Visual intelligent monitoring system and method for power distribution cabinet, computing equipment and storage medium

Abstract

The invention discloses a power distribution cabinet visual intelligent monitoring system and method, computing equipment and a storage medium, and belongs to the technical field of power system equipment monitoring, the system comprises a data acquisition module, edge computing equipment, a user-defined visual interface and a cloud platform, and the modules are in communication connection through a low-power wide area network; the data acquisition module is used for acquiring running state data and environment data of the power distribution cabinet in real time; the edge computing device is used for preprocessing the collected data and evaluating the quality of the power grid, and uploading the preprocessed data to the cloud platform; and the cloud platform is used for training a deep neural network model by using historical data based on a distributed computing framework, performing anomaly detection and fault prediction on real-time data based on the trained model, triggering early warning according to a detection result, and displaying a real-time data stream view and anomaly labeling information in a self-defined visual interface. According to the scheme, the power distribution cabinet anomaly detection accuracy and the information display flexibility can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system equipment monitoring, and in particular to a visual intelligent monitoring system, method, computing device and storage medium for a power distribution cabinet. Background Art

[0002] As an important power management equipment in modern industrial and commercial fields, the distribution cabinet plays a key role in managing, controlling and protecting the power system. However, due to the influence of long-term operation and environmental factors, there is a risk of failure in the distribution cabinet. Therefore, fault prediction and prevention of distribution cabinets are crucial to ensure the stability and safety of the power system. Existing distribution cabinet monitoring systems mostly adopt a fixed-cycle data collection strategy through staff inspections. Some distribution cabinets are usually scattered and far apart. The geographical environment is relatively complex, the timeliness is poor and it is time-consuming and labor-intensive. Abnormalities can often only be discovered after the fault occurs. Unpredicted and unhandled faults may cause serious damage to the distribution system and power outages, affecting the stable operation and maintenance efficiency of the power system.

[0003] With the development and application of advanced technologies such as 5G, artificial intelligence, and cloud platforms, the existing distribution cabinet monitoring system installs monitoring cameras, sensors and other information collection devices locally in the distribution cabinet to transmit the environmental information, access control, video surveillance and other data of the distribution cabinet to the central monitoring room, which then performs remote and centralized monitoring of the distribution cabinets in the system. The existing system has weak comprehensive data analysis capabilities, is highly dependent on the network and the central monitoring room, has low decision-making efficiency in big data scenarios, and cannot meet the monitoring requirements for timely warnings. Summary of the invention

[0004] In order to solve the problems of insufficient real-time monitoring, low efficiency and accuracy of abnormality and fault detection, and inflexible and inflexible information display, this solution proposes a visual intelligent monitoring system, method, computing device and storage medium for distribution cabinets. The multi-dimensional monitoring data collected in real time is transmitted efficiently and stably through a low-power wide area network, which improves the real-time nature of monitoring. The efficiency and accuracy of abnormality and fault detection in distribution cabinets are improved by combining edge computing devices with distributed cloud computing platforms. The flexibility of information display and the efficiency of fault location can be improved by providing a custom visualization interface.

[0005] According to one aspect of the present invention, a visual intelligent monitoring system for a power distribution cabinet is provided, comprising: a data acquisition module, an edge computing device, a custom visualization interface and a cloud platform, wherein the modules are connected via a low-power wide area network communication.

[0006] Among them, the data acquisition module is used to collect the operating status data and environmental data of the distribution cabinet in real time, and transmit the collected data to the edge computing device; the edge computing device is used to preprocess the received data and evaluate the power grid quality, and upload the preprocessed data to the cloud platform; the cloud platform is used to train the deep neural network model based on the distributed computing framework using historical data, and perform anomaly detection and fault prediction on the real-time data based on the trained deep neural network model, trigger early warning according to the detection results, and display the real-time data stream view and anomaly annotation information in the custom visualization interface.

[0007] By adopting the above technical solutions, the probability of equipment failure is reduced through real-time monitoring and fault prediction, thereby reducing the cost of manual inspection and maintenance. The combination of edge computing and cloud platform ensures that the overall system can still operate normally even when a part fails, enhancing the reliability of the system. Users can customize the visualization interface according to actual needs, providing intuitive real-time data flow views and abnormal annotation information, facilitating rapid fault location and maintenance decisions.

[0008] Optionally, in the visual intelligent monitoring system of the distribution cabinet provided by the present invention, the data acquisition module includes at least a current sensor, a voltage sensor, a temperature sensor, a humidity sensor, a vibration and noise sensor, a gas sensor, a camera and a weather forecast interface, which are used to collect current, voltage, temperature, humidity, operating noise, distribution cabinet operation images and meteorological data respectively.

[0009] By adopting the above technical solutions, the system can monitor the operating status of the power distribution cabinet from multiple dimensions and obtain comprehensive performance data, which helps to gain a deeper understanding of the health status of the equipment.

[0010] Optionally, in the visual intelligent monitoring system for distribution cabinets provided by the present invention, the edge computing device is used to pre-process the data received in real time by cleaning and filtering, and the pre-processed data is converted into a unified format and transmitted to the cloud platform based on a secure communication protocol; harmonic analysis is performed on the current waveform through Fourier transform, and the grid quality is evaluated based on the harmonic components and their proportions; the power factor is calculated based on the phase difference between current and voltage, and whether the load properties match the grid is determined based on the power factor, and a power quality report is generated and stored in the edge computing device; maintenance measures are generated based on the impact of meteorological data on power equipment and the power quality report, and the maintenance measures are sent to the mobile phone APP of the operation and maintenance personnel.

[0011] By adopting the above technical solutions, edge computing devices can perform real-time processing at the source of data generation, reduce data transmission delays, and eliminate noise and outliers through data cleaning and filtering, thereby improving data accuracy and reliability, and providing a reliable data basis for subsequent analysis. The generated power quality report provides clear and intuitive data support for operation and maintenance personnel, which helps to quickly identify and solve problems and conduct subsequent analysis.

[0012] Optionally, in the visual intelligent monitoring system for distribution cabinets provided by the present invention, the cloud platform is used to activate the early warning protocol when the deep neural network model determines that the real-time monitoring indicators deviate from the normal range, start the response program, and send the early warning information to the mobile phone APP of the operation and maintenance personnel through the message push service. The early warning information includes the type of abnormality, affected equipment, specific values ​​of the deviation indicators and their normal range, and the time of occurrence.

[0013] Optionally, in the visual intelligent monitoring system for distribution cabinets provided by the present invention, a customized visualization interface provides historical data trend charts and real-time data stream views, and uses different colors and symbols to highlight affected areas and equipment in the real-time data stream view.

[0014] Optionally, in the visual intelligent monitoring system for distribution cabinets provided by the present invention, the custom visualization interface provides a custom display panel so that users can select different information display densities and display methods according to specific application scenarios, and add, delete or adjust different functional modules through drag operations.

[0015] Optionally, in the visual intelligent monitoring system for distribution cabinets provided by the present invention, the cloud platform is used to use a convolutional neural network to process image data, identify visual anomalies inside the distribution cabinet, and use a recurrent neural network to process sensor data and identify abnormal sensor data.

[0016] According to a second aspect of the present invention, a method for visual intelligent monitoring of distribution cabinets is provided, including: real-time collection of operating status data and environmental data of the distribution cabinet; preprocessing the operating status data and environmental data and performing grid quality assessment, and generating maintenance measures according to the grid quality assessment results; using the preprocessed historical data to train a deep neural network model, performing anomaly detection and fault prediction on the preprocessed real-time data based on the trained deep neural network model, and triggering an early warning according to the detection results; and displaying the real-time data stream view and anomaly annotation information through a customized visualization interface.

[0017] According to a third aspect of the present invention, a computing device is provided, comprising: at least one processor; and a memory storing program instructions, wherein the program instructions are configured to be suitable for execution by at least one processor, and the program instructions include instructions for executing the visual intelligent monitoring method for distribution cabinets as described above.

[0018] According to a fourth aspect of the present invention, a readable storage medium storing program instructions is provided, wherein when the program instructions are read and executed by a computing device, the computing device executes the above-mentioned visual intelligent monitoring method for a power distribution cabinet.

[0019] The visual intelligent monitoring system and system for power distribution cabinets provided by the present invention can at least achieve the following technical effects: 1. Through multi-dimensional data analysis and automated early warning mechanisms, the accuracy of fault prediction is improved and the probability of power accidents is reduced.

[0020] 2. The cloud platform uses a distributed computing framework to train deep neural networks, which can learn complex patterns and anomalies from historical data to adapt to the ever-changing operating environment and load conditions and improve the sensitivity of anomaly detection.

[0021] 3. The customized visualization interface improves the operation experience of operation and maintenance personnel, reduces the risk of misinterpretation of data, and thus speeds up the troubleshooting process.

[0022] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings: Figure 1 It shows a structural schematic diagram of a visual intelligent monitoring system 001 for a power distribution cabinet according to an embodiment of the present invention; Figure 2 A schematic diagram of the structure of a computing device 100 according to an embodiment of the present invention is shown; Figure 3 A schematic flow chart of a method 300 for visual intelligent monitoring of a power distribution cabinet according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0024] In view of the problem that the data analysis capability of the distribution cabinet monitoring system is weak and it is unable to effectively identify and evaluate the health status of the distribution cabinet before a fault occurs, which affects the decision-making efficiency, this solution proposes a visual intelligent monitoring system, method, computing device and storage medium for distribution cabinets. Through multi-dimensional data analysis and deep learning model anomaly detection, it can improve the accuracy and coverage of fault warning. Through a customized visual interface, it improves the operating experience of operation and maintenance personnel, reduces the risk of misinterpretation of data, and thus accelerates the troubleshooting process.

[0025] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0026] Figure 1 FIG. 1 is a schematic diagram showing a structure of a visual intelligent monitoring system 001 for a power distribution cabinet according to an embodiment of the present invention. Figure 1 As shown, the system 001 includes: data acquisition modules 1-n, edge computing devices 1-m, custom visualization interfaces and cloud platforms. The modules communicate with each other through a low-power wide area network (LPWAN, such as LoRa, NB-IoT).

[0027] The data acquisition module is used to collect the operating status data and environmental data of the power distribution cabinet in real time, and transmit the collected data to the edge computing device within the preset range. The operating status data mainly includes voltage, current, power, line temperature, operating noise, etc., and the environmental data mainly includes temperature, humidity, dust concentration, etc.

[0028] In one embodiment of the present invention, the data acquisition module may include a current sensor, a voltage sensor, a temperature sensor, a humidity sensor, a vibration and noise sensor, a gas sensor, a camera and a weather forecast interface, which are respectively used to collect current, voltage, temperature, humidity, operating noise, flammable gas concentration, distribution cabinet operation images and meteorological data.

[0029] Edge computing devices can pre-process the received data and evaluate the grid quality, and upload the pre-processed data to the cloud platform.

[0030] For example, the edge computing device first performs pre-processing such as data cleaning and filtering on the data received in real time to remove invalid data, outliers, and duplicate data. After that, the pre-processed data is converted into a unified format and transmitted to the cloud platform based on a secure communication protocol such as HTTPS / MQTT.

[0031] Furthermore, harmonic analysis of the current waveform is performed through Fourier transform, and the quality of the power grid is evaluated based on the harmonic components and their proportions; the power factor is calculated based on the phase difference between current and voltage, and the load nature is judged based on the power factor to determine whether it matches the power grid. A power quality report is generated and stored in the edge computing device. Maintenance measures are generated based on the impact of meteorological data on power equipment and power quality reports to prevent energy waste caused by insufficient reactive compensation, reduce damage caused by bad weather, and send maintenance measures to the mobile phone APP of the operation and maintenance personnel. Rising temperatures may cause equipment to overheat and reduce operating efficiency, so cooling measures need to be taken in advance. High humidity or rainfall may affect the insulation and operating safety of equipment, and moisture-proof and waterproof measures need to be considered.

[0032] For example, if the power factor is too low, there may be insufficient reactive power compensation, and reactive power compensation measures (such as installing capacitors) may be recommended to optimize energy consumption, improve overall energy efficiency, and reduce electricity bills.

[0033] The cloud platform is used to process large-scale data based on a distributed computing framework, train deep neural network models using historical data, detect anomalies and predict faults on real-time data based on the trained deep neural network model, trigger warnings based on the detection results, and display real-time data stream views and anomaly annotation information in a custom visualization interface. For example, Apache Spark or Flink distributed computing frameworks are used for large-scale data processing, and distributed databases such as Hadoop HDFS and Amazon S3 are used to store historical and real-time data.

[0034] In one embodiment of the present invention, the cloud platform can activate the early warning protocol and start the response program when the deep neural network model determines that the real-time monitoring indicators deviate from the normal range, and send the early warning information to the mobile phone APP of the operation and maintenance personnel through the message push service. The early warning information includes the abnormality type (such as overload, short circuit, etc.), the affected equipment, the specific value of the deviation indicator and its normal range, and the time of occurrence.

[0035] In order to improve the accuracy and efficiency of abnormal operation or fault warning of distribution cabinets, this solution uses transfer learning on the basis of a distributed cloud platform. Specifically, in the distribution cabinet monitoring system, transfer learning can be used to quickly adapt to new distribution cabinet models and different environmental conditions, thereby reducing model training time. For example, use convolutional neural networks to process image data and identify visual anomalies inside the distribution cabinet, and use recurrent neural networks to process sensor data and identify abnormal sensor data. Collect new distribution cabinet monitoring data (including different types of distribution cabinets, environmental conditions, and operating status). Apply the pre-trained model to the new data set through fine-tuning technology. Freeze some model layers during fine-tuning and only train the last few layers to adapt to the new task while retaining the pre-trained knowledge. Define the loss function and optimizer and train until the model performs well on the new data. Transfer learning can reduce the time and computing resources required for model training.

[0036] The custom visualization interface provides a custom display panel so that users can choose different information display densities and display methods according to specific application scenarios, and add, delete or adjust different functional modules by dragging and dropping. For example, users can place different functional modules according to their personal preferences. The main control panel displays a system status overview by default, while the submenu provides more granular options, such as the historical data curve of a single distribution cabinet. The custom visualization interface provides historical data trend charts and real-time data stream views, and uses different colors and symbols to highlight the affected areas and devices in the real-time data stream view.

[0037] For example, color changes and flashing are used to attract the attention of maintenance personnel, and multiple color codes are used to distinguish different alarm levels, such as red: high alarm, orange: medium alarm, and green: normal operation. Detailed fault location information is provided, including the device name, location, and connection with other devices. Combined with geographic information system (GIS) technology, the source of the fault can be further accurately located. After receiving the alarm, maintenance personnel can quickly locate the source of the fault through the visualization platform and respond quickly according to the alarm information, such as conducting on-site inspections, restarting equipment, and adjusting loads.

[0038] It can be seen that the visual intelligent monitoring system for distribution cabinets provided by this solution can monitor the operation-related data of distribution cabinets in multiple dimensions, and process and analyze data through edge computing devices near the data source, which can reduce latency, respond to potential power grid problems in a timely manner, and quickly identify abnormal situations through power grid quality assessment. By comprehensively using edge computing, cloud computing and deep learning technologies, the system not only improves the monitoring capabilities of distribution cabinets, but also optimizes operation and maintenance management and reduces the occurrence of failures.

[0039] Figure 2 FIG. 1 is a schematic diagram showing the structure of a computing device 100 according to an embodiment of the present invention. Figure 2 As shown, in a basic configuration 102, computing device 100 includes system memory 106 and one or more processors 104. A memory bus 108 may be used for communication between processor 104 and system memory 106.

[0040] The processor 104 may be any type of processor, including but not limited to a microprocessor (µP), a microcontroller (µC), a digital signal processor (DSP), or any combination thereof. The processor 104 may include one or more levels of cache, such as a level 1 cache 110 and a level 2 cache 112, a processor core 114, and registers 116. An example processor core 114 may include an arithmetic logic unit (ALU), a floating point unit (FPU), a digital signal processing core (DSP core), or any combination thereof. An example memory controller 118 may be used with the processor 104, or in some implementations, the memory controller 118 may be an internal part of the processor 104.

[0041] The system memory 106 may be any type of memory, including but not limited to: volatile memory (such as RAM), non-volatile memory (such as ROM, flash memory, etc.) or any combination thereof. The physical memory in the computing device generally refers to the volatile memory RAM, and the data in the disk needs to be loaded into the physical memory before it can be read by the processor 104. The system memory 106 may include an operating system 120, one or more applications 122, and program data 124. In some embodiments, the application 122 may be arranged to execute instructions on the operating system by one or more processors 104 using the program data 124. The operating system 120 may be, for example, Linux, Windows, etc., which includes program instructions for processing basic system services and performing hardware-dependent tasks. The application 122 includes program instructions for implementing various user-desired functions, and the application 122 may be, for example, a browser, instant messaging software, a software development tool (such as an integrated development environment IDE, a compiler, etc.), etc., but is not limited thereto. When the application 122 is installed in the computing device 100, a driver module may be added to the operating system 120.

[0042] When the computing device 100 starts running, the processor 104 reads and executes the program instructions of the operating system 120 from the memory 106. The application 122 runs on the operating system 120 and uses the interfaces provided by the operating system 120 and the underlying hardware to implement various functions desired by the user. When the user starts the application 122, the application 122 is loaded into the memory 106, and the processor 104 reads and executes the program instructions of the application 122 from the memory 106.

[0043] Computing device 100 also includes a storage device 132 including a removable storage 136 and a non-removable storage 138 , both of which are connected to storage interface bus 134 .

[0044] The computing device 100 may also include an interface bus 140 that facilitates communication from various interface devices (e.g., output devices 142, peripheral interfaces 144, and communication devices 146) to the basic configuration 102 via the bus / interface controller 130. Example output devices 142 include a graphics processing unit 148 and an audio processing unit 150. They can be configured to facilitate communication with various external devices such as a display or speakers via one or more A / V ports 152. Example peripheral interfaces 144 may include a serial interface controller 154 and a parallel interface controller 156, which may be configured to facilitate communication with external devices such as input devices (e.g., keyboards, mice, pens, voice input devices, touch input devices) or other peripherals (e.g., printers, scanners, etc.) via one or more I / O ports 158. Example communication devices 146 may include a network controller 160, which may be arranged to facilitate communication with one or more other computing devices 162 via a network communication link via one or more communication ports 164.

[0045] A network communication link may be an example of a communication medium. The communication medium may generally be embodied as a computer-readable instruction, data structure, program module in a modulated data signal such as a carrier wave or other transmission mechanism, and may include any information delivery medium. A "modulated data signal" may be a signal in which one or more of its data sets or its changes may be performed in a manner that encodes information in the signal. As a non-limiting example, the communication medium may include a wired medium such as a wired network or a dedicated line network, and various wireless media such as sound, radio frequency (RF), microwave, infrared (IR) or other wireless media. The term computer-readable medium used herein may include both storage media and communication media. In a computing device 100 according to the present invention, the application 122 includes instructions for executing the visual intelligent monitoring method 300 of the power distribution cabinet of the present invention.

[0046] Figure 3 FIG. 3 is a flow chart showing a method 300 for visual intelligent monitoring of a power distribution cabinet according to an embodiment of the present invention. Figure 3 As shown, in step S310, the operating status data and environmental data of the power distribution cabinet are collected in real time.

[0047] For example, various sensors, cameras, weather forecast interfaces and other data acquisition devices installed locally in the distribution cabinet are used to collect real-time operating status data such as current, voltage, frequency, line temperature, noise and other operating status data of the distribution cabinet, as well as environmental data such as temperature, humidity and gas concentration.

[0048] Then, in step S320, the operating status data and environmental data collected in real time are preprocessed and the grid quality is evaluated.

[0049] For example, the collected data is cleaned and filtered to remove noise and redundant data, and format conversion is performed. The current waveform is analyzed, and harmonic analysis is performed on the current waveform through Fourier transform. The quality of the power grid is evaluated based on the harmonic components and their proportions. The power factor is calculated based on the phase difference between current and voltage, and the power factor is used to determine whether the load properties match the power grid. A power quality report is generated and stored in the edge computing device. Maintenance measures are generated based on the impact of meteorological data on power equipment and the power quality report, and the maintenance measures are sent to the mobile phone APP of the operation and maintenance personnel.

[0050] In step S330, the deep neural network model is trained using the preprocessed historical data, anomaly detection and fault prediction are performed on the preprocessed real-time data based on the trained deep neural network model, and an early warning is triggered according to the detection results.

[0051] Upload the processed data to the cloud platform for further analysis, and use the distributed computing framework to process large-scale data and train models to optimize model performance. For example, use convolutional neural networks to process image data and identify visual anomalies inside the distribution cabinet, and use recurrent neural networks to process sensor data and identify abnormal sensor data. Collect new distribution cabinet monitoring data (including different types of distribution cabinets, environmental conditions, and operating status). Apply the pre-trained model to the new data set through fine-tuning techniques. Freeze some model layers during fine-tuning and only train the last few layers to adapt to the new task while retaining the pre-trained knowledge. Define the loss function and optimizer, and train until the model performs well on the new data.

[0052] When the deep neural network model determines that the real-time monitoring indicators deviate from the normal range, the early warning protocol is activated, the response program is started, and the early warning information is sent to the operation and maintenance personnel's mobile phone APP through the message push service. The early warning information includes the abnormality type (such as overload, short circuit, etc.), the affected equipment, the specific value of the deviation indicator and its normal range, and the time of occurrence.

[0053] Finally, in step S340, the real-time data stream view and abnormal annotation information are displayed through a customized visualization interface. For example, the real-time data is presented in the form of charts, dashboards, etc., which is convenient for operation and maintenance personnel to monitor, and different colors or icons are used to distinguish normal and abnormal states to help operation and maintenance personnel quickly identify problems.

[0054] The visual intelligent monitoring system and system for power distribution cabinets provided by the present invention can at least achieve the following technical effects: 1. Through multi-dimensional data analysis and automated early warning mechanisms, the accuracy of fault prediction is improved and the probability of power accidents is reduced.

[0055] 2. The cloud platform uses a distributed computing framework to train deep neural networks, which can learn complex patterns and anomalies from historical data to adapt to the ever-changing operating environment and load conditions and improve the sensitivity of anomaly detection.

[0056] 3. Improve the operation experience of operation and maintenance personnel through a customized visual interface, reduce the risk of misinterpretation of data, and thus speed up the troubleshooting process.

[0057] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0058] Those skilled in the art will appreciate that the modules or units or components of the devices in the examples disclosed herein may be arranged in the devices described in the embodiment, or alternatively may be located in one or more devices different from the devices in the examples. The modules in the foregoing examples may be combined into one module or may be divided into multiple submodules.

[0059] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and furthermore may be divided into a plurality of submodules or subunits or subcomponents.

[0060] Furthermore, those skilled in the art will appreciate that although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features from different embodiments is meant to be within the scope of the present invention and to form different embodiments.

[0061] As used herein, unless otherwise specified, the use of ordinal numbers "first," "second," "third," etc. to describe common objects merely indicates that different instances of similar objects are involved, and is not intended to imply that the objects so described must have a given order in time, space, order, or in any other manner.

[0062] Although the present invention has been described according to a limited number of embodiments, it will be apparent to those skilled in the art, with the benefit of the above description, that other embodiments may be envisioned within the scope of the invention thus described. In addition, it should be noted that the language used in this specification is selected primarily for readability and teaching purposes, rather than for explaining or defining the subject matter of the present invention. Therefore, many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the appended claims. The disclosure of the present invention is illustrative and not restrictive with respect to the scope of the present invention, and the scope of the present invention is defined by the appended claims.

Claims

1. A visual intelligent monitoring system for a power distribution cabinet, characterized in that: include: Data acquisition module, edge computing device, custom visualization interface and cloud platform, each module is connected through low-power wide area network communication; The data acquisition module is used to collect the operating status data and environmental data of the power distribution cabinet in real time, and transmit the collected data to the edge computing device; The edge computing device is used to preprocess the received data and evaluate the power grid quality, and upload the preprocessed data to the cloud platform; the cloud platform is used to train the deep neural network model using historical data based on a distributed computing framework, perform anomaly detection and fault prediction on real-time data based on the trained deep neural network model, trigger an early warning based on the detection results, and display the real-time data stream view and anomaly annotation information in the custom visualization interface.

2. The visual intelligent monitoring system for power distribution cabinet according to claim 1 is characterized in that: The data acquisition module includes at least a current sensor, a voltage sensor, a temperature sensor, a humidity sensor, a vibration and noise sensor, a gas sensor, a camera and a weather forecast interface, which are used to collect the operating current and voltage of the distribution cabinet, the ambient temperature, humidity, operating noise, the distribution cabinet operating image and meteorological data respectively.

3. The visual intelligent monitoring system for power distribution cabinet according to claim 1 is characterized in that: The edge computing device is used to pre-process the data received in real time by cleaning and filtering, convert the pre-processed data into a unified format, and transmit it to the cloud platform based on a secure communication protocol; perform harmonic analysis on the current waveform through Fourier transform, and evaluate the quality of the power grid based on the harmonic components and their proportions; calculate the power factor based on the phase difference between current and voltage, determine whether the load properties match the power grid based on the power factor, generate a power quality report and store it in the edge computing device; generate maintenance measures based on the impact of meteorological data on power equipment and the power quality report, and send the maintenance measures to the mobile phone APP of the operation and maintenance personnel.

4. The visual intelligent monitoring system for power distribution cabinet according to claim 1 is characterized in that: The cloud platform is used to activate the early warning mechanism when the deep neural network model determines that the real-time monitoring indicators deviate from the normal range, and send the early warning information to the mobile phone APP of the operation and maintenance personnel through the message push service. The early warning information includes the abnormality type, the affected equipment, the specific value of the deviation indicator and its normal range, and the time of occurrence.

5. The visual intelligent monitoring system for power distribution cabinet according to claim 4 is characterized in that: The customized visualization interface provides a historical data trend graph and a real-time data stream view, and uses different colors and symbols to highlight affected areas and devices in the real-time data stream view.

6. The visual intelligent monitoring system for power distribution cabinet according to claim 1 is characterized in that: The custom visualization interface provides a custom display panel so that users can select different information display densities and display methods according to specific application scenarios, and add, delete or adjust different functional modules through drag operations.

7. The visual intelligent monitoring system for power distribution cabinet according to claim 1 is characterized in that: The cloud platform is used to process image data using a convolutional neural network to identify visual anomalies inside the distribution cabinet, and to process sensor data using a recurrent neural network to identify abnormal sensor data.

8. A method for visual intelligent monitoring of a power distribution cabinet, executed based on the visual intelligent monitoring system for a power distribution cabinet as claimed in any one of claims 1 to 7, characterized in that: include: Collect the operating status data and environmental data of the power distribution cabinet in real time; Preprocessing the operating status data and environmental data and conducting a power grid quality assessment, and generating maintenance measures according to the power grid quality assessment results; Use the preprocessed historical data to train the deep neural network model, perform anomaly detection and fault prediction on the preprocessed real-time data based on the trained deep neural network model, and trigger an early warning based on the detection results; Display real-time data stream views and anomaly annotation information through a custom visualization interface.

9. A computing device, characterized in that include: at least one processor; and a memory storing program instructions, wherein the program instructions are configured to be suitable for being executed by the at least one processor, and the program instructions include instructions for executing the visual intelligent monitoring method for a power distribution cabinet as claimed in claim 8.

10. A readable storage medium storing program instructions, characterized in that: When the program instructions are read and executed by a computing device, the computing device executes the visual intelligent monitoring method for a power distribution cabinet as described in claim 8.

Images