Power distribution box power supply method based on intelligent power transformation technology

Abstract

The invention discloses a distribution box power supply method based on an intelligent power transformation technology, particularly relates to the technical field of power transformation, and comprises the steps of power supply data acquisition, time window division, power supply data analysis, comprehensive analysis and control. The intelligent load, the electric energy quality, the equipment state and the network communication performance data of the distribution box are comprehensively collected, accurate monitoring of the operation state of the distribution box is achieved, then useful information in the data can be deeply mined through the established analysis model, and a scientific basis is provided for operation and maintenance of the distribution box. Moreover, the comprehensive analysis model can comprehensively consider various factors and accurately judge the overall operation state of the distribution box, and finally, a control instruction is sent out according to the judgment result, so that accurate control over the distribution box can be achieved, the reliability and stability of power supply are ensured, and in conclusion, the operation efficiency and the power supply quality of the distribution box are improved.

Description

Technical Field

[0001] The present invention relates to the field of power transformation technology, and more specifically, to a power supply method for a distribution box based on intelligent power transformation technology. Background Art

[0002] The operation process of the distribution box in the existing technology mainly relies on traditional monitoring means and control methods. Usually, the staff will regularly inspect the distribution box, understand its operating status through manual recording and analysis of data, and take corresponding measures to repair and adjust it when abnormalities are found.

[0003] However, the existing technology has some obvious shortcomings in actual operation. On the one hand, the manual inspection method is subjective and uncertain, making it difficult to detect and deal with potential problems in a timely manner. On the other hand, the traditional control method lacks intelligence and automation, and cannot achieve precise control of the distribution box. These problems have seriously affected the operating efficiency and power supply quality of the distribution box. Therefore, a more advanced and reliable distribution box power supply method is urgently needed to solve these problems. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a power supply method for a distribution box based on intelligent power transformation technology, and solves the problems raised in the above-mentioned background technology through the following scheme.

[0005] To achieve the above object, the present invention provides the following technical solution: a power supply method for a distribution box based on intelligent power conversion technology, comprising: Step 1: Power supply data collection: used to collect intelligent load analysis data, power quality monitoring data, equipment status assessment data and network communication performance data of the target distribution box, and transmit the collected data to step 2; Step 2: Time window division: used to determine the monitoring time of the target distribution box data as the target time zone, divide the target time zone by sliding the time window, and mark it as 1, 2...n in sequence, and transmit the data after the time window division to step 3; Step 3: Power supply data analysis: used to establish a mathematical model to analyze the data transmitted in step 2, including an intelligent load analysis data analysis model, a power quality monitoring data analysis model, an equipment status assessment data analysis model, and a network communication performance data analysis model, and transmit the analysis results to step 4; Step 4: Comprehensive analysis: used to establish a comprehensive analysis model to analyze the data transmitted in step 3, and transmit the analysis results to step 5; Step 5: Control: It is used to judge the state of the target distribution box according to the preset value of the comprehensive abnormality index and the comprehensive abnormality index transmitted in step 4, and issue a control instruction according to the judgment result.

[0006] Preferably, the intelligent load analysis data include load forecast deviation rate, dynamic load transfer response time, time-sharing load utilization index and peak-valley difference intelligent adjustment coefficient, which are marked as Lp, Ld, Lt and Lv respectively; the power quality monitoring data include real-time value of harmonic content, voltage swell / sag recovery time, power factor dynamic compensation accuracy and zero-sequence current imbalance, which are marked as Th, Tv, Tp and Tz respectively; the equipment status assessment data include intelligent switch operation time deviation, partial discharge ultrasonic characteristic value, insulation monitoring dielectric loss tangent value and temperature field distribution abnormal warning value, which are marked as So, Sp, Sm and St respectively; the network communication performance data include data acquisition delay time, control instruction execution success rate, network bandwidth utilization and data encryption transmission integrity, which are marked as Da, Dc, Db and De respectively.

[0007] Preferably, the load prediction deviation rate uses an S3800 smart meter with a sampling frequency of 1000Hz, and collects electricity consumption data every 5 minutes. The load is predicted by the LSTM deep learning algorithm, and is compared with the actual value in real time to calculate the deviation rate. The dynamic load transfer response time is calculated by configuring an NI-9215 high-speed data acquisition card with a sampling rate of 100kHz and a Siemens SICAM P855 power quality analyzer to record the complete process of voltage and current jumps during load switching. The time-sharing load utilization index is calculated by using a PMC-350 intelligent measurement terminal with a 1-minute sampling interval and a total of 2880 sampling points in 24 hours. The daily load curve area is calculated using the trapezoidal integration method and compared with the maximum load value. The peak-to-valley difference intelligent adjustment coefficient uses an ABB-REM543 intelligent terminal in conjunction with a load management system to record the load value every 15 minutes, identify the peak-to-valley value through a sliding window algorithm, and calculate the ratio before and after adjustment.

[0008] Preferably, the real-time value of the harmonic content is obtained by using a Fluke 435 II harmonic analyzer with a sampling frequency of 25.6kHz and a window width of 10 cycles. A Hanning window is used for FFT analysis, and the 2-50th harmonic content is calculated in real time. The voltage swell / sag recovery time is calculated by configuring a HIOKI 3196 power quality analyzer with a trigger threshold set to ±10% of the nominal voltage, a sampling rate of 200kHz, and a pre-trigger time of 20ms to capture the complete waveform of the transient process. The power factor dynamic compensation accuracy is obtained by using a Yokogawa WT3000E power analyzer with a sampling interval of 100μs. Through 16-bit AD conversion, the apparent power and active power before and after compensation are measured, and the power factor is calculated in real time. The zero-sequence current unbalance is measured by an OMICRON CMC 356 three-phase test system with a sampling rate of 10kHz. The three-phase current is collected synchronously, and the zero-sequence component is calculated by the symmetrical component method to evaluate the unbalance.

[0009] Preferably, the operation time deviation of the intelligent switch is measured by using a Phantom V711 high-speed camera with a shooting speed of 10,000 frames per second, in conjunction with a GPS timing system, to accurately record the opening and closing process of the switch contacts and calculate the action time deviation. The ultrasonic characteristic value of partial discharge is measured by deploying 8 DMWD-200 ultrasonic sensors with a sampling frequency of 500kHz, and local discharge is located by a waveform feature recognition algorithm. The discharge position is determined by an acoustic emission triangulation method. The dielectric loss tangent value of insulation monitoring is measured by using an OMICRON DIRANA dielectric response analyzer with a test frequency of 45-65Hz and a test voltage of 2kV. The dielectric loss tangent value is calculated by a vector analysis method. The abnormal warning value of the temperature field distribution is measured by using a FLIR T1020 infrared thermal imager with a thermal sensitivity of 0.02°C. A comprehensive scan is performed every 30 minutes to generate a thermal map of the surface temperature distribution of the equipment, and the hot spots are located by combining an image recognition algorithm.

[0010] Preferably, the data acquisition delay time uses Wireshark network analysis software, cooperates with the GPS timing module, captures IEC61850 messages, calculates the GOOSE message transmission delay, sets the sampling accuracy to 1μs, and controls the execution success rate of instructions by deploying the ELK log analysis platform, real-time acquisition of control system operation logs, log parsing through Logstash, statistics of instruction execution status, and calculation of success rate. The network bandwidth utilization rate uses the SolarWinds network traffic analyzer with a sampling interval of 1s to monitor the switch port traffic, obtain bandwidth usage data through the SNMP protocol, and calculate the utilization rate. The data encryption transmission integrity uses the Wireshark protocol analyzer in conjunction with the RSA encryption verification module to perform CRC check on the transmitted data, verify the data integrity through the SHA-256 algorithm, and record the check result.

[0011] Preferably, the intelligent load analysis data analysis model is specifically expressed as: , E.L. i represents the intelligent load assessment value of the i-th time window, Lp i represents the load forecast deviation rate of the i-th time window, Ld i represents the dynamic load transfer response time of the i-th time window, Lt i represents the time-sharing load utilization index of the i-th time window, Lv i Represents the intelligent adjustment coefficient of the peak-to-valley difference in the i-th time window.

[0012] Preferably, the power quality monitoring data analysis model is specifically expressed as: , E.T. i represents the power quality assessment value of the i-th time window, Th irepresents the real-time value of the harmonic content in the ith time window, Tv i Indicates the voltage surge / sag recovery time in the i-th time window, Tp i Indicates the dynamic compensation accuracy of the power factor in the i-th time window, Tz i Represents the zero-sequence current unbalance degree in the i-th time window.

[0013] Preferably, the equipment status assessment data analysis model is specifically expressed as: , E.S. i represents the equipment status evaluation value of the i-th time window, So i represents the intelligent switch operation time deviation in the i-th time window, Sp i represents the local discharge ultrasonic characteristic value of the i-th time window, Sm i Indicates the insulation monitoring dielectric loss tangent value of the i-th time window, St i Represents the abnormal warning value of temperature field distribution in the i-th time window.

[0014] Preferably, the network communication performance data analysis model is specifically expressed as: , E.D. i represents the network communication performance evaluation value of the i-th time window, Da i represents the data collection delay time of the i-th time window, Dc i represents the control instruction execution success rate of the i-th time window, Db i represents the network bandwidth utilization of the i-th time window, De i Indicates the data encryption transmission integrity of the i-th time window.

[0015] Preferably, the comprehensive analysis model is specifically expressed as: , E represents the comprehensive abnormal index of the target distribution box, EL i represents the intelligent load evaluation value of the i-th time window, ET i represents the power quality assessment value of the i-th time window, ES i represents the equipment status evaluation value of the i-th time window, ED i represents the network communication performance evaluation value of the i-th time window, w1, w2, w3 and w4 represent weights, and μ represents other influencing factors of the comprehensive anomaly index.

[0016] Preferably, when the deviation between the comprehensive abnormality index of the target distribution box and the preset value of the comprehensive abnormality index is ±5%, the reactive compensation device is automatically adjusted; when the deviation is ±10%, the load transfer program is started; when the deviation is >±15%, the emergency response plan is triggered, and an early warning signal is sent to the management terminal.

[0017] Technical effects and advantages of the present invention: The present invention collects the intelligent load analysis data, power quality monitoring data, equipment status evaluation data and network communication performance data of the target distribution box through power supply data, so as to fully and accurately understand the operating status of the distribution box. The collected data provides a basis for subsequent analysis and control, which is helpful to timely discover potential problems and improve the reliability and stability of power supply; the monitoring time of the target distribution box data is determined as the target time area through time window division, and the target time area is divided by sliding time window, which is helpful to continuously and dynamically analyze the operating status of the distribution box. The first time window is used as the initial state and does not participate in the actual analysis, thereby avoiding the interference of the initial data on the subsequent analysis results; the collected data is analyzed by establishing a mathematical model through power supply data analysis, including an intelligent load analysis data analysis model, a power quality monitoring data analysis model, an equipment status evaluation data analysis model and a network communication performance data analysis model, which can deeply mine the useful information in the data. Through the analysis model, The operation status of the distribution box in different time windows is quantitatively evaluated, which provides a scientific basis for the subsequent comprehensive analysis and control. By establishing a comprehensive analysis model through comprehensive analysis to analyze the data transmitted in step 3, the performance of the distribution box in terms of intelligent load, power quality, equipment status and network communication performance can be comprehensively considered. Through the comprehensive analysis model, the comprehensive abnormality index of the target distribution box can be obtained, which is helpful to accurately judge the overall operation status of the distribution box. By controlling the status of the target distribution box according to the preset value of the comprehensive abnormality index and the comprehensive abnormality index transmitted in step 4, and issuing control instructions according to the judgment results, precise control of the distribution box can be achieved. By automatically adjusting the reactive compensation device, starting the load transfer program and triggering the emergency response plan, abnormal conditions in the operation of the distribution box can be discovered and handled in time to ensure the reliability and stability of the power supply. At the same time, an early warning signal is sent to the management terminal, which helps the management personnel to understand the operation status of the distribution box in time and take corresponding countermeasures. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of the overall structure of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] refer to Figure 1A power supply method for a distribution box based on intelligent power conversion technology is shown, and the specific steps include: Step 1: Power supply data collection: used to collect the intelligent load analysis data, power quality monitoring data, equipment status assessment data and network communication performance data of the target distribution box, and transmit the collected data to step 2.

[0021] The intelligent load analysis data includes load prediction deviation rate, dynamic load transfer response time, time-sharing load utilization index and peak-valley difference intelligent adjustment coefficient, which are marked as Lp, Ld, Lt and Lv respectively; the power quality monitoring data includes real-time value of harmonic content, voltage swell / sag recovery time, power factor dynamic compensation accuracy and zero-sequence current imbalance, which are marked as Th, Tv, Tp and Tz respectively; the equipment status assessment data includes intelligent switch operation time deviation, partial discharge ultrasonic characteristic value, insulation monitoring dielectric loss tangent value and temperature field distribution abnormal warning value, which are marked as So, Sp, Sm and St respectively; the network communication performance data includes data acquisition delay time, control instruction execution success rate, network bandwidth utilization and data encryption transmission integrity, which are marked as Da, Dc, Db and De respectively.

[0022] The load prediction deviation rate uses an S3800 smart meter with a sampling frequency of 1000Hz. Electricity consumption data is collected every 5 minutes. The load is predicted by the LSTM deep learning algorithm, and the data is compared with the actual value in real time to calculate the deviation rate. The dynamic load transfer response time is calculated by configuring an NI-9215 high-speed data acquisition card with a sampling rate of 100kHz and a Siemens SICAMP855 power quality analyzer to record the complete process of voltage and current jumps during load switching. The time-sharing load utilization index is calculated by using the PMC-350 smart measurement terminal with a 1-minute sampling interval and a total of 2880 sampling points in 24 hours. The daily load curve area is calculated using the trapezoidal integration method and compared with the maximum load value. The peak-to-valley difference intelligent adjustment coefficient uses an ABB-REM543 smart terminal in conjunction with a load management system to record the load value every 15 minutes, identify the peak-to-valley value through a sliding window algorithm, and calculate the ratio before and after adjustment.

[0023] The real-time value of the harmonic content is measured using a Fluke 435 II harmonic analyzer with a sampling frequency of 25.6kHz and a window width of 10 cycles. The Hanning window is used for FFT analysis, and the 2-50th harmonic content is calculated in real time. The voltage swell / sag recovery time is measured by configuring a HIOKI 3196 power quality analyzer with a trigger threshold set to the nominal voltage ±10%, a sampling rate of 200kHz, and a pre-trigger time of 20ms to capture the complete waveform of the transient process. The power factor dynamic compensation accuracy is measured using a Yokogawa WT3000E power analyzer with a sampling interval of 100μs. Through 16-bit AD conversion, the apparent power and active power before and after compensation are measured, and the power factor is calculated in real time. The zero-sequence current unbalance is measured using an OMICRON CMC 356 three-phase test system with a sampling rate of 10kHz. The three-phase current is synchronously collected, and the zero-sequence component is calculated by the symmetrical component method to evaluate the unbalance.

[0024] The operation time deviation of the intelligent switch is measured by a Phantom V711 high-speed camera with a shooting speed of 10,000 frames per second. In conjunction with the GPS timing system, the opening and closing process of the switch contacts is accurately recorded and the action time deviation is calculated. The ultrasonic characteristic value of partial discharge is measured by deploying 8 DMWD-200 ultrasonic sensors with a sampling frequency of 500kHz. The partial discharge is located by a waveform feature recognition algorithm, and the discharge position is determined by the acoustic emission triangulation positioning method. The dielectric loss tangent value of insulation monitoring is measured by an OMICRON DIRANA dielectric response analyzer with a test frequency of 45-65Hz and a test voltage of 2kV. The dielectric loss tangent value is calculated by a vector analysis method. The abnormal warning value of the temperature field distribution is measured by a FLIR T1020 infrared thermal imager with a thermal sensitivity of 0.02°C. A comprehensive scan is performed every 30 minutes to generate a thermal map of the surface temperature distribution of the equipment, and the hot spots are located in combination with the image recognition algorithm.

[0025] The data acquisition delay time uses Wireshark network analysis software, cooperates with GPS timing module, captures IEC61850 messages, calculates GOOSE message transmission delay, sets sampling accuracy to 1μs, and controls the execution success rate of instructions by deploying ELK log analysis platform, real-time collection of control system operation logs, log parsing through Logstash, statistics of instruction execution status, and calculation of success rate. The network bandwidth utilization rate uses SolarWinds network traffic analyzer with a sampling interval of 1s to monitor switch port traffic, obtain bandwidth usage data through SNMP protocol, and calculate utilization rate. The data encryption transmission integrity uses Wireshark protocol analyzer with RSA encryption verification module to perform CRC check on the transmitted data, verify data integrity through SHA-256 algorithm, and record the verification results.

[0026] Step 2: Time window division: used to determine the monitoring time of the target distribution box data as the target time area, divide the target time area by sliding the time window, and mark it as 1, 2...n in sequence, and transmit the data after the time window division to step 3.

[0027] It should be specifically explained in this embodiment that the first time window represents the initial state of the target distribution box and does not participate in the actual analysis.

[0028] Step 3: Power supply data analysis: used to establish a mathematical model to analyze the data transmitted in step 2, including intelligent load analysis data analysis model, power quality monitoring data analysis model, equipment status assessment data analysis model and network communication performance data analysis model, and transmit the analysis results to step 4.

[0029] The intelligent load analysis data analysis model is specifically expressed as follows: , E.L. i represents the intelligent load assessment value of the i-th time window, Lp i represents the load forecast deviation rate of the i-th time window, Ld i represents the dynamic load transfer response time of the i-th time window, Lt i represents the time-sharing load utilization index of the i-th time window, Lv i Represents the intelligent adjustment coefficient of the peak-to-valley difference in the i-th time window.

[0030] The power quality monitoring data analysis model is specifically expressed as: , E.T. i represents the power quality assessment value of the i-th time window, Th i represents the real-time value of the harmonic content in the ith time window, Tv i Indicates the voltage surge / sag recovery time in the i-th time window, Tp i Indicates the dynamic compensation accuracy of the power factor in the i-th time window, Tz i Represents the zero-sequence current unbalance degree in the i-th time window.

[0031] The equipment status assessment data analysis model is specifically expressed as: , E.S. i represents the equipment status evaluation value of the i-th time window, So i represents the intelligent switch operation time deviation in the i-th time window, Sp i represents the local discharge ultrasonic characteristic value of the i-th time window, Sm i Indicates the insulation monitoring dielectric loss tangent value of the i-th time window, St i Represents the abnormal warning value of temperature field distribution in the i-th time window.

[0032] The network communication performance data analysis model is specifically expressed as follows: , E.D. i represents the network communication performance evaluation value of the i-th time window, Da i represents the data collection delay time of the i-th time window, Dc i represents the control instruction execution success rate of the i-th time window, Db i represents the network bandwidth utilization of the i-th time window, De i Indicates the data encryption transmission integrity of the i-th time window.

[0033] Step 4: Comprehensive analysis: used to establish a comprehensive analysis model to analyze the data transmitted in step 3, and transmit the analysis results to step 5.

[0034] The comprehensive analysis model is specifically expressed as: , E represents the comprehensive abnormal index of the target distribution box, EL i represents the intelligent load evaluation value of the i-th time window, ET i represents the power quality assessment value of the i-th time window, ES i represents the equipment status evaluation value of the i-th time window, ED i represents the network communication performance evaluation value of the i-th time window, w1, w2, w3 and w4 represent weights, and μ represents other influencing factors of the comprehensive anomaly index.

[0035] Step 5: Control: It is used to judge the state of the target distribution box according to the preset value of the comprehensive abnormality index and the comprehensive abnormality index transmitted in step 4, and issue a control instruction according to the judgment result.

[0036] When the deviation between the comprehensive abnormality index of the target distribution box and the preset value of the comprehensive abnormality index is ±5%, the reactive compensation device is automatically adjusted; when the deviation is ±10%, the load transfer program is started; when the deviation is >±15%, the emergency response plan is triggered and an early warning signal is sent to the management terminal.

[0037] The present invention collects the intelligent load analysis data, power quality monitoring data, equipment status evaluation data and network communication performance data of the target distribution box through power supply data, so as to fully and accurately understand the operating status of the distribution box. The collected data provides a basis for subsequent analysis and control, which is helpful to timely discover potential problems and improve the reliability and stability of power supply; the monitoring time of the target distribution box data is determined as the target time area through time window division, and the target time area is divided by sliding time window, which is helpful to continuously and dynamically analyze the operating status of the distribution box. The first time window is used as the initial state and does not participate in the actual analysis, thereby avoiding the interference of the initial data on the subsequent analysis results; the collected data is analyzed by establishing a mathematical model through power supply data analysis, including an intelligent load analysis data analysis model, a power quality monitoring data analysis model, an equipment status evaluation data analysis model and a network communication performance data analysis model, which can deeply mine the useful information in the data. Through the analysis model, The operation status of the distribution box in different time windows is quantitatively evaluated, which provides a scientific basis for the subsequent comprehensive analysis and control. By establishing a comprehensive analysis model through comprehensive analysis to analyze the data transmitted in step 3, the performance of the distribution box in terms of intelligent load, power quality, equipment status and network communication performance can be comprehensively considered. Through the comprehensive analysis model, the comprehensive abnormality index of the target distribution box can be obtained, which is helpful to accurately judge the overall operation status of the distribution box. By controlling the status of the target distribution box according to the preset value of the comprehensive abnormality index and the comprehensive abnormality index transmitted in step 4, and issuing control instructions according to the judgment results, precise control of the distribution box can be achieved. By automatically adjusting the reactive compensation device, starting the load transfer program and triggering the emergency response plan, abnormal conditions in the operation of the distribution box can be discovered and handled in time to ensure the reliability and stability of the power supply. At the same time, an early warning signal is sent to the management terminal, which helps the management personnel to understand the operation status of the distribution box in time and take corresponding countermeasures.

[0038] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other; Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A power supply method for a distribution box based on intelligent power transformation technology, characterized in that: include: Step 1: Power supply data collection: used to collect intelligent load analysis data, power quality monitoring data, equipment status assessment data and network communication performance data of the target distribution box, and transmit the collected data to step 2; Step 2: Time window division: used to determine the monitoring time of the target distribution box data as the target time zone, divide the target time zone by sliding the time window, and mark it as 1, 2...n in sequence, and transmit the data after the time window division to step 3; Step 3: Power supply data analysis: used to establish a mathematical model to analyze the data transmitted in step 2, including an intelligent load analysis data analysis model, a power quality monitoring data analysis model, an equipment status assessment data analysis model, and a network communication performance data analysis model, and transmit the analysis results to step 4; Step 4: Comprehensive analysis: used to establish a comprehensive analysis model to analyze the data transmitted in step 3, and transmit the analysis results to step 5; Step 5: Control: It is used to judge the state of the target distribution box according to the preset value of the comprehensive abnormality index and the comprehensive abnormality index transmitted in step 4, and issue a control instruction according to the judgment result.

2. According to claim 1, a power supply method for a distribution box based on intelligent power conversion technology is characterized in that: The intelligent load analysis data includes load prediction deviation rate, dynamic load transfer response time, time-sharing load utilization index and peak-valley difference intelligent adjustment coefficient, which are marked as Lp, Ld, Lt and Lv respectively; the power quality monitoring data includes real-time value of harmonic content, voltage swell / sag recovery time, power factor dynamic compensation accuracy and zero-sequence current imbalance, which are marked as Th, Tv, Tp and Tz respectively; the equipment status assessment data includes intelligent switch operation time deviation, partial discharge ultrasonic characteristic value, insulation monitoring dielectric loss tangent value and temperature field distribution abnormal warning value, which are marked as So, Sp, Sm and St respectively; the network communication performance data includes data acquisition delay time, control instruction execution success rate, network bandwidth utilization and data encryption transmission integrity, which are marked as Da, Dc, Db and De respectively.

3. According to claim 1, a power supply method for a distribution box based on intelligent power conversion technology is characterized in that: The intelligent load analysis data analysis model is specifically expressed as follows: , E.L. i represents the intelligent load assessment value of the i-th time window, Lp i represents the load forecast deviation rate of the i-th time window, Ld i represents the dynamic load transfer response time of the i-th time window, Lt i represents the time-sharing load utilization index of the i-th time window, Lv i Represents the intelligent adjustment coefficient of the peak-to-valley difference in the i-th time window.

4. A power supply method for a distribution box based on intelligent power conversion technology according to claim 1, characterized in that: The power quality monitoring data analysis model is specifically expressed as: , E.T. i represents the power quality assessment value of the i-th time window, Th i represents the real-time value of the harmonic content in the ith time window, Tv i Indicates the voltage surge / sag recovery time in the i-th time window, Tp i Indicates the dynamic compensation accuracy of the power factor in the i-th time window, Tz i Represents the zero-sequence current unbalance degree in the i-th time window.

5. The power supply method for a distribution box based on intelligent power conversion technology according to claim 1 is characterized in that: The equipment status assessment data analysis model is specifically expressed as: , E.S. i represents the equipment status evaluation value of the i-th time window, So i represents the intelligent switch operation time deviation in the i-th time window, Sp i represents the local discharge ultrasonic characteristic value of the i-th time window, Sm i Indicates the insulation monitoring dielectric loss tangent value of the i-th time window, St i Represents the abnormal warning value of temperature field distribution in the i-th time window.

6. The power supply method for a distribution box based on intelligent power transformation technology according to claim 1 is characterized in that: The network communication performance data analysis model is specifically expressed as follows: , E.D. i represents the network communication performance evaluation value of the i-th time window, Da i represents the data collection delay time of the i-th time window, Dc i represents the control instruction execution success rate of the i-th time window, Db i represents the network bandwidth utilization of the i-th time window, De i Indicates the data encryption transmission integrity of the i-th time window.

7. The power supply method for a distribution box based on intelligent power conversion technology according to claim 1 is characterized in that: The comprehensive analysis model is specifically expressed as: , E represents the comprehensive abnormal index of the target distribution box, EL i represents the intelligent load evaluation value of the i-th time window, ET i represents the power quality assessment value of the i-th time window, ES i represents the equipment status evaluation value of the i-th time window, ED i represents the network communication performance evaluation value of the i-th time window, w1, w2, w3 and w4 represent weights, and μ represents other influencing factors of the comprehensive anomaly index.

8. The power supply method for a distribution box based on intelligent power conversion technology according to claim 1 is characterized in that: When the deviation between the comprehensive abnormality index of the target distribution box and the preset value of the comprehensive abnormality index is ±5%, the reactive compensation device is automatically adjusted; when the deviation is ±10%, the load transfer program is started; when the deviation is >±15%, the emergency response plan is triggered and an early warning signal is sent to the management terminal.

Images