A method, device, equipment and storage medium for monitoring and viewing a converter valve

Abstract

The present invention discloses a method, device, equipment and storage medium for monitoring and viewing a converter valve. After obtaining a monitoring image including all converter modules, the copper busbars connecting the converter modules and the valve box, as well as all converter modules, are extracted from the monitoring image. The converter modules are numbered based on the distance from the converter modules to the copper busbars, and the numbers of the converter modules that each camera is responsible for monitoring are determined. When an abnormal signal from a converter module with a target number is received, the monitoring screen of the camera corresponding to the converter module with the target number is called, and the area where the converter module with the target number is located in the monitoring screen is zoomed in, thereby realizing automatic calling and zooming in of the monitoring screen of the abnormal converter module without the need for staff operation, thereby improving viewing efficiency and reducing labor costs.

Description

Technical Field

[0001] The present invention relates to a converter valve monitoring technology, and in particular to a converter valve monitoring and viewing method, device, equipment and storage medium. Background Art

[0002] The converter valve is the core equipment of the DC transmission project. It obtains the desired DC voltage and realizes power control by connecting the three-phase AC voltage to the DC end in sequence.

[0003] At substations, multiple converter modules are typically connected in series to form a converter valve. These converter modules are housed in a valve box, which houses a camera. During operation, personnel are prohibited from entering the valve box. When the backend displays an abnormality alarm for a converter module, it becomes necessary to inspect that specific converter module. The current inspection method involves personnel selecting the corresponding camera feed from a monitor based on their experience, then selecting the corresponding converter module from that feed and zooming in on the feed for easier inspection.

[0004] The above inspection process is highly dependent on the experience of the staff. If the staff is inexperienced, it will take a lot of time. Summary of the Invention

[0005] The present invention provides a converter valve monitoring and viewing method, device, equipment and storage medium to automatically call and amplify the monitoring screen of an abnormal converter module without the need for staff operation, thereby improving viewing efficiency and reducing labor costs.

[0006] In a first aspect, the present invention provides a method for monitoring and viewing a converter valve, comprising:

[0007] Acquiring a monitoring image including all converter modules, where the converter valve includes multiple converter modules;

[0008] Extracting the copper busbar connecting the converter module and the valve box, and all the converter modules from the monitoring image;

[0009] Numbering the commutation modules based on the distance from the commutation modules to the copper busbar;

[0010] Determine the number of the commutation module that each camera is responsible for monitoring;

[0011] When an abnormal signal of a commutation module with a target number is received, the monitoring screen of the camera corresponding to the commutation module with the target number is called;

[0012] Enlarge the area where the commutation module with the target number is located in the monitoring screen.

[0013] Optionally, extracting the copper busbar connecting the converter module and the valve box, and all the converter modules from the monitoring image, includes:

[0014] The copper busbar connecting the commutation module and the valve box is extracted from the monitoring image using a target detection model, and a detection frame surrounding the commutation module and a detection frame surrounding the copper busbar are formed in the monitoring image.

[0015] Optionally, the target detection model is a YOLO V5 model, which includes a backbone network, a neck network, and a detection head. The target detection model is used to extract the copper busbar connecting the converter module and the valve box from the monitoring image, and form a detection frame surrounding the converter module and the copper busbar in the monitoring image, including:

[0016] Extracting feature maps of multiple scales from the surveillance image using the backbone network;

[0017] Performing multiple sampling using the feature map of the neck network to obtain sampling features of multiple different scales, and fusing the sampling features and feature maps of the same scale to obtain fused feature maps of multiple different scales;

[0018] The detection head is used to process the fused feature map to obtain target detection results at different scales. The target detection results include identifying the commutation module and the copper busbar, and forming a detection frame surrounding the commutation module and a detection frame surrounding the copper busbar in the monitoring image.

[0019] Optionally, two rows of stacked converter modules are provided in the valve box, and the converter modules are numbered based on the distance from the converter modules to the copper busbar, including:

[0020] For each of the commutation modules, calculating the distance between the center of the detection frame of the commutation module and the center of the detection frame of the copper busbar;

[0021] For the commutation modules in the first row, the commutation modules are sequentially numbered according to the ascending order of the distance;

[0022] For the commutation modules in the second row, the numbering of the first row is continued, and the commutation modules are numbered sequentially according to the descending order of the distance.

[0023] Optionally, after determining the number of the converter module that each camera is responsible for monitoring, the method further includes:

[0024] The numbers of the two oppositely stacked converter modules are verified based on the numbers of the converter modules in the first row and the numbers of the converter modules in the second row.

[0025] Optionally, enlarging the area where the commutation module with the target number is located in the monitoring screen includes:

[0026] Determine a target detection frame surrounding the commutation module with the target number;

[0027] The area within the target detection frame is maximized in the display image.

[0028] Optionally, maximizing the area within the target detection frame in the display image includes:

[0029] Calculating target distances from each edge of the target detection frame to the corresponding edge of the display screen, with the goal of minimizing the sum of distances from each edge of the target detection frame to the corresponding edge of the display screen;

[0030] The area within the target detection frame is enlarged according to the target distance from each side of the target detection frame to the corresponding edge of the display screen.

[0031] In a second aspect, the present invention further provides a converter valve monitoring and viewing device, comprising:

[0032] An image acquisition module is used to acquire monitoring images including all converter modules, where the converter valve includes multiple converter modules;

[0033] a target detection module, configured to extract the copper busbar connecting the commutation module and the valve box, and all the commutation modules from the monitoring image;

[0034] a numbering module, configured to number the commutation modules based on the distance between the commutation modules and the copper busbar;

[0035] A number determination module, used to determine the number of the commutation module that each camera is responsible for monitoring;

[0036] A monitoring screen calling module is used to call the monitoring screen of the camera corresponding to the target numbered commutation module when receiving an abnormal signal from the target numbered commutation module;

[0037] The area magnification module is used to magnify the area where the commutation module with the target number is located in the monitoring screen.

[0038] In a third aspect, the present invention further provides an electronic device, comprising:

[0039] one or more processors;

[0040] a storage device for storing one or more programs;

[0041] When the one or more programs are executed by the one or more processors, the one or more processors implement the converter valve monitoring and viewing method provided in the first aspect of the present invention.

[0042] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for monitoring and viewing a converter valve as provided in the first aspect of the present invention.

[0043] The converter valve monitoring and viewing method provided by the present invention, after obtaining a monitoring image including all converter modules, extracts the copper busbar connecting the converter module and the valve box, as well as all converter modules, from the monitoring image, numbering the converter modules based on the distance from the converter module to the copper busbar, and determining the number of the converter module that each camera is responsible for monitoring. When an abnormal signal of a converter module with a target number is received, the monitoring screen of the camera corresponding to the converter module with the target number is called, and the area where the converter module with the target number is located in the monitoring screen is zoomed in, thereby realizing automatic calling and zooming in of the monitoring screen of the abnormal converter module without the need for staff operation, thereby improving viewing efficiency and reducing labor costs.

[0044] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0046] Figure 1 A flow chart of a method for monitoring and viewing a converter valve provided by the present invention;

[0047] Figure 2 A schematic structural diagram of a converter valve monitoring and viewing device provided by the present invention;

[0048] Figure 3 A schematic structural diagram of an electronic device provided by an embodiment of the present invention.

[0049] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0050] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0051] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0052] Figure 1 This is a flow chart of a converter valve monitoring and viewing method provided by the present invention. This embodiment is applicable to the case of automatically viewing the converter module. The method can be executed by the converter valve monitoring and viewing device provided by the present invention. The device can be implemented by software and / or hardware and is usually configured in an electronic device, such as Figure 1 As shown, the commutation module monitoring and viewing method includes:

[0053] S101: Acquire a monitoring image including all converter modules.

[0054] In an embodiment of the present invention, a converter valve includes multiple converter modules connected in series, each of which is disposed within a valve box. The magnification of a camera within the valve box is adjusted to a minimum to maximize the image it can capture, thereby obtaining a monitoring image that includes all the converter modules.

[0055] S102: Extract the copper busbars connecting the commutation modules and the valve box, as well as all commutation modules, from the monitoring image.

[0056] In this embodiment of the present invention, the copper busbars connecting the converter modules to the valve box, as well as all converter modules, are extracted from the aforementioned surveillance imagery encompassing all converter modules. The copper busbars connect the converter modules to the valve box. The converter modules within the valve box are connected in series, while the converter modules on one edge of the converter valve connect the entire converter valve to equipment outside the valve box via the copper busbars, transmitting the current output by the converter valve to the outside of the valve box. Typically, multiple converter modules are stacked in one or more rows, with the copper busbars exposed on the same side of each row, visible to the camera.

[0057] In some embodiments of the present invention, a pre-trained object detection model's object detection algorithm can be used to extract the copper busbars connecting the commutation modules to the valve box, as well as all commutation modules, from the surveillance image. Exemplarily, the object detection model can be a one-stage object detection model (e.g., a YOLO model or an SDD model) or a two-stage object detection model (e.g., R-CNN, Fast R-CNN, or Faster R-CNN).

[0058] For example, in one embodiment of the present invention, the YOLO V5 model is used to extract the copper busbars connecting the commutation modules and the valve box, as well as all commutation modules, from monitoring images. The YOLO V5 model includes a backbone network, a neck network, and a detection head. The process of using the YOLO V5 model to extract the copper busbars connecting the commutation modules and the valve box from monitoring images is as follows:

[0059] S1021. Use the backbone network to extract feature maps of various scales from surveillance images.

[0060] The backbone network's primary function is to extract features at multiple scales from the input surveillance image, generating feature maps at multiple scales for use in subsequent detection tasks. For example, the backbone network includes two convolutional modules, a C3 module, a convolutional module, a C3 module, a convolutional module, a C3 module, a convolutional module, a C3 module, a convolutional module, a C3 module, and an SPPF (Specail Pyramid Pooling Fast) module.

[0061] The convolution module includes a convolutional layer (Conv), a batch normalization layer (Batch Normalization), and an activation function layer (SiLU) connected in sequence.

[0062] The C3 module includes a first convolution unit, a second convolution unit, a third convolution unit, and a bottleneck. The bottleneck includes at least two convolution units connected in sequence. The structure of the convolution unit is the same as the convolution module in the previous embodiment, including a convolution layer, a batch normalization layer, and an activation function layer connected in sequence. The processing process of the C3 module is as follows:

[0063] 1. In the first convolution unit, the input features of the C3 module are convolved, batch normalized, and nonlinearly activated to obtain the first convolution feature.

[0064] 2. In the second convolution unit, the input features of the C3 module are convolved, batch normalized, and nonlinearly activated to obtain a second convolution feature with a scale half that of the first convolution feature.

[0065] 3. Process the first convolution feature in Bottleneck to obtain a third convolution feature with a scale half that of the first convolution feature.

[0066] The stride of the convolutional modules in the Bottleneck is 2, which halves the size of the input feature map. This is done to increase the network's receptive field while reducing computational effort. By halving the size of the feature map, the network focuses more on the global information of the object, thereby improving feature extraction. The other convolutional units in the C3 module have a stride of 1, meaning they do not alter the size of the feature map. This maintains the spatial resolution of the feature map, thereby better preserving local information about the object. These convolutional units also serve to further extract features, increasing the network's depth and receptive field.

[0067] 4. Fuse the second convolution feature and the third convolution feature to obtain the fourth convolution feature.

[0068] The second convolution feature and the third convolution feature are fused (Concat) to obtain a fourth convolution feature whose dimension is the sum of the dimensions of the second convolution feature and the third convolution feature.

[0069] 5. In the third convolution unit, the fourth convolution feature is convolved, batch normalized, and nonlinearly activated to obtain the output feature of the C3 module.

[0070] The SPPF module includes a fourth convolution unit, a fifth convolution unit, a first maximum pooling layer, a second maximum pooling layer and a third maximum pooling layer. The above-mentioned convolution unit is represented by ConvBNSiLU, and its structure is the same as the convolution module in the aforementioned embodiment, including a convolution layer, a batch normalization layer and an activation function layer connected in sequence. The above-mentioned maximum pooling layer is represented by Maxpool. The SPPF module is a pooling module, which is usually used in convolutional neural networks. It aims to achieve spatial invariance and position invariance of input data in order to improve the recognition ability of the neural network. The main idea is to apply receptive fields of different sizes to the same image, so as to capture feature information of different scales. In the SPPF module, pooling operations of different sizes are first performed on the input feature map to obtain a set of feature maps of different sizes. These feature maps are then connected together and reduced in dimension through a fully connected layer to finally obtain a feature vector of fixed size. The processing process of the SPPF module is as follows:

[0071] 1. In the fourth convolution unit, the input features of the SPPF module are convolved, batch normalized, and nonlinearly activated to obtain convolution features.

[0072] 2. In the first maximum pooling layer, the convolution feature output by the fourth convolution unit is subjected to maximum pooling processing to obtain the first pooling feature.

[0073] 3. In the second maximum pooling layer, the first pooling feature is subjected to maximum pooling processing to obtain the second pooling feature.

[0074] 4. In the third maximum pooling layer, the second pooling feature is subjected to maximum pooling processing to obtain the third pooling feature.

[0075] 5. Fuse the convolution features output by the fourth convolution unit, the first pooling features, the second pooling features, and the third pooling features to obtain the fused features.

[0076] 6. In the fifth convolutional unit, the fused features are convolved, batch normalized, and nonlinearly activated to obtain the output features of the SPPF module.

[0077] S1022. Use the neck network feature map to perform multiple sampling to obtain sampling features of multiple different scales, and fuse the sampling features and feature maps of the same scale to obtain fused feature maps of multiple different scales.

[0078] The Neck network is a series of network layers that mix and combine image features and pass them to the prediction layer. It adopts the PANet (Path Aggregation Network) structure. Neck is mainly used to generate feature pyramids.

[0079] Exemplarily, two of the C3 modules and the SPPF module in the aforementioned embodiment respectively output three feature maps of different scales, namely a first feature map, a second feature map, and a third feature map.

[0080] The processing of the neck network is:

[0081] 1. The third feature map output by the SPPF module is input into the convolution module (ConvBNSiLU) and upsampling layer (Upsample) connected in sequence for processing to obtain the first upsampled feature.

[0082] 2. Fuse (Concat) the first upsampled feature with the second feature map output by the third C3 module in the backbone network to obtain the first fused feature.

[0083] 3. The first fusion feature is input into the C3 module, convolution module and upsampling layer connected in sequence for processing to obtain the second upsampling feature.

[0084] 4. Fuse the second upsampled feature with the first feature map output by the second C3 module in the backbone network (Concat) to obtain the second fused feature.

[0085] 5. The second fusion feature is input into the C3 module and the convolution module connected in sequence for processing to obtain the first down-sampled feature.

[0086] 6. Fuse the first down-sampled features with the features output by the convolution module in step 3 to obtain the third fused features.

[0087] 7. The third fusion feature is input into the C3 module and the convolution module connected in sequence for processing to obtain the second down-sampled feature.

[0088] 8. Fuse the second down-sampled features with the features output by the convolution module in step 1 to obtain the fourth fused features.

[0089] 9. Input the fourth fusion feature into the C3 module for processing. The structure of the C3 module is the same as that of the C3 module mentioned above, and the embodiment of the present invention will not be repeated here.

[0090] S1023. Use a detection head to process the fused feature map to obtain target detection results at different scales. The target detection results include identifying the commutation module and the copper busbar, and forming a detection frame surrounding the commutation module and a detection frame surrounding the copper busbar in the monitoring image.

[0091] In an embodiment of the present invention, multiple fused feature maps of different scales output by the neck network (Neck) are input into the detection head (Head) of YOLO V5 for processing to obtain target detection results at different image scales. The target detection results include identifying the commutation module and the copper busbar, and forming a detection frame surrounding the commutation module and the copper busbar in the monitoring image.

[0092] The detection head can include a region proposal network (RPN), an alignment layer (RoIPooling layer), a fully connected layer, a classification head, and a regression head. For example, the detection head processes the fused feature map as follows:

[0093] The region generation network receives the fused feature map and filters candidate regions of interest (RoIs) that may contain the target (person). These candidate regions are represented by candidate anchor boxes. The alignment layer aligns the resulting candidate regions with the pixels of the captured image to avoid discrepancies between the resulting candidate target regions and the actual target locations. The classification head classifies the pixel-aligned candidate regions and determines the probability that a converter module or busbar is present in the candidate regions. The regression head performs edge regression on the boundaries and pose of the pixel-aligned candidate regions to obtain a detection box representing the converter module or busbar.

[0094] S103: Number the commutation modules based on the distances from the commutation modules to the copper busbars.

[0095] After extracting the commutation modules and copper busbars, the commutation modules are numbered based on the distance from the commutation modules to the copper busbars. For example, the commutation modules can be numbered sequentially according to the distance from the commutation modules to the copper busbars, for example, the smaller the distance, the higher the number.

[0096] For example, in some embodiments of the present invention, two rows of stacked converter modules are provided in the valve box, and the converter modules are numbered based on the distance from the converter modules to the copper busbar, including:

[0097] S1031. For each commutation module, calculate the distance between the center of the detection frame of the commutation module and the center of the detection frame of the copper busbar.

[0098] For example, for each converter module, the distance from the center of the detection frame of the converter module to the center of the detection frame of the copper busbar is calculated. For example, the distance in the embodiment of the present invention may be a distance in pixel coordinates.

[0099] S1032: For the commutation modules in the first row, number the commutation modules sequentially in ascending order of distance.

[0100] For the first row (i.e., the upper layer) of commutation modules, they are numbered sequentially in ascending order of distance. For example, assuming there are N commutation modules, the commutation module closest to the copper busbar in the first row is numbered 01. As the distance increases, the numbering increases, to 02, 03, 04, and finally to N / 2.

[0101] S1033: For the commutation modules in the second row, continue the numbering of the first row and number the commutation modules in descending order of distance.

[0102] For the commutation modules in the second row (i.e., the lower layer), the numbering continues from the first row and is sequentially numbered in descending order of distance. For example, for the commutation modules in the second row, the one farthest from the copper busbar is numbered N. As the distances get closer, the numbers decrease, successively to N-1, N-2, N-3, and finally to N / 2+1.

[0103] In some embodiments of the present invention, after determining the number of the converter module that each camera is responsible for monitoring, the method further includes:

[0104] The numbers of the two oppositely stacked commutation modules are verified based on the numbers of the commutation modules in the first row and the numbers of the commutation modules in the second row.

[0105] For example, after numbering, the numbers of the commutation modules at corresponding positions on the upper and lower layers need to meet a certain relationship: if the upper layer commutation module is numbered Q, then the lower layer commutation module must be numbered N+1-Q. If this relationship is not met, manual judgment is introduced.

[0106] S104: Determine the serial number of the converter module that each camera is responsible for monitoring.

[0107] After numbering each converter module, the number of the converter module that each camera is responsible for monitoring is determined. For example, cameras are set up in predetermined locations, and each camera is responsible for monitoring one or more converter modules. After numbering each converter module, the number of the converter module that each camera is responsible for monitoring is determined. For example, camera 1 (responsible for monitoring converter modules 01, 02, 03, 04, and 05); camera 2 (responsible for monitoring converter modules 04, 05, 06, 07, and 08); and camera 3 (responsible for monitoring converter modules 07, 08, 09, 10, and 11).

[0108] S105. When an abnormal signal of the commutation module with the target number is received, the monitoring screen of the camera corresponding to the commutation module with the target number is called.

[0109] When an abnormality signal is received from a target-numbered converter module, the monitoring screen of the camera corresponding to the target-numbered converter module is called. For example, when an abnormality signal is received indicating an abnormality in converter module 02, the monitoring screen of camera 1, which is responsible for monitoring the target-numbered converter module, is called and displayed on the monitor. This monitoring screen also includes the monitoring screens of other converter modules, such as converter modules 01, 03, 04, and 05.

[0110] S106: Enlarge the area where the commutation module with the target number is located in the monitoring image.

[0111] In order to observe the commutation module with the target number more clearly, the area where the commutation module with the target number is located in the monitoring screen is enlarged.

[0112] For example, a target detection frame is first determined to surround the target numbered inverter module, and the area within the target detection frame is maximized on the display screen of the monitor. The process of determining the detection frame has been described in detail in the above embodiments and will not be repeated here.

[0113] Exemplarily, the target distances from each side of the target detection frame to the corresponding edge of the display screen are calculated with the goal of minimizing the sum of the distances (d1+d2+d3+d4) from each side of the target detection frame to the corresponding edge of the display screen. Exemplarily, an optimization algorithm can be used to minimize the sum of the distances (d1+d2+d3+d4) from each side of the target detection frame to the corresponding edge of the display screen, with the constraint that the distances from each side of the target detection frame to the corresponding edge of the display screen are all greater than 0, to calculate the target distances from each side of the target detection frame to the corresponding edge of the display screen. Then, the area within the target detection frame is enlarged according to the target distances from each side of the target detection frame to the corresponding edge of the display screen.

[0114] The converter valve monitoring and viewing method provided by the present invention, after obtaining a monitoring image including all converter modules, extracts the copper busbar connecting the converter module and the valve box, as well as all converter modules, from the monitoring image, numbering the converter modules based on the distance from the converter module to the copper busbar, and determining the number of the converter module that each camera is responsible for monitoring. When an abnormal signal of a converter module with a target number is received, the monitoring screen of the camera corresponding to the converter module with the target number is called, and the area where the converter module with the target number is located in the monitoring screen is zoomed in, thereby realizing automatic calling and zooming in of the monitoring screen of the abnormal converter module without the need for staff operation, thereby improving viewing efficiency and reducing labor costs.

[0115] The present invention also provides a device for monitoring and viewing a converter valve. Figure 2 A schematic diagram of the structure of a converter valve monitoring and viewing device provided by the present invention is shown as follows: Figure 2 As shown, the converter valve monitoring and viewing device includes:

[0116] An image acquisition module 201 is configured to acquire a monitoring image of all converter modules, where the converter valve includes multiple converter modules.

[0117] The target detection module 202 is configured to extract the copper busbar connecting the commutation module and the valve box, as well as all the commutation modules, from the monitoring image;

[0118] A numbering module 203 is configured to number the commutation modules based on the distance between the commutation modules and the copper busbar;

[0119] A number determination module 204 is used to determine the number of the commutation module that each camera is responsible for monitoring;

[0120] The monitoring screen calling module 205 is used to call the monitoring screen of the camera corresponding to the target numbered commutation module when receiving the abnormal signal of the target numbered commutation module;

[0121] The area magnifying module 206 is configured to magnify the area where the commutation module with the target number is located in the monitoring image.

[0122] In some embodiments of the present invention, the target detection module 202 includes:

[0123] The target detection submodule is used to extract the copper busbar connecting the commutation module and the valve box from the monitoring image using a target detection model, and form a detection frame surrounding the commutation module and a detection frame surrounding the copper busbar in the monitoring image.

[0124] In some embodiments of the present invention, the target detection model is a YOLO V5 model, which includes a backbone network, a neck network, and a detection head. The target detection submodule includes:

[0125] A feature map extraction unit, configured to extract feature maps of multiple scales from the monitoring image using the backbone network;

[0126] A feature map fusion unit is used to perform multiple sampling using the feature map of the neck network to obtain sampling features of multiple different scales, and to fuse the sampling features and feature maps of the same scale to obtain fused feature maps of multiple different scales;

[0127] A detection unit is used to process the fused feature map using the detection head to obtain target detection results at different scales, wherein the target detection results include identifying the commutation module and the copper busbar, and forming a detection frame surrounding the commutation module and a detection frame surrounding the copper busbar in the monitoring image.

[0128] In some embodiments of the present invention, two rows of stacked converter modules are provided in the valve box, and the numbering module 203 includes:

[0129] a distance calculation submodule, configured to calculate, for each of the commutation modules, a distance from a center of a detection frame of the commutation module to a center of a detection frame of the copper busbar;

[0130] a first numbering submodule, configured to sequentially number the commutation modules in the first row according to the ascending order of the distance;

[0131] The second numbering submodule is configured to continue the numbering of the first row for the commutation modules in the second row and sequentially number the commutation modules in descending order of the distance.

[0132] In some embodiments of the present invention, the converter valve monitoring and viewing device further includes:

[0133] The number verification module is used to verify the numbers of the two stacked converter modules based on the numbers of the converter modules in the first row and the numbers of the converter modules in the second row after determining the numbers of the converter modules monitored by each camera.

[0134] In some embodiments of the present invention, the region magnification module 206 includes:

[0135] A target detection frame determination submodule, configured to determine a target detection frame surrounding the commutation module with the target number;

[0136] The maximization submodule is used to maximize the area within the target detection frame in the display image.

[0137] In some embodiments of the present invention, the maximization submodule includes:

[0138] a target distance calculation unit, configured to calculate a target distance from each side of the target detection frame to the edge corresponding to the display screen, with the sum of the distances from each side of the target detection frame to the edge corresponding to the display screen being minimized;

[0139] The enlarging unit is configured to enlarge the area within the target detection frame according to target distances from each side of the target detection frame to a corresponding edge of the display screen.

[0140] The above-mentioned converter valve monitoring and viewing device can execute the converter valve monitoring and viewing method provided by the aforementioned embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the converter valve monitoring and viewing method.

[0141] Figure 3 A schematic diagram of the structure of an electronic device provided for an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0142] like Figure 3As shown, the electronic device includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0143] Multiple components in the electronic device are connected to the I / O interface 15, including an input unit 16, such as a keyboard, mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, optical disk, etc.; and a communication unit 19, such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0144] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, or microcontroller. The processor 11 executes the various methods and processes described above, such as the converter valve monitoring and review method.

[0145] In some embodiments, the converter valve monitoring and review method can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the converter valve monitoring and review method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to execute the converter valve monitoring and review method via any other suitable means (e.g., via firmware).

[0146] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0147] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0148] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0149] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0150] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0151] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0152] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the converter valve monitoring and viewing method provided in any embodiment of the present application.

[0153] The computer program product may be implemented by writing computer program code for performing the operations of the present invention in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0154] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0155] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for monitoring and checking a converter valve, characterized in that: include: Acquiring a monitoring image including all converter modules, where the converter valve includes multiple converter modules; Extracting the copper busbar connecting the commutation module and the valve box, and all the commutation modules from the monitoring image; Numbering the commutation modules based on the distance from the commutation modules to the copper busbar; Determine the number of the commutation module that each camera is responsible for monitoring; When an abnormal signal of a commutation module with a target number is received, the monitoring screen of the camera corresponding to the commutation module with the target number is called; Enlarge the area where the commutation module with the target number is located in the monitoring screen.

2. The method for monitoring and checking the converter valve according to claim 1, characterized in that: Extracting the copper busbar connecting the converter module and the valve box, and all the converter modules from the monitoring image, including: The copper busbar connecting the commutation module and the valve box is extracted from the monitoring image using a target detection model, and a detection frame surrounding the commutation module and a detection frame surrounding the copper busbar are formed in the monitoring image.

3. The method for monitoring and checking the converter valve according to claim 2, characterized in that: The target detection model is a YOLO V5 model, which includes a backbone network, a neck network, and a detection head. The target detection model is used to extract the copper busbar connecting the commutation module and the valve box from the monitoring image, and form a detection frame surrounding the commutation module and the copper busbar in the monitoring image, including: Extracting feature maps of multiple scales from the surveillance image using the backbone network; Performing multiple sampling using the feature map of the neck network to obtain sampling features of multiple different scales, and fusing the sampling features and feature maps of the same scale to obtain fused feature maps of multiple different scales; The detection head is used to process the fused feature map to obtain target detection results at different scales. The target detection results include identifying the commutation module and the copper busbar, and forming a detection frame surrounding the commutation module and a detection frame surrounding the copper busbar in the monitoring image.

4. The method for monitoring and checking the converter valve according to claim 2, characterized in that: Two rows of stacked converter modules are provided in the valve box, and the converter modules are numbered based on the distance from the converter modules to the copper busbar, including: For each of the commutation modules, calculating the distance between the center of the detection frame of the commutation module and the center of the detection frame of the copper busbar; For the commutation modules in the first row, the commutation modules are sequentially numbered according to the ascending order of the distance; For the commutation modules in the second row, the numbering of the first row is continued, and the commutation modules are numbered sequentially according to the descending order of the distance.

5. The method for monitoring and checking the converter valve according to claim 4, characterized in that: After determining the number of the converter module that each camera is responsible for monitoring, the method further includes: The numbers of the two oppositely stacked commutation modules are verified based on the numbers of the commutation modules in the first row and the numbers of the commutation modules in the second row.

6. The method for monitoring and checking a converter valve according to any one of claims 1 to 4, characterized in that: Enlarging the area where the commutation module with the target number is located in the monitoring screen includes: Determine a target detection frame surrounding the commutation module with the target number; The area within the target detection frame is maximized in the display image.

7. The method for monitoring and checking a converter valve according to claim 6, characterized in that: Maximizing the area within the target detection frame in the display screen includes: Calculating target distances from each edge of the target detection frame to the corresponding edge of the display screen, with the goal of minimizing the sum of distances from each edge of the target detection frame to the corresponding edge of the display screen; The area within the target detection frame is enlarged according to the target distance from each side of the target detection frame to the corresponding edge of the display screen.

8. A converter valve monitoring and viewing device, characterized in that: include: An image acquisition module is used to acquire monitoring images including all converter modules, where the converter valve includes multiple converter modules; a target detection module, configured to extract the copper busbar connecting the commutation module and the valve box, and all the commutation modules from the monitoring image; a numbering module, configured to number the commutation modules based on the distance between the commutation modules and the copper busbar; A number determination module, used to determine the number of the commutation module that each camera is responsible for monitoring; A monitoring screen calling module is used to call the monitoring screen of the camera corresponding to the target numbered commutation module when receiving an abnormal signal from the target numbered commutation module; The area magnification module is used to magnify the area where the commutation module with the target number is located in the monitoring screen.

9. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the converter valve monitoring and viewing method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the converter valve monitoring and viewing method according to any one of claims 1 to 7 is implemented.

Images