Security protection strategy determination method and device of transformer substation, equipment and storage medium

Abstract

The invention discloses a safety protection strategy determination method and device for a transformer substation, equipment and a storage medium. The method comprises the steps that a target scene image of to-be-arranged safety protection measures in a transformer substation is acquired, and the target scene image comprises at least one power transformation device; the target scene image is input into a pre-trained target equipment classification model, a target equipment type corresponding to at least one power transformation equipment is determined based on a model output result, and the target equipment classification model is obtained by training a pre-established convolutional neural network based on a sample power transformation equipment image; and determining a target safety protection strategy corresponding to the power transformation equipment according to the target equipment type of the power transformation equipment. And the target security protection strategy can be quickly and accurately determined.

Description

Technical Field

[0001] The present invention relates to the technical field of substation security protection, and in particular to a substation security protection strategy determination method, device, equipment and storage medium. Background Art

[0002] The substation integrated automation system is the brain and command center for the normal operation of the primary and secondary equipment of the substation, and is responsible for monitoring and remote control of the primary and secondary equipment of the substation. According to the requirements of the operating procedures, the substation integrated automation system needs to be regularly modified to ensure its working performance.

[0003] At present, before carrying out the comprehensive automation transformation of substations, substation operators need to arrange safety measures for the equipment to be transformed according to the safety protection strategy to avoid abnormal situations such as equipment damage, misoperation, and electric shock accidents caused by human misoperation and misoperation. The safety protection strategy is mainly determined by the work experience of the operators. Due to the complexity of on-site equipment and the inconsistency of work experience and skill levels of different personnel, it is impossible to accurately determine the safety protection strategy corresponding to each substation equipment. Summary of the invention

[0004] The present invention provides a method, device, equipment and storage medium for determining a safety protection strategy for a substation, so as to solve the problem that it is impossible to accurately determine the safety protection strategy corresponding to each substation equipment.

[0005] According to one aspect of the present invention, a method for determining a security protection strategy for a substation is provided, the method comprising:

[0006] Acquire a target scene image in a substation where safety protection measures are to be arranged, wherein the target scene image includes at least one substation equipment;

[0007] Inputting the target scene image into a pre-trained target device classification model, and determining a target device type corresponding to at least one substation device based on a model output result, wherein the target device classification model is obtained by training a pre-established convolutional neural network based on a sample substation device image;

[0008] A target safety protection strategy corresponding to the power substation equipment is determined according to a target equipment type of the power substation equipment.

[0009] According to another aspect of the present invention, a device for determining a security protection strategy for a substation is provided, the device comprising:

[0010] A scene image acquisition module, used to acquire a target scene image in a substation where safety protection measures are to be arranged, wherein the target scene image includes at least one substation equipment;

[0011] A device type determination module, used for inputting the target scene image into a pre-trained target device classification model, and determining the target device type corresponding to at least one substation device based on the model output result, wherein the target device classification model is obtained by training a pre-established convolutional neural network based on sample substation device images;

[0012] The protection strategy determination module is used to determine the target safety protection strategy corresponding to the power substation equipment according to the target device type of the power substation equipment.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for determining a safety protection strategy for a substation described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining a safety protection strategy for a substation described in any embodiment of the present invention when executed.

[0018] The technical solution of the embodiment of the present invention obtains the target scene image of the substation where the safety protection measures are to be arranged, wherein the target scene image includes at least one substation equipment; the equipment layout and the number of equipment in the substation can be intuitively obtained; then, the target scene image is input into a pre-trained target equipment classification model, and the target equipment type corresponding to at least one substation equipment is determined based on the model output result, wherein the target equipment classification model is obtained by training a pre-established convolutional neural network based on sample substation equipment images; and the target equipment type of at least one substation equipment included in the target scene image is accurately determined. Finally, the target safety protection strategy corresponding to the substation equipment is determined according to the target equipment type of the substation equipment, which solves the problem of being unable to accurately determine the safety protection strategy corresponding to each substation equipment, and achieves the beneficial effect of improving the efficiency and accuracy of determining the target safety protection strategy.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] 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.

[0021] Figure 1 is a flow chart of a method for determining a security protection strategy for a substation provided according to Embodiment 1 of the present invention;

[0022] Figure 2a is a flow chart of a method for determining a security protection strategy for a substation provided in accordance with Embodiment 2 of the present invention;

[0023] Figure 2b This is a sample flow chart of determining a target safety protection strategy of a method for determining a safety protection strategy for a substation provided in accordance with Embodiment 2 of the present invention;

[0024] Figure 2c This is a sample flow chart of safety detection of a method for determining a safety protection strategy for a substation provided in accordance with Embodiment 2 of the present invention;

[0025] Figure 3 This is a schematic diagram of the structure of a device for determining a security protection strategy for a substation provided according to Embodiment 3 of the present invention;

[0026] Figure 4 It is a structural schematic diagram of an electronic device for implementing the method for determining a safety protection strategy for a substation according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 described embodiments 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 creative work should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", etc. in the specification 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 data 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 that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] Embodiment 1

[0030] Figure 1 A flowchart of a method for determining a security protection strategy for a substation is provided for the first embodiment of the present invention. This embodiment is applicable to the situation where a security protection strategy for a substation is determined. The method can be executed by a security protection strategy determination device for a substation. The security protection strategy determination device for a substation can be implemented in the form of hardware and / or software. The security protection strategy determination device for a substation can be configured in an electronic device. Figure 1 As shown, the method includes:

[0031] S110, obtaining a target scene image in the substation where safety protection measures are to be arranged.

[0032] Wherein, the target scene image includes at least one type of power transformation equipment.

[0033] Specifically, the target scene image where the safety protection measures are to be arranged in the substation is captured based on the pre-installed multimedia equipment in the substation.

[0034] Optionally, after obtaining the target scene image where safety protection measures are to be arranged in the substation, it also includes: preprocessing the target scene image, and updating the target scene image based on the preprocessed scene image; wherein the preprocessing includes: at least one of image denoising processing, grayscale transformation processing and filtering processing.

[0035] Specifically, the target scene image is subjected to image denoising processing, and a denoising algorithm is used to process the image to remove noise in the image, such as random noise, Gaussian noise, etc., so as to improve the clarity of the image. The target scene image is subjected to grayscale transformation processing, and the color image is converted into a grayscale image, so as to simplify subsequent processing steps and reduce the amount of calculation. The target scene image is subjected to filtering processing to further smooth the image, remove high-frequency noise and details in the image, and retain low-frequency features. The contrast of the image is enhanced to improve the visual effect of the image. The filtered image is used as a new target scene image.

[0036] S120: Input the target scene image into a pre-trained target device classification model, and determine a target device type corresponding to at least one power transformation device based on a model output result.

[0037] The target device classification model is obtained by training a pre-established convolutional neural network based on sample substation equipment images. The model output result can be understood as the device classification prediction result output by the model.

[0038] Specifically, the target scene image is input into a pre-trained target device classification model, the model infers the input target scene image, outputs the model output result, and the model output result is analyzed to obtain an array containing the prediction probabilities of various types of substation equipment.

[0039] Optionally, the target device classification model includes an input layer, at least one convolution layer connected to the input layer, an activation layer connected to the convolution layer, a pooling layer connected to the last convolution layer, and a fully connected layer connected to the pooling layer; accordingly, the target scene image is input into a pre-trained target device classification model, and the target device type corresponding to at least one substation is determined based on the model output result, including: inputting the target scene image into the convolution layer through the input layer, and extracting the initial image features of the target scene image through the convolution layer; performing a nonlinear transformation on the initial image features through the activation layer, and extracting key image features from the initial image features after the nonlinear transformation through the pooling layer; integrating the initial image features and the key image features into target image features through the fully connected layer, and performing device classification prediction based on the target image features to obtain the target device type corresponding to at least one substation.

[0040] Specifically, the input layer receives the target scene image as input and adjusts the image to the size and format required by the model. The convolution layer extracts the initial image features of the target scene image, slides the convolution kernel on the image, calculates the convolution result, and performs convolution operations on the input image through multiple convolution kernels to generate multiple feature maps. The activation layer performs nonlinear transformation on the feature map output by the convolution layer to increase the nonlinear expression ability of the model. The feature map is operated element by element by using the activation function. The feature map output by the activation layer is subjected to maximum pooling or average pooling through the pooling layer to extract the key image features from the initial image features after the nonlinear transformation. Finally, the initial image features and key image features are integrated into the target image features through the fully connected layer, and the equipment classification prediction is performed based on the target image features to obtain the target equipment type corresponding to at least one substation equipment.

[0041] Optionally, before inputting the target scene image into a pre-trained target device classification model, it also includes: constructing a data set, dividing the data set into a training set and a test set; wherein the data set contains sample substation equipment images of a variety of substation equipment and a standard equipment type label corresponding to each sample substation equipment image; based on the training set, the pre-constructed initial convolutional neural network model is iteratively trained for a preset number of times, and in each iteration, the model loss is determined based on the initial equipment type label output by the model and the standard equipment type label, and the model parameters are adjusted based on the model loss; based on the test set, each trained model is tested to obtain multiple model performance indicators, and the target device classification model is determined based on the multiple model performance indicators.

[0042] Specifically, sample substation equipment images covering a variety of substation equipment are collected. These sample substation equipment images should fully reflect the appearance characteristics of various types of substation equipment. At the same time, each sample substation equipment image is equipped with a corresponding standard equipment type label. The entire data set is divided into a training set and a test set. The training set is used for model training and optimization, and the test set is used to evaluate the performance of the model. The training set is input into a pre-built convolutional neural network model for multiple (preset number) iterations of training. In each iteration, the model outputs the initial equipment type label. The model loss is calculated by comparing the initial equipment type label with the standard equipment type label. Based on the loss value, the model parameters are adjusted using the back propagation algorithm to optimize the model performance. The performance of the model that completes each training is evaluated using the test set. Evaluation indicators may include accuracy and recall, etc. The model with the best performance is selected as the target equipment classification model based on multiple model performance indicators.

[0043] Optionally, the target equipment type includes at least one of an open-type disconnector, a fully enclosed disconnector, a live busbar equipment, an adjacent operating equipment, a protection screen equipment, and a measurement and control screen equipment.

[0044] S130. Determine a target security protection strategy corresponding to the power substation according to a target device type of the power substation.

[0045] Among them, the target security protection strategy can be understood as a strategy for deploying security protection measures.

[0046] Specifically, at least one safety protection measure corresponding to the target device type is determined according to the target device type of the power substation, and a target safety protection strategy corresponding to the power substation is generated based on the at least one safety protection measure.

[0047] The technical solution of the embodiment of the present invention obtains the target scene image of the substation where the safety protection measures are to be arranged, wherein the target scene image includes at least one substation equipment; the equipment layout and the number of equipment in the substation can be intuitively obtained; then, the target scene image is input into a pre-trained target equipment classification model, and the target equipment type corresponding to at least one substation equipment is determined based on the model output result, wherein the target equipment classification model is obtained by training a pre-established convolutional neural network based on sample substation equipment images; and the target equipment type of at least one substation equipment included in the target scene image is accurately determined. Finally, the target safety protection strategy corresponding to the substation equipment is determined according to the target equipment type of the substation equipment, which solves the problem of being unable to accurately determine the safety protection strategy corresponding to each substation equipment, and achieves the beneficial effect of improving the efficiency and accuracy of determining the target safety protection strategy.

[0048] Embodiment 2

[0049] Figure 2a A flowchart of a method for determining a safety protection strategy for a substation provided in Embodiment 2 of the present invention is provided. This embodiment is a further optimization of the above embodiment. Optionally, the method further includes: when the substation equipment has arranged safety protection measures, performing safety detection on the safety protection measures to obtain safety detection results; when the safety detection results do not meet the preset safety detection conditions, generating safety prompt information corresponding to the substation equipment, and displaying the safety prompt information.

[0050] like Figure 2a As shown, the method includes:

[0051] S210. Acquire a target scene image in a substation where safety protection measures are to be arranged, wherein the target scene image includes at least one substation equipment.

[0052] S220. Input the target scene image into a pre-trained target device classification model, and determine the target device type corresponding to at least one substation device based on the model output result, wherein the target device classification model is obtained by training a pre-established convolutional neural network based on sample substation device images.

[0053] S230. Determine a target security protection strategy corresponding to the power substation according to a target device type of the power substation.

[0054] Figure 2b A sample flow chart of a method for determining a substation security protection strategy for determining a target security protection strategy is provided. Figure 2b As shown, identify the type of disconnector equipment. If it is judged to be an open disconnector, output target safety protection strategy 1: open the mechanism box door and untie the motor power wiring; install a limit device on the drive shaft of the open disconnector; use insulating tape to seal the five-proof padlock and operating handle of the corresponding disconnector in the corresponding terminal box. Identify the type of disconnector equipment. If it is judged to be a fully enclosed disconnector, output target safety protection strategy 2: open the terminal box door and untie the motor power wiring; remove the mechanism box of the fully enclosed disconnector and seal it with tooling; use insulating tape to seal the five-proof padlock and operating handle of the corresponding disconnector in the corresponding terminal box; use locks to block the manual operation hole. Identify whether there is a live busbar device above the disconnector. If there is a live busbar device, output target safety protection strategy 3: install red cloth on the disconnector pillar and mark it with the words "The upper busbar is live, climbing is strictly prohibited". Identify whether there are other operating equipment within 70cm of the disconnector and earthing switch equipment at their workplace. If so, output target safety protection strategy 4: Install red cloth on the operating equipment within 70cm and mark it with the words "Equipment in operation". Identify whether the protection screen and measurement and control screen equipment at their workplace are multi-device types on the same screen. If so, output target safety protection strategy 5: Use red cloth to isolate the protection devices, measurement and control devices, circuits, pressure plates, and circuit breakers on the corresponding protection screen and measurement and control screen that are not in the interval of this comprehensive reform. Identify whether their work involves the replacement of the disconnector equipment. If so, output target safety protection strategy 6: On the corresponding bus differential protection screen, switch the forced position of the disconnector that needs to be replaced to the forced sub-position. Identify their working area and output target safety protection strategy 7: safety fence layout area and layout range.

[0055] S240: When safety protection measures have been arranged for the power transformation equipment, perform safety inspection on the safety protection measures to obtain safety inspection results.

[0056] Among them, the safety inspection results can be understood as the inspection results of the safety protection measures that have been arranged for the substation equipment.

[0057] Specifically, image data of the substation equipment where safety protection measures have been arranged is obtained, and deep learning or machine learning technology, such as convolutional neural network, is used to identify the type of substation equipment and its safety protection measures in the image. A safety detection result is generated based on the identified substation equipment type and its safety protection measures.

[0058] Figure 2c A sample flow chart of safety detection of a method for determining a safety protection strategy for a substation is provided. Figure 2c As shown, for open-type disconnectors, identify whether the motor power wiring in the mechanism box is untied; identify whether the limit device is installed on the transmission shaft; identify whether the five-protection padlock and operating handle of the disconnector in the terminal box are sealed with insulating tape. For fully enclosed disconnectors, identify whether the motor power wiring in the mechanism box is untied; identify whether the mechanism box is dismantled and sealed with tooling; identify whether the five-protection padlock and operating handle of the disconnector in the terminal box are sealed with insulating tape; identify whether the manual operation hole is sealed. In the case of live busbar equipment above the disconnector, identify whether a red cloth with the words "the upper busbar is live, climbing is strictly prohibited" is installed on the support of the disconnector. If there are other operating equipment within 70 cm of the disconnector and grounding knife switch equipment at the work site, identify whether the operating equipment within 70 cm is installed with a red cloth with the words "equipment in operation". If the protective screen and measurement and control screen equipment at the work site are multiple devices on the same screen, identify the protective devices, measurement and control devices, circuits, pressure plates, and circuit breakers on the corresponding protective screen and measurement and control screen that are not in the interval of this comprehensive reform and isolate them with red cloth. If their work involves the replacement of the isolating switch, identify that the forced position of the isolating switch to be replaced has been switched to the forced separation position on the corresponding bus differential protection screen.

[0059] S250: When the safety detection result does not meet the preset safety detection condition, generate safety prompt information corresponding to the power transformation equipment, and display the safety prompt information.

[0060] Specifically, the safety detection results are compared with the preset safety detection conditions. Exemplarily, the safety protection measures of the substation equipment are compared to see if they are consistent with the preset safety detection conditions, the specific safety protection measures that are inconsistent are recorded, and the existing safety hazards and recommended countermeasures are analyzed. Based on the comparison results and the identification of the substation equipment (such as name, number, location, etc.), safety hazards and countermeasures, a safety prompt information corresponding to the substation equipment is generated. The generated safety prompt information is displayed to the user terminal in a preset display method. According to the requirements of the preset display method, the format of the information is adjusted. For example, if the display method is a text message notification, the information should be brief and clear; if it is an email notification, it may include more detailed content and attachments. Select a suitable display method according to the type and availability of the user terminal. Among them, the preset display methods include text messages, emails, etc., which are not limited in this embodiment.

[0061] Optionally, the preset safety detection condition includes at least one of the following:

[0062] The motor power wiring has been untied, the limit device has been installed, the five-protection padlock and the operating handle have been sealed, the red cloth has been installed, the manual operation hole has been sealed, and the isolation switch position has been switched to the forced separation position.

[0063] The technical solution of the embodiment of the present invention performs safety detection on the safety protection measures to obtain safety detection results when the substation equipment has been equipped with safety protection measures; generates safety prompt information corresponding to the substation equipment and displays the safety prompt information when the safety detection results do not meet the preset safety detection conditions. By performing regular or real-time safety detection on the safety protection measures, safety hazards or potential problems in the substation equipment can be discovered in time. The effectiveness of the safety protection measures is verified to ensure that they can play the expected protective role in actual operation. By introducing an automated detection system and an intelligent prompt mechanism, real-time monitoring and rapid response to safety protection measures for substation equipment can be achieved. The frequency and intensity of manual inspections are reduced, and the operation and maintenance efficiency is improved. The generated safety prompt information can directly point to the substation equipment with safety hazards and specific safety protection measures. This helps operation and maintenance personnel to quickly locate the problem and take corresponding solutions, shorten processing time, and improve processing efficiency.

[0064] Embodiment 3

[0065] Figure 3 This is a schematic diagram of the structure of a device for determining a security protection strategy for a substation provided by Embodiment 3 of the present invention. Figure 3 As shown, the apparatus includes: a scene image acquisition module 310 , a device type determination module 320 and a protection strategy determination module 330 .

[0066] Among them, the scene image acquisition module 310 is used to obtain the target scene image of the substation where the safety protection measures are to be arranged, wherein the target scene image includes at least one substation equipment; the equipment type determination module 320 is used to input the target scene image into a pre-trained target equipment classification model, and determine the target equipment type corresponding to at least one substation equipment based on the model output result, wherein the target equipment classification model is obtained by training a pre-established convolutional neural network based on sample substation equipment images; the protection strategy determination module 330 is used to determine the target safety protection strategy corresponding to the substation equipment according to the target equipment type of the substation equipment.

[0067] The technical solution of the embodiment of the present invention obtains the target scene image of the substation where the safety protection measures are to be arranged, wherein the target scene image includes at least one substation equipment; the equipment layout and the number of equipment in the substation can be intuitively obtained; then, the target scene image is input into a pre-trained target equipment classification model, and the target equipment type corresponding to at least one substation equipment is determined based on the model output result, wherein the target equipment classification model is obtained by training a pre-established convolutional neural network based on sample substation equipment images; and the target equipment type of at least one substation equipment included in the target scene image is accurately determined. Finally, the target safety protection strategy corresponding to the substation equipment is determined according to the target equipment type of the substation equipment, which solves the problem of being unable to accurately determine the safety protection strategy corresponding to each substation equipment, and achieves the beneficial effect of improving the efficiency and accuracy of determining the target safety protection strategy.

[0068] Optionally, the target device classification model includes an input layer, at least one convolution layer connected to the input layer, an activation layer connected to the convolution layer, a pooling layer connected to the last convolution layer, and a fully connected layer connected to the pooling layer; accordingly, the device type determination module includes:

[0069] A convolution unit, used to input the target scene image into the convolution layer through the input layer, and extract initial image features of the target scene image through the convolution layer;

[0070] An activation and pooling unit, configured to perform a nonlinear transformation on the initial image features through the activation layer, and extract key image features from the initial image features after the nonlinear transformation through the pooling layer;

[0071] The classification prediction unit is used to integrate the initial image features and the key image features into target image features through the fully connected layer, and perform equipment classification prediction based on the target image features to obtain a target equipment type corresponding to at least one substation equipment.

[0072] Optionally, the device further comprises:

[0073] A data set construction module, used for constructing a data set before inputting the target scene image into a pre-trained target device classification model, and dividing the data set into a training set and a test set; wherein the data set includes sample substation device images of various substation devices and a standard device type label corresponding to each sample substation device image;

[0074] A model training module, configured to perform a preset number of iterative training on a pre-built initial convolutional neural network model based on the training set, determine a model loss based on an initial device type label output by the model and the standard device type label in each iteration, and adjust model parameters based on the model loss;

[0075] The target model determination module is used to test the model that completes each training based on the test set to obtain multiple model performance indicators, and determine the target device classification model based on the multiple model performance indicators.

[0076] Optionally, the target equipment type includes at least one of an open-type disconnector, a fully enclosed disconnector, a live busbar equipment, an adjacent operating equipment, a protection screen equipment, and a measurement and control screen equipment.

[0077] The device also includes:

[0078] A safety detection module, used for performing safety detection on the safety protection measures to obtain safety detection results when the safety protection measures have been arranged for the power transformation equipment;

[0079] The safety prompt module is used to generate safety prompt information corresponding to the substation equipment and display the safety prompt information when the safety detection result does not meet the preset safety detection conditions.

[0080] Optionally, the preset safety detection condition includes at least one of the following:

[0081] The motor power wiring has been untied, the limit device has been installed, the five-protection padlock and the operating handle have been sealed, the red cloth has been installed, the manual operation hole has been sealed, and the isolation switch position has been switched to the forced separation position.

[0082] Optionally, the device further comprises:

[0083] An image preprocessing module is used to preprocess the target scene image for the safety protection measures to be arranged in the substation after acquiring the target scene image, and update the target scene image based on the preprocessed scene image; wherein the preprocessing includes: at least one of image denoising processing, grayscale transformation processing and filtering processing.

[0084] The device for determining the security protection strategy of a substation provided by an embodiment of the present invention can execute the method for determining the security protection strategy of a substation provided by any embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method.

[0085] Embodiment 4

[0086] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. 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 can 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.

[0087] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by 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 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0088] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0089] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as the method for determining the security protection strategy of a substation.

[0090] In some embodiments, the method for determining the security protection strategy of a substation can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for determining the security protection strategy of a substation described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the method for determining the security protection strategy of a substation in any other appropriate manner (for example, by means of firmware).

[0091] Various implementations of the systems and techniques described above 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), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including 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.

[0092] 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, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0093] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0094] To provide interaction with a user, the systems and techniques described herein may 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 a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0095] The systems and techniques described herein may be implemented in a computing system that includes backend 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 frontend components (e.g., a user computer with a graphical user interface or a 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 backend components, middleware components, or frontend components. The components of the system may 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.

[0096] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0097] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0098] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining a safety protection strategy for a substation, characterized in that: include: Acquire a target scene image in a substation where safety protection measures are to be arranged, wherein the target scene image includes at least one substation equipment; Inputting the target scene image into a pre-trained target device classification model, and determining a target device type corresponding to at least one substation device based on a model output result, wherein the target device classification model is obtained by training a pre-established convolutional neural network based on a sample substation device image; A target safety protection strategy corresponding to the power substation equipment is determined according to a target equipment type of the power substation equipment.

2. The method according to claim 1, characterized in that The target device classification model includes an input layer, at least one convolution layer connected to the input layer, an activation layer connected to the convolution layer, a pooling layer connected to the last convolution layer, and a fully connected layer connected to the pooling layer; The step of inputting the target scene image into a pre-trained target device classification model, and determining a target device type corresponding to at least one power transformation device based on a model output result, comprises: Inputting the target scene image into the convolution layer through the input layer, and extracting initial image features of the target scene image through the convolution layer; The initial image features are nonlinearly transformed by the activation layer, and key image features are extracted from the initial image features after the nonlinear transformation by the pooling layer; The initial image features and the key image features are integrated into target image features through the fully connected layer, and device classification prediction is performed based on the target image features to obtain a target device type corresponding to at least one power transformation device.

3. The method according to claim 1, characterized in that Before inputting the target scene image into a pre-trained target device classification model, the method further includes: Constructing a data set, and dividing the data set into a training set and a test set; wherein the data set includes sample substation equipment images of various substation equipment and a standard equipment type label corresponding to each sample substation equipment image; Performing a preset number of iterative training on the pre-built initial convolutional neural network model based on the training set, determining the model loss based on the initial device type label output by the model and the standard device type label in each iteration, and adjusting the model parameters based on the model loss; The model that has completed training each time is tested based on the test set to obtain multiple model performance indicators, and the target device classification model is determined based on the multiple model performance indicators.

4. The method according to claim 1, characterized in that: The target equipment type includes at least one of an open disconnector, a fully enclosed disconnector, a live busbar equipment, an adjacent operating equipment, a protection panel equipment and a measurement and control panel equipment.

5. The method according to claim 1, characterized in that Also includes: In the case where safety protection measures have been arranged for the power transformation equipment, performing safety detection on the safety protection measures to obtain safety detection results; When the safety detection result does not meet the preset safety detection condition, safety prompt information corresponding to the power transformation equipment is generated and displayed.

6. The method according to claim 5, characterized in that The preset safety detection condition includes at least one of the following: The motor power wiring has been untied, the limit device has been installed, the five-protection padlock and the operating handle have been sealed, the red cloth has been installed, the manual operation hole has been sealed, and the isolation switch position has been switched to the forced separation position.

7. The method according to claim 1, characterized in that After obtaining the target scene image in the substation where the safety protection measures are to be arranged, the following steps are also included: The target scene image is preprocessed, and the target scene image is updated based on the preprocessed scene image; wherein the preprocessing includes: at least one of image denoising processing, grayscale transformation processing and filtering processing.

8. A device for determining a safety protection strategy for a substation, characterized in that: include: A scene image acquisition module, used to acquire a target scene image in a substation where safety protection measures are to be arranged, wherein the target scene image includes at least one substation equipment; A device type determination module, used for inputting the target scene image into a pre-trained target device classification model, and determining the target device type corresponding to at least one substation device based on the model output result, wherein the target device classification model is obtained by training a pre-established convolutional neural network based on sample substation device images; The protection strategy determination module is used to determine the target safety protection strategy corresponding to the power substation equipment according to the target device type of the power substation equipment.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for determining a safety protection strategy for a substation according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining a safety protection strategy for a substation according to any one of claims 1 to 8 when executed.

Images