CN113758652B - Oil leakage detection method and device for converter transformer, computer equipment and storage medium - Google Patents
Oil leakage detection method and device for converter transformer, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113758652B CN113758652B CN202111033198.XA CN202111033198A CN113758652B CN 113758652 B CN113758652 B CN 113758652B CN 202111033198 A CN202111033198 A CN 202111033198A CN 113758652 B CN113758652 B CN 113758652B
- Authority
- CN
- China
- Prior art keywords
- data
- oil temperature
- oil
- temperature data
- neural network
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 60
- 238000003062 neural network model Methods 0.000 claims abstract description 139
- 238000000034 method Methods 0.000 claims abstract description 52
- 230000008569 process Effects 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims description 116
- 238000012795 verification Methods 0.000 claims description 61
- 230000007774 longterm Effects 0.000 claims description 38
- 238000011156 evaluation Methods 0.000 claims description 27
- 238000004590 computer program Methods 0.000 claims description 24
- 230000015654 memory Effects 0.000 claims description 19
- 238000001914 filtration Methods 0.000 claims description 17
- 238000009826 distribution Methods 0.000 claims description 14
- 238000002372 labelling Methods 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 7
- 238000002759 z-score normalization Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 description 12
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 230000007787 long-term memory Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000000670 limiting effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000002829 reductive effect Effects 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 1
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
- G01M3/26—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Housings And Mounting Of Transformers (AREA)
Abstract
The application relates to a converter transformer oil leakage detection method, a converter transformer oil leakage detection device, computer equipment and a storage medium. The method comprises the steps of obtaining real-time oil temperature data and real-time oil level data of a converter transformer to be detected; inputting the real-time oil temperature data into a preset Bayes long-short-term neural network model, and obtaining an oil level prediction result corresponding to the real-time oil temperature data; and acquiring an oil leakage detection result corresponding to the converter transformer according to the oil level prediction result and the real-time oil level data. According to the method and the device, the corresponding relation between the real-time oil temperature data and the oil level data in the historical data is learned through the preset Bayes long-short-term neural network model, then the predicted oil level prediction result is obtained through the real-time oil temperature data, whether the converter transformer to be detected has oil leakage or not is determined through comparison of the real-time oil level data and the oil level prediction result, oil leakage detection can be carried out on the converter transformer at any time, and the detection timeliness of the oil leakage detection process is guaranteed.
Description
Technical Field
The application relates to the field of power distribution of power grids, in particular to a method and a device for detecting oil leakage of a converter transformer, computer equipment and a storage medium.
Background
The distribution network refers to a power network that receives electric energy from a power transmission network or a regional power plant, and distributes the electric energy locally or step by step according to voltage through a distribution facility. The system consists of overhead lines, cables, towers, distribution transformers, isolating switches, reactive compensators, a plurality of auxiliary facilities and the like, and plays a role in distributing electric energy in a power network. The converter transformer is core equipment in a high-voltage direct-current transmission system, and is insulated by oil commonly used in the converter transformer. The common oil conservator of the converter transformer stores oil, and the oil level in the oil conservator can be increased and reduced along with the increase of the oil temperature of the converter transformer body.
At present, only when the oil level of a conservator of the converter transformer is lower than a certain value, the oil leakage detection system can alarm, and early warning at the oil leakage stage just begins can not be realized. And when oil seepage occurs, the oil level of the converter transformer oil conservator is possibly influenced by high oil temperature and cannot drop, and the oil leakage condition cannot be judged in time according to the oil level.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a method, an apparatus, a computer device, and a storage medium for detecting oil leakage of a converter transformer, which can detect oil leakage in time.
A method of detecting oil leakage of a converter transformer, the method comprising:
Acquiring real-time oil temperature data and real-time oil level data of a converter transformer to be detected;
inputting the real-time oil temperature data into a preset Bayes long-short period neural network model, and acquiring an oil level prediction result corresponding to the real-time oil temperature data, wherein the preset Bayes long-short period neural network model is obtained based on the historical oil temperature data and the historical oil level data of the converter transformer in a training way;
and acquiring an oil leakage detection result corresponding to the converter transformer according to the oil level prediction result and the real-time oil level data.
In one embodiment, before inputting the real-time oil temperature data into a preset bayesian long-short-term neural network model and obtaining the oil level prediction result corresponding to the real-time oil temperature data, the method further includes:
acquiring oil temperature data in historical data and oil level data corresponding to the oil temperature data;
labeling the oil temperature data through the oil level data corresponding to the oil temperature data to obtain model training data;
and training the initial Bayes long-term neural network model through the model training data to obtain a preset Bayes long-term neural network model.
In one embodiment, the marking the oil temperature data by the oil level data corresponding to the oil temperature data, and obtaining model training data includes:
Filtering the oil temperature data and the oil level data based on an isolated forest algorithm;
extracting oil level data corresponding to the filtered oil temperature data;
and marking the oil temperature data according to the oil level data corresponding to the oil temperature data after the filtering treatment, and obtaining model training data.
In one embodiment, the marking the oil temperature data by the oil level data corresponding to the oil temperature data, and obtaining model training data includes:
performing a normalization process on the oil temperature data and the oil level data by a z-score normalization process;
extracting oil level data corresponding to the standardized oil temperature data;
and marking the oil temperature data according to the oil level data corresponding to the standardized oil temperature data, and obtaining model training data.
In one embodiment, the model training data includes training set data and verification set data, and the training the initial bayesian long-short-term neural network model by the model training data includes:
training the initial Bayes long-short-term neural network model through the training set data to obtain a Bayes long-short-term neural network model to be verified;
And verifying the Bayesian long-short-term neural network model to be verified through the verification group data, and taking the Bayesian long-short-term neural network model to be verified as a preset Bayesian long-short-term neural network model when verification passes.
In one embodiment, the verifying the bayesian long-short-term neural network model to be verified through the verification set data includes:
inputting the oil temperature data in the verification group data into the Bayes long-term and short-term neural network model to be verified, and obtaining verification oil level data;
acquiring evaluation index data corresponding to a Bayes long-short-term neural network model to be verified based on oil level marking data corresponding to the oil temperature data and the verification oil level data;
and when the evaluation index data is lower than a preset evaluation index threshold, judging that the Bayesian long-short-term neural network model to be verified passes verification.
An oil leakage detection device for a converter transformer, the device comprising:
the data acquisition module is used for acquiring real-time oil temperature data and real-time oil level data of the converter transformer to be detected;
the oil level prediction module is used for inputting the real-time oil temperature data into a preset Bayes long-short-period neural network model to obtain an oil level prediction result corresponding to the real-time oil temperature data, and the preset Bayes long-period neural network model is obtained based on the historical oil temperature data and the historical oil level data of the converter transformer in a training mode;
And the oil leakage detection module is used for acquiring an oil leakage detection result corresponding to the converter transformer according to the oil level prediction result and the real-time oil level data.
In one embodiment, the method further comprises a model training module for:
acquiring oil temperature data in historical data and oil level data corresponding to the oil temperature data;
labeling the oil temperature data through the oil level data corresponding to the oil temperature data to obtain model training data;
and training the initial Bayes long-term neural network model through the model training data to obtain a preset Bayes long-term neural network model.
A computer device comprising a memory storing a computer program and a processor which when executing the computer program performs the steps of:
acquiring real-time oil temperature data and real-time oil level data of a converter transformer to be detected;
inputting the real-time oil temperature data into a preset Bayes long-short period neural network model, and acquiring an oil level prediction result corresponding to the real-time oil temperature data, wherein the preset Bayes long-short period neural network model is obtained based on the historical oil temperature data and the historical oil level data of the converter transformer in a training way;
And acquiring an oil leakage detection result corresponding to the converter transformer according to the oil level prediction result and the real-time oil level data.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring real-time oil temperature data and real-time oil level data of a converter transformer to be detected;
inputting the real-time oil temperature data into a preset Bayes long-short period neural network model, and acquiring an oil level prediction result corresponding to the real-time oil temperature data, wherein the preset Bayes long-short period neural network model is obtained based on the historical oil temperature data and the historical oil level data of the converter transformer in a training way;
and acquiring an oil leakage detection result corresponding to the converter transformer according to the oil level prediction result and the real-time oil level data.
According to the oil leakage detection method, the oil leakage detection device, the computer equipment and the storage medium for the converter transformer, the real-time oil temperature data and the real-time oil level data of the converter transformer to be detected are obtained; inputting the real-time oil temperature data into a preset Bayes long-short-term neural network model, and obtaining an oil level prediction result corresponding to the real-time oil temperature data; and acquiring an oil leakage detection result corresponding to the converter transformer according to the oil level prediction result and the real-time oil level data. According to the method and the device, the corresponding relation between the real-time oil temperature data and the oil level data in the historical data is learned through the preset Bayes long-short-term neural network model, then the predicted oil level prediction result is obtained through the real-time oil temperature data, whether the converter transformer to be detected has oil leakage or not is determined through comparison of the real-time oil level data and the oil level prediction result, oil leakage detection can be carried out on the converter transformer at any time, and the detection timeliness of the oil leakage detection process is guaranteed.
Drawings
FIG. 1 is a diagram of an application environment of a method for detecting oil leakage of a converter transformer according to an embodiment;
FIG. 2 is a flow chart of a method for detecting oil leakage of a converter transformer according to an embodiment;
FIG. 3 is a schematic diagram of the operation of a Bayes long-term and short-term memory neural network according to one embodiment:
FIG. 4 is a flow chart of a model training step in one embodiment;
FIG. 5 is a flow chart illustrating the steps for obtaining model training data in one embodiment;
FIG. 6 is a flowchart illustrating a step of obtaining model training data according to another embodiment;
FIG. 7 is a block diagram of an oil leakage detection device of a converter transformer according to an embodiment;
fig. 8 is an internal structural diagram of a computer device in one embodiment.
Description of the embodiments
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The oil leakage detection method of the converter transformer can be applied to an application environment shown in fig. 1. The terminal 102 is connected to the server 104 through a network, where the terminal 102 may predict, by sending real-time oil temperature data of the converter transformer to be detected to the server 104, a state of the converter transformer to be detected through the server 104, and determine whether an oil leakage condition exists in the converter transformer to be detected. The server 104 may obtain real-time oil temperature data and real-time oil level data of the converter transformer to be detected; inputting the real-time oil temperature data into a preset Bayes long-short-period neural network model, obtaining an oil level prediction result corresponding to the real-time oil temperature data, and training and obtaining the preset Bayes long-period neural network model based on the historical oil temperature data and the historical oil level data of the converter transformer; and acquiring an oil leakage detection result corresponding to the converter transformer according to the oil level prediction result and the real-time oil level data. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smartphones, tablet computers, portable wearable devices, oil temperature detection sensing devices on a converter transformer to be detected, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers, or may be a cloud server.
In one embodiment, as shown in fig. 2, a method for detecting oil leakage of a converter transformer is provided, and this embodiment is described by taking the application of the method to the server 104 in fig. 1 as an example. In this embodiment, the method includes the steps of:
step 201, acquiring real-time oil temperature data and real-time oil level data of a converter transformer to be detected.
The converter transformer to be detected is a target object detected by the oil leakage detection method of the converter transformer, and the converter transformer refers to a power transformer connected between a converter bridge and an alternating current system. The converter transformer is used for realizing the connection of the converter bridge and the alternating current bus, and providing a three-phase conversion voltage with a neutral point not grounded for the converter bridge, which not only participates in the mutual conversion of alternating current and direct current of the converter, but also plays roles of changing the value of the alternating current voltage, inhibiting direct current short-circuit current and the like. The converter transformer is core equipment in a high-voltage direct-current transmission system, and is insulated by oil commonly used in the converter transformer. The common oil conservator of the converter transformer stores oil, and the oil level in the oil conservator can be increased and reduced along with the increase of the oil temperature of the converter transformer body. The real-time oil temperature data is basic data detected by the oil leakage detection method of the converter transformer, and the real-time oil temperature data can be obtained by detecting a sensor for monitoring the real-time oil temperature data of the converter transformer. The real-time oil level data can also be measured by an oil level detection sensor of the converter transformer to be detected.
Specifically, the oil leakage detection method for the converter transformer can specifically detect oil leakage of the converter transformer based on the corresponding relation between the oil temperature and the oil level in the current converter transformer. Therefore, the neural network model can be trained based on the historical data corresponding to the current converter transformer to be detected, when the specific oil leakage condition needs to be predicted, the predicted oil level corresponding to the converter transformer to be detected can be determined through the real-time oil temperature data of the converter transformer to be detected, and whether the oil leakage condition exists in the current converter transformer can be recognized through comparing the predicted oil level with the actual oil level.
And 203, inputting the real-time oil temperature data into a preset Bayes long-short-period neural network model, obtaining an oil level prediction result corresponding to the real-time oil temperature data, and training and obtaining the preset Bayes long-period neural network model based on the historical oil temperature data and the historical oil level data of the converter transformer.
The bayesian long-term neural network model specifically refers to a long-term memory neural network based on bayesian optimization, which is the same as the traditional long-term memory neural network in principle, and specifically can refer to fig. 3, f in fig. 3 t I is a forgetful door t For input door, C t To update the gate, O t The output door is provided with a plurality of output doors,
respectively the weight and bias of the corresponding gate, h t-1 For the output of the last moment, x t Is the input at this point. />
And tan h are both activation functions, respectively:
the forget gate, the input gate, the update gate and the output gate are respectively:
the Bayes long-short-term memory neural network is different from the traditional long-short-term neural network in that the Bayes long-short-term neural network utilizes probability density distribution to sample weights and offsets, and then optimizes distribution parameters, wherein the formula is as follows:
parameters ρ and μ are used to represent different weight and bias distributions.
Specifically, after the real-time oil temperature data is obtained, a preset bayesian long-short-term neural network model corresponding to the current converter transformer to be detected can be matched, the preset bayesian long-short-term neural network model is obtained based on the historical oil temperature data and the oil level data training of the converter transformer, for example, for oil leakage detection in the current year, the real-time oil temperature data and the oil level data of the converter transformer to be detected in normal operation in the last year can be used as matched training data to train and obtain the preset bayesian long-short-term neural network model, and therefore oil level detection of the converter transformer to be detected in real time is achieved. In one embodiment, the preset bayesian long-short term neural network model of the present application may be implemented in a system with an environment of python3.7.5 and pytorch1.5.1, and includes 2 hidden layers and 1 output layer, the number of neurons in the hidden layers is 20, the loss function uses a mean square error MSE, and the optimization algorithm is Adam.
And 205, acquiring an oil leakage detection result corresponding to the converter transformer according to the oil level prediction result and the real-time oil level data.
Specifically, after the oil level prediction result corresponding to the real-time oil temperature data is obtained through a preset Bayes long-short-term neural network model, the final oil leakage detection result can be determined through comparison of the oil level prediction result and the real-time oil level data, and if the oil level data of the oil level prediction result is abnormal compared with the real-time oil level data, if the oil level data is too low, the oil leakage phenomenon of the converter transformer can be judged.
According to the oil leakage detection method of the converter transformer, the real-time oil temperature data and the real-time oil level data of the converter transformer to be detected are obtained; inputting the real-time oil temperature data into a preset Bayes long-short-term neural network model, and obtaining an oil level prediction result corresponding to the real-time oil temperature data; and acquiring an oil leakage detection result corresponding to the converter transformer according to the oil level prediction result and the real-time oil level data. According to the method and the device, the corresponding relation between the real-time oil temperature data and the oil level data in the historical data is learned through the preset Bayes long-short-term neural network model, then the predicted oil level prediction result is obtained through the real-time oil temperature data, whether the converter transformer to be detected has oil leakage or not is determined through comparison of the real-time oil level data and the oil level prediction result, oil leakage detection can be carried out on the converter transformer at any time, and the detection timeliness of the oil leakage detection process is guaranteed.
In one embodiment, as shown in fig. 4, before step 203, the method further includes: .
Step 401, acquiring oil temperature data in the history data and oil level data corresponding to the oil temperature data.
And 403, marking the oil temperature data through the oil level data corresponding to the oil temperature data, and obtaining model training data.
And step 405, training the initial Bayes long-term neural network model through model training data to obtain a preset Bayes long-term neural network model.
The historical data can be specifically oil temperature data and oil level data corresponding to the oil temperature data in the normal operation process of the converter transformer to be detected in a certain latest time period.
Specifically, before the oil level data is predicted through the preset Bayesian long-short-term neural network model, training of the preset Bayesian long-short-term neural network model can be completed through historical data, in the training process, oil temperature data in the historical data and the oil level data corresponding to the oil temperature data can be acquired first, then the oil level data is marked with the oil level data to form marked model training data, and then the initial Bayesian long-short-term neural network model is subjected to supervised training through the marked model training to obtain the preset Bayesian long-short-term neural network model. In this embodiment, the model training data is constructed by the oil temperature data in the history data and the oil level data corresponding to the oil temperature data, so that the preset bayesian long-short-term neural network model is completed, and the recognition accuracy of the preset bayesian long-term neural network model in recognizing the oil level data can be effectively ensured.
In one embodiment, as shown in FIG. 5, step 403 includes:
and step 502, filtering the oil temperature data and the oil level data based on an isolated forest algorithm.
And 504, extracting oil level data corresponding to the filtered oil temperature data.
And 506, marking the oil temperature data according to the oil level data corresponding to the filtered oil temperature data, and obtaining model training data.
The isolated forest is an anomaly detection method, a binary tree is adopted to segment data, and the depth of the data point in the binary tree represents the data separation degree. Let the iTree be a binary tree structure. The depth of data x in each itrate is: h (x) =e+c (n)
Wherein e represents the number of edges passing through in the process of data from a root node to leaf nodes of a binary tree structure iTree, n is the number of training samples, C (n) represents the average depth of the constructed binary tree, and a calculation formula of C (n) is as follows:
Specifically, due to acquisition errors and other reasons, abnormality may occur in the oil temperature data in the historical data and part of the data in the oil level data, so that the oil temperature data and the oil level data can be filtered by an isolated forest algorithm before model training is performed. In the filtering process, if any one of the oil level or oil temperature data is abnormal, a group of data corresponding to the oil level or oil temperature data can be removed, and after the filtering is finished, the oil level data corresponding to the oil temperature data after the filtering is extracted; and labeling the oil temperature data according to the oil level data corresponding to the oil temperature data after filtering processing, and obtaining model training data. In the scheme in the embodiment, the oil temperature data and the oil level data in the historical data are detected mainly through an isolated forest to perform abnormality detection, and data errors caused by factors such as faults of the oil temperature and oil level sensor are removed. The isolated forest is an unsupervised anomaly detection method suitable for continuous data, namely, the method does not need to be trained by marked samples, has linear time complexity and high precision, and is a state-of-the-art algorithm meeting the requirement of big data processing. Therefore, the data quality of model training data is improved, and the recognition accuracy of the preset Bayes long-short-term neural network model is further improved.
In one embodiment, as shown in fig. 6, step 403 further includes:
in step 601, the oil temperature data and the oil level data are normalized by the z-score normalization process.
And 603, extracting oil level data corresponding to the normalized oil temperature data.
And step 605, marking the oil temperature data according to the oil level data corresponding to the standardized oil temperature data, and obtaining model training data.
Before model training data are built, the oil temperature data and the oil level data can be standardized, so that training efficiency of subsequent model training and detection efficiency of an oil leakage detection process of the converter transformer are improved. The data normalization modes include Min-max normalization (Min-max normalization), log function conversion, atan function conversion, z-score normalization, fuzzy quantization, etc. The z-score normalization is used herein. Compared with other normalization methods, the data subjected to the z-score normalization process accords with normal distribution.
Specifically, in the model training process, the oil temperature data and the oil level data can be standardized through the z-score standardization process; then extracting oil level data corresponding to the standardized oil temperature data; and marking the oil temperature data according to the oil level data corresponding to the standardized oil temperature data, and obtaining model training data. In this embodiment, the data is normalized. The calculation efficiency of the subsequent processing process can be effectively improved.
In one embodiment, the model training data includes training set data and validation set data, step 405 includes: training the initial Bayes long-term and short-term neural network model through training group data to obtain a Bayes long-term and short-term neural network model to be verified; and verifying the Bayesian long-short-term neural network model to be verified through verification group data, and taking the Bayesian long-short-term neural network model to be verified as a preset Bayesian long-short-term neural network model when verification passes.
Specifically, in the training process, in order to ensure the availability of the obtained preset bayesian long-short term neural network model, model training data can be divided into two groups, namely a training group and a verification group. The training set data is used for training the initial Bayesian long-short-term neural network model and obtaining the Bayesian long-short-term neural network model to be verified in the middle process. And then verifying the Bayesian long-short-term neural network model to be verified through verification group data, and outputting the Bayesian long-short-term neural network model to be verified as a preset Bayesian long-short-term neural network model when verification passes. And when the verification is not passed, the parameters need to be adjusted to retrain until the verification is passed. In this embodiment, through training and verification of the initial bayesian long-short-term neural network model, usability of the obtained preset bayesian long-short-term neural network model can be guaranteed, and therefore accuracy of oil leakage detection of the converter transformer is guaranteed.
In one embodiment, verifying the bayesian long-short neural network model to be verified by the verification set data comprises: inputting oil temperature data in verification group data into a Bayes long-term and short-term neural network model to be verified, and obtaining verification oil level data; acquiring evaluation index data corresponding to a Bayes long-term and short-term neural network model to be verified based on oil level marking data corresponding to oil temperature data and verification oil level data; and when the evaluation index data is lower than a preset evaluation index threshold, judging that the Bayesian long-short-term neural network model to be verified passes verification.
Specifically, when the Bayesian long-short neural network model to be verified is verified through the verification group data, the actual oil leakage detection process of the converter transformer can be simulated. Acquiring verification oil level data by inputting oil temperature data in verification group data into a Bayes long-term and short-term neural network model to be verified; acquiring evaluation index data corresponding to a Bayes long-term and short-term neural network model to be verified based on oil level marking data corresponding to oil temperature data and verification oil level data; and when the evaluation index data is lower than a preset evaluation index threshold, judging that the Bayesian long-short-term neural network model to be verified passes verification. In the verification process, the Bayesian long-short-term neural network model to be verified can be verified by using a plurality of different errors, such as data of average absolute error (MAE), average absolute percentage error (MAPE), root Mean Square Error (RMSE) and the like, by solving the evaluation index data corresponding to each different oil temperature data in the verification group data and solving the average value, when the data all meet the preset evaluation index threshold value, the Bayesian long-short-term neural network model to be verified is judged to pass the verification. In this embodiment, whether the bayesian long-short-term neural network model to be verified is effective or not is judged by presetting an evaluation index threshold, and the preset bayesian long-short-term neural network model meeting the expected requirement can be effectively obtained.
It should be understood that, although the steps in the flowcharts of fig. 2-6 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2-6 may include multiple steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the steps or stages in other steps or other steps.
In one embodiment, as shown in fig. 7, there is provided an oil leakage detection apparatus for a converter transformer, including:
the data acquisition module 702 is configured to acquire real-time oil temperature data and real-time oil level data of the converter transformer to be detected.
The oil level prediction module 704 is configured to input the real-time oil temperature data into a preset bayesian long-short-term neural network model, obtain an oil level prediction result corresponding to the real-time oil temperature data, and train and obtain the preset bayesian long-term neural network model based on the historical oil temperature data and the historical oil level data of the converter transformer.
And the oil leakage detection module 706 is configured to obtain an oil leakage detection result corresponding to the converter transformer according to the oil level prediction result and the real-time oil level data.
In one embodiment, the method further comprises a model training module for: acquiring oil temperature data in the historical data and oil level data corresponding to the oil temperature data; labeling the oil temperature data through the oil level data corresponding to the oil temperature data to obtain model training data; and training the initial Bayes long-short-term neural network model through model training data to obtain a preset Bayes long-short-term neural network model.
In one embodiment, the model training module is further configured to: filtering the oil temperature data and the oil level data based on an isolated forest algorithm; extracting oil level data corresponding to the filtered oil temperature data; and labeling the oil temperature data according to the oil level data corresponding to the oil temperature data after filtering processing, and obtaining model training data.
In one embodiment, the model training module is further configured to: the oil temperature data and the oil level data are subjected to standardization processing through z-score standardization processing; extracting oil level data corresponding to the standardized oil temperature data; and marking the oil temperature data according to the oil level data corresponding to the standardized oil temperature data, and obtaining model training data.
In one embodiment, the model training data includes training set data and validation set data, the model training module further configured to: training the initial Bayes long-term and short-term neural network model through training group data to obtain a Bayes long-term and short-term neural network model to be verified; and verifying the Bayesian long-short-term neural network model to be verified through verification group data, and taking the Bayesian long-short-term neural network model to be verified as a preset Bayesian long-short-term neural network model when verification passes.
In one embodiment, the model training module is further configured to: inputting oil temperature data in verification group data into a Bayes long-term and short-term neural network model to be verified, and obtaining verification oil level data; acquiring evaluation index data corresponding to a Bayes long-term and short-term neural network model to be verified based on oil level marking data corresponding to oil temperature data and verification oil level data; and when the evaluation index data is lower than a preset evaluation index threshold, judging that the Bayesian long-short-term neural network model to be verified passes verification.
The specific limitation of the converter transformer oil leakage detection device can be referred to the limitation of the converter transformer oil leakage detection method hereinabove, and will not be described herein. The above-mentioned oil leakage detection device for the converter transformer can be implemented by all or part of software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 8. The computer device includes a processor, a memory, and a network interface connected by a 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, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer equipment is used for storing the oil leakage detection related data of the converter transformer. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of detecting oil leakage of a converter transformer.
It will be appreciated by those skilled in the art that the structure shown in fig. 8 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
acquiring real-time oil temperature data and real-time oil level data of a converter transformer to be detected;
inputting the real-time oil temperature data into a preset Bayes long-short-period neural network model, obtaining an oil level prediction result corresponding to the real-time oil temperature data, and training and obtaining the preset Bayes long-period neural network model based on the historical oil temperature data and the historical oil level data of the converter transformer;
and acquiring an oil leakage detection result corresponding to the converter transformer according to the oil level prediction result and the real-time oil level data.
In one embodiment, the processor when executing the computer program further performs the steps of: acquiring oil temperature data in the historical data and oil level data corresponding to the oil temperature data; labeling the oil temperature data through the oil level data corresponding to the oil temperature data to obtain model training data; and training the initial Bayes long-short-term neural network model through model training data to obtain a preset Bayes long-short-term neural network model.
In one embodiment, the processor when executing the computer program further performs the steps of: filtering the oil temperature data and the oil level data based on an isolated forest algorithm; extracting oil level data corresponding to the filtered oil temperature data; and labeling the oil temperature data according to the oil level data corresponding to the oil temperature data after filtering processing, and obtaining model training data.
In one embodiment, the processor when executing the computer program further performs the steps of: the oil temperature data and the oil level data are subjected to standardization processing through z-score standardization processing; extracting oil level data corresponding to the standardized oil temperature data; and marking the oil temperature data according to the oil level data corresponding to the standardized oil temperature data, and obtaining model training data.
In one embodiment, the processor when executing the computer program further performs the steps of: training the initial Bayes long-term and short-term neural network model through training group data to obtain a Bayes long-term and short-term neural network model to be verified; and verifying the Bayesian long-short-term neural network model to be verified through verification group data, and taking the Bayesian long-short-term neural network model to be verified as a preset Bayesian long-short-term neural network model when verification passes.
In one embodiment, the processor when executing the computer program further performs the steps of: inputting oil temperature data in verification group data into a Bayes long-term and short-term neural network model to be verified, and obtaining verification oil level data; acquiring evaluation index data corresponding to a Bayes long-term and short-term neural network model to be verified based on oil level marking data corresponding to oil temperature data and verification oil level data; and when the evaluation index data is lower than a preset evaluation index threshold, judging that the Bayesian long-short-term neural network model to be verified passes verification.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring real-time oil temperature data and real-time oil level data of a converter transformer to be detected;
inputting the real-time oil temperature data into a preset Bayes long-short-period neural network model, obtaining an oil level prediction result corresponding to the real-time oil temperature data, and training and obtaining the preset Bayes long-period neural network model based on the historical oil temperature data and the historical oil level data of the converter transformer;
and acquiring an oil leakage detection result corresponding to the converter transformer according to the oil level prediction result and the real-time oil level data.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring oil temperature data in the historical data and oil level data corresponding to the oil temperature data; labeling the oil temperature data through the oil level data corresponding to the oil temperature data to obtain model training data; and training the initial Bayes long-short-term neural network model through model training data to obtain a preset Bayes long-short-term neural network model.
In one embodiment, the computer program when executed by the processor further performs the steps of: filtering the oil temperature data and the oil level data based on an isolated forest algorithm; extracting oil level data corresponding to the filtered oil temperature data; and labeling the oil temperature data according to the oil level data corresponding to the oil temperature data after filtering processing, and obtaining model training data.
In one embodiment, the computer program when executed by the processor further performs the steps of: the oil temperature data and the oil level data are subjected to standardization processing through z-score standardization processing; extracting oil level data corresponding to the standardized oil temperature data; and marking the oil temperature data according to the oil level data corresponding to the standardized oil temperature data, and obtaining model training data.
In one embodiment, the computer program when executed by the processor further performs the steps of: training the initial Bayes long-term and short-term neural network model through training group data to obtain a Bayes long-term and short-term neural network model to be verified; and verifying the Bayesian long-short-term neural network model to be verified through verification group data, and taking the Bayesian long-short-term neural network model to be verified as a preset Bayesian long-short-term neural network model when verification passes.
In one embodiment, the computer program when executed by the processor further performs the steps of: inputting oil temperature data in verification group data into a Bayes long-term and short-term neural network model to be verified, and obtaining verification oil level data; acquiring evaluation index data corresponding to a Bayes long-term and short-term neural network model to be verified based on oil level marking data corresponding to oil temperature data and verification oil level data; and when the evaluation index data is lower than a preset evaluation index threshold, judging that the Bayesian long-short-term neural network model to be verified passes verification.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in 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, or the like. Volatile memory can include random access memory (RandomAccessMemory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can take many forms, such as static random access memory (StaticRandomAccessMemory, SRAM) or dynamic random access memory (DynamicRandomAccessMemory, DRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples represent only a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (10)
1. A method of detecting oil leakage of a converter transformer, the method comprising:
acquiring real-time oil temperature data and real-time oil level data of a converter transformer to be detected;
inputting the real-time oil temperature data into a preset Bayes long-short period neural network model, and acquiring an oil level prediction result corresponding to the real-time oil temperature data, wherein the preset Bayes long-short period neural network model is obtained based on the historical oil temperature data and the historical oil level data of the converter transformer in a training way;
acquiring an oil leakage detection result corresponding to the converter transformer according to the oil level prediction result and the real-time oil level data;
the preset Bayes long-term and short-term neural network model utilizes probability density distribution to sample weights and offsets, and then the distribution parameters are optimized to obtain the formula:
wherein ,
and />
For distributing parameters->
Representing probability density functions, parameters ρ and μ, for representing different weight and bias distributions;
the method for obtaining the oil level prediction result comprises the following steps of inputting the real-time oil temperature data into a preset Bayes long-short-term neural network model, and before obtaining the oil level prediction result corresponding to the real-time oil temperature data:
acquiring oil temperature data in historical data and oil level data corresponding to the oil temperature data;
labeling the oil temperature data through the oil level data corresponding to the oil temperature data to obtain model training data;
training an initial Bayes long-term and short-term neural network model through the model training data to obtain a preset Bayes long-term and short-term neural network model;
the model training data comprises training group data and verification group data;
training the initial Bayes long-term and short-term neural network model through the model training data, wherein the obtaining of the preset Bayes long-term and short-term neural network model comprises the following steps:
training the initial Bayes long-short-term neural network model through the training set data to obtain a Bayes long-short-term neural network model to be verified;
verifying the Bayesian long-short-term neural network model to be verified through the verification group data, and taking the Bayesian long-short-term neural network model to be verified as a preset Bayesian long-short-term neural network model when verification passes;
The step of verifying the Bayesian long-short-term neural network model to be verified through the verification group data comprises the following steps:
inputting the oil temperature data in the verification group data into the Bayes long-term and short-term neural network model to be verified, and obtaining verification oil level data;
acquiring evaluation index data corresponding to a Bayes long-short-term neural network model to be verified based on oil level marking data corresponding to the oil temperature data and the verification oil level data;
and when the evaluation index data is lower than a preset evaluation index threshold, judging that the Bayesian long-short-term neural network model to be verified passes verification.
2. The method of claim 1, wherein the labeling the oil temperature data with oil level data corresponding to the oil temperature data, and obtaining model training data comprises:
filtering the oil temperature data and the oil level data based on an isolated forest algorithm;
extracting oil level data corresponding to the filtered oil temperature data;
and marking the oil temperature data according to the oil level data corresponding to the oil temperature data after the filtering treatment, and obtaining model training data.
3. The method of claim 1, wherein the labeling the oil temperature data with oil level data corresponding to the oil temperature data, and obtaining model training data comprises:
Performing a normalization process on the oil temperature data and the oil level data by a z-score normalization process;
extracting oil level data corresponding to the standardized oil temperature data;
and marking the oil temperature data according to the oil level data corresponding to the standardized oil temperature data, and obtaining model training data.
4. The method according to claim 1, wherein the real-time oil temperature data is obtained by sensor detection monitoring converter transformer real-time oil temperature data.
5. An oil leakage detection device for a converter transformer, the device comprising:
the data acquisition module is used for acquiring real-time oil temperature data and real-time oil level data of the converter transformer to be detected;
the oil level prediction module is used for inputting the real-time oil temperature data into a preset Bayes long-short-period neural network model to obtain an oil level prediction result corresponding to the real-time oil temperature data, and the preset Bayes long-period neural network model is obtained based on the historical oil temperature data and the historical oil level data of the converter transformer in a training mode;
the oil leakage detection module is used for acquiring an oil leakage detection result corresponding to the converter transformer according to the oil level prediction result and the real-time oil level data;
The preset Bayes long-term and short-term neural network model utilizes probability density distribution to sample weights and offsets, and then the distribution parameters are optimized to obtain the formula:
wherein ,
and />
For distributing parameters->
Representing probability density functions, parameters ρ and μ, for representing different weight and bias distributions;
the model training module is used for acquiring oil temperature data in the historical data and oil level data corresponding to the oil temperature data; labeling the oil temperature data through the oil level data corresponding to the oil temperature data to obtain model training data; training an initial Bayes long-term and short-term neural network model through the model training data to obtain a preset Bayes long-term and short-term neural network model;
the model training data includes training set data and verification set data, the model training module is further configured to: training the initial Bayes long-short-term neural network model through the training set data to obtain a Bayes long-short-term neural network model to be verified; inputting the oil temperature data in the verification group data into the Bayes long-term and short-term neural network model to be verified, and obtaining verification oil level data; acquiring evaluation index data corresponding to a Bayes long-short-term neural network model to be verified based on oil level marking data corresponding to the oil temperature data and the verification oil level data; and when the evaluation index data is lower than a preset evaluation index threshold, judging that the Bayesian long-short-term neural network model to be verified passes verification, and when the verification passes, taking the Bayesian long-short-term neural network model to be verified as a preset Bayesian long-short-term neural network model.
6. The apparatus of claim 5, wherein the model training module is further to: filtering the oil temperature data and the oil level data based on an isolated forest algorithm; extracting oil level data corresponding to the filtered oil temperature data; and marking the oil temperature data according to the oil level data corresponding to the oil temperature data after the filtering treatment, and obtaining model training data.
7. The apparatus of claim 5, wherein the model training module is further to: performing a normalization process on the oil temperature data and the oil level data by a z-score normalization process; extracting oil level data corresponding to the standardized oil temperature data; and marking the oil temperature data according to the oil level data corresponding to the standardized oil temperature data, and obtaining model training data.
8. The apparatus of claim 5, wherein the real-time oil temperature data is obtained by sensor detection monitoring converter transformer real-time oil temperature data.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 4 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111033198.XA CN113758652B (en) | 2021-09-03 | 2021-09-03 | Oil leakage detection method and device for converter transformer, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111033198.XA CN113758652B (en) | 2021-09-03 | 2021-09-03 | Oil leakage detection method and device for converter transformer, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113758652A CN113758652A (en) | 2021-12-07 |
| CN113758652B true CN113758652B (en) | 2023-05-30 |
Family
ID=78792934
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111033198.XA Active CN113758652B (en) | 2021-09-03 | 2021-09-03 | Oil leakage detection method and device for converter transformer, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113758652B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115424826B (en) * | 2022-11-07 | 2023-04-14 | 中国南方电网有限责任公司超高压输电公司广州局 | Method, device, equipment and storage medium for determining cooling performance of converter transformer |
| CN117553998B (en) * | 2024-01-11 | 2024-03-26 | 南京立业电力变压器有限公司 | Static pressure constant voltage device and method for transformer |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1591182A2 (en) * | 2004-04-28 | 2005-11-02 | HILTI Aktiengesellschaft | Drill bit, drilling system and method to determine the electromagnetical environment of a drill bit |
| EP1786083A1 (en) * | 2005-11-15 | 2007-05-16 | Union Fenosa Distribucion, S.A. | Method and system for monitoring power transformers |
| WO2013040667A1 (en) * | 2011-09-19 | 2013-03-28 | Universidade Estadual De Campinas . Unicamp | Gas leak detection system and method, method for determining the importance and location of a gas leak by means of neural networks, and use in rigid and/or flexible pipes |
| CN103245861A (en) * | 2013-05-03 | 2013-08-14 | 云南电力试验研究院（集团）有限公司电力研究院 | Transformer fault diagnosis method based on Bayesian network |
| CN109359271A (en) * | 2018-12-21 | 2019-02-19 | 浙江大学 | A kind of deformation of transformer winding degree online test method that logic-based returns |
| CN111006741A (en) * | 2019-12-25 | 2020-04-14 | 中国南方电网有限责任公司超高压输电公司广州局 | Oil level abnormity detection method and system for oil-immersed transformer body |
| CN111610466A (en) * | 2020-05-14 | 2020-09-01 | 国网江苏省电力有限公司电力科学研究院 | Transformer state prediction method and device and storage medium |
| CN111650451A (en) * | 2020-04-28 | 2020-09-11 | 中国南方电网有限责任公司超高压输电公司广州局 | Converter transformer fault reason identification method and system |
| CN111797365A (en) * | 2020-06-09 | 2020-10-20 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Converter transformer temperature abnormity judgment method and system |
| CN112001417A (en) * | 2020-07-17 | 2020-11-27 | 国网宁夏电力有限公司检修公司 | Monitoring method, medium and system for transformer oil conservator |
| CN113218537A (en) * | 2021-05-25 | 2021-08-06 | 中国南方电网有限责任公司超高压输电公司广州局 | Training method, device, equipment and storage medium of temperature anomaly detection model |
-
2021
- 2021-09-03 CN CN202111033198.XA patent/CN113758652B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1591182A2 (en) * | 2004-04-28 | 2005-11-02 | HILTI Aktiengesellschaft | Drill bit, drilling system and method to determine the electromagnetical environment of a drill bit |
| EP1786083A1 (en) * | 2005-11-15 | 2007-05-16 | Union Fenosa Distribucion, S.A. | Method and system for monitoring power transformers |
| WO2013040667A1 (en) * | 2011-09-19 | 2013-03-28 | Universidade Estadual De Campinas . Unicamp | Gas leak detection system and method, method for determining the importance and location of a gas leak by means of neural networks, and use in rigid and/or flexible pipes |
| CN103245861A (en) * | 2013-05-03 | 2013-08-14 | 云南电力试验研究院（集团）有限公司电力研究院 | Transformer fault diagnosis method based on Bayesian network |
| CN109359271A (en) * | 2018-12-21 | 2019-02-19 | 浙江大学 | A kind of deformation of transformer winding degree online test method that logic-based returns |
| CN111006741A (en) * | 2019-12-25 | 2020-04-14 | 中国南方电网有限责任公司超高压输电公司广州局 | Oil level abnormity detection method and system for oil-immersed transformer body |
| CN111650451A (en) * | 2020-04-28 | 2020-09-11 | 中国南方电网有限责任公司超高压输电公司广州局 | Converter transformer fault reason identification method and system |
| CN111610466A (en) * | 2020-05-14 | 2020-09-01 | 国网江苏省电力有限公司电力科学研究院 | Transformer state prediction method and device and storage medium |
| CN111797365A (en) * | 2020-06-09 | 2020-10-20 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Converter transformer temperature abnormity judgment method and system |
| CN112001417A (en) * | 2020-07-17 | 2020-11-27 | 国网宁夏电力有限公司检修公司 | Monitoring method, medium and system for transformer oil conservator |
| CN113218537A (en) * | 2021-05-25 | 2021-08-06 | 中国南方电网有限责任公司超高压输电公司广州局 | Training method, device, equipment and storage medium of temperature anomaly detection model |
Non-Patent Citations (1)
| Title |
|---|
| "基于贝叶斯推理和多传感器信息融合的换流变缺陷分类算法研究";周春阳等;《变压器》;第57卷(第11期);第15-20页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113758652A (en) | 2021-12-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110766059A (en) | Transformer fault prediction method, device and equipment | |
| CN113758652B (en) | Oil leakage detection method and device for converter transformer, computer equipment and storage medium | |
| CN110334866B (en) | Power equipment fault probability prediction method and system considering insulation defect type and fault correlation | |
| Liu et al. | Fault diagnosis of water quality monitoring devices based on multiclass support vector machines and rule-based decision trees | |
| CN115796434B (en) | Management and control method and device for power distribution network, electronic equipment and storage medium | |
| CN112115636B (en) | Advanced prediction method and system for insulation aging life of power cable | |
| CN110334865B (en) | Power equipment fault rate prediction method and system based on convolutional neural network | |
| Wang et al. | Transient stability evaluation model based on SSDAE with imbalanced correction | |
| Xue et al. | LSTM-based intelligent fault detection for fuzzy Markov jump systems and its application to tunnel diode circuits | |
| CN115221233A (en) | Transformer substation multi-class live detection data anomaly detection method based on deep learning | |
| Wang et al. | Data-driven prediction method for characteristics of voltage sag based on fuzzy time series | |
| Chen | Review on supervised and unsupervised learning techniques for electrical power systems: Algorithms and applications | |
| Kuyunani et al. | Improving voltage harmonics forecasting at a wind farm using deep learning techniques | |
| CN114266284A (en) | Method, device, equipment and program product for detecting insulation defect type of switch cabinet | |
| Li et al. | A probabilistic data-driven method for response-based load shedding against fault-induced delayed voltage recovery in power systems | |
| CN117077052A (en) | Dry-type transformer abnormality detection method based on working condition identification | |
| CN117114161A (en) | Method for predicting wind deflection flashover risk of power transmission line based on meta-learning | |
| CN117154680A (en) | Wind power prediction method based on non-stationary transducer model | |
| CN115684786A (en) | Inverter switching tube health diagnosis method, device and system based on gram angular field and parallel CNN | |
| Aizpurua et al. | Probabilistic power transformer condition monitoring in smart grids | |
| CN115409100A (en) | Method, device, medium and equipment for generating power accident emergency scheme | |
| Vogt et al. | Multi-task distribution learning approach to anomaly detection of operational states of wind turbines | |
| CN114510469A (en) | Method, device, equipment and medium for identifying bad data of power system | |
| CN115730506A (en) | Transformer oil temperature abnormity early warning method based on information decision | |
| Moradzadeh et al. | Image processing-based data integrity attack detection in dynamic line rating forecasting applications |
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 |