Power distribution method based on artificial intelligence and intelligent power distribution cabinet

Abstract

The invention relates to an artificial intelligence-based power distribution method and an intelligent power distribution cabinet, and relates to the field of data processing, and the method comprises the steps: collecting historical power distribution data and a current power distribution position; obtaining the number of power distribution users based on the current power distribution position; according to the historical power distribution data and the number of the power distribution users, the household power consumption condition is known; collecting a people stream monitoring video; recording a people flow walking condition based on the people flow monitoring video; and obtaining predicted power consumption data in combination with the household average power consumption condition and the people flow walking condition, and performing power distribution according to the predicted power consumption data. The application has the effect of improving the flexibility and response efficiency of the power distribution system.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to an artificial intelligence-based power distribution method and an intelligent power distribution cabinet. Background Art

[0002] The AI-based power distribution method refers to a technical solution that deeply integrates AI technology with the power distribution link of the power system and optimizes the allocation of power resources through intelligent algorithms, data processing and other means.

[0003] At present, the power distribution method based on artificial intelligence mainly collects multi-source data such as voltage and current by deploying sensors, smart meters and other equipment, and mines the data features after cleaning and processing; uses machine learning algorithms to predict loads and deep learning algorithms to estimate the output of new energy, and combines intelligent optimization algorithms such as genetic algorithms to dispatch the distribution network and optimize the output of distributed power sources and energy storage equipment; at the same time, a system architecture combining edge computing and cloud computing is adopted to realize rapid local data processing and optimal configuration of global power resources, thereby improving the efficiency of power resource allocation.

[0004] In the actual power distribution process, the gathering and evacuation of people are closely related to the power load. Due to the lack of systematic consideration of human flow factors, the existing technology will have the risk of oversupply or insufficient power supply, which in turn reduces the flexibility and response efficiency of the power distribution system and needs to be improved. Summary of the Invention

[0005] In order to improve the flexibility and response efficiency of the power distribution system, the present invention provides an artificial intelligence-based power distribution method and an intelligent power distribution cabinet.

[0006] In a first aspect, the present invention provides an artificial intelligence-based power distribution method, which adopts the following technical solutions: An artificial intelligence-based power distribution method, comprising: Collect historical power distribution data and current power distribution location; deriving the number of power distribution users based on the current power distribution location; Knowing the average electricity consumption per household based on the historical power distribution data and the number of power distribution users; Collect crowd monitoring videos; Recording the movement of people based on the crowd monitoring video; The average household electricity consumption and the movement of people are combined to obtain predicted electricity consumption data, and electricity is distributed based on the predicted electricity consumption data.

[0007] By employing this technical solution, the system first collects historical power distribution data and current power distribution locations, accurately calculating the number of power users and average power consumption per household, laying the data foundation for load forecasting. Simultaneously, through real-time analysis of dynamic characteristics such as movement patterns and gathering density using crowd monitoring videos, a correlation model is established between changes in crowd flow and power demand. The core innovation lies in the multi-dimensional fusion analysis of average household power consumption and crowd movement data. For example, deep learning algorithms are used to identify the power load characteristics corresponding to different crowd flow patterns, generating predicted power consumption data that better reflects actual scenarios and enabling dynamic adjustments to power distribution plans, thereby significantly improving the flexibility and responsiveness of the distribution system.

[0008] Optionally, a method for correcting the predicted electricity consumption data is also included: generating a climate electricity consumption total based on the historical electricity distribution data; In response to the total climate electricity consumption, the number of electricity distribution users and the preset reference period days, the average daily user electricity consumption is obtained; Collect the current power distribution date and current climate; The predicted power usage data is modified in response to the current power distribution date, the current date climate, and the daily average user power usage.

[0009] Optionally, also include: Collect the surrounding humidity value of the intelligent distribution cabinet; If the ambient humidity value does not exceed the preset reference humidity value, real-time fault detection is performed using a preset fault detection method; If the surrounding humidity value exceeds a preset reference humidity value, collecting surrounding image information; Determining whether the surrounding image information contains a preset puddle feature; When the surrounding image information does not contain the puddle feature, a rain warning is reported for the area, and power distribution and flood prevention are carried out using a preset flood prevention method.

[0010] Optionally, also include: When the surrounding image information contains the puddle feature, performing a region selection on the puddle feature from the surrounding image information to obtain a puddle range; Collect puddle depth information and puddle distance values; Combining the puddle range and the puddle depth information to generate a humidity impact value; Obtaining a corrected humidity value according to the surrounding humidity value, the puddle distance value, and the humidity impact value; When the corrected humidity value does not exceed the reference humidity value, performing real-time fault detection using a preset fault detection method; When the corrected humidity value exceeds the reference humidity value, a regional rain warning is reported, and power distribution flood prevention is carried out using a preset flood prevention method.

[0011] Optionally, the fault detection method includes: Collect device operation sounds; operating the sound according to the device to generate an operating spectrogram; Compare the operating spectrum to see if it matches the preset standard spectrum Figure 1 To; If and only if the operating spectrum graph is inconsistent with the standard spectrum graph, combining the operating spectrum graph and the standard spectrum graph to determine the degree of spectrum difference; When the difference between the spectrum graphs does not exceed a preset reference difference, a device abnormality prompt is reported; When the difference between the spectrum graphs exceeds a preset reference difference, the control device stops running and reports a device abnormality prompt.

[0012] Optionally, the flood prevention method includes: Collect water level height values; Determining whether the water level value is higher than a preset starting height value; If the water level value is not higher than the starting height value, continue to collect water level values; If the water level value is higher than the starting height value, a water separation height value is obtained based on the water level value; Based on the water-isolating height value, the preset water-isolating device is controlled to start, thereby isolating the equipment from rainwater.

[0013] Optionally, also include: Determining whether the water separation height value exceeds a preset operating height value; When the water separation height value exceeds the operating height value, a power outage prompt is reported and the equipment operation is stopped; When the water-blocking height value does not exceed the operating height value, collecting the thermal image of the equipment operation; identifying high temperature areas from thermal imaging of the equipment operation; The high temperature area is subjected to regional heat dissipation using a preset high temperature heat dissipation method.

[0014] Optionally, the high-temperature heat dissipation method includes: The fan direction is determined based on the high temperature area and the preset fan installation position; In response to the device operating thermal imaging and the high temperature area to know the area temperature value; deriving a fan speed based on the temperature value of the area; Based on the fan direction, the preset positive blade fan and the preset reverse blade fan are controlled to adjust their directions and rotate at the fan speed; The water circulation channel preset below the water-isolating device is controlled to open so that rainwater circulates in the water circulation channel.

[0015] Optionally, also include: Collect historical maintenance data and current date; Knowing the upcoming maintenance date based on the historical maintenance data; Combine the recent maintenance date with the preset equipment maintenance cycle to determine the required maintenance date; Calculate the maintenance distance in days based on the required maintenance date and the current date; When the maintenance distance days are less than the preset maintenance reminder days, report the equipment maintenance reminder; Collect device signals of preset water-blocking devices; When the device signal is consistent with the preset start signal, an equipment maintenance prompt is reported.

[0016] In a second aspect, the present application provides an artificial intelligence-based intelligent power distribution cabinet, which adopts the following technical solutions: An artificial intelligence-based intelligent power distribution cabinet includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute any of the above-mentioned artificial intelligence-based power distribution methods.

[0017] In summary, this application includes at least one of the following beneficial technical effects: 1. The system first collects historical power distribution data and current power distribution locations, accurately calculates the number of power distribution users and average power consumption per household, and lays a data foundation for load forecasting; at the same time, through crowd monitoring videos, it analyzes dynamic characteristics such as people's movement trajectories and gathering density in real time, and establishes a correlation model between changes in crowd flow and power demand. The core innovation lies in the multi-dimensional fusion analysis of average household power consumption and crowd movement data. For example, through deep learning algorithms, it identifies the power load characteristics corresponding to different crowd flow patterns, generates predicted power consumption data that is more in line with actual scenarios, and realizes dynamic adjustment of power distribution plans, thereby greatly improving the flexibility and response efficiency of the power distribution system; 2. The system first collects the water level height value in real time and compares it with the preset starting height value. When the water level is within the limit, it continues to monitor to ensure the rational use of resources. Once the water level exceeds the threshold, the required water isolation height is immediately calculated according to the actual water level, and the water isolation device is automatically activated to physically isolate the equipment, realizing the automation and precision of flood control response, so that the activation timing and protection intensity of the protection device always fit the actual flood situation. Compared with fixed height protection or manual operation, it greatly shortens the response time, improves the reliability of the distribution system in extreme weather, and effectively reduces the risk of power outages caused by floods.

[0018] 3. The system first calculates the optimal fan orientation based on the high-temperature area and the preset fan position. Using thermal imaging of the equipment during operation, it accurately obtains the regional temperature value, and then determines the fan speed. It then coordinates the control of the positive and reverse blade fans to form a convection field, accelerating heat dissipation. Furthermore, when the temperature exceeds the threshold, the water circulation channel under the water barrier automatically opens, utilizing the natural cooling source of rainwater for heat exchange. This ensures efficient cooling while ensuring waterproofing. In both flood prevention and high-temperature scenarios, the coordinated work of the waterproofing and cooling systems effectively ensures the stable operation of the power distribution equipment and improves the adaptability and reliability of the power distribution system under complex operating conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a method flow chart of an artificial intelligence-based power distribution method; Figure 2 It is a method flow chart of a high temperature heat dissipation method; Figure 3 It is a method flow chart of the equipment maintenance method. DETAILED DESCRIPTION

[0020] The present invention is further described in detail below with reference to the accompanying drawings and embodiments.

[0021] Reference Figure 1 , the embodiment of the present application discloses an artificial intelligence-based power distribution method, comprising the following steps: S1: Collect historical power distribution data and current power distribution location.

[0022] Historical power distribution data refers to data such as total power consumption and peak hours over a period of time. The specific time period for recording is pre-determined by those skilled in the art and is not detailed here. Historical power distribution data is retrieved from a pre-determined power distribution data storage system, which stores data on each power distribution event in the distribution cabinet. This system is pre-determined by those skilled in the art and is not detailed here.

[0023] The current distribution location refers to the current geographical location of the distribution box. The current distribution location is collected by the GPS positioning chip preset in the distribution box.

[0024] S2: Calculate the number of power distribution users based on the current power distribution location.

[0025] The number of distribution users refers to the total number of electricity users covered by the distribution cabinet at the current distribution location. The number of distribution users corresponding to the current distribution location can be found using a preset distribution user comparison table. This table records the number of distribution users corresponding to different current distribution locations. The comparison information in the distribution user comparison table is generated by technicians in this field through sequential testing of the number of distribution users corresponding to different current distribution locations, and is not detailed here.

[0026] S3: Based on historical power distribution data and the number of power distribution users, we can understand the average power consumption per household.

[0027] Average household electricity consumption refers to the average electricity consumption indicator calculated by dividing the total electricity consumption in historical power distribution data by the number of distributed users. Average household electricity consumption is calculated by taking the quotient between the total electricity consumption in historical power distribution data and the number of distributed users.

[0028] S4: Collect crowd monitoring video.

[0029] Crowd monitoring video refers to the real-time video stream collected by cameras installed in the power distribution area to record the movement trajectory of people.

[0030] S5: Based on crowd monitoring video to record the movement of people.

[0031] Crowd movement refers to the flow of people into and out of the distribution area. Understanding this movement can reveal changes in the number of people within the distribution area. This movement is determined through AI analysis of crowd monitoring videos. Determining crowd movement through AI analysis of videos is common knowledge in the field and will not be elaborated upon here.

[0032] S6: Combine the average household electricity consumption and the movement of people to obtain predicted electricity consumption data, and distribute electricity based on the predicted electricity consumption data.

[0033] Predicted electricity usage data refers to data required for power distribution, including total electricity consumption, load distribution, and peak loads within a distribution area over a future period. This data is calculated using an AI algorithm that analyzes historical household electricity usage patterns and real-time user activity patterns. The specific AI algorithms used are well-known in the field and will not be detailed here.

[0034] After obtaining the predicted power consumption data, the intelligent distribution cabinet needs to be controlled to distribute power according to the predicted power consumption data.

[0035] The method for correcting the predicted electricity consumption data includes the following steps: S70: Generate a climate-related total electricity consumption based on historical electricity distribution data.

[0036] Climate-related electricity consumption refers to the total electricity consumption corresponding to different climate conditions (such as temperature, humidity, and rainfall). Climate-related electricity consumption can be determined by understanding historical power distribution data, which contains the total electricity consumption under different climate conditions.

[0037] S71: Responding to the total climate electricity consumption, the number of power distribution users and the preset reference period days to obtain the average daily user electricity consumption.

[0038] The number of days in the reference period refers to a preset statistical period used to calculate the average daily electricity consumption of users. The number of days in the reference period is set in advance by those skilled in the art and will not be described in detail here.

[0039] Daily average user electricity consumption refers to the average daily electricity consumption of a single user. This is obtained by averaging the total climate electricity consumption by the number of distribution users and the number of days in the benchmark period.

[0040] S72: Collect the current power distribution date and the current climate.

[0041] The current power distribution date is the specific date when power consumption forecasting and power distribution operations are required. The current power distribution date is obtained by adjusting the system clock.

[0042] The current date climate refers to the real-time climate parameters of the current power distribution date. The current date climate is obtained by retrieving meteorological data.

[0043] S73: Modifying the predicted power consumption data in response to the current power distribution date, the current climate, and the average daily power consumption of users.

[0044] By understanding the current power distribution date, the weekday or weekend attribute of the current date is known, and the date correction coefficient associated with the current power distribution date is retrieved from a preset date correction comparison table. The date correction comparison table records the correspondence between the weekday or weekend attribute and the date correction coefficient. The date correction comparison table is pre-configured by those skilled in the art and is not further described here.

[0045] For example, the preset working day correction coefficient in the date correction comparison table is 1.0, and the weekend correction coefficient is 1.1. When the current power distribution date is Saturday, the query results in a correction coefficient of 1.1.

[0046] Then, by understanding the current climate, the corresponding climate correction coefficient is matched from a preset climate correction table. The climate correction table records the mapping relationship between different climate parameter ranges and climate correction coefficients. This table is pre-set by technical personnel in this field based on the correlation analysis between climate conditions and total electricity consumption in historical power distribution data. For example, when the current temperature is detected to be ≥35°C, the corresponding climate correction coefficient is 1.15; if it is raining and the rainfall is ≥5mm / h, the correction coefficient is matched to 0.9. The specific mapping relationship is formed by statistical analysis of historical data and is not detailed here.

[0047] Finally, the date correction coefficient is multiplied by the climate correction coefficient to obtain the comprehensive environmental correction factor. Then, based on the difference between the average daily user electricity consumption and the average value in the benchmark period (for example, the average daily electricity consumption on weekdays is 5% higher than the 30-day average, corresponding to an adjustment rate of +5%), dynamic calibration is performed using the formula "corrected forecast value = initial forecast value × comprehensive environmental correction factor × (1 + average daily electricity consumption adjustment rate)" to correct the predicted electricity consumption data.

[0048] The following steps are also included: S80: Collects the ambient humidity value of the intelligent power distribution cabinet.

[0049] The ambient humidity value refers to the air humidity value of the environment surrounding the intelligent power distribution cabinet. The ambient humidity value is measured by the humidity sensor preset on the intelligent power distribution cabinet.

[0050] S81: If the ambient humidity value does not exceed the preset reference humidity value, real-time fault detection is performed using a preset fault detection method.

[0051] The reference humidity value is a threshold used to detect whether the humidity around the intelligent power distribution cabinet is too high, thereby determining whether heavy rain will occur. The reference humidity value is set in advance by those skilled in the art and will not be described in detail here.

[0052] The fault detection method is a method for performing routine fault detection on the power distribution cabinet when no excessive humidity is detected. The specific fault detection method is described in detail in subsequent S810 to S815 and will not be described in detail here.

[0053] If the surrounding humidity value does not exceed the benchmark humidity value, it means that the environment around the intelligent distribution cabinet is not too humid, which means that there will be no heavy rain. Daily fault detection is required, and the distribution cabinet needs to be fault-detected using the fault detection method.

[0054] S82: If the surrounding humidity value exceeds the preset reference humidity value, collect surrounding image information.

[0055] Surrounding image information refers to the real-time image of the area surrounding the intelligent distribution cabinet. The surrounding image information is captured by a camera.

[0056] If the surrounding humidity value exceeds the baseline humidity value, it means that the environment around the smart distribution cabinet is too humid. It is necessary to collect surrounding image information to further detect the cause of excessive humidity.

[0057] S83: Determine whether the surrounding image information contains a preset puddle feature.

[0058] The puddle feature refers to the visual features that match the shape of accumulated water in the image. The puddle feature is pre-set by those skilled in the art and will not be described in detail here.

[0059] By determining whether the surrounding image information contains puddle features, it is determined whether the surrounding environment of the smart distribution cabinet is too humid due to the presence of puddles around the smart distribution cabinet.

[0060] S84: When the surrounding image information does not contain puddle features, a rain warning is reported for the area, and power distribution and flood prevention are performed using a preset flood prevention method.

[0061] Flood control methods refer to emergency measures used to prevent water levels from intruding into power distribution equipment during heavy rain. Specific flood control methods are described in detail in subsequent S840-S844 and are not detailed here.

[0062] If the surrounding imagery doesn't contain puddle features, it indicates the humidity around the smart distribution cabinet isn't caused by puddles, but rather widespread wet weather, such as regional rainfall. The system should report a rain alert and initiate flood control measures to prevent rainwater from intruding into the distribution equipment.

[0063] The following steps are also included: S85: When the surrounding image information includes a puddle feature, perform a region selection on the puddle feature from the surrounding image information to obtain a puddle range.

[0064] The puddle range refers to the actual area of ​​water accumulation within the surrounding imagery, as indicated by the box selection. The puddle range is determined by boxing and marking the puddle features within the surrounding imagery. Image feature selection techniques are well-known in the art and will not be detailed here.

[0065] If the surrounding image information contains puddle features, it indicates that the environment around the smart distribution cabinet is too humid and there is a puddle. To further detect the cause of the excessive humidity, it is necessary to first select the puddle range for subsequent steps.

[0066] S850: Collecting puddle depth information and puddle distance values.

[0067] The puddle depth information refers to the vertical depth of the accumulated water within the puddle. The puddle distance value refers to the straight-line distance from the puddle edge to the intelligent distribution cabinet. The puddle depth information and puddle distance value are measured using an infrared rangefinder.

[0068] S851: Integrate puddle range and puddle depth information to generate a moisture impact value.

[0069] The humidity impact value refers to the additional effect a puddle has on the surrounding humidity. The humidity impact value can be calculated by considering the puddle's extent and depth. The formula for calculating the humidity impact value is common knowledge in the field and will not be detailed here.

[0070] S852: Obtain a corrected humidity value based on the surrounding humidity value, the puddle distance value, and the humidity impact value.

[0071] The corrected humidity value refers to the corrected surrounding humidity value. The corrected humidity value is calculated by the surrounding humidity value × humidity impact value × distance attenuation coefficient, where the distance attenuation coefficient is obtained by querying the preset humidity impact comparison table. The comparison table records the mapping relationship between the puddle distance value interval and the attenuation coefficient. For example: when the puddle distance value is ≤1 meter, the corresponding attenuation coefficient is 0.9; when 1 meter < distance value ≤2 meters, the corresponding coefficient is 0.7; when the distance value is >2 meters, the corresponding coefficient is 0.5. The humidity impact comparison table is formed by technical personnel in this field based on the statistical analysis of the degree of influence of puddles on the surrounding humidity at different distances in historical data. For example, by measuring the humidity increment at different distances and fitting the attenuation curve, the continuous distance value is divided into discrete intervals and the corresponding coefficients are recorded in sequence, so as to achieve quantitative characterization of the distance attenuation effect.

[0072] S853: Based on the fact that the corrected humidity value does not exceed the reference humidity value, real-time fault detection is performed using a preset fault detection method.

[0073] When the corrected humidity value does not exceed the reference humidity value, it indicates that the reason why the environment around the intelligent distribution cabinet is too humid is due to puddles, which means that there will not be heavy rain. Daily fault detection is required, and the distribution cabinet needs to be fault-detected using the fault detection method.

[0074] S854: When the corrected humidity value exceeds the baseline humidity value, a regional rain warning is reported, and power distribution flood prevention is performed using a preset flood prevention method.

[0075] When the corrected humidity value exceeds the baseline humidity value, it indicates that the reason why the environment around the intelligent distribution cabinet is too humid is not only caused by puddles, but also indicates that heavy rain will come. It is necessary to report the regional rain warning and use flood prevention methods to distribute flood-proof power to the distribution cabinet.

[0076] The fault detection method includes the following steps: S810: Collect device operation sound.

[0077] Equipment operating sound refers to the mechanical vibration noise generated by power distribution equipment during operation. Equipment operating sound is collected by preset acoustic sensors.

[0078] S811: Generate an operating spectrum graph according to the operating sound of the device.

[0079] An operating spectrogram converts the device's operating sound wave signals into a visual graph of frequency-amplitude distribution. Spectrogram conversion techniques are well-known in the field and will not be detailed here.

[0080] S812: Compare the running spectrum with the preset standard spectrum Figure 1 To.

[0081] The standard spectrum diagram refers to the spectrum characteristic template when the device is operating normally. The standard spectrum diagram is pre-set by those skilled in the art and will not be described in detail here.

[0082] By judging whether the running spectrum is consistent with the standard spectrum Figure 1 To know if the device is operating abnormally.

[0083] S813: If and only if the running spectrum graph is inconsistent with the standard spectrum graph, combine the running spectrum graph and the standard spectrum graph to know the difference between the spectrum graphs.

[0084] Spectrogram difference refers to the quantitative difference between the running spectrogram and the standard spectrogram in terms of frequency distribution, amplitude, and other dimensions. The spectrogram difference is calculated by calculating the mean square error of the amplitude values ​​at each frequency point between the two.

[0085] When the operating spectrum graph is inconsistent with the standard spectrum graph, it indicates that the operating status of the power distribution equipment is abnormal. The spectrum graph difference must be calculated first for subsequent steps.

[0086] S814: When the difference between the spectrum graphs does not exceed the preset reference difference, a device abnormality prompt is reported.

[0087] The baseline difference refers to the spectrum difference threshold used to determine whether the device needs to alarm.

[0088] When the difference of the spectrum graph does not exceed the benchmark difference, it means that although the operating status of the distribution equipment has not reached the emergency fault threshold, it has deviated from the spectrum characteristic range of normal operation, and the equipment abnormality prompt needs to be reported.

[0089] S815: When the difference between the spectrum graphs exceeds a preset reference difference, the control device stops running and reports a device abnormality prompt.

[0090] When the difference in the spectrum graph exceeds the benchmark difference, it means that the operating status of the distribution equipment has significantly deviated from the normal standard and there is an abnormal situation that may cause a serious fault. At this time, the equipment must be controlled to stop running and the equipment abnormality prompt must be reported.

[0091] Flood prevention methods include the following steps: S840: Collect water level value.

[0092] The water level refers to the vertical height of water accumulated around the power distribution equipment. The water level is measured by the water level sensor preset in the power distribution cabinet.

[0093] S841: Determine whether the water level value is higher than the preset starting height value.

[0094] The start height value refers to the water level threshold that triggers the start of the water barrier device. The start height value is set in advance by those skilled in the art and will not be described in detail here.

[0095] By judging whether the water level value is higher than the starting height value, we can know whether the water level is too high, and then judge whether the water isolation device needs to be started.

[0096] S842: If the water level value is not higher than the start height value, continue to collect the water level value.

[0097] If the water level value is not higher than the starting height value, it means that the water level is not too high and there is no need to start the water isolation device. Just continue to collect the water level value.

[0098] S843: If the water level value is higher than the start height value, a water separation height value is obtained based on the water level value.

[0099] The water barrier height value refers to the required protective height of the water barrier. The water barrier height value is calculated by adding the water level value to a preset safety margin. The safety margin is set in advance by those skilled in the art and will not be detailed here.

[0100] S844: Based on the water-blocking height value, the preset water-blocking device is controlled to start, thereby isolating the equipment from rainwater.

[0101] A water barrier is a device used to prevent rainwater from entering distribution equipment. It includes a retractable water barrier. By raising the barrier to the desired height, the equipment is shielded from rainwater.

[0102] The following steps are also included: S845: Determine whether the water separation height value exceeds the preset operating height value.

[0103] The operating height value refers to the maximum protective height at which the power distribution equipment in the power distribution cabinet can continue to operate when the water barrier is in place. The operating height value is set in advance by those skilled in the art and will not be detailed here.

[0104] By judging whether the water-proof height value exceeds the operating height value, it can be determined whether the operation of the power distribution equipment in the distribution cabinet needs to be stopped.

[0105] S846: When the water separation height value exceeds the operating height value, a power outage prompt is reported and the equipment operation is stopped.

[0106] When the water-blocking height exceeds the operating height, it means that the power distribution equipment in the power distribution cabinet needs to be stopped. Therefore, a power outage prompt must be reported before the equipment is stopped.

[0107] S847: When the water separation height value does not exceed the operating height value, the acquisition device operates thermal imaging.

[0108] Equipment operation thermal imaging refers to the surface temperature distribution image of distribution equipment taken by an infrared camera.

[0109] When the water-proof height value does not exceed the operating height value, it means that there is no need to stop the operation of the power distribution equipment in the distribution cabinet. It is necessary to first collect thermal images of the equipment operation for subsequent steps.

[0110] S848: Identify high temperature areas from thermal imaging of equipment operation.

[0111] The high temperature area refers to the device part where the temperature in the thermal imaging exceeds a preset threshold. The specific threshold is set in advance by those skilled in the art and will not be described in detail here.

[0112] The high temperature area can be obtained by identifying the high temperature area of ​​the device parts whose temperature exceeds the preset threshold from the thermal imaging of the device operation. The identification of high temperature areas in thermal imaging is common knowledge in the field and will not be described in detail here.

[0113] S849: Use the preset high-temperature heat dissipation method to perform regional heat dissipation in the high-temperature area.

[0114] High-temperature heat dissipation methods are used to dissipate heat from high-temperature areas within the power distribution cabinet. The specific high-temperature heat dissipation methods are described in detail in S8490 to S8494 and are not detailed here.

[0115] When a high-temperature area is identified, it is necessary to use a high-temperature heat dissipation method to dissipate heat in the high-temperature area.

[0116] Reference Figure 2 , the high temperature heat dissipation method includes the following steps: S8490: Determine the fan orientation based on the high-temperature area and the preset fan installation location.

[0117] The fan mounting locations refer to the fixed points of the pre-deployed straight-blade and reverse-blade fans inside the power distribution cabinet. The fan mounting locations are pre-determined by those skilled in the art and will not be described in detail here.

[0118] By comparing the relative relationship between the coordinates of the high-temperature area and the fan installation position, the air supply direction of each fan can be determined, thereby obtaining the fan orientation, and then forming a directional heat dissipation airflow for the high-temperature area.

[0119] S8491: In response to the device operating thermal imaging and high temperature areas to know the area temperature value.

[0120] The regional temperature value refers to the temperature at the center or highest point of a high-temperature area, extracted by scanning the interior of the distribution cabinet with an infrared thermal imager. By performing pixel-level analysis on the thermal image, areas with temperatures exceeding a preset threshold are identified and their average temperature is calculated as the regional temperature value.

[0121] S8492: Calculates fan speed based on zone temperature.

[0122] Fan speed refers to the number of revolutions per minute (RPM) required for both forward and reverse blade fans to effectively dissipate heat. A preset temperature-speed comparison table can be used to determine the fan speed corresponding to each regional temperature. This table records the fan speeds corresponding to different regional temperatures. The table was created by those skilled in the art through sequential testing of fan speeds corresponding to different regional temperatures, and is not detailed here.

[0123] S8493: Controls the fan direction to adjust the direction of the preset positive-blade fan and the preset reverse-blade fan, and rotates them at the fan speed.

[0124] The positive blade fan and the reverse blade fan are controlled to adjust their directions to be consistent with the fan direction and rotate at the fan speed to dissipate heat for the power distribution equipment.

[0125] S8494: Control the opening of the water circulation channel preset below the water-isolating device to allow rainwater to circulate in the water circulation channel.

[0126] The water circulation channel is a pre-designed, sealed conduit within the water barrier's interlayer. Its inlet and outlet are connected to a pre-installed rainwater collection device. When the system detects a high temperature, the channel valve automatically opens, utilizing the natural flow of rainwater and a micro-pump to circulate the water. This conducts heat away from the cabinet, achieving passive cooling.

[0127] Reference Figure 3 , the equipment maintenance method includes the following steps: S90: Collect historical maintenance data and current date.

[0128] Historical maintenance data refers to the records of every maintenance operation performed on the equipment since it was put into operation. This historical maintenance data is retrieved from a pre-set maintenance data storage system, which stores every maintenance record of the power distribution cabinet. This maintenance data storage system is pre-configured by those skilled in the art and will not be described in detail here.

[0129] The current date refers to the current system date, which is obtained from the system clock built into the power distribution cabinet.

[0130] S91: Know the upcoming maintenance date based on historical maintenance data.

[0131] The recent maintenance date refers to the completion date of the most recent maintenance operation in the historical maintenance data. The recent maintenance date is obtained by querying the historical maintenance data. The historical maintenance data contains the recent maintenance date.

[0132] S92: The required maintenance date is determined by combining the recent maintenance date with the preset equipment maintenance cycle.

[0133] The equipment maintenance cycle refers to the interval between regular maintenance of the power distribution cabinet. The equipment maintenance cycle is set in advance by technical personnel in this field and will not be detailed here.

[0134] The required maintenance date is the specific date when the distribution cabinet needs maintenance. The required maintenance date is calculated by summing the recent maintenance date and the equipment maintenance cycle.

[0135] S93: Calculate the number of days until maintenance based on the required maintenance date and the current date.

[0136] Maintenance distance days refers to the difference in days between the required maintenance date and the current date. The maintenance distance days can be calculated by calculating the difference between the required maintenance date and the current date.

[0137] S94: When the number of days until maintenance is less than the preset number of days for maintenance reminder, report a device maintenance reminder.

[0138] The maintenance reminder days refer to the number of days before the maintenance warning is triggered. The maintenance reminder days are set in advance by those skilled in the art and will not be described in detail here.

[0139] When the maintenance distance days are lower than the maintenance reminder days, it means that the time node for maintenance of the power distribution cabinet is approaching, and the equipment maintenance reminder needs to be reported to notify the operation and maintenance personnel.

[0140] S95: Collect the device signal of the preset water isolation device.

[0141] The device signal is a signal used to determine whether the water barrier device is activated. The device signal is collected by the signal transceiver on the water barrier device.

[0142] S96: When the device signal is consistent with the preset start signal, report the equipment maintenance prompt.

[0143] The start signal is a signal indicating that the water barrier device has been started. The start signal is set in advance by a person skilled in the art and will not be described in detail here.

[0144] When the device signal is consistent with the start-up signal, it means that the water isolation device has been started according to the preset logic. This indicates that water has accumulated around the distribution cabinet and the water level has reached the threshold for triggering the device to start. At this time, an equipment maintenance prompt needs to be reported to avoid the water isolation device from being unable to be used normally next time.

[0145] Based on the same inventive concept, the present invention provides an artificial intelligence-based intelligent distribution cabinet, including a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute an artificial intelligence-based distribution method.

[0146] Those skilled in the art will clearly understand that for the sake of convenience and brevity, the division of the above-mentioned functional modules is only used as an example for illustration. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working processes of the above-mentioned systems, devices, and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0147] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiment. All technical solutions based on the concept of the present invention are within the scope of protection of the present invention. It should be noted that for those skilled in the art, various improvements and modifications that do not depart from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A power distribution method based on artificial intelligence, characterized in that: include: Collect historical power distribution data and current power distribution location; deriving the number of power distribution users based on the current power distribution location; Knowing the average electricity consumption per household based on the historical power distribution data and the number of power distribution users; Collect crowd monitoring videos; Recording the movement of people based on the crowd monitoring video; The average household electricity consumption and the movement of people are combined to obtain predicted electricity consumption data, and electricity is distributed based on the predicted electricity consumption data.

2. The power distribution method based on artificial intelligence according to claim 1, characterized in that: Also included is a method for correcting the predicted electricity consumption data: generating a climate electricity consumption total based on the historical electricity distribution data; In response to the total climate electricity consumption, the number of electricity distribution users and the preset reference period days, the average daily user electricity consumption is obtained; Collect the current power distribution date and current climate; The predicted power usage data is modified in response to the current power distribution date, the current date climate, and the daily average user power usage.

3. The power distribution method based on artificial intelligence according to claim 1, characterized in that: Also includes: Collect the surrounding humidity value of the intelligent distribution cabinet; If the ambient humidity value does not exceed the preset reference humidity value, real-time fault detection is performed using a preset fault detection method; If the surrounding humidity value exceeds a preset reference humidity value, collecting surrounding image information; Determining whether the surrounding image information contains a preset puddle feature; When the surrounding image information does not contain the puddle feature, a rain warning is reported for the area, and power distribution and flood prevention are carried out using a preset flood prevention method.

4. The power distribution method based on artificial intelligence according to claim 3, characterized in that: Also includes: When the surrounding image information contains the puddle feature, performing a region selection on the puddle feature from the surrounding image information to obtain a puddle range; Collect puddle depth information and puddle distance values; Combining the puddle range and the puddle depth information to generate a humidity impact value; Obtaining a corrected humidity value according to the surrounding humidity value, the puddle distance value, and the humidity impact value; When the corrected humidity value does not exceed the reference humidity value, performing real-time fault detection using a preset fault detection method; When the corrected humidity value exceeds the reference humidity value, a regional rain warning is reported, and power distribution flood prevention is carried out using a preset flood prevention method.

5. The power distribution method based on artificial intelligence according to claim 3, characterized in that: The fault detection method comprises: Collect device operation sounds; operating the sound according to the device to generate an operating spectrogram; Comparing whether the operating spectrum is consistent with a preset standard spectrum; If and only if the operating spectrum graph is inconsistent with the standard spectrum graph, combining the operating spectrum graph and the standard spectrum graph to determine the degree of spectrum difference; When the difference between the spectrum graphs does not exceed a preset reference difference, a device abnormality prompt is reported; When the difference between the spectrum graphs exceeds a preset reference difference, the control device stops running and reports a device abnormality prompt.

6. The power distribution method based on artificial intelligence according to claim 3, characterized in that: The flood prevention method includes: Collect water level height values; Determining whether the water level value is higher than a preset starting height value; If the water level value is not higher than the starting height value, continue to collect water level values; If the water level value is higher than the starting height value, a water separation height value is obtained based on the water level value; Based on the water-isolating height value, the preset water-isolating device is controlled to start, thereby isolating the equipment from rainwater.

7. The power distribution method based on artificial intelligence according to claim 6, characterized in that: Also includes: Determining whether the water separation height value exceeds a preset operating height value; When the water separation height value exceeds the operating height value, a power outage prompt is reported and the equipment operation is stopped; When the water-blocking height value does not exceed the operating height value, collecting the thermal image of the equipment operation; identifying high temperature areas from thermal imaging of the equipment operation; The high temperature area is subjected to regional heat dissipation using a preset high temperature heat dissipation method.

8. The power distribution method based on artificial intelligence according to claim 7, characterized in that: The high-temperature heat dissipation method comprises: The fan direction is determined based on the high temperature area and the preset fan installation position; In response to the device operating thermal imaging and the high temperature area to know the area temperature value; deriving a fan speed based on the temperature value of the area; Based on the fan direction, the preset positive blade fan and the preset reverse blade fan are controlled to adjust their directions and rotate at the fan speed; The water circulation channel preset below the water-isolating device is controlled to open so that rainwater circulates in the water circulation channel.

9. The power distribution method based on artificial intelligence according to claim 1, characterized in that: Also includes: Collect historical maintenance data and current date; Knowing the upcoming maintenance date based on the historical maintenance data; Combine the recent maintenance date with the preset equipment maintenance cycle to determine the required maintenance date; Calculate the maintenance distance in days based on the required maintenance date and the current date; When the maintenance distance days are less than the preset maintenance reminder days, report the equipment maintenance reminder; Collect device signals of preset water-blocking devices; When the device signal is consistent with the preset start signal, an equipment maintenance prompt is reported.

10. An intelligent power distribution cabinet based on artificial intelligence, characterized in that: The invention comprises a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executes an artificial intelligence-based power distribution method as described in any one of claims 1 to 9.

Images