Fault alarm method for oil-immersed inverted current transformer
By using the fault detection model and Beidou short message communication function in the oil-immersed inverted current transformer, the problem of inefficiency of traditional fault detection methods is solved, and reliable fault detection and data transmission in the network-free coverage area is realized, which improves the Safety and reliability of power systems.
Patent Information
- Application Number
- CN202411680763.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-22
- Publication Date
- 2025-02-14
AI Technical Summary
Traditional current transformer fault detection methods are inefficient, unable to monitor the status of equipment in real time, and unable to effectively monitor in remote areas without network coverage, resulting in the impact of the safety and reliability of the power system.
The fault alarm method of the oil-immersed inverted current transformer is used to obtain operating data such as temperature, humidity, oil level and current, and use a pre-constructed fault detection model to perform feature extraction and analysis to achieve automatic identification and positioning of faults. This method also utilizes the short message communication function of the Beidou satellite navigation system to ensure reliable data transmission in areas without ground network coverage.
It improves the accuracy and timeliness of fault detection, ensures reliable data transmission in remote areas without network coverage, and improves the operational safety and reliability of the power system.
Smart Images
Figure CN119438984A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of power system monitoring, and in particular to a fault alarm method for an oil-immersed inverted current transformer. Background Art
[0002] With the continuous growth of global electricity demand and the rapid development of power grid infrastructure, the safety and reliability of power systems have become particularly important. As a key measurement and protection device in the power system, the stability of the performance of current transformers directly affects the operating efficiency and safety of the power system. In traditional current transformer monitoring, fault detection mainly relies on regular maintenance and manual inspection, which is not only inefficient, but also easily leads to failure to detect faults in time, thus causing serious power accidents.
[0003] Traditional current transformer fault detection methods usually rely on offline detection and regular maintenance, which has multiple limitations in practice. First, offline detection cannot monitor the status of the equipment in real time, which can easily lead to delayed detection of faults. Second, regular maintenance requires a lot of manpower and material resources, which is costly and inefficient. In addition, traditional methods cannot achieve effective monitoring in remote areas without network coverage, which poses a challenge to widely distributed power facilities. Summary of the invention
[0004] The purpose of the present invention is to overcome the deficiencies in the prior art and provide a fault alarm method for an oil-immersed inverted current transformer, which can effectively identify and locate faults, improve the accuracy and timeliness of fault detection, and ensure reliable data transmission in areas without ground network coverage, no longer restricted by geographical location.
[0005] To achieve the above object, the present invention is implemented by adopting the following technical solutions: In one aspect, the present invention provides a fault alarm method for an oil-immersed inverted current transformer, comprising: Acquiring operating data of the oil-immersed inverted current transformer; the operating data of the oil-immersed inverted current transformer includes temperature, humidity, oil level and current of the oil-immersed inverted current transformer; Obtaining a fault detection result of the oil-immersed inverted current transformer according to the operating data of the oil-immersed inverted current transformer and a pre-built fault detection model; sending the fault detection result of the oil-immersed inverted current transformer to a remote monitoring center to obtain an alarm processing result of the oil-immersed inverted current transformer; The processing steps of the fault detection model include: Performing feature extraction and feature dimension reduction on the operating data of the oil-immersed inverted current transformer in sequence to obtain a temperature feature after dimension reduction, a humidity feature after dimension reduction, an oil level feature after dimension reduction, and a current feature after dimension reduction; The temperature feature after dimensionality reduction, the humidity feature after dimensionality reduction, the oil level feature after dimensionality reduction and the current feature after dimensionality reduction are spliced to obtain a spliced feature; Perform secondary feature extraction on the spliced features to obtain final features; Adding the final feature and the operating data of the oil-immersed inverted current transformer to obtain the added feature; The added features are subjected to three feature extractions to obtain the fault detection result of the oil-immersed inverted current transformer.
[0006] Optionally, also include: Before training the fault detection model, data enhancement technology is used to add noise to the original training data set, perform data translation, perform data perturbation and perform data synthesis to obtain an extended training data set.
[0007] Optionally, the construction of the fault detection model includes: Get the original convolutional neural network model; A channel attention layer, a splicing layer, a convolution layer, a maximum pooling layer, two fully connected layers and an addition layer are sequentially added between the input layer and the convolution layer of the original convolutional neural network model to obtain a fault detection model.
[0008] Optionally, the channel attention layer includes a temperature channel attention module, a humidity channel attention module, an oil level channel attention module and a current channel attention module; Each channel attention module consists of a convolutional layer, a global average pooling layer, and two fully connected layers.
[0009] Optionally, the operating data of the oil-immersed inverted current transformer is collected by a sensor; The sensors include a temperature sensor, a humidity sensor, an oil level sensor and a current sensor; The temperature sensor is installed around the coil and the iron core of the oil-immersed inverted current transformer; The humidity sensor is installed inside the oil tank of the oil-immersed inverted current transformer; The oil level sensor is installed on the side wall of the oil tank of the oil-immersed inverted current transformer; The current sensor is installed at the output end of the oil-immersed inverted current transformer.
[0010] Optionally, the fault detection result of the oil-immersed inverted current transformer is sent to a remote monitoring center through a Beidou message communication module to obtain an alarm processing result of the oil-immersed inverted current transformer.
[0011] Optionally, also include: The operating data of the oil-immersed inverted current transformer and the fault detection result are stored in a data storage device.
[0012] Optionally, also include: The operating data, fault detection results and alarm processing results of the oil-immersed inverted current transformer are monitored through the user interface module.
[0013] Optionally, the remote monitoring center sends the alarm processing result to the user interface module.
[0014] On the other hand, the present invention provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the fault alarm method for the oil-immersed inverted current transformer described in the first aspect are implemented.
[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention can effectively identify and locate faults, improve the accuracy and timeliness of fault detection, and quickly transmit fault information to a remote monitoring center to ensure timely response and processing through real-time monitoring of the operating status of the oil-immersed inverted current transformer and automatic processing and analysis of the collected data through a pre-built fault detection model; perform three feature extractions to ensure the importance of channels, improve the extraction capability of fault type discrimination, and the probability distribution of fault types and fault locations; utilize the short message communication function of the Beidou satellite navigation system to ensure reliable data transmission in areas without ground network coverage, and even in remote areas without ground network coverage, reliable data transmission can be achieved, so that the monitoring and management of the oil-immersed inverted current transformer are no longer restricted by geographical locations. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 The figure is a schematic flow chart of a fault alarm method for an oil-immersed inverted current transformer according to an embodiment of the present invention; Figure 2 Shown is a schematic diagram of the structure of a fault detection model of the present invention in an embodiment; Figure 3 The figure shows a schematic structural diagram of an operating data monitoring system of an oil-immersed inverted current transformer according to an embodiment of the present invention; Figure 4 Shown is a schematic structural diagram of a terminal device in an embodiment of the present invention.
[0017] In the figure: 101-current sensor; 102-oil level sensor; 103-humidity sensor; 104-temperature sensor; 105-liquid level line; 106-oil-immersed inverted current transformer; 200-terminal equipment; 201-data storage device; 202-Beidou message communication module; 203-user interface module; 204-quick connector or pluggable interface. DETAILED DESCRIPTION
[0018] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.
[0019] The term "and / or" is only a description of the association relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " generally indicates that the related objects are in an "or" relationship.
[0020] Example 1
[0021] like Figure 1 As shown, this embodiment introduces a fault alarm method for an oil-immersed inverted current transformer, which specifically includes the following steps: Step 1: Obtaining the operating data of the oil-immersed inverted current transformer 106; the operating data of the oil-immersed inverted current transformer 106 includes the temperature, humidity, oil level and current of the oil-immersed inverted current transformer 106; the operating data of the oil-immersed inverted current transformer 106 is collected by sensors; the sensors include a temperature sensor 104, a humidity sensor 103, an oil level sensor 102 and a current sensor 101; the operating data monitoring system of the oil-immersed inverted current transformer 106 is as follows Figure 3 shown.
[0022] The temperature sensor 104 is installed around the coil and the core of the oil-immersed inverted current transformer 106 through a high temperature resistant and oil resistant fixing device, and is used to monitor the temperature change of the oil-immersed inverted current transformer 106; The humidity sensor 103 is installed inside the oil tank of the oil-immersed inverted current transformer 106 through a high temperature resistant and oil resistant fixing device and is higher than the liquid level line 105 of the oil tank, and is used to monitor the change of the moisture content in the oil; The oil level sensor 102 is mounted on the side wall of the oil tank of the oil-immersed inverted current transformer 106 through a high temperature resistant and oil resistant fixing device, and is used to monitor the oil level change; The current sensor 101 is installed at the output port of the oil-immersed inverted current transformer 106 through a high temperature resistant and oil resistant fixing device, and is used to accurately measure the current change.
[0023] The sensors are all mounted on the housing or internal structure of the oil-immersed inverted current transformer 106 through high temperature and oil resistant fixing devices to ensure stability and reliability in high temperature and high pressure environments.
[0024] Step 2: According to the operation data of the oil-immersed inverted current transformer 106 and the pre-built fault detection model, the fault detection result of the oil-immersed inverted current transformer 106 is obtained, and the fault detection model includes an input layer, a channel attention layer, a splicing layer, a second convolution layer, a maximum pooling layer, a first fully connected layer, a second fully connected layer, an addition layer, a third convolution layer, an average pooling layer, a first fully connected layer, and a second fully connected layer. The structure of the fault detection model is as follows: Figure 2 shown.
[0025] The channel attention layer includes a temperature channel attention module, a humidity channel attention module, an oil level channel attention module and a current channel attention module; The temperature channel attention module consists of a temperature first convolutional layer followed by a global average pooling layer, then a first fully connected layer with a ReLU activation function, and finally a second fully connected layer with a Sigmoid activation function. The humidity channel attention module consists of a humidity first convolutional layer followed by a global average pooling layer, then a first fully connected layer with a ReLU activation function, and finally a second fully connected layer with a Sigmoid activation function. The oil level channel attention module consists of a first oil level convolutional layer followed by a global average pooling layer, then a first fully connected layer with a ReLU activation function, and finally a second fully connected layer with a Sigmoid activation function. The current channel attention module consists of a first current convolutional layer followed by a global average pooling layer, then a first fully connected layer with a ReLU activation function, and finally a second fully connected layer with a Sigmoid activation function. In this embodiment, the convolution kernel sizes of the first temperature convolution layer, the first humidity convolution layer, the first oil level convolution layer, the first current convolution layer, the second convolution layer, and the third convolution layer are all 1x1.
[0026] The construction of the fault detection model includes: Get the original Convolutional Neural Networks (CNN) model; Adding a channel attention layer, a splicing layer, a convolution layer, a maximum pooling layer, two fully connected layers and an addition layer in sequence between the input layer and the convolution layer of the original convolutional neural network model to obtain a fault detection model; In this embodiment, a channel attention layer is added to emphasize important feature channels, thereby improving the model's ability to extract fault features, identify faults, and locate faults for input data.
[0027] The processing steps of the fault detection model include: The temperature of the oil-immersed inverted current transformer 106 is subjected to feature extraction and feature dimension reduction through the input layer input temperature channel attention module to obtain the temperature feature after dimension reduction; the humidity of the oil-immersed inverted current transformer 106 is subjected to feature extraction and feature dimension reduction through the input layer input humidity channel attention module to obtain the humidity feature after dimension reduction; the oil level of the oil-immersed inverted current transformer 106 is subjected to feature extraction and feature dimension reduction through the input layer input oil level attention module to obtain the oil level feature after dimension reduction; the current of the oil-immersed inverted current transformer 106 is subjected to feature extraction and feature dimension reduction through the input layer input current channel attention module to obtain the current feature after dimension reduction.
[0028] The temperature feature after dimensionality reduction, the humidity feature after dimensionality reduction, the oil level feature after dimensionality reduction and the current feature after dimensionality reduction are input into the splicing layer for splicing to obtain the spliced feature.
[0029] The concatenated features are sequentially input into the second convolutional layer, the maximum pooling layer, the first fully connected layer, and the second fully connected layer for secondary feature extraction to obtain the final features.
[0030] The final feature and the operating data of the oil-immersed inverted current transformer 106 are input into the addition layer, added together, and the added feature is obtained.
[0031] The added features are sequentially input into the third convolutional layer, the average pooling layer, the first fully connected layer, and the second fully connected layer, and feature extraction is performed three times to obtain the fault detection result of the oil-immersed inverted current transformer 106. The fault detection result includes the probability distribution of the fault type and the fault location.
[0032] In this embodiment, the first feature extraction strengthens the focus on important channels by adaptively adjusting the weight of each channel, obtains the importance of each channel through global average pooling, and then generates the weight of the channel through the fully connected layer; the second feature extraction improves the extraction ability of fault type discrimination by focusing on the important parameters in the first feature, and usually uses the maximum pooling of the feature map to generate a spatial attention map to highlight the key area; the third feature extraction further reduces the size of the feature map, and maps the features to the final output space to obtain the probability distribution of the fault type and fault location.
[0033] Before training the fault detection model, data enhancement technology is used to add noise, perform data translation, perform data perturbation and perform data synthesis in the original training data set to obtain an extended training data set. The original training data set is the historical fault data of the oil-immersed inverted current transformer 106.
[0034] After the extended training data set is obtained, a trained fault detection model is obtained through training, and the training method can be obtained using any method in the prior art.
[0035] By integrating the fault detection model in the terminal device 200, the multi-dimensional data from the sensor can be automatically processed and analyzed. The fault detection model in this embodiment can learn the characteristics of normal and abnormal states from a large amount of historical data, thereby achieving efficient fault identification and location. This intelligent data processing capability significantly improves the accuracy and timeliness of fault alarms.
[0036] Step three: The terminal device 200 sends the fault detection result of the oil-immersed inverted current transformer 106 to the remote monitoring center through the Beidou message communication module 202. The remote monitoring center outputs the alarm processing result of the oil-immersed inverted current transformer 106 and sends the alarm processing result to the user interface module 203. The user interface module 203 monitors the operating data, fault detection results and alarm processing results of the oil-immersed inverted current transformer 106, and the maintenance personnel perform debugging and maintenance.
[0037] The terminal device 200 includes a fault detection model, a data storage device 201, a Beidou message communication module 202, a user interface module 203 and a quick connector 204 or a pluggable interface 204. The structure of the terminal device is as follows Figure 4 shown.
[0038] The fault detection model is used to detect whether the oil-immersed inverted current transformer 106 has a fault and output a fault detection result. The fault detection result is input into a remote monitoring center through the Beidou message communication module 202 , and the remote monitoring center sends the alarm processing result to the user interface module 203 .
[0039] The data storage device 201 is used to record historical fault data and operation data of the oil-immersed inverted current transformer 106 .
[0040] The user interface module 203 is used to monitor the operating data, fault detection results and alarm processing results of the oil-immersed inverted current transformer 106 .
[0041] As a global navigation satellite system independently developed by China, the Beidou satellite navigation system has the advantages of wide coverage, high accuracy, and strong anti-interference ability. The introduction of Beidou message communication technology can not only realize real-time monitoring of oil-immersed inverted current transformers, but also provide a reliable data transmission channel in remote areas without ground network coverage. Using the Beidou short message communication function, fault information can be transmitted to the remote monitoring center in real time to ensure that the fault is quickly responded to and handled.
[0042] When this embodiment is applied, a fault detection model is embedded in the terminal device to process and analyze the multi-dimensional data collected from the sensor. Through feature extraction and fault identification, it can accurately locate and determine the fault type, improve the accuracy and timeliness of fault identification, and adopt the Beidou message communication module to realize the remote transmission of fault alarm information. This module supports short message communication function, which is particularly suitable for areas without ground network coverage, ensuring that the alarm data can be quickly transmitted to the remote monitoring center and maintenance personnel.
[0043] Example 2
[0044] Based on Example 1, this example introduces a specific experimental design of a fault alarm method for an oil-immersed inverted current transformer, including the following steps: An oil-immersed inverted current transformer 106 is selected in a substation in a remote area, a sensor is installed, and a data connection is established with a central monitoring room through a Beidou message communication module 202. The central monitoring room is a remote monitoring center.
[0045] The temperature sensor 104 , the humidity sensor 103 , the oil level sensor 102 , the current sensor 101 , and the terminal device 200 are installed at positions corresponding to the oil-immersed inverted current transformer 106 .
[0046] The sensor is connected to the terminal device 200 using a quick connector or a pluggable interface 204 .
[0047] The oil leakage of the selected oil-immersed inverted current transformer 106 is controlled.
[0048] The terminal device 200 collects and stores the data sent by the temperature sensor 104 {T t0 , T t-1 , T t-2 ,…T t-21}, data of humidity sensor 103 {H t0 , H t-1 , H t-2 ,…H t-21}, data of the oil level sensor 102 {P t0 , P t-1 , P t-2 ,…P t-21} and the data of the current sensor 101 {I t0 ,I t-1 ,I t-2 ,…I t-21}, where t0 is the current time, and t-1, t-2, ..., t-21 are the historical time record data. All sensor data form a 22×1×4 array as the input data of the fault detection model input layer in the terminal device 200.
[0049] The terminal device 200 detects that a fault occurs in the oil-immersed inverted current transformer 106 , and the terminal device 200 sends the fault information to the central monitoring room through the Beidou message communication module 202 .
[0050] The central monitoring room receives the fault alarm information sent by the terminal device 200 in real time, automatically generates processing suggestions using intelligent analysis software, and sends them to maintenance personnel in a timely manner.
[0051] This embodiment can also achieve reliable data transmission in remote areas without ground network coverage, so that the monitoring and management of the oil-immersed inverted current transformer are no longer restricted by geographical location, thereby improving the operational safety and reliability of the power system.
[0052] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
[0053] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0054] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0055] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0056] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.
Claims
1. A fault alarm method for an oil-immersed inverted current transformer, characterized in that: include: Obtain the operating data of the oil-immersed inverted current transformer; The operation data of the oil-immersed inverted current transformer includes the temperature, humidity, oil level and current of the oil-immersed inverted current transformer; Obtaining a fault detection result of the oil-immersed inverted current transformer according to the operating data of the oil-immersed inverted current transformer and a pre-built fault detection model; Sending the fault detection result of the oil-immersed inverted current transformer to a remote monitoring center to obtain the alarm processing result of the oil-immersed inverted current transformer; The processing steps of the fault detection model include: Performing feature extraction and feature dimension reduction on the operating data of the oil-immersed inverted current transformer in sequence to obtain a temperature feature after dimension reduction, a humidity feature after dimension reduction, an oil level feature after dimension reduction, and a current feature after dimension reduction; The temperature feature after dimensionality reduction, the humidity feature after dimensionality reduction, the oil level feature after dimensionality reduction and the current feature after dimensionality reduction are spliced to obtain a spliced feature; Perform secondary feature extraction on the spliced features to obtain final features; Adding the final feature and the operating data of the oil-immersed inverted current transformer to obtain the added feature; The added features are subjected to three feature extractions to obtain the fault detection result of the oil-immersed inverted current transformer.
2. The fault alarm method of the oil-immersed inverted current transformer according to claim 1, characterized in that: Also includes: Before training the fault detection model, data enhancement technology is used to add noise to the original training data set, perform data translation, perform data perturbation and perform data synthesis to obtain an extended training data set.
3. The fault alarm method of the oil-immersed inverted current transformer according to claim 1, characterized in that: The construction of the fault detection model includes: Get the original convolutional neural network model; A channel attention layer, a splicing layer, a convolution layer, a maximum pooling layer, two fully connected layers and an addition layer are sequentially added between the input layer and the convolution layer of the original convolutional neural network model to obtain a fault detection model.
4. The fault alarm method of the oil-immersed inverted current transformer according to claim 3, characterized in that: The channel attention layer includes a temperature channel attention module, a humidity channel attention module, an oil level channel attention module and a current channel attention module; Each channel attention module consists of a convolutional layer, a global average pooling layer, and two fully connected layers.
5. The fault alarm method of the oil-immersed inverted current transformer according to claim 1, characterized in that: The operating data of the oil-immersed inverted current transformer is collected by a sensor; The sensors include a temperature sensor, a humidity sensor, an oil level sensor and a current sensor; The temperature sensor is installed around the coil and the iron core of the oil-immersed inverted current transformer; The humidity sensor is installed inside the oil tank of the oil-immersed inverted current transformer; The oil level sensor is installed on the side wall of the oil tank of the oil-immersed inverted current transformer; The current sensor is installed at the output end of the oil-immersed inverted current transformer.
6. The fault alarm method of the oil-immersed inverted current transformer according to claim 1, characterized in that: The fault detection result of the oil-immersed inverted current transformer is sent to a remote monitoring center through a Beidou message communication module to obtain an alarm processing result of the oil-immersed inverted current transformer.
7. The fault alarm method of the oil-immersed inverted current transformer according to claim 1, characterized in that: Also includes: The operating data of the oil-immersed inverted current transformer and the fault detection result are stored in a data storage device.
8. The fault alarm method of the oil-immersed inverted current transformer according to claim 1, characterized in that: Also includes: The operating data, fault detection results and alarm processing results of the oil-immersed inverted current transformer are monitored through the user interface module.
9. The fault alarm method of the oil-immersed inverted current transformer according to claim 8, characterized in that: The remote monitoring center sends the alarm processing result to the user interface module.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the fault alarm method for an oil-immersed inverted current transformer according to any one of claims 1 to 9 are implemented.