the transformer condensate water is in a secondary fault state, the shutdown maintenance treatment is set, the shutdown time is less than or equal to 30 minutes and less than or equal to 50 minutes, so as to determine whether the source of the condensate water and a refrigerating system have water leakage phenomenon, if the refrigerating system water leakage phenomenon does not occur, the drying treatment is carried out, the drying time is less than or equal to 30 minutes and less than or equal to 50 minutes, and the drying temperature is less than or equal to 100 degrees and less than or equal to 120 degrees.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
The foregoing is merely a preferred embodiment of the present invention, and it should be noted that it will be apparent to those skilled in the art that several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the scope of the invention.
Claims (5)
1. A transformer inspection image intelligent identification and fault detection method is characterized in that: the method comprises the following specific steps:
s1, determining the position of a target transformer, and deploying acquisition equipment around the target transformer by adopting a uniform interval distribution method; establishing a three-dimensional model, simulating the position of the transformer, and obviously marking the geographic coordinates of the transformer and the coordinates of the acquisition equipment in the three-dimensional model;
the collection devices are divided into three categories: the intelligent humidity sensor comprises a plurality of infrared cameras, a plurality of humidity sensors and a plurality of sound wave sensors, wherein various acquisition devices are not in the same circuit with a transformer;
the infrared camera is used for detecting the change condition of the texture value when the temperature of the outer shell of the transformer changes, wherein the detection of the outer shell of the transformer before the transformer is started is recorded as initial detection, and the detection of the outer shell of the transformer after the transformer is started is recorded as secondary detection;
the humidity sensor is used for detecting the humidity value change condition of the outer transformer shell, wherein the detection of the outer transformer shell before the transformer is started is recorded as initial detection, and the detection of the outer transformer shell after the transformer is started is recorded as secondary detection;
the sound wave sensor is used for detecting the sound wave value change condition of the outer transformer shell, wherein the detection of the outer transformer shell before the transformer is started is recorded as initial detection, and the detection of the outer transformer shell after the transformer is started is recorded as secondary detection;
the infrared cameras are uniformly distributed around the transformer, so that the monitoring range of the cameras covers the shell of the transformer;
meanwhile, the parallel interval between the infrared cameras is less than or equal to 0.15 meter, and the vertical interval is less than or equal to 0.25 meter;
the method comprises the steps that a plurality of infrared cameras continuously monitor a transformer for a long time, so that initial monitoring data and secondary monitoring data of the temperature rise of an outer shell of the transformer, namely a first texture value WL1 under initial monitoring and a second texture value WL2 under secondary monitoring, are respectively obtained;
the humidity sensors are uniformly arranged at the top of the transformer outer shell, so that the monitoring range of the humidity sensors covers the top of the transformer;
meanwhile, the horizontal distance between the humidity sensors is less than or equal to 0.1 meter, and the distance between the humidity sensors and the transformer is less than or equal to 0.15 meter;
the plurality of humidity sensors are used for continuously monitoring the transformer for a long time, so that data of initial monitoring of the air humidity at the upper end of the transformer shell body on the transformer and data of secondary monitoring of the transformer are respectively obtained, namely a first humidity value SD1 under the initial monitoring and a second humidity value SD2 under the secondary monitoring;
the sound wave sensors are symmetrically arranged at the top and the bottom of the transformer, so that the monitoring range of the sound wave sensors covers the transformer, and the sound change inside the transformer is monitored;
the plurality of acoustic wave sensors are used for continuously monitoring the transformer for a long time, so that data of initial monitoring of the acoustic wave change in the outer shell of the transformer and data of secondary monitoring of the transformer are respectively obtained, namely a first acoustic wave value SB1 under the initial monitoring and a second acoustic wave value SB2 under the secondary monitoring;
s2, acquiring initial monitoring data and secondary monitoring data of the acquisition equipment, respectively preprocessing the initial monitoring data and the secondary monitoring data, and respectively establishing a first data set and a second data set based on the processed initial monitoring data and the processed secondary monitoring data;
s3, establishing a digital twin model, and respectively analyzing a first data set and a second data set, wherein the first data set comprises a first texture value WL1, a first humidity value SD1 and a first sound wave value SB1, and the second data set comprises a second texture value WL2, a second humidity value SD2 and a second sound wave value SB2;
s4, comparing the first data set with the second data set through a digital twin model, and further respectively obtaining a texture difference coefficient WLX, a humidity difference coefficient SDX and an acoustic wave difference coefficient SBC;
s5, inputting a texture difference coefficient WLX, a humidity difference coefficient SDX and an acoustic wave difference coefficient SBC into a digital twin model, and calculating to obtain a fault resolution coefficient GZX through the model, wherein the fault resolution coefficient GZX is obtained through the calculation of the following formula:
GZX＝(WLX*a1+SDX*a2+SBC*a3/a1+a2+a3)+A；
wherein: WLX is a texture difference coefficient, SDX is a humidity difference coefficient, SBC is an acoustic wave difference coefficient, a1, a2 and a3 are weight values, a1 is more than or equal to 0.25 and less than or equal to 0.35,0.45, a2 is more than or equal to 0.55,0.4 and less than or equal to a3 is more than or equal to 0.45, a1+a2+a3 is more than or equal to 1.1, A is a correction constant, and the values of a1, a2, a3 and A are adjusted and set by a customer or are generated by fitting an analysis function;
s6, calculating and obtaining a fault resolution coefficient GZX according to the step S5, and comparing the obtained fault resolution coefficient GZX with a fault threshold GYZ to obtain a comparison result:
when the fault resolution coefficient GZX is more than or equal to the fault threshold GYZ, the condensate water in the transformer exceeds the safety range, and the transformer is in a fault state and needs to be overhauled;
when the fault resolution coefficient GZX is smaller than the fault threshold GYZ, the condensate water in the transformer does not exceed the safety range, and maintenance is not needed;
combining and calculating the fault resolution coefficient GZX and the fault threshold GYZ to obtain a comparison difference BXZ, and performing secondary comparison on the comparison difference and the fault threshold to obtain a comparison result:
BXZ/GYZ is less than or equal to 5 percent, represents that the condensate water of the transformer is in a first-stage fault state, and is subjected to shutdown drying treatment, wherein the drying time is less than or equal to 20 minutes and less than or equal to 40 minutes, and the drying temperature is more than or equal to 80 degrees and less than or equal to 120 degrees;
5% < BXZ/GYZ less than or equal to 15%, wherein the transformer condensate water is in a secondary fault state, the shutdown maintenance treatment is set, the shutdown time is less than or equal to 30 minutes and less than or equal to 50 minutes, so as to determine the source of the condensate water and whether the refrigerating system has a water leakage phenomenon, if the refrigerating system does not have the water leakage phenomenon, the drying treatment is carried out, the drying time is less than or equal to 30 minutes and less than or equal to 50 minutes, and the drying temperature is less than or equal to 100 degrees and less than or equal to 120 degrees;
BXZ/GYZ is more than 15%, which represents that the condensed water of the transformer is in a three-level fault state, disassembly and inspection are carried out, and professional overhaul equipment is used for detecting all unit parts in the transformer;
wherein the comparison difference BXZ is obtained by calculation by the following formula:
BXZ＝GZX-GYZ；
wherein: GZX is the failure resolution coefficient and GYZ is the failure threshold.
2. The intelligent identification and fault detection method for the transformer inspection image according to claim 1, wherein the intelligent identification and fault detection method is characterized by comprising the following steps of: the texture difference coefficient WLX is obtained by combining and calculating the first texture data WL1 and the second texture data WL2, and the specific calculation formula is as follows:
WLX＝(WL1-WL2/WL1)+B；
wherein: WL1 is the first texture data, WL2 is the second texture data, B is the correction constant, and the value of B is set by the customer adjustment or generated by an analytical function fit.
3. The intelligent identification and fault detection method for the transformer inspection image according to claim 2, wherein the intelligent identification and fault detection method is characterized by comprising the following steps of: the humidity difference coefficient SDX is obtained through calculation according to the following formula:
SDX＝((SD1-SD2)/SD1)+C；
wherein: SD1 is a first humidity value, SD2 is a second humidity value, C is a correction constant, and the value of C is set by a customer adjustment or generated by an analytical function fit.
4. The intelligent identification and fault detection method for the transformer inspection image according to claim 3, wherein the intelligent identification and fault detection method is characterized by comprising the following steps of: the acoustic wave difference coefficient SBC is obtained through calculation according to the following formula:
SBC＝((SB1-SB2)/SB1)+D；
wherein: SB1 is the first acoustic value, SB2 is the second acoustic value, D is the correction constant, and the value of D is set by the customer adjustment or generated by an analytical function fit.
5. The intelligent identification and fault detection system for the transformer inspection image comprises the intelligent identification and fault detection method for the transformer inspection image according to any one of claims 1-4, and is characterized in that: comprising the following steps: the system comprises a monitoring module, a three-dimensional modeling module, a data processing module, a data analysis module, a data comparison module and an execution module:
the monitoring module monitors condensed water in the transformer through the infrared camera, the humidity sensor and the acoustic wave sensor under the monitoring module so as to acquire initial monitoring data and secondary monitoring data;
the three-dimensional modeling module is used for obviously marking the geographic coordinates of the transformer and the coordinates of the acquisition equipment;
the data processing module is used for preprocessing the acquired initial monitoring data and the secondary monitoring data, dividing the processed initial monitoring data and the processed secondary monitoring data into a first data set and a second data set, wherein the first data set comprises a first texture value WL1, a first humidity value SD1 and a first sound wave value SB1, and the second data set comprises a second texture value WL2, a second humidity value SD2 and a second sound wave value SB2;
the data analysis module is used for carrying out combination calculation on the first data set and the second data set so as to obtain a fault resolution coefficient GZX;
the data comparison module is used for comparing the acquired fault resolution coefficient GZX with a fault threshold GYZ, wherein the fault resolution coefficient GZX is more than or equal to the fault threshold GYZ and represents that the transformer breaks down, and the fault resolution coefficient GZX is less than the fault threshold GYZ and represents that the transformer does not break down;
and the execution module is used for executing the corresponding overhaul flow according to the comparison result of the data comparison module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311631212.5A CN117330137B (en) | 2023-12-01 | 2023-12-01 | Intelligent identification and fault detection method and system for transformer inspection image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311631212.5A CN117330137B (en) | 2023-12-01 | 2023-12-01 | Intelligent identification and fault detection method and system for transformer inspection image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117330137A CN117330137A (en) | 2024-01-02 |
| CN117330137B true CN117330137B (en) | 2024-03-08 |
Family
ID=89277819
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311631212.5A Active CN117330137B (en) | 2023-12-01 | 2023-12-01 | Intelligent identification and fault detection method and system for transformer inspection image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117330137B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113339688A (en) * | 2021-06-02 | 2021-09-03 | 江苏高特阀业有限公司 | Drain valve leakage monitoring system and method thereof |
| CN113964671A (en) * | 2021-10-29 | 2022-01-21 | 中能智控有限公司 | Power supply control system and method for high-voltage cabinet |
| WO2022095616A1 (en) * | 2020-11-03 | 2022-05-12 | 国网智能科技股份有限公司 | On-line intelligent inspection system and method for transformer substation |
| CN116452749A (en) * | 2023-04-27 | 2023-07-18 | 中国长江电力股份有限公司 | Equipment three-dimensional thermal imaging method, device and equipment based on digital twin |
| CN116758447A (en) * | 2023-04-26 | 2023-09-15 | 中国能源建设集团广东省电力设计研究院有限公司 | Digital twinning-based substation equipment fault analysis system |
| CN116826958A (en) * | 2023-05-26 | 2023-09-29 | 云南电网有限责任公司文山供电局 | Intelligent safety inspection method for digital transmission channel |
| CN116885858A (en) * | 2023-09-08 | 2023-10-13 | 中国标准化研究院 | Power distribution network fault processing method and system based on digital twin technology |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110334740A (en) * | 2019-06-05 | 2019-10-15 | 武汉大学 | The electrical equipment fault of artificial intelligence reasoning fusion detects localization method |
-
2023
- 2023-12-01 CN CN202311631212.5A patent/CN117330137B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022095616A1 (en) * | 2020-11-03 | 2022-05-12 | 国网智能科技股份有限公司 | On-line intelligent inspection system and method for transformer substation |
| CN113339688A (en) * | 2021-06-02 | 2021-09-03 | 江苏高特阀业有限公司 | Drain valve leakage monitoring system and method thereof |
| CN113964671A (en) * | 2021-10-29 | 2022-01-21 | 中能智控有限公司 | Power supply control system and method for high-voltage cabinet |
| CN116758447A (en) * | 2023-04-26 | 2023-09-15 | 中国能源建设集团广东省电力设计研究院有限公司 | Digital twinning-based substation equipment fault analysis system |
| CN116452749A (en) * | 2023-04-27 | 2023-07-18 | 中国长江电力股份有限公司 | Equipment three-dimensional thermal imaging method, device and equipment based on digital twin |
| CN116826958A (en) * | 2023-05-26 | 2023-09-29 | 云南电网有限责任公司文山供电局 | Intelligent safety inspection method for digital transmission channel |
| CN116885858A (en) * | 2023-09-08 | 2023-10-13 | 中国标准化研究院 | Power distribution network fault processing method and system based on digital twin technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117330137A (en) | 2024-01-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jin et al. | Anomaly detection of cooling fan and fault classification of induction motor using Mahalanobis–Taguchi system | |
| CN110910383A (en) | Phase modulator fault monitoring method and system based on infrared image recognition | |
| KR20200014129A (en) | Diagnosis method of electric transformer using Deep Learning | |
| CN114252749B (en) | Transformer partial discharge detection method and device based on multiple sensors | |
| CN117270514B (en) | Production process whole-flow fault detection method based on industrial Internet of things | |
| CN109945977B (en) | Thermal fault diagnosis method and system for dry-type transformer | |
| CN114004306A (en) | Equipment fault evaluation system and method based on multi-dimensional data of Internet of things | |
| CN116500441B (en) | Motor fault detection and positioning method and system | |
| CN117082105A (en) | Environment-friendly intelligent hospital facility monitoring system and method | |
| CN111830438B (en) | Transformer fault detection method and transformer | |
| CN117330137B (en) | Intelligent identification and fault detection method and system for transformer inspection image | |
| CN114895163A (en) | Cable inspection positioning device and method based on cable insulation performance | |
| CN117662510B (en) | Fan fault diagnosis system and method thereof | |
| CN117741517A (en) | Capacitor equipment online monitoring method and system based on artificial intelligence | |
| KR101600698B1 (en) | System and Method for Predicting Life of Power Transformer | |
| CN117477769A (en) | Early warning method and system for electric power system | |
| CN111551853B (en) | Hydro-generator stator core lamination loosening fault detection method | |
| CN114562429A (en) | Wind turbine generator blade damage early warning method based on clearance and sound vibration monitoring | |
| JP2014026327A (en) | Device state diagnostic apparatus using actual operation data | |
| JP2009238190A (en) | Maintenance plan support system | |
| CN117993895B (en) | Full life cycle management system of power grid equipment | |
| CN110927488B (en) | Transformer running state monitoring method based on membership function | |
| CN118311363A (en) | Defect detection method and system for substation equipment | |
| CN118209260A (en) | Oil leakage monitoring and early warning system for transformer oil storage cabinet | |
| CN113780337A (en) | Generator inspection method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |