Distribution network power supply AI intelligent visualization system and method

Abstract

The invention relates to the technical field of power distribution networks, in particular to a distribution network power supply AI intelligent visualization system and method, and the method comprises the steps: collecting data of equipment in a power distribution network in real time, and carrying out the processing and analysis of the collected data, and obtaining analysis data; converting the analysis data based on the AI intelligent visual gateway, and displaying the state data of the power distribution network equipment; according to the method, the state of the distribution network is monitored and analyzed in real time, abnormal conditions can be found and processed in time, power failure accidents are reduced, the power supply reliability is improved, the distribution network structure is optimized and adjusted according to the analysis data, and the power supply reliability is improved. The operation efficiency and the power supply capability of the distribution network are improved, a visual and easy-to-use visual interface is provided based on the AI intelligent visual gateway technology, so that operation and maintenance personnel can know the state and the operation condition of the distribution network more conveniently, and the problem that the equipment condition is difficult to master in real time in the existing power distribution network monitoring process is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution networks, and in particular to a distribution network power supply AI intelligent visualization system and method. Background Art

[0002] With the rapid construction of urban development, the total number of distribution substations increases year by year, resulting in a sharp increase in the inspection workload. Under the current limited operation and maintenance manpower and material resources, the inspection cycle is lengthened, and there are certain safety hazards in the current manual inspection mode.

[0003] Compared with the lean monitoring mode of substations, the current environmental monitoring degree and scope of distribution substations are seriously backward, and it is impossible to effectively locate and analyze faults. Regarding the environmental facilities conditions of current ring main units, it is also a very difficult task for operation and maintenance management personnel to statistically analyze the data of a large number of ring main unit devices, and it is difficult to grasp the overall situation of the devices. Summary of the Invention

[0004] The purpose of the present invention is to provide a distribution network power supply AI intelligent visualization system and method, aiming to solve the problem that it is difficult to grasp the device situation in real time in the existing distribution network monitoring.

[0005] To achieve the above object, in the first aspect, the present invention provides a distribution network power supply AI intelligent visualization system, including the following steps:

[0006] Collect data of devices in the distribution network in real time, and process and analyze the collected data to obtain analysis data;

[0007] Convert the analysis data based on the AI intelligent visualization gateway, and display the status data of distribution network devices;

[0008] Perform device anomaly location and risk assessment based on the analysis data, and give early warnings or alarms.

[0009] Among them, the specific method for collecting data in the distribution network in real time, and processing and analyzing the collected data to obtain analysis data:

[0010] Collect data of devices in the distribution network in real time based on sensor technology to obtain collected data;

[0011] Use AI algorithms to perform cleaning, denoising, and standardization preprocessing on the collected data to obtain standardized data;

[0012] Adopt deep learning technology to analyze the standardized data, analyze abnormal devices and potential risks, and obtain analysis data.

[0013] Among them, the specific method of using deep learning technology to analyze the standardized data, analyze abnormal devices and potential risks, and obtain analysis data is as follows:

[0014] Use deep learning technology to analyze the standardized data and obtain analysis information;

[0015] Compare and analyze the analysis information with the preset standard data to obtain abnormal data;

[0016] Based on the abnormal data, analyze abnormal devices and potential risks to obtain analysis data.

[0017] Among them, the specific method of using the AI intelligent visualization gateway to convert the analysis data and display the status data of distribution network devices is as follows:

[0018] Based on the AI intelligent visualization gateway, convert the analysis data, graph the data, and obtain a data graph;

[0019] Display the data graph or send it to the administrator operation terminal for display.

[0020] Among them, the specific method of performing device anomaly location and risk assessment based on the analysis data, and giving early warnings or alarms is as follows:

[0021] Trace the abnormal devices based on the abnormal data in the analysis data to obtain the locations of the abnormal devices;

[0022] Automatically generate the positioning coordinates of the abnormal devices based on the locations of the abnormal devices to achieve device anomaly location;

[0023] Based on the abnormal data, conduct a risk assessment on the fault types of the abnormal devices, and give early warnings or alarms.

[0024] Among them, the specific method of performing a risk assessment on the fault types of abnormal devices based on the abnormal data, and giving early warnings or alarms is as follows:

[0025] Based on the abnormal data, conduct a risk assessment on the fault types of the abnormal devices to obtain the risk levels;

[0026] Based on the magnitudes of the risk levels, send alarm messages or early warning messages to the administrator operation terminal for alarm or early warning respectively.

[0027] In a second aspect, the present invention also provides a distribution network power supply AI intelligent visualization system, which is applied to the distribution network power supply AI intelligent visualization method as described in the first aspect above, and is characterized in that;

[0028] It includes a data acquisition module, a data analysis module, a visualization module, an abnormal risk analysis module, and an early warning module. The data acquisition module, the data analysis module, the visualization module, the abnormal risk analysis module, and the early warning module are connected in sequence;

[0029] The data acquisition module collects data of equipment in the distribution network in real time based on sensor technology to obtain the collected data;

[0030] The data analysis module performs cleaning, denoising, and standardization preprocessing on the collected data based on AI algorithms to obtain standardized data, and uses deep learning technology to analyze the standardized data, analyze abnormal equipment and potential risks, and obtain analysis data;

[0031] The visualization module converts the analysis data based on an AI intelligent visualization gateway and displays the status data of distribution network equipment;

[0032] The abnormal risk analysis module performs equipment abnormal location and risk assessment based on the analysis data;

[0033] The early warning module performs risk assessment on the fault types of abnormal equipment based on the abnormal data to give early warnings or alarms.

[0034] A distribution network power supply AI intelligent visualization system and method of the present invention collect data of equipment in the distribution network in real time, process and analyze the collected data to obtain analysis data; convert the analysis data based on an AI intelligent visualization gateway and display the status data of distribution network equipment; perform equipment abnormal location and risk assessment based on the analysis data, and give early warnings or alarms. This method can timely detect and handle abnormal situations by real-time monitoring and analysis of the status of the distribution network, reduce the occurrence of power outages, improve power supply reliability, optimize and adjust the distribution network structure according to the analysis data, improve the operation efficiency and power supply capacity of the distribution network, and provide an intuitive and easy-to-use visualization interface based on AI intelligent visualization gateway technology, enabling operation and maintenance personnel to more conveniently understand the status and operation of the distribution network, and solving the problem that it is difficult to grasp the equipment situation in real time in the existing distribution network monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0036] Figure 1 It is a flowchart of a distribution network power supply AI intelligent visualization method provided by the present invention.

[0037] Figure 2 It is a flowchart of a specific method for real-time collecting data in a distribution network, processing and analyzing the collected data, and obtaining analysis data.

[0038] Figure 3 It is a flowchart of a specific method for analyzing the standardized data by using deep learning technology, analyzing abnormal devices and potential risks, and obtaining analysis data.

[0039] Figure 4 It is a flowchart of a specific method for converting the analysis data based on an AI intelligent visualization gateway and displaying the status data of distribution network devices.

[0040] Figure 5 It is a flowchart of a specific method for locating device anomalies and risk assessment based on the analysis data, and giving early warnings or alarms.

[0041] Figure 6 It is a flowchart of a specific method for risk assessment of the fault types of abnormal devices based on the abnormal data, and giving early warnings or alarms.

[0042] Figure 7 It is a connection schematic diagram of a distribution network power supply AI intelligent visualization system provided by the present invention.

[0043] In the figure: 1 - data acquisition module, 2 - data analysis module, 3 - visualization module, 4 - abnormal risk analysis module, 5 - early warning module, 6 - data processing unit, 7 - data analysis unit, 8 - traceability unit, 9 - positioning unit, 10 - evaluation unit. Specific implementation manners

[0044] The embodiments of the present invention are described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements with the same or similar functions from beginning to end. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present invention, and should not be construed as a limitation to the present invention.

[0045] Please refer to Figures 1 to 6 , in a first aspect, the present invention provides a distribution network power supply AI intelligent visualization method, including the following steps:

[0046] S1 Real-time collect data of devices in the distribution network, and process and analyze the collected data to obtain analysis data;

[0047] Specific method:

[0048] S11 Based on sensor technology, real-time collect data of devices in the distribution network to obtain collected data;

[0049] In the embodiment of the present invention, data of devices in the distribution network is collected in real time through sensors or electronic devices, including key parameters such as device voltage, device current, power factor, and load change, to obtain the collected data.

[0050] S12 Use an AI algorithm to perform cleaning, denoising, and standardization preprocessing on the collected data to obtain standardized data;

[0051] In the embodiment of the present invention, artificial intelligence algorithms, such as machine learning and deep learning, are used to perform data cleaning, denoising, data conversion, and standardization preprocessing on the collected data to obtain standardized data.

[0052] S13 Use deep learning technology to analyze the standardized data, analyze abnormal devices and potential risks, and obtain analysis data.

[0053] Specific method:

[0054] S131 Use deep learning technology to analyze the standardized data to obtain analysis information;

[0055] S132 Compare and analyze the analysis information with the preset standard data to obtain abnormal data;

[0056] S133 Analyze abnormal devices and potential risks based on the abnormal data to obtain analysis data.

[0057] In the embodiment of the present invention, this layer can automatically identify the fault type, predict the fault development trend, and give corresponding treatment suggestions.

[0058] S2 Based on the AI intelligent visualization gateway, convert the analysis data and display the status data of the distribution network devices;

[0059] Specific method:

[0060] S21 Based on the AI intelligent visualization gateway, convert the analysis data, graphify the data, and obtain a data graph;

[0061] In the embodiment of the present invention, based on the AI intelligent visualization gateway, the analysis data is converted, and the result is presented in an intuitive and vivid manner so that the operation and maintenance personnel can clearly understand the operation status of the distribution network at a glance.

[0062] S22 Display the data graph or send it to the administrator's operation terminal for display.

[0063] S3 Based on the analysis data, perform device anomaly location and risk assessment, and give an early warning or alarm.

[0064] Specific method:

[0065] S31 traces the abnormal device based on the abnormal data in the analysis data to obtain the location of the abnormal device;

[0066] In the embodiment of the present invention, tracing the abnormal device based on the abnormal data in the analysis data to trace the number and location of the faulty device, which is convenient for maintenance personnel to obtain the location of the abnormal device in the first time.

[0067] S32 automatically generates the positioning coordinates of the abnormal device based on the location of the abnormal device to achieve the abnormal positioning of the device;

[0068] S33 conducts a risk assessment on the fault type of the abnormal device based on the abnormal data, and issues a warning or an alarm.

[0069] Specific method:

[0070] S331 conducts a risk assessment on the fault type of the abnormal device based on the abnormal data to obtain the risk level;

[0071] S332 sends an alarm message or a warning message to the administrator's operation terminal based on the size of the risk level, and issues an alarm or a warning respectively.

[0072] In the embodiment of the present invention, a warning or alarm operation is determined based on the size of the risk level. If the risk level is relatively low, a warning message and the risk of potential safety hazards are sent to the administrator's operation terminal for a warning operation. If the risk level is relatively high, an alarm message is sent to the administrator's operation terminal for an alarm operation.

[0073] Please refer to Figure 7 , in the second aspect, the present invention also provides a distribution network power supply AI intelligent visualization system, which is applied to the distribution network power supply AI intelligent visualization method as described in the first aspect above, and is characterized in that;

[0074] It includes a data acquisition module 1, a data analysis module 2, a visualization module 3, an abnormal risk analysis module 4 and a warning module 5, and the data acquisition module 1, the data analysis module 2, the visualization module 3, the abnormal risk analysis module 4 and the warning module 5 are connected in sequence;

[0075] The data acquisition module 1, based on sensor technology, real-time collects the data of the equipment in the distribution network to obtain the collected data;

[0076] The data analysis module 2 conducts cleaning, denoising, and standardization preprocessing on the collected data based on AI algorithms to obtain standardized data, and uses deep learning technology to analyze the standardized data to analyze abnormal devices and potential risks to obtain analysis data;

[0077] The visualization module 3 converts the analysis data based on the AI intelligent visualization gateway and displays the status data of the distribution network equipment;

[0078] The abnormal risk analysis module 4 locates equipment abnormalities and assesses risks based on the analysis data;

[0079] The early warning module 5 assesses the risk of the fault type of the abnormal equipment based on the abnormal data and issues an early warning or alarm.

[0080] In the embodiment of the present invention, the data acquisition module 1 collects data of equipment in the distribution network in real time based on sensor technology, including key parameters such as equipment voltage, equipment current, power factor, and load change, to obtain the collected data; the data analysis module 2 performs cleaning, denoising, and standardization preprocessing on the collected data based on AI algorithms to obtain standardized data, and uses deep learning technology to analyze the standardized data, analyze abnormal equipment and potential risks, to obtain analysis data; the visualization module 3 converts the analysis data based on the AI intelligent visualization gateway and displays the status data of the distribution network equipment; the abnormal risk analysis module 4 locates equipment abnormalities and assesses risks based on the analysis data. This layer can automatically identify the fault type, predict the development trend of the fault, and give corresponding treatment suggestions. The early warning module 5 assesses the risk of the fault type of the abnormal equipment based on the abnormal data and issues an early warning or alarm.

[0081] Further, the data analysis module 2 includes a data processing unit 6 and a data analysis unit 7, and the data processing unit 6 is connected to the data analysis unit 7;

[0082] The data processing unit 6 performs cleaning, denoising, and standardization preprocessing on the collected data based on AI algorithms to obtain standardized data;

[0083] The data analysis unit 7 analyzes the standardized data based on deep learning technology, analyzes abnormal equipment and potential risks, to obtain analysis data.

[0084] In the embodiment of the present invention, the data processing unit 6 performs cleaning, denoising, and standardization preprocessing on the collected data based on AI algorithms to obtain standardized data; the data analysis unit 7 analyzes the standardized data based on deep learning technology, analyzes abnormal equipment and potential risks, to obtain analysis data.

[0085] Further, the abnormal risk analysis module 4 includes a tracing unit 8, a positioning unit 9, and an evaluation unit 10;

[0086] The tracing unit 8 traces the abnormal equipment based on the abnormal data in the analysis data to obtain the location of the abnormal equipment;

[0087] The positioning unit 9 automatically generates the positioning coordinates of the abnormal device based on the abnormal device position, realizing the abnormal positioning of the device.

[0088] The evaluation unit 10 conducts a risk assessment on the fault type of the abnormal device based on the abnormal data.

[0089] In the embodiment of the present invention, the tracing unit 8 traces the abnormal device based on the abnormal data in the analysis data to obtain the abnormal device position; the positioning unit 9 automatically generates the positioning coordinates of the abnormal device based on the abnormal device position, realizing the abnormal positioning of the device; the evaluation unit 10 conducts a risk assessment on the fault type of the abnormal device based on the abnormal data.

[0090] What is disclosed above is only a preferred embodiment of a distribution network power supply AI intelligent visualization system and method of the present invention. Of course, the scope of the rights of the present invention cannot be limited thereby. Those of ordinary skill in the art can understand all or part of the processes of implementing the above embodiments, and the equivalent changes made according to the claims of the present invention still fall within the scope covered by the invention.

Claims

1. A distribution network power supply AI intelligent visualization method, characterized in that: The following steps are involved: Collect data from devices in the distribution network in real time, and process and analyze the collected data to obtain analysis data; The analysis data is converted based on the AI ​​intelligent visualization gateway, and the status data of the distribution network equipment is displayed; Based on the analysis data, equipment abnormality location and risk assessment are performed, and early warning or alarm is issued.

2. The distribution network power supply AI intelligent visualization method according to claim 1, characterized in that; The specific method of collecting data in the distribution network in real time and processing and analyzing the collected data to obtain the analyzed data is as follows: Based on sensor technology, data from equipment in the distribution network is collected in real time to obtain collected data; Using AI algorithms to clean, denoise, and standardize the collected data to obtain standardized data; The standardized data is analyzed using deep learning technology to analyze abnormal equipment and potential risks to obtain analysis data.

3. The AI ​​intelligent visualization method for power distribution network according to claim 2, It is characterized by: The specific method of using deep learning technology to analyze the standardized data, analyze abnormal equipment and potential risks, and obtain analysis data is as follows: Using deep learning technology to analyze the standardized data to obtain analysis information; Comparing and analyzing the analysis information with preset standard data to obtain abnormal data; Abnormal equipment and potential risks are analyzed based on the abnormal data to obtain analysis data.

4. The AI ​​intelligent visualization method for power distribution network according to claim 1, It is characterized by: The specific method of converting the analysis data based on the AI ​​intelligent visualization gateway and displaying the distribution network equipment status data is as follows: The analysis data is converted based on an AI intelligent visualization gateway, and the data is visualized to obtain a data graph; The data graph is displayed or sent to an administrator operation terminal for display.

5. The AI ​​intelligent visualization method for power distribution network according to claim 3, It is characterized by: The specific method of locating equipment abnormalities and conducting risk assessment based on the analysis data, and issuing early warnings or alarms is as follows: Tracing the abnormal device based on the abnormal data in the analysis data to obtain the location of the abnormal device; Automatically generate the positioning coordinates of the abnormal device based on the abnormal device position to achieve abnormal device positioning; Based on the abnormal data, a risk assessment is performed on the fault type of the abnormal equipment, and an early warning or alarm is issued.

6. The AI ​​intelligent visualization method for power distribution network according to claim 5, It is characterized by: The specific method of performing risk assessment on the fault type of abnormal equipment based on the abnormal data and issuing early warning or alarm is: Performing risk assessment on the fault type of the abnormal equipment based on the abnormal data to obtain a risk level; Based on the risk level, an alarm message or a warning message is sent to the administrator operation terminal to issue an alarm or a warning respectively.

7. A distribution network power supply AI intelligent visualization system, applied to the distribution network power supply AI intelligent visualization method according to any one of claims 1 to 6, characterized in that ； It includes a data acquisition module, a data analysis module, a visualization module, an abnormal risk analysis module and an early warning module, wherein the data acquisition module, the data analysis module, the visualization module, the abnormal risk analysis module and the early warning module are connected in sequence; The data acquisition module collects data of devices in the distribution network in real time based on sensor technology to obtain collected data; The data analysis module cleans, removes noise, and performs standardization preprocessing on the collected data based on an AI algorithm to obtain standardized data, and uses deep learning technology to analyze the standardized data, analyze abnormal equipment and potential risks, and obtain analysis data; The visualization module converts the analysis data based on the AI ​​intelligent visualization gateway and displays the status data of the distribution network equipment; The abnormal risk analysis module performs equipment abnormality location and risk assessment based on the analysis data; The early warning module performs risk assessment on the fault type of the abnormal equipment based on the abnormal data, and issues an early warning or alarm.

Images