Power isolation switch jam early warning system, method and device and storage medium

Abstract

The embodiment of the invention provides an electric power isolation switch jam early warning system, method and device and a storage medium. The system comprises a data acquisition module, a rear-end processing module and a front-end visualization module. The data acquisition module can acquire mechanical characteristic parameters in real time through a sensor deployed at a power isolation switch, so that the problems of low efficiency and data lag of traditional manual inspection are solved; the rear-end processing module processes data collected by the sensor through a prediction model, can generate an early warning result containing the jamming probability and early warning information of the power isolation switch, and solves the problem that the potential jamming risk of the power isolation switch cannot be found in a traditional mode. The front-end visualization module displays information such as an early warning result through a browser interface, and can support simultaneous access of multiple users; based on the modules, the power isolation switch jam early warning system can realize real-time monitoring of the operation state of the power isolation switch and jam risk early warning, and the probability of sudden shutdown is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of power inspection, and in particular to a power isolation switch jamming early warning system, method, device and storage medium. BACKGROUND

[0002] In a modern power system, the power isolation switch as a key device of the power grid directly affects the safety and stability of the power grid. The power isolation switch needs to be frequently mechanically operated (such as opening and closing) during operation, and may appear jamming due to factors such as mechanical component wear and lubrication failure during long-term operation. Once jamming failure occurs, it may cause device downtime, power grid cascading failure, even safety accidents, and cause significant economic losses.

[0003] At present, the management and maintenance of the power isolation switch relies on manual inspection, and the operation and maintenance personnel need to collect the parameters of the isolation switch on site regularly. This method has problems such as long inspection cycle, lagging data recording, and large manual error, and can only be repaired after the power isolation switch is found to have jamming, which causes the related power equipment to also be shut down. SUMMARY

[0004] The embodiments of the present application provide a power isolation switch jamming early warning system, method, device and storage medium, so as to achieve the effect of state monitoring and jamming early warning of the power isolation switch.

[0005] In a first aspect, the embodiments of the present application provide a power isolation switch jamming early warning system, comprising:

[0006] A data acquisition module configured to acquire mechanical characteristic parameters of the power isolation switch and transmit the acquired data to a backend processing module;

[0007] The backend processing module is configured to receive the data transmitted by the data acquisition module, input the data into a pre-trained prediction model, obtain a warning result output by the prediction model, and transmit the warning result to a front-end visualization module. The warning result includes a jamming probability of the power isolation switch and warning information;

[0008] The front-end visualization module is configured to receive the warning result transmitted by the backend processing module and visually display the warning result through a browser interface.

[0009] In some possible implementation manners, the backend processing module further includes a database storage unit and an asynchronous task processing unit;

[0010] The database storage unit is configured to store the data transmitted by the data acquisition module in a database;

[0011] The asynchronous task processing unit is configured to input the data stored in the database into the prediction model asynchronously.

[0012] In some possible implementations, the backend processing module also includes a verification unit, which is used to verify the validity of the data before storing it in the database; wherein, the validity verification includes judging the reasonableness of the numerical range of current and rotation angle in the mechanical characteristic parameters.

[0013] In some possible implementations, the front-end visualization module is also used for:

[0014] Responding to user requests, perform at least one of the following operations on the data stored in the database: query, delete, add, and modify.

[0015] In some possible implementations, the front-end visualization module is also used for:

[0016] Receive the data to be predicted uploaded by the user through the browser interface. The data to be predicted includes the mechanical characteristic parameters of the power disconnect switch to be predicted.

[0017] The predictive model processes the data to be predicted, generates early warning results, and transmits them to the front-end visualization module.

[0018] In some possible implementations, the front-end visualization module also supports remote access to the browser interface from multiple terminals and dynamically updates and displays charts representing the changing trends of mechanical characteristic parameters of the power disconnect switch through chart components.

[0019] In some possible implementations, the prediction model includes at least one convolutional layer, at least one bidirectional timing processing layer, and at least one fully connected layer for predicting the jamming state and jamming probability of the power disconnect switch based on mechanical characteristic parameters.

[0020] Secondly, embodiments of this application provide a method for early warning of power disconnect switch jamming, applied to a power disconnect switch jamming early warning system as described in any of the first aspects, the method comprising:

[0021] The browser interface of the front-end visualization module receives diagnostic requests for the power disconnect switch.

[0022] Based on the diagnostic request, the mechanical characteristic parameters of the power disconnect switch are obtained through the browser interface or data acquisition module;

[0023] The back-end processing module processes the acquired mechanical characteristic parameters to generate early warning results, which characterize the jammed state of the power disconnect switch.

[0024] The warning results are visualized through the browser interface of the front-end visualization module.

[0025] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0026] The memory stores instructions that the computer executes;

[0027] The processor executes computer execution instructions stored in memory, causing the processor to perform the method described in the second aspect above.

[0028] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method described in the second aspect above.

[0029] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the method described in the second aspect above.

[0030] The power disconnect switch jamming early warning system, method, device, and storage medium provided in this application embodiment can include a data acquisition module, a back-end processing module, and a front-end visualization module. The data acquisition module uses sensors deployed at the power disconnect switch to collect mechanical characteristic parameters (such as current, angle, and torque) in real time, solving the problems of low efficiency and data lag in traditional manual inspections. The back-end processing module processes the sensor-collected data using a predictive model to generate early warning results containing the jamming probability and warning information of the power disconnect switch, solving the problem that traditional methods cannot detect potential jamming risks in power disconnect switches. The front-end visualization module displays warning results and other information through a browser interface, supporting simultaneous access by multiple users. Based on these modules, the power disconnect switch jamming early warning system can achieve real-time monitoring of the power disconnect switch's operating status and early warning of jamming risks, reducing the probability of sudden shutdowns. Attached Figure Description

[0031] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0032] Figure 1 This is a schematic diagram of a power disconnect switch jamming early warning system provided in an embodiment of this application;

[0033] Figure 2 This is a schematic diagram of the structure of a backend processing module provided in an embodiment of this application;

[0034] Figure 3 A schematic diagram of a diagnostic process for tic disorders provided in an embodiment of this application;

[0035] Figure 4 A flowchart illustrating a power disconnect switch jamming early warning method provided in an embodiment of this application;

[0036] Figure 5This is a schematic diagram of the structure of an electronic device provided in this application.

[0037] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0038] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0039] In modern power system operation and maintenance, power disconnect switches are key equipment in the power grid, and their operating status directly affects the safety and stability of the grid. Traditional disconnect switch management relies on manual inspection, which has problems such as long inspection cycles, delayed data recording, and difficulty in predicting jammed faults. On the one hand, mechanical characteristic parameters such as current, angle, and torque collected manually are easily affected by human factors, resulting in insufficient data accuracy and real-time performance, making it difficult to detect subtle equipment anomalies. On the other hand, repairs can only be carried out after a jammed fault occurs, leading to long equipment downtime, high operation and maintenance costs, and may even trigger cascading failures in the power grid.

[0040] Although some intelligent monitoring systems have been developed in related technologies, these systems mostly focus on monitoring the overall parameters of the power grid, lack specific management functions for power disconnect switches, and require the download of specific software to use, thus failing to support concurrent access by multiple users.

[0041] Based on this, this application proposes a technical concept that uses the Internet of Things (IoT) to collect mechanical characteristic parameters (such as current, angle, torque, etc.) of power disconnect switches in real time, combines this with an artificial intelligence prediction model to dynamically analyze the data and provide risk warnings, and implements a web system based on a B / S (Browser / Server) architecture to support remote access and visual interaction by multiple users through a browser, forming a closed-loop management system of "collection-processing-prediction-feedback". This technical concept, through sensor deployment, model prediction, browser access, and visualization, can solve the problems of data lag, low interaction efficiency, and difficulty in detecting potential jamming risks in traditional power disconnect switch management, achieving real-time monitoring and intelligent operation and maintenance of power disconnect switch jamming status.

[0042] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0043] Figure 1 This is a schematic diagram of a power disconnect switch jamming early warning system provided in an embodiment of this application. Figure 1 As shown, the system may include a data acquisition module, a back-end processing module, and a front-end visualization module.

[0044] The data acquisition module is used to collect the mechanical characteristic parameters of the power disconnect switch and transmit the collected data to the back-end processing module.

[0045] In this embodiment, the data acquisition module may include an Internet of Things (IoT) sensor and a data transmission device deployed at the power disconnect switch. The IoT sensor can collect the mechanical characteristic parameters of the power disconnect switch in real time, and the data transmission device transmits the data collected by the IoT sensor to the back-end processing module. The mechanical characteristic parameters may include the A-phase current, B-phase current, C-phase current, rotation angle, and spindle torque of the power disconnect switch.

[0046] For example, the IoT acquisition module acquires parameters through sensors deployed at key parts of the power disconnect switch. The specific process is as follows: Sensor deployment: Current sensors are deployed in the current monitoring circuit of the power disconnect switch to acquire the A-phase / B-phase / C-phase current, angle sensors are deployed on the mechanical transmission spindle to acquire the rotation angle, and torque sensors are deployed to acquire the spindle torque. The sensors are connected to the local data acquisition terminal via RS485 bus, and the acquisition frequency is set to 1 time / second to ensure real-time capture of changes in the operating status of the equipment; Data transmission: The acquisition terminal encapsulates the parameters in JSON format and transmits them to the backend (i.e., the backend processing module) interface via HTTP protocol with encryption. Data verification bits are enabled during transmission to prevent data loss or tampering.

[0047] The backend processing module receives data transmitted from the data acquisition module and inputs the data into a pre-trained prediction model to obtain the early warning results output by the prediction model and transmit them to the frontend visualization module. The early warning results include the probability of jamming of the power disconnect switch and early warning information.

[0048] In this embodiment, the backend processing module can be deployed on a server or cloud platform. This module can be equipped with a large model trained based on machine learning and neural networks, which processes relevant data of the power disconnect switch to predict jamming conditions. For example, the backend processing module can be built based on the Django framework.

[0049] The front-end visualization module is used to receive the warning results transmitted from the back-end processing module and display them visually through the browser interface.

[0050] In this embodiment, the front-end visualization module and the back-end processing module can adopt a B / S architecture, with the back-end processing module acting as a server. The front-end visualization module can use Echarts combined with HTML, CSS, and JavaScript to construct a browser interface. This browser interface can visualize information such as the stuck status of the power disconnect switch through chart components, and can also support user operation through the browser interface.

[0051] In the above embodiments, the data acquisition module can collect mechanical characteristic parameters (such as current, angle, and torque) in real time through sensors deployed at the power disconnect switch, solving the problems of low efficiency and data lag in traditional manual inspections. The back-end processing module processes the sensor-collected data through a predictive model, generating warning results that include the probability of jamming of the power disconnect switch and early warning information, solving the problem that traditional methods cannot detect potential jamming risks of power disconnect switches. The front-end visualization module displays warning results and other information through a browser interface, supporting simultaneous access by multiple users. Based on these modules, the power disconnect switch jamming early warning system can realize real-time monitoring of the operating status of the power disconnect switch and early warning of jamming risks, reducing the probability of sudden shutdowns.

[0052] Figure 2 This is a schematic diagram of the structure of a backend processing module provided in an embodiment of this application. Figure 2 As shown, the backend processing module may also include a database storage unit, an asynchronous task processing unit, and a verification unit.

[0053] The database storage unit is used to store the data transmitted by the data acquisition module into the database.

[0054] In this embodiment of the application, the database storage unit may include a database system for storing structured storage device data, user information, and operation logs.

[0055] For example, a MySQL database can be used to implement structured data management, with data stored in separate tables, such as an equipment data table, a user information table, and an operation log table. The equipment data table stores the mechanical characteristic parameters and acquisition time of the power disconnect switch, including fields such as "Equipment ID," "Current Value," and "Acquisition Time." The user information table stores user identity information and permission levels, including fields such as "Username," "Encrypted Password," and "Permission Level." The operation log table records user operation events and timestamps, including fields such as "Operator," "Operation Time," and "Operation Type."

[0056] The asynchronous task processing unit is used to asynchronously input data stored in the database into the prediction model.

[0057] In the embodiments of this application, the asynchronous task processing unit can be a unit for managing multi-threaded or asynchronous tasks, which can distribute processing requests through a task queue.

[0058] The verification unit is used to validate the data before storing it in the database. This validation includes assessing the reasonableness of the numerical ranges for current and rotation angle in the mechanical characteristic parameters.

[0059] In this embodiment, after receiving data such as the mechanical characteristic parameters of the power disconnect switch, the backend processing module can first perform format verification through the verification unit, and then perform validity verification. If the verification passes, the data is temporarily stored in the memory buffer, and every 10 data entries are written to the MySQL database table in batches. If the verification fails, a JSON response of "Invalid data format: specific error field" is returned. After receiving the response, the data acquisition module retransmits the batch of data.

[0060] In the above embodiments, based on the mechanical characteristic parameters of the power disconnect switch collected by the data acquisition module, the back-end processing module can further improve data reliability through a verification unit. Format verification ensures the integrity of data transmission, and numerical range judgment eliminates abnormal data, thereby avoiding invalid data from interfering with the prediction model and improving the overall stability of the system operation.

[0061] In one embodiment, the front-end visualization module also supports remote access to the browser interface from multiple terminals and dynamically updates and displays charts representing the changing trends of mechanical characteristic parameters of the power disconnect switch through chart components.

[0062] In this embodiment, the browser interface provided by the front-end visualization module supports concurrent access by multiple users through different terminals. Based on a B / S architecture, this module provides a web interface to any terminal (such as a PC, mobile phone, or tablet) via the HTTP protocol, allowing users to access system functions through a browser without installing a client. The front-end visualization module can also dynamically update charts and data tables using the Echarts component, enabling real-time monitoring of lag status and lag risk warnings.

[0063] In the above embodiments, the front-end visualization module can further enhance operational flexibility by enabling remote access from multiple terminals, based on real-time monitoring of the power disconnect switch status. Users can monitor equipment status, query data, and export reports in real time without being on-site, thereby reducing manual inspection costs and improving operational efficiency. Furthermore, the use of Echarts dynamic charts and label highlighting technology addresses the low interaction efficiency of traditional systems. The dynamic refresh function allows maintenance personnel to grasp equipment status changes in real time, and the label colors intuitively reflect risk levels, significantly improving decision-making efficiency. This technology, through optimized visual interaction, provides a more intuitive monitoring interface for power grid operation and maintenance.

[0064] In one embodiment, the front-end visualization module is also used for:

[0065] Responding to user requests, perform at least one of the following operations on the data stored in the database: query, delete, add, and modify.

[0066] In this embodiment, the front-end visualization module can also provide users with data management functions through a browser interface. Specifically, this includes functions such as querying, adding, editing, and deleting real-time and / or historical data of power disconnect switches. It supports filtering data by device type and time dimension, improves browsing efficiency with paginated display, supports monthly and yearly statistical data, generates visual trend charts, and provides Excel format export. For example, when a user requests data for a specific power disconnect switch through the browser interface, the front-end visualization module forwards the request to the back-end processing module. The back-end processing module retrieves the corresponding data from the database based on the request and sends it back to the front-end visualization module. After receiving the back-end data, the front-end visualization module dynamically refreshes the charts and displays operation prompts to ensure that the user can monitor the device status in real time.

[0067] In one embodiment, the front-end visualization module is also used for:

[0068] The system receives data to be predicted uploaded by users through a browser interface. This data includes the mechanical characteristic parameters of the power disconnect switch to be predicted. The system processes the data using a prediction model, generates early warning results, and transmits them to the front-end visualization module.

[0069] In this embodiment of the application, the front-end visualization module can also provide users with a diagnostic function for stuck objects through a browser interface.

[0070] Figure 3 This is a schematic flowchart illustrating a diagnostic process for tic-tacs provided in an embodiment of this application. Figure 3As shown, users can upload the mechanical characteristic parameters of the power disconnect switch through the browser interface. The front-end visualization module transmits the parameters to the back-end processing module. The back-end processing module can input the parameters into the prediction model for processing and send the model output results back to the front-end visualization module. Finally, the front-end visualization module presents the jamming status and other data to the user through the browser interface.

[0071] For example, the cascade diagnostic tool supports uploading TXT (text format) files and "one-click run diagnostic" operation. The diagnostic results are displayed in the form of "cascade status + probability + level label", and different colors are used to highlight the normal, general cascade, severe cascade, and critical cascade levels.

[0072] The jamming diagnosis process can include: the user clicks the "Select File" button to upload the TXT file to be diagnosed; after the file format is verified, the user clicks the "One-Click Run Jamming Diagnosis" button; the front end sends the file information to the back-end processing module via an asynchronous request; after the diagnosis results are returned, the interface displays the jamming status and jamming probability in the "Prediction Results" area, and can also highlight the corresponding jamming level label according to the probability value; the data statistics and export function supports statistical analysis of disconnector operation data by month and year, and the exported file is in Excel format, including fields such as serial number, detection time, equipment type, current of each phase, rotation angle, and spindle torque.

[0073] For example, when the backend processing module works with the frontend visualization module to implement data management and system malfunction diagnostics, the asynchronous task processing unit can use an asynchronous task processing mechanism to limit the number of POST requests per minute from a single IP address and manage the number of failed login attempts through a caching strategy to ensure system stability. Here, the POST request can be a webpage request initiated by the user through a browser.

[0074] For example, the asynchronous task processing unit can limit a single IP to a maximum of 20 POST requests per minute using decorators to prevent malicious request attacks; the Django caching framework is used to store the number of failed login attempts, and if a total of 5 failed attempts are made, the IP will be locked for 5 minutes, during which time login requests from that IP will be rejected.

[0075] For example, the backend processing module can also perform hierarchical permission management: the backend implements hierarchical permission control through the interface. Administrator accounts can view the full operation log through the interface and perform add, delete, modify and password reset operations on all user accounts; ordinary users can only modify their own mobile phone number and email address through the interface and cannot access other user data or system core configurations.

[0076] In the above embodiments, the interactivity and usability of the system can be further improved by refining the diagnostic, data management, and statistical export functions. The diagnostic function supports offline data upload and real-time diagnosis, the data management function enables flexible management of device data, and the statistical export function provides multi-dimensional data visualization and export capabilities, thereby meeting the diverse needs of maintenance personnel.

[0077] In one embodiment, the prediction model includes at least one convolutional layer, at least one bidirectional timing processing layer, and at least one fully connected layer, for predicting the jamming state and jamming probability of a power disconnector based on mechanical characteristic parameters.

[0078] Among them, convolutional layers refer to neural network layers used to extract local features of input data. Bidirectional temporal processing layers refer to neural network layers used to model long-term dependencies in time series. Fully connected layers refer to neural network layers used to integrate features and output the final result.

[0079] In this embodiment, the convolutional layer can extract local features of parameters such as current, angle, and torque (e.g., current fluctuation trend) through a sliding window; the bidirectional time-series processing layer can model the long-term dependency of parameter changes (e.g., periodicity of torque changes) through forward and backward propagation; and the fully connected layer can integrate the extracted features and output the jamming probability.

[0080] For example, the inference process of the prediction model in the backend processing module may include the following steps:

[0081] S1. Obtain the mechanical characteristic parameters of the disconnector from the IoT acquisition module or the uploaded TXT file, organize them in the order of acquisition time, and extract the angle, torque, and current characteristic data.

[0082] S2. Set the feature data length to 99, padding with 0s if the length is insufficient and truncating if the length exceeds the limit.

[0083] S3. Load the pre-trained normalizer and perform normalization processing on the feature data after uniform length.

[0084] S4. Construct an artificial intelligence prediction model, which includes a 1D convolutional layer, a pooling layer, a Dropout layer, a bidirectional LSTM layer, and a fully connected layer.

[0085] S5. Input the normalized feature data into the model, calculate it through forward propagation, and obtain the Kaze probability through the activation function.

[0086] In the above embodiments, the combination of convolutional layers and bidirectional temporal processing layers can further improve the accuracy of the prediction model in analyzing the correlation between mechanical characteristic parameters. Convolutional layers capture local features, bidirectional temporal processing layers model long-term dependencies, and fully connected layers fuse features to output the jamming probability, thereby significantly improving the accuracy and adaptability of early warning for jamming conditions of power disconnect switches.

[0087] Figure 4 This is a flowchart illustrating a method for early warning of power disconnect switch jamming, provided as an embodiment of this application. This method can be applied to the power disconnect switch jamming early warning system in any of the above embodiments. Figure 4 As shown, the method may include:

[0088] Step S401: Receive diagnostic requests for the power disconnect switch through the browser interface of the front-end visualization module.

[0089] Step S402: Based on the diagnostic request, obtain the mechanical characteristic parameters of the power disconnect switch through the browser interface or data acquisition module.

[0090] Step S403: The obtained mechanical characteristic parameters are processed by the back-end processing module to generate an early warning result.

[0091] Among them, the early warning result characterizes the jammed state of the power disconnect switch.

[0092] For example, the backend processing module built on the Django framework can acquire real-time disconnect switch parameter data collected by IoT sensors. Combined with an asynchronous task processing mechanism and caching strategy, asynchronous task processing can limit the frequency of requests from a single IP address, while the caching strategy manages information such as the number of failed login attempts. Through a constructed AI prediction and diagnostic model, the disconnect switch parameters, after data alignment and normalization, are used as model input to predict the disconnect switch's jamming state and probability. After receiving a request from the frontend, the backend interacts with the MySQL database, involving operations on multiple tables such as the user information table, device data table, and operation log table, to complete data storage and retrieval, generate processing results, and encapsulate the prediction results and data processing results into JSON format before feeding them back to the frontend visualization module.

[0093] Step S404: Visualize the warning results through the browser interface of the front-end visualization module.

[0094] For example, based on the data fed back by the backend processing module, the frontend visualization module can be dynamically updated. The updates include refreshing the trend charts of the current of each phase of the switch, the rotation angle, and the spindle torque through Echarts, highlighting the jamming level label, which covers normal, general jamming, severe jamming, and critical jamming, and popping up operation result prompts, such as data saving successful, deletion successful, etc.; the operating status of the disconnecting switch is reflected in real time through dynamic interface updates.

[0095] The following example illustrates a scenario where a user interacts with the system through a browser interface. This example includes the following flow:

[0096] Login and Registration Interaction: Login Interface: After the user enters their username, password, and image verification code, the front-end asynchronously sends data to the back-end interface via AJAX. The back-end calls the registration form validation logic. If the validation passes, a session valid for 3 hours is created, and the user is redirected to the system's main interface. If the validation fails, the corresponding error message is returned, and the front-end displays a red error message below the login form. Registration Interface: New users click "Register Now" and are redirected to the registration page. They fill in their username, mobile phone number, email address, password, and confirm password. The front-end validates the input in real time through the user form. The back-end checks the uniqueness of the username and saves the data to the user table, recording the time synchronously. After successful registration, the user is automatically redirected to the login page. Cardiac Diagnosis Function: File Upload: When the user clicks the "Select File" button in the "Input Panel" on the main interface, the front end restricts the upload to only TXT format files via the accept=".txt" attribute. After uploading, the interface displays "Selected: [File Name]". If no file is selected, the "One-Click Run Cardiac Diagnosis" button is disabled. Diagnosis Trigger: When the "One-Click Run Cardiac Diagnosis" button is enabled, the front end sends the file data to the back end interface in FormData format. The back end calls relevant functions to load the pre-trained artificial intelligence prediction and diagnosis model and normalizer, and processes the feature data in the file. Result Display: After the back end returns the diagnosis result, the front end's "Prediction Result" panel displays the cardiac status and highlights the corresponding cardiac level label with the light1 style. At the same time, a temporary notification is displayed at the top of the interface. Data Management and Statistics: Data Viewing: The front-end retrieves data through an interface and uses Echarts to draw "Current Trend Chart of Switch A / B / C Phases", "Rotation Angle Trend Chart", and "Main Shaft Torque Trend Chart". The charts support mouse hover to view specific values; the data tables are displayed in paginated format; Data Operations: Clicking "Add Data" pops up a modal dialog box. After the user fills in the parameters and clicks "Save", the front-end submits the data through the interface. After the back-end verifies the data, it is saved to the database and the operation log is recorded; Clicking the "Edit" or "Delete" button on a data entry causes the front-end to call the interface to update or delete the data and refresh the table data; Statistical Export: Clicking the "Monthly Statistics" or "Yearly Statistics" tabs causes the front-end to request the interface to retrieve data aggregated by the time dimension and display it in tabular form; Clicking the "Export Excel" button causes the front-end to request the interface, and the back-end generates an Excel file containing fields such as "Serial Number", "Detection Time", "Equipment Type", and "Parameter Values", which is downloaded to the local machine through a browser. The file name format is "Power Disconnect Switch Operation Data_Year_Equipment Type.xlsx".

[0097] In the above embodiments, the power disconnect switch jamming early warning system can improve the user's interactive experience. Echarts visual charts intuitively display parameter trends, and dynamic updates and pop-up prompts ensure that users receive feedback in real time. The operation process is simple and reduces the threshold for use.

[0098] Figure 5 This is a schematic diagram of the structure of an electronic device provided in this application. Figure 5 As shown, the electronic device 50 provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the device 50 further includes a communication component 503. The processor 501, memory 502, and communication component 503 are connected via a bus 504.

[0099] In a specific implementation, at least one processor 501 executes computer execution instructions stored in memory 502, causing at least one processor 501 to perform the above-described method.

[0100] The specific implementation process of processor 501 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0101] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0102] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0103] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0104] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0105] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0106] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0107] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0108] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0109] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0110] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0111] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0112] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0113] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A power disconnect switch jamming early warning system, characterized in that, include: The data acquisition module is used to collect the mechanical characteristic parameters of the power disconnect switch and transmit the collected data to the back-end processing module; The back-end processing module is used to receive the data transmitted by the data acquisition module and input the data into the pre-trained prediction model to obtain the early warning result output by the prediction model and transmit it to the front-end visualization module. The early warning result includes the jamming probability of the power disconnect switch and the early warning information. The front-end visualization module is used to receive the warning results transmitted by the back-end processing module and display them visually through a browser interface.

2. The system according to claim 1, characterized in that, The backend processing module also includes a database storage unit and an asynchronous task processing unit; The database storage unit is used to store the data transmitted by the data acquisition module into the database; The asynchronous task processing unit is used to asynchronously input the data stored in the database into the prediction model.

3. The system according to claim 2, characterized in that, The backend processing module further includes a verification unit, which is used to verify the validity of the data before storing it in the database; wherein, the validity verification includes judging the reasonableness of the numerical range of the current and rotation angle in the mechanical characteristic parameters.

4. The system according to claim 2 or 3, characterized in that, The front-end visualization module is also used for: In response to a user request, perform at least one of the following operations on the data stored in the database: query, delete, add, and modify.

5. The system according to any one of claims 1 to 3, characterized in that, The front-end visualization module is also used for: Receive data to be predicted uploaded by users through a browser interface, the data to be predicted including the mechanical characteristic parameters of the power disconnect switch to be predicted; The prediction model processes the data to be predicted, generates early warning results, and transmits them to the front-end visualization module.

6. The system according to any one of claims 1 to 3, characterized in that, The front-end visualization module also supports remote access to the browser interface from multiple terminals, and dynamically updates and displays charts representing the changing trends of the mechanical characteristic parameters of the power disconnect switch through chart components.

7. The system according to any one of claims 1 to 3, characterized in that, The prediction model includes at least one convolutional layer, at least one bidirectional timing processing layer, and at least one fully connected layer, used to predict the jamming state and jamming probability of the power disconnect switch based on the mechanical characteristic parameters.

8. A method for early warning of jamming of a power disconnect switch, characterized in that, The method, applied to the power disconnect switch jamming early warning system as described in any one of claims 1 to 7, comprises: The diagnostic request for the power disconnect switch is received through the browser interface of the front-end visualization module. Based on the diagnostic request, the mechanical characteristic parameters of the power disconnect switch are obtained through the browser interface or the data acquisition module. The back-end processing module processes the acquired mechanical characteristic parameters to generate an early warning result, which characterizes the jammed state of the power disconnect switch. The warning results are visualized through the browser interface of the front-end visualization module.

9. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in claim 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in claim 8.

Images