CN115639327B - Sleeve fault detection method and device based on oil-immersed sleeve gas detection - Google Patents
Sleeve fault detection method and device based on oil-immersed sleeve gas detection Download PDFInfo
- Publication number
- CN115639327B CN115639327B CN202211660424.1A CN202211660424A CN115639327B CN 115639327 B CN115639327 B CN 115639327B CN 202211660424 A CN202211660424 A CN 202211660424A CN 115639327 B CN115639327 B CN 115639327B
- Authority
- CN
- China
- Prior art keywords
- fault
- gas concentration
- decision tree
- target
- gas
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The application relates to a bushing fault detection method and device based on oil-immersed bushing gas detection. The method comprises the following steps: the method comprises the steps of obtaining gas concentration data collected by gas detection sensing probes placed in all regions in an oil-immersed bushing, determining the bushing region corresponding to the gas concentration data as a suspicious fault region under the condition that the gas concentration data meet fault conditions, inputting the gas concentration data corresponding to the suspicious fault region into a target decision tree model to obtain fault type identification results and fault region identification results corresponding to the gas concentration data, comparing the fault regions represented by the suspicious fault region and the fault region identification results, and determining a target fault identification result of the oil-immersed bushing. By adopting the method, the gas concentration data of each area of the sleeve can be accurately and efficiently detected by using the gas detection sensing probe, the fault area is accurately determined through the gas concentration data, the sleeve fault type and the fault area are accurately identified, and the sleeve fault detection accuracy is improved.
Description
Technical Field
The present application relates to the field of optical sensing system technology, and in particular, to a method, a system, an apparatus, a computer device, a storage medium, and a computer program product for detecting a casing fault based on gas detection of an oil-immersed casing.
Background
The transformer bushing is used as an important component of power transmission and transformation equipment, and faults such as partial discharge, abnormal temperature rise and the like can occur in the transformer bushing due to insulation moisture and the like, so that the insulation of the bushing is aged and deteriorated, and even insulation breakdown is caused in severe cases, and the safe and stable operation of a power system is influenced. At present, oil-immersed insulation sleeves are mostly adopted by high-voltage and high-capacity power transformers at home and abroad, and analysis of dissolved gas in oil on the oil-immersed insulation sleeves is one of the primary methods for fault diagnosis and early warning of the sleeves.
At present, a method for detecting gas dissolved in oil of an oil immersed bushing is mainly an oil chromatography, however, when the oil chromatography is used for sampling fault gas, because it takes several hours for the fault gas to be dissolved into the oil and diffused to an oil taking port from the generation, the detection period is long, and in addition, when the oil chromatography is used for judging a fault according to the concentration of the fault gas, the fault state cannot be accurately judged according to fault characteristics, which is not beneficial to improving the accuracy of bushing fault detection.
Disclosure of Invention
In view of the above, it is necessary to provide a method, an apparatus, a computer device, a computer readable storage medium and a computer program product for detecting a casing failure based on gas detection of an oil-immersed casing, which can improve the accuracy of casing failure detection.
In a first aspect, the present application provides a method for detecting a casing fault based on oil-immersed casing gas detection, where the method includes:
acquiring gas concentration data acquired by gas detection sensing probes placed in various areas in the oil-immersed bushing; the gas detection sensing probe is provided with a nano-scale micropore for gas to pass through;
determining a casing region corresponding to the gas concentration data as a suspicious fault region under the condition that the gas concentration data meets a fault condition;
inputting gas concentration data corresponding to the suspicious fault area into a target decision tree model to obtain a fault type identification result and a fault area identification result corresponding to the gas concentration data;
comparing the suspicious fault area with the fault area represented by the fault area identification result, and determining a target fault identification result of the oil-immersed bushing; the target fault identification result comprises a target fault area and a fault type represented by the fault type identification result.
In one embodiment, the determining, in the case that the gas concentration data satisfies a fault condition, a casing region corresponding to the gas concentration data as a suspected fault region includes:
obtaining a gas concentration threshold for a gas type of the casing region;
and under the condition that the gas concentration data is larger than a preset gas concentration threshold value, determining that the casing region corresponding to the gas concentration data is the suspicious fault region.
In one embodiment, the method further comprises:
acquiring a sample data set, and constructing an initial decision tree model according to a training data set in the sample data set;
pruning the initial decision tree model to obtain a pruning decision tree model;
testing the pruning decision tree model by utilizing the test data set in the sample data set to obtain a test result corresponding to the pruning decision tree model;
determining the pruning decision tree model as the target decision tree model if the test result indicates that the pruning decision tree model passes the test.
In one embodiment, the training data set includes a plurality of feature quantities; the characteristic quantity is determined according to a three-ratio method; the constructing an initial decision tree model according to the training data set in the sample data set includes:
determining an information gain ratio of the plurality of feature quantities to the training data set;
determining target characteristic quantities according to information gain ratios corresponding to the characteristic quantities;
according to the information gain ratio corresponding to the target characteristic quantity, a decision tree node corresponding to the target characteristic quantity is constructed;
removing the target characteristic quantity from the plurality of characteristic quantities to obtain a plurality of new characteristic quantities;
and returning to the step of determining the information gain ratio of each characteristic quantity to the training data set until the initial decision tree model is obtained.
In one embodiment, the constructing a decision tree node corresponding to the target feature quantity according to the information gain ratio corresponding to the target feature quantity includes:
and when the information gain ratio corresponding to the target characteristic quantity is 0, taking the fault type with the largest ratio in the training data set as the class corresponding to the single node to form the decision tree model.
In one embodiment, the constructing a decision tree node corresponding to the target feature quantity according to the information gain ratio corresponding to the target feature quantity further includes:
when the information gain ratio corresponding to the target characteristic quantity is not 0, dividing the training data set into a plurality of non-empty subsets to obtain data sets corresponding to a plurality of divided sub-nodes;
and taking the fault type with the highest data set occupation ratio corresponding to each child node as the class corresponding to the corresponding child node to form the decision tree model.
In a second aspect, the present application further provides a casing fault detection system based on oil-immersed casing gas detection, the system includes: the system comprises a solid laser, a spectrum detection unit, an optical switch, a sensing probe and computer equipment; the spectrum detection unit is respectively connected with the solid laser, the computer equipment and the optical switch, and the computer equipment is connected with the sensing probe through the optical switch; wherein:
the solid laser is used for sending broadband light to the optical switch through the spectrum detection unit;
the optical switch is used for enabling the broadband light sent by the solid laser to enter the sensing probe;
the sensing probe is provided with nano-scale micropores for gas to pass through, is placed in each area in the oil-immersed sleeve and is used for returning scattered light to the spectrum detection unit; the scattered light is generated after the interaction between the broadband light and the gas in the sensing probe;
the spectrum detection unit is used for receiving and analyzing scattered light returned by the sensing probe to obtain spectrum detection data;
the computer equipment is used for acquiring gas concentration data of each region in the oil-immersed bushing according to the spectrum detection data;
the computer equipment is further used for determining a casing area corresponding to the gas concentration data as a suspicious fault area under the condition that the gas concentration data meet a fault condition;
the computer equipment is further used for inputting the gas concentration data corresponding to the suspicious fault area into a target decision tree model to obtain a fault type identification result and a fault area identification result corresponding to the gas concentration data;
the computer device is further used for comparing the suspicious fault region with the fault region represented by the fault region identification result, and determining a target fault identification result of the oil-immersed bushing; the target fault identification result comprises a target fault area and a fault type represented by the fault type identification result.
In a third aspect, the present application further provides a casing fault detection apparatus based on oil-immersed casing gas detection, where the apparatus includes:
the acquisition module is used for acquiring gas concentration data acquired by the gas detection sensing probes arranged in all areas in the oil-immersed bushing; the gas detection sensing probe is provided with a nano-scale micropore for gas to pass through;
the determining module is used for determining the casing area corresponding to the gas concentration data as a suspicious fault area under the condition that the gas concentration data meet the fault condition;
the identification module is used for inputting the gas concentration data corresponding to the suspicious fault area into a target decision tree model to obtain a fault type identification result and a fault area identification result corresponding to the gas concentration data;
the comparison module is used for comparing the suspicious fault area with the fault area represented by the fault area identification result and determining a target fault identification result of the oil-immersed bushing; the target fault identification result comprises a target fault area and a fault type represented by the fault type identification result.
In a fourth aspect, the present application further provides a computer device. The computer device comprises a memory and a processor, the memory storing a computer program which, when executed by the processor, carries out the steps of the method described above.
In a fifth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method described above.
In a sixth aspect, the present application further provides a computer program product. The computer program product comprises a computer program which, when being executed by a processor, carries out the steps of the above-mentioned method.
According to the bushing fault detection method, the system, the device, the computer equipment, the storage medium and the computer program product based on oil-immersed bushing gas detection, gas concentration data acquired by the gas detection sensing probe placed in each area in the oil-immersed bushing is acquired, the gas detection sensing probe is provided with the nanoscale micropores for gas to pass through, as the nanoscale micropores only allow gas micromolecules dissolved in oil to pass through and enter the inside of the sensing probe, macromolecular substances in the oil are stopped at the outside of the sensing probe, the influence of the macromolecular substances in the oil on gas concentration detection can be avoided, in-situ oil-gas separation is realized, the time required by gas concentration detection can be shortened, the detection efficiency is improved, and under the condition that the gas concentration data meet the fault condition, the bushing area corresponding to the gas concentration data is determined to be a suspicious fault area, so that the area where the fault possibly exists is determined, the method has the advantages that the workload of fault detection is reduced, the detection efficiency is improved, the gas concentration data corresponding to a suspicious fault area are input into a target decision tree model, the fault type identification result and the fault area identification result corresponding to the gas concentration data are obtained, so that a more accurate fault area identification result is determined, the target fault identification result of the oil-immersed bushing is determined by comparing the suspicious fault area with the fault area represented by the fault area identification result, the target fault identification result comprises the target fault area and the fault type represented by the fault type identification result, so that the accurate fault area is determined by comparison, the gas concentration data of each area in the bushing can be directly and rapidly measured by a gas detection sensing probe, the accuracy and the efficiency of gas concentration data detection are improved, the suspicious fault area is determined by using the detected gas concentration data, and analyzing the gas concentration data by using a decision tree model to obtain a target fault identification result, comparing a fault area represented by a fault area identification result in the target fault identification result with a suspicious fault area, determining an accurate fault area, realizing accurate identification of the casing fault type and the fault area, and improving the accuracy of casing fault detection.
Drawings
Fig. 1 is an application environment diagram of a bushing fault detection method based on oil-immersed bushing gas detection in an embodiment;
fig. 2 is a schematic flow chart of a bushing fault detection method based on oil-immersed bushing gas detection according to an embodiment;
fig. 3 is a schematic flow chart of another method for detecting a casing fault based on gas detection of an oil-immersed casing according to an embodiment;
FIG. 4 is a schematic flow chart diagram illustrating the process of modeling a decision tree in one embodiment;
FIG. 5 is a schematic diagram of a sensing probe arrangement in one embodiment;
FIG. 6 is a schematic diagram of a casing fault detection system based on oil-immersed casing gas detection according to an embodiment;
fig. 7 is a block diagram of a casing fault detection device based on oil-immersed casing gas detection according to an embodiment;
FIG. 8 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.
The bushing fault detection method based on oil-immersed bushing gas detection provided by the embodiment of the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or can be placed on a cloud or other network server, the terminal 102 acquires gas concentration data acquired by gas detection sensing probes placed in various regions in the oil-immersed bushing, the gas detection sensing probes are provided with nano-scale micro-holes for allowing gas to pass through, under the condition that the gas concentration data meet a fault condition, the bushing region corresponding to the gas concentration data is determined to be a suspicious fault region by the terminal 102, the gas concentration data corresponding to the suspicious fault region is input into a target decision tree model by the terminal 102, a fault type identification result and a fault region identification result corresponding to the gas concentration data are obtained, the suspicious fault region and the fault region characterized by the fault region identification result are compared by the terminal 102, a target fault identification result of the oil-immersed bushing is determined, and the target fault identification result comprises a target fault region and a fault type characterized by the fault type identification result. The terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, and the like. The server 104 may be implemented as a stand-alone server or as a server cluster comprised of multiple servers.
It is understood that the method can also be applied to a server, and can also be applied to a system comprising a terminal and a server, and is realized through the interaction of the terminal and the server.
In some embodiments, as shown in fig. 2, a method for detecting a casing fault based on gas detection of an oil-immersed casing is provided, which is described by taking the method as an example for being applied to the terminal in fig. 1, and includes the following steps:
step S202, acquiring gas concentration data collected by gas detection sensing probes placed in various areas in an oil-immersed bushing; the gas detection sensing probe is provided with a nano-scale micropore for gas to pass through.
The oil-immersed bushing may be an oil-immersed insulating bushing used for a lead of a power transformer.
The gas detection sensing probe can be a hollow photonic crystal fiber with a nano-scale micropore drilled on the side surface, and the inside of the fiber core of the nano-scale micropore paper fiber.
The gas concentration data may be concentration data corresponding to a characteristic gas dissolved in oil of the oil-immersed bushing.
As an example, the terminal receives the spectrum data sent by the spectrum detection unit, analyzes the spectrum data, and then determines the concentration data corresponding to the characteristic gas dissolved in the oil-immersed bushing.
And step S204, under the condition that the gas concentration data meet the fault condition, determining the casing area corresponding to the gas concentration data as a suspicious fault area.
The fault condition may be a condition for determining whether the casing gas concentration data meets an empirical gas concentration threshold, and in practical application, the fault condition may include a gas concentration condition and a gas type condition.
The sleeve region can refer to different regions of an oil filling region inside the sleeve, and in practical application, the sleeve region can comprise a guide rod region, a capacitor core region and an oil conservator region.
Where a suspected fault region may refer to a casing region where a fault is determined to be likely based on gas concentration data.
As an example, a worker sets a gas concentration threshold value of each gas in each casing area according to experience, if the gas concentration data of any one gas in any casing area exceeds the gas concentration threshold value set by the worker, the terminal determines that the casing area corresponding to the gas concentration data is a suspicious fault area, and if the gas concentration data does not exceed the gas concentration threshold value, the terminal continues to read the gas concentration data of other gases.
Step S206, inputting the gas concentration data corresponding to the suspicious fault area into a target decision tree model to obtain a fault type identification result and a fault area identification result corresponding to the gas concentration data.
The target decision tree model may refer to a decision tree model for outputting a fault type and a fault region according to gas concentration data.
The fault type identification result may refer to a decision tree output result for the fault type output by the target decision tree model.
The fault region identification result may refer to a decision tree output result for the fault region output by the target decision tree model.
As an example, the terminal establishes a data set according to gas concentration data corresponding to a suspicious fault area, inputs the data in the data set into a target decision tree model, and further obtains a fault type identification result and a fault area identification result output by the target decision tree.
Step S208, comparing the suspicious fault area with the fault area represented by the fault area identification result, and determining a target fault identification result of the oil-immersed bushing; the target fault identification result comprises a target fault area and a fault type represented by the fault type identification result.
The target fault identification result may refer to an identification result composed of a target fault area and a fault type represented by the fault type identification result.
As an example, the terminal compares a suspicious fault region with a fault region represented by a fault region identification result, determines whether an overlap region exists in the suspicious fault region and the fault region represented by the fault region identification result, determines that the overlap region is a target fault region if the overlap region exists, and re-reads gas concentration data if the overlap region does not exist.
In the bushing fault detection method based on oil-immersed bushing gas detection, gas concentration data collected by gas detection sensing probes placed in all areas in an oil-immersed bushing are obtained, the gas detection sensing probes are provided with nanoscale micropores for gas to pass through, only small gas molecules dissolved in oil are allowed to pass through and enter the sensing probes by the nanoscale micropores, macromolecular substances in the oil are stopped outside the sensing probes, the influence of the macromolecular substances in the oil on the gas concentration detection can be avoided, in-situ oil-gas separation is realized, the time required by the gas concentration detection can be shortened, the detection efficiency is improved, and a bushing area corresponding to the gas concentration data is determined to be a suspicious fault area under the condition that the gas concentration data meets fault conditions, so that an area where faults possibly exist is determined, the workload of fault detection is reduced, and the detection efficiency is improved, inputting gas concentration data corresponding to a suspected fault area into a target decision tree model to obtain a fault type identification result and a fault area identification result corresponding to the gas concentration data so as to determine a more accurate fault area identification result, determining a target fault identification result of the oil-immersed bushing by comparing the suspected fault area with a fault area represented by the fault area identification result, determining an accurate fault area by comparing the target fault identification result with the fault type represented by the fault type identification result, directly and quickly measuring the gas concentration data of each area in the bushing by using a gas detection sensing probe, improving the accuracy and efficiency of gas concentration data detection, determining the suspected fault area by using the detected gas concentration data, and analyzing the gas concentration data by using the decision tree model, and obtaining a target fault identification result, and further comparing a fault area represented by the fault area identification result in the target fault identification result with a suspicious fault area to determine an accurate fault area, thereby realizing accurate identification of the casing fault type and the fault area and improving the accuracy of casing fault detection.
In some embodiments, the determining, in the case that the gas concentration data satisfies a fault condition, a casing region corresponding to the gas concentration data as a suspected fault region includes:
a gas concentration threshold for a gas type of the casing region is obtained.
The gas type may refer to a type of gas dissolved in oil of the oil-immersed bushing, and in practical applications, the gas type may include methane, ethane, ethylene, acetylene, and hydrogen.
The gas concentration threshold may refer to a concentration threshold corresponding to each gas in each casing region, which is set by a worker according to experience.
And under the condition that the gas concentration data is larger than the gas concentration threshold value, determining that the casing area corresponding to the gas concentration data is the suspicious fault area.
As an example, as shown in fig. 3, according to past experience data, a worker sets appropriate gas concentration thresholds for different types of fault feature gas concentrations in different areas, a terminal reads seven typical fault gas concentrations in an oil filling area inside a casing, if the gas concentration data exceeds the gas concentration threshold, the terminal determines that the casing area corresponding to the gas concentration data is a suspicious fault area, if the gas concentration data does not exceed the gas concentration threshold, the terminal continues to monitor gas concentration information corresponding to each gas in the casing, the terminal directly uses a decision tree model established in advance according to a selected feature quantity and a sample data set as input to determine a fault type and a fault area, compares the decision tree determination result with the suspicious fault area, and if the decision tree determination result and the suspicious fault area have a coincidence area, it is determined that the decision tree determination result is correct, that a fault type accurate to the fault area is obtained, and if there is no coincidence area, the worker re-reads sensing data.
In this embodiment, whether the casing region corresponding to the gas concentration data is a suspicious fault region is determined according to the gas concentration data and the preset gas concentration threshold, so that the fault region can be roughly determined, the workload of fault detection is reduced, and the fault detection efficiency is improved.
In some embodiments, the method further comprises:
and acquiring a sample data set, and constructing an initial decision tree model according to a training data set in the sample data set.
The sample data set may be a data set composed of data required for establishing a decision tree model and testing the decision tree model, and in practical application, the sample data set may include a training data set and a testing data set; for example: the terminal is according to 8: a scale of 2 divides the sample data set into a training data set and a test data set.
The training data set may refer to a data set composed of data required for building a decision tree model.
The initial decision tree model may refer to a preliminarily established decision tree model which is not optimized through testing.
As an example, the terminal converts the gas concentration data into three ratios according to a three-ratio method: the terminal uses ratio data corresponding to the three ratios to form a characteristic quantity set, and each characteristic quantity can contain information: and the terminal takes the three ratios of all the suspicious fault areas as characteristic quantities, gives a label value to each casing fault type, performs matching processing on each fault type, the casing area and the three ratios of the casing area, and constructs a sample data set. Taking the jacket area 1 as an example, the characteristic quantities generated are: alpha is alpha 1 、β 1 、γ 1 If the casing region 1 has no fault, it is a normal state,the label value is 0, the rest characteristic quantities are sequentially assigned with 1, 2, 3, \8230andK according to the statistical occurrence probability of various typical faults of the casing from low to high, wherein K represents the K-th fault.
And pruning the initial decision tree model to obtain a pruning decision tree model.
The pruning process may refer to an operation of deleting or pruning the redundant weights and the non-critical weights in the decision tree model.
The pruning decision tree may refer to a decision tree model subjected to pruning.
As an example, to prevent the decision tree model from being over-fit or under-fit, the terminal performs pruning on the initial decision tree, and particularly, pruning is implemented by minimizing the overall loss function of the decision tree, so as to obtain a reliable pruning decision tree model.
And testing the pruning decision tree model by utilizing the test data set in the sample data set to obtain a test result corresponding to the pruning decision tree model.
The test data set may refer to a data set composed of data required for testing the decision tree model.
The test result may be a decision tree output result obtained by testing the pruning decision tree with the test data set.
And under the condition that the test result indicates that the pruning decision tree model passes the test, determining the pruning decision tree model as the target decision tree model.
As an example, the terminal judges the accuracy of the pruning decision tree model by using the test data set, inputs the test data set into the pruning decision tree model, and when the accuracy of the test result output by the pruning decision tree model reaches more than 95%, the pruning decision tree model is regarded as effective, otherwise, the sample data set is updated, and the decision tree model is re-established.
In the embodiment, the initial decision tree model is constructed according to the training data set in the sample data set, after the initial decision tree model is pruned, the pruning decision tree model is tested according to the test data set in the sample data set, and the target decision tree model is determined under the condition that the test result passes, so that pruning optimization and test of the constructed decision tree model can be realized, and the accuracy of the identification result of the decision tree model is improved.
In some embodiments, the training data set includes a plurality of feature quantities; the characteristic quantity is determined according to a three-ratio method; the constructing an initial decision tree model according to the training data set in the sample data set includes:
an information gain ratio of the plurality of feature quantities to the training data set is determined.
The feature quantity may refer to data constituting a sample data set.
In practical application, the calculation formula corresponding to the empirical entropy H (D) of the sample data set or the test data set may be represented as:
the formula for calculating the empirical conditional entropy H (D | a) of a feature on a data set can be expressed as:
the calculation formula of the information gain g (D, a) can be expressed as:
the calculation formula of the information gain ratio gR (D, a) can be expressed as:
and determining the target characteristic quantity according to the information gain ratio corresponding to each characteristic quantity.
The target feature amount may be a feature amount having the largest information gain ratio.
And constructing a decision tree node corresponding to the target characteristic quantity according to the information gain ratio corresponding to the target characteristic quantity.
The decision tree node may refer to a position where data is classified in the representation decision tree model.
And removing the target characteristic quantity from the plurality of characteristic quantities to obtain a plurality of new characteristic quantities.
And returning to the step of determining the information gain ratio of each characteristic quantity to the training data set until the initial decision tree model is obtained.
As an example, as shown in fig. 4, the terminal reads data of all sensing probes in sensing regions under typical faults inside various casings; the terminal combines the three ratio method according to the data of each sensing area to form a sample data set, wherein the training data set is marked as D, n data are in total, a set formed by all characteristic quantities is marked as A, K fault types are supposed to be divided, each fault type is marked as Ck, a decision tree for finally classifying faults is output and marked as T, and the method comprises the following steps of: 2, dividing the data into a training data set and a testing data set, calculating the information gain ratio of each characteristic quantity to D in the A by the terminal, and selecting the characteristic quantity Ag with the maximum information gain ratio G (the characteristic G represents the G-th node of the decision tree); if the information gain ratio G of the Ag is 0, the terminal sets the T as a single node tree, the class Ck with the largest number of instances in the D is taken as the class of the node, the class with the largest number of instances in the D is the fault type with the largest proportion in the training data set, and the decision tree T can be obtained; if the information gain ratio G of the Ag is not 0, for each possible value ai of the Ag, the terminal divides D into a plurality of non-empty subsets according to Ag = ai and records the subsets as Di, the terminal takes the class with the largest number of instances in the Di as a mark to construct sub-nodes, and the nodes and the sub-nodes form a tree to obtain a decision tree T, the terminal removes the characteristic Ag in the characteristic set A to obtain a new characteristic set A, the terminal takes the ith node and the Di as sample data sets, A as the characteristic set, each node is traversed to recursively calculate according to the steps until the decision tree T is obtained and then jumps out of recursion, and then the initial decision tree can be generated preliminarily according to a training data set.
In the embodiment, the information gain ratio of the characteristic quantity is determined, each node of the decision tree model is determined by the information gain ratio, the identification standard of each decision tree node can be accurately controlled, the identification branches are refined, and the accuracy of the identification result of the decision tree model is improved.
In some embodiments, the constructing a decision tree node corresponding to the target feature quantity according to the information gain ratio corresponding to the target feature quantity includes:
and when the information gain ratio corresponding to the target characteristic quantity is 0, taking the fault type with the largest ratio in the training data set as the class corresponding to the single node to form the decision tree model.
As an example, if the information gain ratio G of Ag is 0, the terminal sets T as a single node tree, and takes the class Ck with the largest number of instances in D as the class of the node, and the class with the largest number of instances in D is the fault type occupying the largest proportion in the training data set, so as to obtain the decision tree T.
In this embodiment, when the information gain ratio corresponding to the target feature amount is 0, the branch is established as a single-node branch, and in an extreme case, that is, when the input feature amount is not related to the fault type or has low correlation, the input feature amount can be directly corresponding to the largest fault type, so that the applicability of the decision tree model to data in a data set is improved, and the flexibility of fault identification is improved.
In some embodiments, the constructing a decision tree node corresponding to the target feature quantity according to the information gain ratio corresponding to the target feature quantity further includes:
and when the information gain ratio corresponding to the target characteristic quantity is not 0, dividing the training data set into a plurality of non-empty subsets to obtain data sets corresponding to the divided sub-nodes.
The data sets corresponding to the plurality of child nodes may refer to a plurality of subsets obtained by classifying the feature quantities of the training data in the training data set according to whether the feature quantities are greater than, less than or equal to the target feature quantities.
And taking the fault type with the highest data set occupation ratio corresponding to each child node as the class corresponding to the corresponding child node to form the decision tree model.
As an example, if the information gain ratio G of Ag is not 0, for each possible value ai of Ag, the terminal divides D into a plurality of non-empty subsets according to Ag = ai, and records it as Di, the terminal uses the class with the largest number of instances in Di as a label to construct sub-nodes, and forms a tree by the nodes and their sub-nodes, so as to obtain a decision tree T, the terminal removes the feature Ag in the feature set a to obtain a new feature set a, the terminal uses the ith node, di as a sample data set, a as a feature set, and traverses each node to recursively calculate according to the above method steps until a recursion is skipped after the decision tree T is obtained.
In the embodiment, when the information gain ratio corresponding to the target characteristic quantity is not 0, the sub-node data sets are divided, and the sub-node data sets are divided in a class mode, so that the construction of each branch node of the decision tree can be accurately realized, the identification accuracy of the decision tree model is improved, the C4.5 algorithm of the decision tree is used for training the three ratio value containing the fault region and the fault characteristic gas concentration as the sample data set, and finally the fault diagnosis method capable of realizing the specific fault region is obtained.
In some embodiments, the present application further provides a bushing fault detection system based on oil-immersed bushing gas detection, where the system includes: the system comprises a solid laser, a spectrum detection unit, an optical switch, a sensing probe and computer equipment; the spectrum detection unit is respectively connected with the solid laser, the computer equipment and the optical switch, and the computer equipment is connected with the sensing probe through the optical switch; wherein:
the solid laser is used for sending broadband light to the optical switch through the spectrum detection unit.
Among them, a solid laser may refer to an element for emitting broadband light.
And the optical switch is used for enabling the broadband light sent by the solid laser to enter the sensing probe.
The optical switch may refer to an element controlled by a computer device, and may control whether to allow broadband light to pass through according to a control instruction.
As an example, the optical switch is controlled by a computer to select the passed optical path, namely, the measuring point needing to be measured, and the diffusion of the dissolved gas in the oil is considered to be slow, so that the real-time requirement is not high, and therefore, the gas components and the concentration of each measuring point can be effectively detected by using the computer to control the optical switch.
The sensing probe is provided with nano-scale micropores for gas to pass through, is placed in each area in the oil-immersed sleeve and is used for returning scattered light to the spectrum detection unit; the scattered light is generated after the interaction between the broadband light and the gas in the sensing probe.
The sensing probe can be a gas detection sensing probe placed in each area in an oil immersed bushing, and in the concrete implementation, the sensing probe can be prepared from HC-800-02 type hollow photonic crystal fiber, the length of the sensing probe is not less than 0.5m, the distance between micropores on the side surface of the sensing probe is not more than 10cm, and the exchange of fault gas in the fiber core is ensured.
As an example, as shown in fig. 5, the arrangement of the sensing probe in the oil-immersed bushing may be: the sleeve oil filling area comprises an oil conservator, a guide rod, a capacitor core and a lifting seat oil tank. Considering that the oil in the guide rod and the capacitor core area is fully contacted with the inner structure of the guide rod, a sensing probe is arranged at the axial interval of 20 cm in the two areas, and considering that the dissolved gas in the oil does not relate to the internal fault of the sleeve and does not need to be measured in the case of the lifting seat oil tank, a sensing probe is arranged at the position 15cm away from the top in the area with higher oil flow speed, namely the side close to the capacitor core. Finally, the oil filling area in the casing is divided into a plurality of areas, each area corresponds to one sensing probe, and the dissolved gas concentration information of the area can be directly reflected.
And the spectrum detection unit is used for receiving and analyzing the scattered light returned by the sensing probe to obtain spectrum detection data.
In practical applications, the spectrum detection unit may include a raman probe and a raman spectrometer.
As an example, as shown in fig. 6, a solid laser emits a broadband light, the broadband light passes through a raman probe and reaches an optical switch, a computer device controls an optical path connected to the optical switch to be connected, so that the broadband light reaches a sensing probe, the broadband light interacts with gas molecules inside the sensing probe after reaching the sensing probe to generate backward raman scattering light, a raman spectrometer collects and detects the backward raman scattering light to obtain spectral data, and the computer device collects the spectral data through an acquisition card and analyzes the spectral data to obtain the composition and the concentration of the gas dissolved in the oil.
And the computer equipment is used for acquiring gas concentration data of each region in the oil-immersed sleeve according to the spectrum detection data.
The computer device is further configured to determine a casing region corresponding to the gas concentration data as a suspicious fault region when the gas concentration data satisfies a fault condition.
And the computer equipment is also used for inputting the gas concentration data corresponding to the suspicious fault area into a target decision tree model to obtain a fault type identification result and a fault area identification result corresponding to the gas concentration data.
The computer device is further used for comparing the suspicious fault region with the fault region represented by the fault region identification result, and determining a target fault identification result of the oil-immersed bushing; the target fault identification result comprises a target fault area and a fault type represented by the fault type identification result.
In the embodiment, the optical fiber sensing technology is utilized to realize the direct in-situ detection of the quasi-distributed dissolved gas in the oil filling area inside the sleeve, the oil-gas separation process is not needed, and the problems that the detection period is long and the fault location is difficult to realize due to the single detection area in the traditional detection method are solved.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the present application further provides a bushing fault detection apparatus based on oil-immersed bushing gas detection, for implementing the above-mentioned bushing fault detection method based on oil-immersed bushing gas detection. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the method, so that specific limitations in one or more embodiments of the oil-immersed bushing gas detection-based bushing fault detection device provided below can be referred to the limitations on the bushing fault detection method based on oil-immersed bushing gas detection, and details are not repeated here.
In one embodiment, as shown in fig. 7, there is provided a casing fault detection apparatus based on oil-immersed casing gas detection, including: an acquisition module 702, a determination module 704, a recognition module 706, and a comparison module 708, wherein:
the acquisition module 702 is used for acquiring gas concentration data acquired by gas detection sensing probes placed in various regions in the oil-immersed bushing; the gas detection sensing probe is provided with a nano-scale micropore for gas to pass through;
a determining module 704, configured to determine, when the gas concentration data meets a fault condition, a casing region corresponding to the gas concentration data as a suspected fault region;
the identification module 706 is configured to input the gas concentration data corresponding to the suspicious fault region into a target decision tree model, so as to obtain a fault type identification result and a fault region identification result corresponding to the gas concentration data;
a comparison module 708, configured to compare the suspicious fault region with a fault region represented by the fault region identification result, and determine a target fault identification result of the oil-immersed bushing; the target fault identification result comprises a target fault area and a fault type represented by the fault type identification result.
In one embodiment, the determining module 704 is further configured to obtain a gas concentration threshold for a gas type of the casing region; and under the condition that the gas concentration data is larger than the gas concentration threshold value, determining that the casing region corresponding to the gas concentration data is the suspicious fault region.
In one embodiment, the apparatus further includes a decision tree module, where the decision tree module is specifically configured to obtain a sample data set, and construct an initial decision tree model according to a training data set in the sample data set; pruning the initial decision tree model to obtain a pruning decision tree model; testing the pruning decision tree model by utilizing the test data set in the sample data set to obtain a test result corresponding to the pruning decision tree model; determining the pruning decision tree model as the target decision tree model if the test result indicates that the pruning decision tree model passes the test.
In one embodiment, the decision tree module is further specifically configured to determine an information gain ratio of the plurality of feature quantities to the training data set; determining target characteristic quantities according to information gain ratios corresponding to the characteristic quantities; according to the information gain ratio corresponding to the target characteristic quantity, a decision tree node corresponding to the target characteristic quantity is constructed; removing the target characteristic quantity from the plurality of characteristic quantities to obtain a plurality of new characteristic quantities; returning to the step of determining the information gain ratio of each characteristic quantity to the training data set until the initial decision tree model is obtained; the training data set includes a plurality of feature quantities; the characteristic quantity is determined according to a three-ratio method.
In one embodiment, the decision tree module is further specifically configured to, when the information gain ratio corresponding to the target feature quantity is 0, use the fault type with the largest proportion in the training data set as a class corresponding to a single node to form the decision tree model.
In one embodiment, the decision tree module is further configured to divide the training data set into a plurality of non-empty subsets when the information gain ratio corresponding to the target feature quantity is not 0, so as to obtain a data set corresponding to the divided sub-nodes; and taking the fault type with the highest data set occupation ratio corresponding to each child node as the class corresponding to the corresponding child node to form the decision tree model.
All or part of each module in the oil-immersed bushing gas detection-based bushing fault detection device can be realized through software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 8. The computer apparatus includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input device. The processor, the memory and the input/output interface are connected by a system bus, and the communication interface, the display unit and the input device are connected by the input/output interface to the system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The input/output interface of the computer device is used for exchanging information between the processor and an external device. The communication interface of the computer device is used for communicating with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a method for casing fault detection based on oil-immersed casing gas detection. The display unit of the computer device is used for forming a visual picture and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the configuration shown in fig. 8 is a block diagram of only a portion of the configuration associated with the present application, and is not intended to limit the computing device to which the present application may be applied, and that a particular computing device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is further provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method embodiments when executing the computer program.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, carries out the steps in the method embodiments described above.
It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the relevant laws and regulations and standards of the relevant country and region.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), magnetic Random Access Memory (MRAM), ferroelectric Random Access Memory (FRAM), phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the various embodiments provided herein may be, without limitation, general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, or the like.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (10)
1. A bushing fault detection method based on oil-immersed bushing gas detection is characterized by comprising the following steps:
acquiring gas concentration data acquired by gas detection sensing probes placed in various regions in the oil-immersed bushing; the gas detection sensing probe is provided with a nano-scale micropore for gas to pass through;
determining a casing region corresponding to the gas concentration data as a suspicious fault region under the condition that the gas concentration data meets a fault condition;
inputting gas concentration data corresponding to the suspicious fault area into a target decision tree model to obtain a fault type identification result and a fault area identification result;
comparing the suspicious fault area with the fault area represented by the fault area identification result, and determining a target fault identification result of the oil-immersed bushing; the target fault identification result comprises a target fault area and a fault type represented by the fault type identification result.
2. The method of claim 1, wherein determining the casing region corresponding to the gas concentration data as a suspected fault region in the case that the gas concentration data satisfies a fault condition comprises:
obtaining a gas concentration threshold for a gas type of the casing region;
and under the condition that the gas concentration data is larger than the gas concentration threshold value, determining that the casing area corresponding to the gas concentration data is the suspicious fault area.
3. The method of claim 1, further comprising:
acquiring a sample data set, and constructing an initial decision tree model according to a training data set in the sample data set;
pruning the initial decision tree model to obtain a pruning decision tree model;
testing the pruning decision tree model by utilizing the test data set in the sample data set to obtain a test result corresponding to the pruning decision tree model;
and under the condition that the test result indicates that the pruning decision tree model passes the test, determining the pruning decision tree model as the target decision tree model.
4. The method according to claim 3, characterized in that the training data set includes a plurality of feature quantities; the characteristic quantity is determined according to a three-ratio method; the constructing an initial decision tree model according to the training data set in the sample data set comprises:
determining an information gain ratio of each feature quantity in the training data set to the training data set;
determining target characteristic quantities according to information gain ratios corresponding to the characteristic quantities;
according to the information gain ratio corresponding to the target characteristic quantity, a decision tree node corresponding to the target characteristic quantity is constructed;
removing the target characteristic quantity from the plurality of characteristic quantities to obtain a plurality of new characteristic quantities;
and returning to the step of determining the information gain ratio of each characteristic quantity to the training data set until the initial decision tree model is obtained.
5. The method according to claim 4, wherein the constructing the decision tree node corresponding to the target feature quantity according to the information gain ratio corresponding to the target feature quantity comprises:
and when the information gain ratio corresponding to the target characteristic quantity is 0, taking the fault type with the largest ratio in the training data set as the class corresponding to the single node to form the initial decision tree model.
6. The method according to claim 4, wherein the constructing the decision tree node corresponding to the target feature quantity according to the information gain ratio corresponding to the target feature quantity further comprises:
when the information gain ratio corresponding to the target characteristic quantity is not 0, dividing the training data set into a plurality of non-empty subsets to obtain data sets corresponding to a plurality of divided sub-nodes;
and taking the fault type with the highest data set occupation ratio corresponding to each child node as the class corresponding to the corresponding child node to form the initial decision tree model.
7. A bushing fault detection system based on oil-immersed bushing gas detection, the system comprising: the system comprises a solid laser, a spectrum detection unit, an optical switch, a sensing probe and computer equipment; the spectrum detection unit is respectively connected with the solid laser, the computer equipment and the optical switch, and the computer equipment is connected with the sensing probe through the optical switch; wherein:
the solid laser is used for sending broadband light to the optical switch through the spectrum detection unit;
the optical switch is used for enabling the broadband light sent by the solid laser to enter the sensing probe;
the sensing probe is provided with nano-scale micropores for gas to pass through, is placed in each area in the oil-immersed sleeve and is used for returning scattered light to the spectrum detection unit; the scattered light is generated after the interaction between the broadband light and the gas in the sensing probe;
the spectrum detection unit is used for receiving and analyzing the scattered light returned by the sensing probe to obtain spectrum detection data;
the computer equipment is used for acquiring gas concentration data of each region in the oil-immersed bushing according to the spectrum detection data;
the computer device is further configured to determine a casing region corresponding to the gas concentration data as a suspected fault region when the gas concentration data satisfies a fault condition;
the computer equipment is also used for inputting the gas concentration data corresponding to the suspicious fault area into a target decision tree model to obtain a fault type identification result and a fault area identification result;
the computer device is further configured to compare the suspicious fault region with a fault region represented by the fault region identification result, and determine a target fault identification result of the oil-immersed bushing; the target fault identification result comprises a target fault area and a fault type represented by the fault type identification result.
8. A casing fault detection device based on oil-immersed casing gas detection, characterized in that the device comprises:
the acquisition module is used for acquiring gas concentration data acquired by the gas detection sensing probes placed in all areas in the oil-immersed bushing; the gas detection sensing probe is provided with a nano-scale micropore for gas to pass through;
the determining module is used for determining the casing area corresponding to the gas concentration data as a suspicious fault area under the condition that the gas concentration data meet the fault condition;
the identification module is used for inputting the gas concentration data corresponding to the suspicious fault area into a target decision tree model to obtain a fault type identification result and a fault area identification result;
the comparison module is used for comparing the suspicious fault area with the fault area represented by the fault area identification result and determining a target fault identification result of the oil-immersed bushing; the target fault identification result comprises a target fault area and a fault type represented by the fault type identification result.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211660424.1A CN115639327B (en) | 2022-12-21 | 2022-12-21 | Sleeve fault detection method and device based on oil-immersed sleeve gas detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211660424.1A CN115639327B (en) | 2022-12-21 | 2022-12-21 | Sleeve fault detection method and device based on oil-immersed sleeve gas detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115639327A CN115639327A (en) | 2023-01-24 |
| CN115639327B true CN115639327B (en) | 2023-04-07 |
Family
ID=84949825
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211660424.1A Active CN115639327B (en) | 2022-12-21 | 2022-12-21 | Sleeve fault detection method and device based on oil-immersed sleeve gas detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115639327B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115934005B (en) * | 2023-03-13 | 2023-09-22 | 深圳中科超算技术有限公司 | Data storage method and system |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4377542B2 (en) * | 2000-10-20 | 2009-12-02 | 株式会社東芝 | Internal partial discharge monitoring device for high voltage equipment |
| CN103995215B (en) * | 2014-05-08 | 2016-07-13 | 国家电网公司 | A kind of smart power grid fault diagnostic method based on multi-level feedback adjustment |
| CN107016507A (en) * | 2017-04-07 | 2017-08-04 | 国网技术学院 | Electric network fault method for tracing based on data mining technology |
| CN109298993B (en) * | 2017-07-21 | 2022-07-29 | 深圳市中兴微电子技术有限公司 | Method and device for detecting fault and computer readable storage medium |
| CN110068741A (en) * | 2019-05-29 | 2019-07-30 | 国网河北省电力有限公司石家庄供电分公司 | A method of the transformer fault diagnosis based on categorised decision tree |
| CN111222556B (en) * | 2019-12-31 | 2023-12-05 | 中国南方电网有限责任公司 | Method and system for identifying electricity utilization category based on decision tree algorithm |
| CN111339872A (en) * | 2020-02-18 | 2020-06-26 | 国网信通亿力科技有限责任公司 | Power grid fault classification method based on classification model |
| CN113159113B (en) * | 2021-03-09 | 2022-07-01 | 西华大学 | Smart power grid fault diagnosis method capable of repairing remote measurement under information malicious tampering |
| CN113516297B (en) * | 2021-05-26 | 2024-03-19 | 平安国际智慧城市科技股份有限公司 | Prediction method and device based on decision tree model and computer equipment |
| CN113466372A (en) * | 2021-07-01 | 2021-10-01 | 国网四川省电力公司电力科学研究院 | Quick on-line monitoring device of multiple spot position transformer |
| CN114113887B (en) * | 2021-11-22 | 2023-06-20 | 深圳供电局有限公司 | Fault positioning method and system for power distribution network |
| CN114492595A (en) * | 2021-12-31 | 2022-05-13 | 贵州电网有限责任公司 | Decision tree-based transformer fault diagnosis method |
| CN114895222A (en) * | 2022-04-29 | 2022-08-12 | 三峡大学 | Diagnosis method for identifying various faults and multiple faults of transformer |
| CN115453284A (en) * | 2022-08-30 | 2022-12-09 | 国网福建省电力有限公司电力科学研究院 | Main transformer online chromatographic detection discharge fault simulation device and method |
-
2022
- 2022-12-21 CN CN202211660424.1A patent/CN115639327B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115639327A (en) | 2023-01-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kalyuzhny et al. | A neutral theory with environmental stochasticity explains static and dynamic properties of ecological communities | |
| Matthews et al. | Multimodal species abundance distributions: a deconstruction approach reveals the processes behind the pattern | |
| CN112129741B (en) | Insulating oil aging analysis method and device, computer equipment and storage medium | |
| CN115639327B (en) | Sleeve fault detection method and device based on oil-immersed sleeve gas detection | |
| CN115080742A (en) | Text information extraction method, device, equipment, storage medium and program product | |
| CN111680506A (en) | External key mapping method and device of database table, electronic equipment and storage medium | |
| CN115841046A (en) | Accelerated degradation test data processing method and device based on wiener process | |
| CN110968802B (en) | Analysis method and analysis device for user characteristics and readable storage medium | |
| Liu et al. | Analysis of large heterogeneous repairable system reliability data with static system attributes and dynamic sensor measurement in big data environment | |
| CN115659985A (en) | Electric power knowledge graph entity alignment method and device and computer equipment | |
| JP2023536773A (en) | Text quality evaluation model training method and text quality determination method, device, electronic device, storage medium and computer program | |
| Khalyasmaa et al. | Data mining applied to decision support systems for power transformers’ health diagnostics | |
| CN116827971B (en) | Block chain-based carbon emission data storage and transmission method, device and equipment | |
| Priyanka et al. | Rank-based risk target data analysis using digital twin on oil pipeline network based on manifold learning | |
| CN113946983A (en) | Method and device for evaluating weak links of product reliability and computer equipment | |
| CN116503031B (en) | Personnel similarity calculation method, device, equipment and medium based on resume analysis | |
| CN116050475A (en) | Training method and device for key pollutant concentration prediction model and computer equipment | |
| CN113518010B (en) | Link prediction method, device and storage medium | |
| CN116071864A (en) | Early warning processing method, device, equipment, storage medium and computer program product | |
| CN111985163A (en) | Rubidium clock life prediction method and device | |
| Matuzas et al. | On the efficiency of functional decomposition in fault tree analysis | |
| Fletcher et al. | Species distributions | |
| CN109284861A (en) | Prediction processing method, medium, device and calculating equipment | |
| CN115604130B (en) | APP popularity prediction model construction method, prediction method, device and storage medium | |
| CN113434713B (en) | Forestry big data construction method and system based on one graph |
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 |