AI-based voltage monitoring and voltage sag determination method, medium and equipment

Abstract

The invention relates to the technical field of electric power, in particular to an AI-based voltage monitoring and voltage sag judgment method, a medium and equipment. The method comprises the following steps of voltage sag source judgment device configuration, voltage and current monitoring and effective value calculation, voltage sag judgment and recording, disturbance voltage and disturbance current calculation, voltage sag characteristic analysis and reason judgment and voltage sag source judgment AI technology. Real-time monitoring of a power grid operation state and timely discovery of a voltage sag event are ensured, and safety and stability of power grid operation are improved; the accuracy of voltage sag source judgment is improved through the AI technology, the AI model is used for processing and analyzing the real-time data of the power grid, intelligent judgment and prediction of the voltage sag source are achieved, and the operation efficiency and reliability of the power grid are improved.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to an AI-based voltage monitoring and voltage sag determination method, medium and device. Background Art

[0002] With the continuous advancement of power systems, the safe and stable operation of power grids has become increasingly critical. Voltage sag, as a common power quality problem, poses a threat to both power grids and user equipment. To solve this problem, technicians are constantly exploring. For example, Chinese patent CN113189444A proposes a method and device for determining the source of voltage sag, which realizes automatic monitoring. However, traditional methods still have problems: they rely on manually preset thresholds and simple algorithms, lack intelligent analysis, resulting in insufficient judgment accuracy and difficulty in identifying specific causes. At the same time, the lack of intelligent prediction capabilities limits the efficiency and reliability of power grid operation. When a voltage sag occurs, it is impossible to quickly locate the source of the fault and take countermeasures. In addition, the data processing capabilities of traditional methods are limited, making it difficult to comprehensively process and analyze real-time power grid data, which limits the optimization of the power grid's operating status. Summary of the invention

[0003] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art and provide an AI-based voltage monitoring and voltage sag determination method, medium and device.

[0004] The technical solution adopted by the present invention is as follows: A voltage monitoring and voltage sag determination method, medium and device based on AI, comprising the following steps: S1. Setting of voltage sag source determination device: a dedicated device for voltage sag source determination, including the following specific steps: S11. Device component configuration: Confirm that the voltage sag source determination device includes a sampling unit and a data processing unit; Verify the connection status between the sampling unit and the power grid monitoring device to ensure stable data transmission; Check the algorithm implementation of the data processing unit to ensure that the symmetrical component method and phase difference calculation are accurate; S12, sampling unit operation: Set the sampling frequency and sampling time window to capture the three-phase voltage and three-phase current waveforms; Extract the waveform data of a voltage sag event from the power grid monitoring device and perform preliminary verification; S13, data processing unit operation: The sampled data are processed by the symmetrical component method to obtain the three-phase fundamental frequency positive sequence voltage and the three-phase fundamental frequency positive sequence current; Calculate the phase difference between the three-phase fundamental frequency positive sequence voltage and the three-phase fundamental frequency positive sequence current; Draw a curve of the phase difference changing with time, and analyze the characteristics of the curve and the polarity of the first peak; S14. Determine the location of the voltage sag source: Determine the location of the voltage sag source based on the polarity of the first peak of the phase difference curve; S2. Voltage and current monitoring and effective value calculation: Real-time monitoring of the operation status of the power grid is carried out at the monitoring point, and the voltage and current data of the monitoring point are specifically measured, including the following specific steps: S21. Monitoring point setting: select a number of monitoring points to ensure that the operation status of the power grid is fully reflected; S22, data acquisition: use high-precision sensors to collect voltage and current data of monitoring points in real time; S23, effective value calculation: processing the collected voltage data to calculate the effective value of each phase voltage; S3. Voltage sag determination and recording: When the effective value of the voltage of one or more phases is detected to be lower than 90% of the rated voltage, the system determines it as a voltage sag event, including the following specific steps: S31, voltage sag determination: compare the effective value of each phase voltage with 90% of the rated voltage in real time. If it is lower than this threshold, it is determined as a voltage sag event; S32, recording voltage sag information: recording the specific time when the voltage sag occurs, and saving the waveform data at that time; S4. Calculation of disturbance voltage and disturbance current: synchronously sampling the signals before and after the voltage sag, and calculating the disturbance voltage and disturbance current, including the following specific steps: S41, synchronous sampling: before and after the voltage sag occurs, the voltage and current signals are synchronously sampled; S42, difference calculation: performing difference calculation on the sampled data to obtain a disturbance voltage and a disturbance current; S5, calculation of disturbance power and determination of the location of voltage sag source: calculation of disturbance power and determination of the location of voltage sag source according to the polarity of disturbance power, including the following specific steps: S51, disturbance power calculation: multiply the disturbance voltage by the disturbance current to obtain the disturbance power; S52, determining the location of the voltage sag source: determining the location of the voltage sag source according to the polarity of the disturbance power; S6. Voltage sag characteristics analysis and cause determination: Based on monitoring data and disturbance analysis, conduct an in-depth analysis of voltage sag characteristics and determine the cause of voltage sag, including the following specific steps: S61, data collection: obtaining the monitoring node name, the corresponding relationship between the current and voltage within a predetermined time and time; S62, recording key data: recording the current before the voltage sag and the current value within a predetermined time period after the voltage sag; S63, characteristic analysis: based on the above data, obtain voltage deviation characteristics, current deviation characteristics, loss capacity and voltage sag duration; S64, cause determination: Combine the indicator dimensions to analyze and determine the cause of the voltage sag to improve the accuracy of the determination; S7. AI technology for determining the source of voltage sag: AI technology is used to improve the accuracy of determining the source of voltage sag, including the following specific steps: S71, monitoring data acquisition: monitoring the operation status of the power grid at the monitoring point and acquiring real-time monitoring data; S72, voltage sag determination: AI determines whether a voltage sag event occurs in the power grid; S73, average power calculation: AI calculates the average power of a fundamental wave cycle before the grid voltage sag occurs and the average power of a fundamental wave cycle during the grid voltage sag; S74, active power difference calculation: calculate the difference between the two average powers to obtain the active power difference; S75. Determine the location of the voltage sag source: Based on the flow direction of the active power difference and a predefined reference direction, the AI ​​determines the location of the voltage sag source in the power grid relative to the monitoring point.

[0005] The present technical solution realizes effective monitoring of grid voltage and current and accurate determination of voltage sag events. Specifically, through the setting of the voltage sag source determination device in step S1, the correct configuration of the device components and the stable transmission of data are ensured, including the configuration of the device components, the operation of the sampling unit, the operation of the data processing unit, and the determination of the location of the voltage sag source; through the voltage and current monitoring and effective value calculation in step S2, the real-time monitoring of the grid operation status and the collection of voltage and current data are realized, including the setting of monitoring points, data collection and effective value calculation processes; through the voltage sag determination and recording in step S3, the determination and recording of voltage sag events are realized, including accurately determining voltage sag events by comparing the effective value of each phase voltage with the threshold of the rated voltage in real time, and recording the specific time and waveform of the voltage sag. data; through the calculation of disturbance voltage and disturbance current in step S4, and the calculation of disturbance power and determination of the azimuth of voltage sag source in step S5, the impact of voltage sag events on the power grid is deeply analyzed, and the azimuth of voltage sag source is determined according to the polarity of disturbance power; through the voltage sag characteristic analysis and cause determination in step S6, a comprehensive analysis of voltage sag events is carried out, and the cause of voltage sag is accurately determined, including the process of data collection, key data recording, characteristic analysis and cause determination; through the AI ​​technology for voltage sag source determination in step S7, the accuracy of voltage sag source determination is improved by using AI technology, including monitoring data acquisition, voltage sag determination, average power calculation, active power difference calculation and voltage sag source azimuth determination.

[0006] In addition, the AI-based voltage monitoring and voltage sag determination method, medium, and device proposed in the present invention also have the following additional technical features: According to an embodiment of the present invention, the voltage sag source determination device of step S1 further includes the following steps: S15, sampling unit calibration: the sampling unit is calibrated regularly to ensure that it can accurately collect voltage data. The calibration process includes adjusting the sampling frequency and calibrating the sampling accuracy. S16, data processing unit verification: verify the data processing unit to ensure that it can correctly process and analyze the data collected by the sampling unit. The verification process includes testing the data processing algorithm and verifying the accuracy of the data processing results; S17. Self-diagnosis function configuration: configure the self-diagnosis function of the device so that it can monitor the operating status of the device in real time and promptly detect and report potential faults or abnormalities.

[0007] This technical solution ensures the accuracy and reliability of the voltage sag source determination device and improves the stability and fault self-diagnosis capability of the device during operation through the calibration of the sampling unit of S15, the verification of the data processing unit of S16 and the configuration of the self-diagnosis function of S17.

[0008] According to one embodiment of the present invention, in the monitoring point setting of step S21, the same polarity direction of the internal voltage and current transformer of the monitoring point is used as the positive direction of the reference direction. If the bus active power measured by the voltage and current transformers after installation is positive, the reference direction is the same as the active power flow direction; conversely, if the measured bus active power is negative, the reference direction is opposite to the active power flow direction.

[0009] This technical solution defines the same polarity direction of the voltage and current transformers in the monitoring point setting as the positive direction of the reference direction, and determines the relationship between the reference direction and the active power flow direction according to the positive and negative active power, thereby providing an accurate reference benchmark for subsequent voltage and current monitoring and voltage sag determination.

[0010] According to one embodiment of the present invention, in the voltage sag determination of step S31, the voltages relative to the neutral point of the power grid, that is, the difference between the phase voltage and the zero-sequence voltage of the power grid, are monitored. When the voltage of any phase of the three-phase power grid neutral point is less than 90% of the rated phase voltage, it is determined that a voltage sag has occurred.

[0011] This technical solution monitors the voltage of each relative grid neutral point, that is, the difference between the phase voltage and the zero-sequence voltage of the grid, and sets it as a voltage sag when any phase is less than 90% of the rated phase voltage, thereby achieving accurate judgment of voltage sag events.

[0012] According to an embodiment of the present invention, in the difference calculation of step S42, the disturbance voltage and disturbance current monitored by the monitoring point are defined as: (1) Where:

[0013] The solution method for disturbance voltage and disturbance current is: (2) Where: is the number of sampling points in a single cycle, Take a positive integer to represent the fundamental wave period number of the sampling interval during the disturbance and before the disturbance, and the disturbance power is obtained as: (3) Where: is the instantaneous disturbance power; is the average disturbance power.

[0014] This technical solution determines the location of the subsequent voltage sag source by defining and calculating the disturbance voltage and disturbance current, and solving the instantaneous disturbance power and average disturbance power.

[0015] According to an embodiment of the present invention, the cause determination in step S64 includes the following specific steps: S641. Analysis of the propagation path of disturbance power: Use power grid simulation software to establish a power grid model including generators, transformers, lines, and loads; simulate the injection of disturbance power in the model, set the size, polarity, and position of the disturbance power; use the power grid model to track the propagation path of the disturbance power in the power grid and record the power changes of each node; S642, attenuation characteristics analysis: Calculate the attenuation coefficient: Calculate the attenuation coefficient of the disturbance power during the propagation process based on the resistance, inductance and capacitance of the power grid; apply the attenuation coefficient to each node on the propagation path to simulate the actual attenuation of the disturbance power; S643, load and line parameter correction: according to the actual load of the power grid, adjust the load size of each node in the model to reflect the actual power grid operation status; according to the actual line parameter measurement value or calibration result, correct the line parameters in the model to improve the accuracy of the model; S644. Correction and optimization of determination results: Compare the disturbance power distribution obtained by simulation with the actual monitoring data to find out the areas with large differences; according to the comparison results, adjust the line length and impedance of the power grid model to reduce the difference between simulation and reality; use the corrected model to re-simulate and calculate to obtain a more accurate disturbance power distribution, and then determine the location of the voltage sag source.

[0016] This technical solution achieves in-depth analysis and accurate determination of the cause of voltage sag through disturbance power propagation path analysis, attenuation characteristic analysis, load and line parameter correction, and determination result correction and optimization in the cause determination of S64, thereby improving the accuracy and credibility of the determination results.

[0017] According to an embodiment of the present invention, the step S75 of determining the voltage sag source position includes the following specific steps: S751. Use the training set data to train the AI ​​model, and optimize the model parameters through the back propagation algorithm so that the model can accurately determine the source of the voltage sag; S752. Evaluation indicators include the proportion of correctly identified voltage sag sources to the total number, the proportion of correctly identified voltage sag events that actually occurred, and the harmonic mean of accuracy and recall, which can fully reflect the model's determination ability and performance; S753. According to the evaluation results, adjust the learning rate, network structure, and activation function of the model until the optimal parameter combination is found; S754, removing features irrelevant to the determination of the voltage sag source, and increasing the disturbance power, the amplitude and duration of the voltage sag; S755. Integrate the trained AI model into the power grid monitoring system, collect voltage, current, and power, and input them into the AI ​​model to achieve real-time monitoring of the power grid operation status and determine the source of voltage sag; S756. Use AI models to process and analyze real-time data of the power grid to predict potential voltage sag events; the prediction results include the time, location, fault type and fault location of the voltage sag event.

[0018] This technical solution achieves intelligent determination and prediction of voltage sag sources through AI model training, evaluation index setting, model parameter adjustment, feature selection and optimization, model integration into the power grid monitoring system, and real-time data processing and analysis in S75's determination of voltage sag source location, thereby improving the safety and stability of power grid operation.

[0019] The invention also provides a computer-readable storage medium and an electronic device.

[0020] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the AI-based voltage monitoring and voltage sag determination method.

[0021] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the voltage monitoring and voltage sag determination method based on AI is implemented.

[0022] Compared with the prior art, the present invention has the following beneficial effects: (1) Realize effective monitoring of grid voltage and current and accurate determination of voltage sag events, including configuration of voltage sag source determination device, voltage and current monitoring and effective value calculation, voltage sag determination and recording, etc., to ensure real-time monitoring of grid operation status and timely detection of voltage sag events, and improve the safety and stability of grid operation; (2) Improve the accuracy of voltage sag source determination through AI technology, use AI models to process and analyze real-time grid data, realize intelligent determination and prediction of voltage sag sources, and improve grid operation efficiency and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flow diagram of the method of the present invention.

[0024] Figure 2 It is a structural schematic diagram of a voltage sag source determination device.

[0025] Figure 3 It is the disturbance power curve caused by the fault.

[0026] Figure 4It is the voltage and current curve caused by the fault.

[0027] Figure 5 It is the disturbance power curve of the monitoring point. DETAILED DESCRIPTION

[0028] 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 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.

[0029] Example 1 like Figures 1 to 5 As shown, this embodiment provides an AI-based voltage monitoring and voltage sag determination method, medium and device, including the following steps: S1. Voltage sag source determination device settings: Figure 2 As shown, the dedicated device for determining the voltage sag source includes the following specific steps: S11. Device component configuration: Confirm that the voltage sag source determination device includes a sampling unit and a data processing unit; Verify the connection status between the sampling unit and the power grid monitoring device to ensure stable data transmission; Check the algorithm implementation of the data processing unit to ensure that the symmetrical component method and phase difference calculation are accurate; S12, sampling unit operation: Set the sampling frequency and sampling time window to capture the three-phase voltage and three-phase current waveforms; Extract the waveform data of a voltage sag event from the power grid monitoring device and perform preliminary verification; S13, data processing unit operation: The sampled data are processed by the symmetrical component method to obtain the three-phase fundamental frequency positive sequence voltage and the three-phase fundamental frequency positive sequence current; Calculate the phase difference between the three-phase fundamental frequency positive sequence voltage and the three-phase fundamental frequency positive sequence current; Draw a curve of the phase difference changing with time, and analyze the characteristics of the curve and the polarity of the first peak; S14. Determine the location of the voltage sag source: Determine the location of the voltage sag source based on the polarity of the first peak of the phase difference curve; S2. Voltage and current monitoring and effective value calculation: Real-time monitoring of the operation status of the power grid is carried out at the monitoring point, and the voltage and current data of the monitoring point are specifically measured, including the following specific steps: S21. Monitoring point setting: select a number of monitoring points to ensure that the operation status of the power grid is fully reflected; S22, data acquisition: use high-precision sensors to collect voltage and current data of monitoring points in real time; S23, effective value calculation: processing the collected voltage data to calculate the effective value of each phase voltage; S3. Voltage sag determination and recording: When the effective value of the voltage of one or more phases is detected to be lower than 90% of the rated voltage, the system determines it as a voltage sag event, including the following specific steps: S31, voltage sag determination: compare the effective value of each phase voltage with 90% of the rated voltage in real time. If it is lower than this threshold, it is determined as a voltage sag event; S32, recording voltage sag information: recording the specific time when the voltage sag occurs, and saving the waveform data at that time; S4. Calculation of disturbance voltage and disturbance current: synchronously sampling the signals before and after the voltage sag, and calculating the disturbance voltage and disturbance current, including the following specific steps: S41, synchronous sampling: before and after the voltage sag occurs, the voltage and current signals are synchronously sampled; S42, difference calculation: performing difference calculation on the sampled data to obtain a disturbance voltage and a disturbance current; S5, calculation of disturbance power and determination of the location of voltage sag source: calculation of disturbance power and determination of the location of voltage sag source according to the polarity of disturbance power, including the following specific steps: S51, disturbance power calculation: multiply the disturbance voltage by the disturbance current to obtain the disturbance power; S52, determining the location of the voltage sag source: determining the location of the voltage sag source according to the polarity of the disturbance power; S6. Voltage sag characteristics analysis and cause determination: Based on monitoring data and disturbance analysis, conduct an in-depth analysis of voltage sag characteristics and determine the cause of voltage sag, including the following specific steps: S61, data collection: obtaining the monitoring node name, the corresponding relationship between the current and voltage within a predetermined time and time; S62, recording key data: recording the current before the voltage sag and the current value within a predetermined time period after the voltage sag; S63, characteristic analysis: based on the above data, obtain voltage deviation characteristics, current deviation characteristics, loss capacity and voltage sag duration; S64, cause determination: Combine the indicator dimensions to analyze and determine the cause of the voltage sag to improve the accuracy of the determination; S7. AI technology for determining the source of voltage sag: AI technology is used to improve the accuracy of determining the source of voltage sag, including the following specific steps: S71, monitoring data acquisition: monitoring the operation status of the power grid at the monitoring point and acquiring real-time monitoring data; S72, voltage sag determination: AI determines whether a voltage sag event occurs in the power grid; S73, average power calculation: AI calculates the average power of a fundamental wave cycle before the grid voltage sag occurs and the average power of a fundamental wave cycle during the grid voltage sag; S74, active power difference calculation: calculate the difference between the two average powers to obtain the active power difference; S75. Determine the location of the voltage sag source: Based on the flow direction of the active power difference and a predefined reference direction, the AI ​​determines the location of the voltage sag source in the power grid relative to the monitoring point.

[0030] like Figures 1 to 5 As shown, the present technical solution realizes effective monitoring of the voltage and current of the power grid and accurate determination of voltage sag events. Specifically, through the setting of the voltage sag source determination device in step S1, the correct configuration of the device components and the stable transmission of data are ensured, including the configuration of the device components, the operation of the sampling unit, the operation of the data processing unit and the determination of the location of the voltage sag source; through the voltage and current monitoring and effective value calculation in step S2, the real-time monitoring of the power grid operation status and the collection of voltage and current data are realized, including the setting of monitoring points, data collection and effective value calculation processes; through the voltage sag determination and recording in step S3, the determination and recording of voltage sag events are realized, including accurately determining the voltage sag event by comparing the effective value of each phase voltage with the threshold of the rated voltage in real time, and recording the specific time and waveform of the voltage sag. data; through the calculation of disturbance voltage and disturbance current in step S4, and the calculation of disturbance power and determination of the azimuth of voltage sag source in step S5, the impact of voltage sag events on the power grid is deeply analyzed, and the azimuth of voltage sag source is determined according to the polarity of disturbance power; through the voltage sag characteristic analysis and cause determination in step S6, a comprehensive analysis of voltage sag events is carried out, and the cause of voltage sag is accurately determined, including the process of data collection, key data recording, characteristic analysis and cause determination; through the AI ​​technology for voltage sag source determination in step S7, the accuracy of voltage sag source determination is improved by using AI technology, including monitoring data acquisition, voltage sag determination, average power calculation, active power difference calculation and voltage sag source azimuth determination.

[0031] In addition, the AI-based voltage monitoring and voltage sag determination method, medium, and device proposed in the present invention also have the following additional technical features: According to an embodiment of the present invention, the voltage sag source determination device of step S1 further includes the following steps: S15, sampling unit calibration: the sampling unit is calibrated regularly to ensure that it can accurately collect voltage data. The calibration process includes adjusting the sampling frequency and calibrating the sampling accuracy. S16, data processing unit verification: verify the data processing unit to ensure that it can correctly process and analyze the data collected by the sampling unit. The verification process includes testing the data processing algorithm and verifying the accuracy of the data processing results; S17. Self-diagnosis function configuration: configure the self-diagnosis function of the device so that it can monitor the operating status of the device in real time and promptly detect and report potential faults or abnormalities.

[0032] This technical solution ensures the accuracy and reliability of the voltage sag source determination device and improves the stability and fault self-diagnosis capability of the device during operation through the calibration of the sampling unit of S15, the verification of the data processing unit of S16 and the configuration of the self-diagnosis function of S17.

[0033] According to one embodiment of the present invention, in the monitoring point setting of step S21, the same polarity direction of the internal voltage and current transformer of the monitoring point is used as the positive direction of the reference direction. If the bus active power measured by the voltage and current transformers after installation is positive, the reference direction is the same as the active power flow direction; conversely, if the measured bus active power is negative, the reference direction is opposite to the active power flow direction.

[0034] This technical solution defines the same polarity direction of the voltage and current transformers in the monitoring point setting as the positive direction of the reference direction, and determines the relationship between the reference direction and the active power flow direction according to the positive and negative active power, thereby providing an accurate reference benchmark for subsequent voltage and current monitoring and voltage sag determination.

[0035] According to one embodiment of the present invention, in the voltage sag determination of step S31, the voltages relative to the neutral point of the power grid, that is, the difference between the phase voltage and the zero-sequence voltage of the power grid, are monitored. When the voltage of any phase of the three-phase power grid neutral point is less than 90% of the rated phase voltage, it is determined that a voltage sag has occurred.

[0036] This technical solution monitors the voltage of each relative grid neutral point, that is, the difference between the phase voltage and the zero-sequence voltage of the grid, and sets it as a voltage sag when any phase is less than 90% of the rated phase voltage, thereby achieving accurate judgment of voltage sag events.

[0037] According to an embodiment of the present invention, in the difference calculation of step S42, the disturbance voltage and disturbance current monitored by the monitoring point are defined as: (1) Where:

[0038] The solution method for disturbance voltage and disturbance current is: (2) Where: is the number of sampling points in a single cycle, Take a positive integer to represent the fundamental wave period number of the sampling interval during the disturbance and before the disturbance, and the disturbance power is obtained as: (3) Where: is the instantaneous disturbance power; is the average disturbance power.

[0039] This technical solution determines the location of the subsequent voltage sag source by defining and calculating the disturbance voltage and disturbance current, and solving the instantaneous disturbance power and average disturbance power.

[0040] According to an embodiment of the present invention, the cause determination in step S64 includes the following specific steps: S641. Analysis of the propagation path of disturbance power: Use power grid simulation software to establish a power grid model including generators, transformers, lines, and loads; simulate the injection of disturbance power in the model, set the size, polarity, and position of the disturbance power; use the power grid model to track the propagation path of the disturbance power in the power grid and record the power changes of each node; S642, attenuation characteristics analysis: Calculate the attenuation coefficient: Calculate the attenuation coefficient of the disturbance power during the propagation process based on the resistance, inductance and capacitance of the power grid; apply the attenuation coefficient to each node on the propagation path to simulate the actual attenuation of the disturbance power; S643, load and line parameter correction: according to the actual load of the power grid, adjust the load size of each node in the model to reflect the actual power grid operation status; according to the actual line parameter measurement value or calibration result, correct the line parameters in the model to improve the accuracy of the model; S644. Correction and optimization of determination results: Compare the disturbance power distribution obtained by simulation with the actual monitoring data to find out the areas with large differences; according to the comparison results, adjust the line length and impedance of the power grid model to reduce the difference between simulation and reality; use the corrected model to re-simulate and calculate to obtain a more accurate disturbance power distribution, and then determine the location of the voltage sag source.

[0041] This technical solution achieves in-depth analysis and accurate determination of the cause of voltage sag through disturbance power propagation path analysis, attenuation characteristic analysis, load and line parameter correction, and determination result correction and optimization in the cause determination of S64, thereby improving the accuracy and credibility of the determination results.

[0042] According to an embodiment of the present invention, the step S75 of determining the voltage sag source position includes the following specific steps: S751. Use the training set data to train the AI ​​model, and optimize the model parameters through the back propagation algorithm so that the model can accurately determine the source of the voltage sag; S752. Evaluation indicators include the proportion of correctly identified voltage sag sources to the total number, the proportion of correctly identified voltage sag events that actually occurred, and the harmonic mean of accuracy and recall, which can fully reflect the model's determination ability and performance; S753. According to the evaluation results, adjust the learning rate, network structure, and activation function of the model until the optimal parameter combination is found; S754, removing features irrelevant to the determination of the voltage sag source, and increasing the disturbance power, the amplitude and duration of the voltage sag; S755. Integrate the trained AI model into the power grid monitoring system, collect voltage, current, and power, and input them into the AI ​​model to achieve real-time monitoring of the power grid operation status and determine the source of voltage sag; S756. Use AI models to process and analyze real-time data of the power grid to predict potential voltage sag events; the prediction results include the time, location, fault type and fault location of the voltage sag event.

[0043] This technical solution achieves intelligent determination and prediction of voltage sag sources through AI model training, evaluation index setting, model parameter adjustment, feature selection and optimization, model integration into the power grid monitoring system, and real-time data processing and analysis in S75's determination of voltage sag source location, thereby improving the safety and stability of power grid operation.

[0044] Corresponding to the above embodiment, the present invention further provides an electronic device.

[0045] The electronic device of the embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the AI-based voltage monitoring and voltage sag determination method according to the above embodiment of the present invention can be implemented.

[0046] The electronic device according to the embodiment of the present invention is provided with a voltage sag source determination device to ensure the correct configuration of the device and stable data transmission; voltage and current monitoring and effective value calculation are performed to monitor the operation status of the power grid in real time and collect voltage and current data; voltage sag events are determined and recorded by comparing the effective value of the voltage with the rated voltage threshold; the disturbance voltage, current and power are calculated to deeply analyze the impact of the voltage sag on the power grid and determine the location of the voltage sag source; the voltage sag characteristics are comprehensively analyzed and the causes are determined, including data collection, key data recording, characteristic analysis and cause determination; AI technology is used to improve the accuracy of voltage sag source determination, including monitoring data acquisition, voltage sag determination, power calculation and location determination, as an intelligent upgrade and supplement to the first two links.

[0047] Corresponding to the above embodiment, the present invention also proposes a computer-readable storage medium.

[0048] The computer-readable storage medium of the embodiment of the present invention stores a computer program, which, when executed by a processor, can implement the AI-based voltage monitoring and voltage sag determination method according to the above embodiment of the present invention.

[0049] According to the computer-readable storage medium of the embodiment of the present invention, a voltage sag source determination device is set to ensure correct configuration of the device and stable data transmission; voltage and current monitoring and effective value calculation are performed to monitor the operation status of the power grid in real time and collect voltage and current data; voltage sag events are determined and recorded by comparing the effective value of the voltage with the rated voltage threshold; the disturbance voltage, current and power are calculated, the impact of the voltage sag on the power grid is deeply analyzed, and the location of the sag source is determined; the voltage sag characteristics are comprehensively analyzed and the causes are determined, including data collection, key data recording, characteristic analysis and cause determination; AI technology is used to improve the accuracy of voltage sag source determination, including monitoring data acquisition, voltage sag determination, power calculation and location determination, as an intelligent upgrade and supplement to the first two links.

[0050] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" explicitly or implicitly include one or more of the features. "Multiple" means two or more, unless otherwise clearly and specifically defined.

[0051] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, fixed connection, detachable connection, or integration; mechanical connection, electrical connection; direct connection, indirect connection through an intermediate medium, internal connection between two elements or interaction between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention will be understood according to specific circumstances.

[0052] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature means that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature means that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0053] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described are combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art will combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0054] Any process or method description in the flowchart or otherwise described herein is understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions are not performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0055] The logic and / or steps represented in the flowchart or otherwise described herein, for example, are considered to be an ordered list of executable instructions for implementing logical functions, and are specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that fetches instructions from an instruction execution system, device or apparatus and executes instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" is any device that contains, stores, communicates, propagates or transmits a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (R), a read-only memory (ROM), an erasable and editable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium is even a paper or other suitable medium on which the program is printed, because the program is obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting or processing in other suitable ways if necessary, and then storing it in a computer memory.

[0056] It should be understood that the various parts of the present invention are implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, a plurality of steps or methods are implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PG based on AI voltage monitoring and voltage sag determination method, medium and device), a field programmable gate array (FPG based on AI voltage monitoring and voltage sag determination method, medium and device), etc.

[0057] A person of ordinary skill in the art would understand that all or part of the steps carried out in the above-mentioned embodiment method are implemented by instructing related hardware through a program, and the program is stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0058] In addition, each functional unit in each embodiment of the present invention is integrated into a processing module, each unit exists physically separately, or two or more units are integrated into one module. The above-mentioned integrated module is implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it is also stored in a computer-readable storage medium.

[0059] Although the embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, substitute and modify the above embodiments within the scope of the present invention.

Claims

1. A voltage monitoring and voltage sag determination method based on AI, characterized in that: The steps include: S1. Setting of voltage sag source determination device: a dedicated device for voltage sag source determination, including the following specific steps: S11. Device component configuration: Confirm that the voltage sag source determination device includes a sampling unit and a data processing unit; Verify the connection status between the sampling unit and the power grid monitoring device to ensure stable data transmission; Check the algorithm implementation of the data processing unit to ensure that the symmetrical component method and phase difference calculation are accurate; S12, sampling unit operation: Set the sampling frequency and sampling time window to capture the three-phase voltage and three-phase current waveforms; Extract the waveform data of a voltage sag event from the power grid monitoring device and perform preliminary verification; S13, data processing unit operation: The sampled data are processed by the symmetrical component method to obtain the three-phase fundamental frequency positive sequence voltage and the three-phase fundamental frequency positive sequence current; Calculate the phase difference between the three-phase fundamental frequency positive sequence voltage and the three-phase fundamental frequency positive sequence current; Draw a curve of the phase difference changing with time, and analyze the characteristics of the curve and the polarity of the first peak; S14. Determine the location of the voltage sag source: Determine the location of the voltage sag source based on the polarity of the first peak of the phase difference curve; S2. Voltage and current monitoring and effective value calculation: Real-time monitoring of the operation status of the power grid is carried out at the monitoring point, and the voltage and current data of the monitoring point are specifically measured, including the following specific steps: S21. Monitoring point setting: select a number of monitoring points to ensure that the operation status of the power grid is fully reflected; S22, data acquisition: use high-precision sensors to collect voltage and current data of monitoring points in real time; S23, effective value calculation: processing the collected voltage data to calculate the effective value of each phase voltage; S3. Voltage sag determination and recording: When the effective value of the voltage of one or more phases is detected to be lower than 90% of the rated voltage, the system determines it as a voltage sag event, including the following specific steps: S31, voltage sag determination: compare the effective value of each phase voltage with 90% of the rated voltage in real time. If it is lower than this threshold, it is determined as a voltage sag event; S32, recording voltage sag information: recording the specific time when the voltage sag occurs, and saving the waveform data at that time; S4. Calculation of disturbance voltage and disturbance current: synchronously sampling the signals before and after the voltage sag, and calculating the disturbance voltage and disturbance current, including the following specific steps: S41, synchronous sampling: before and after the voltage sag occurs, the voltage and current signals are synchronously sampled; S42, difference calculation: performing difference calculation on the sampled data to obtain a disturbance voltage and a disturbance current; S5, calculation of disturbance power and determination of the location of the voltage sag source: calculation of the disturbance power and determination of the location of the voltage sag source according to the polarity of the disturbance power, including the following specific steps: S51, disturbance power calculation: multiply the disturbance voltage by the disturbance current to obtain the disturbance power; S52, determining the location of the voltage sag source: determining the location of the voltage sag source according to the polarity of the disturbance power; S6. Voltage sag characteristics analysis and cause determination: Based on monitoring data and disturbance analysis, conduct an in-depth analysis of voltage sag characteristics and determine the cause of voltage sag, including the following specific steps: S61, data collection: obtaining the monitoring node name, the corresponding relationship between the current and voltage within a predetermined time and time; S62, recording key data: recording the current before the voltage sag and the current value within a predetermined time period after the voltage sag; S63, characteristic analysis: based on the above data, obtain voltage deviation characteristics, current deviation characteristics, loss capacity and voltage sag duration; S64, cause determination: Combine the indicator dimensions to analyze and determine the cause of the voltage sag to improve the accuracy of the determination; S7. AI technology for determining the source of voltage sag: AI technology is used to improve the accuracy of determining the source of voltage sag, including the following specific steps: S71, monitoring data acquisition: monitoring the operation status of the power grid at the monitoring point and acquiring real-time monitoring data; S72, voltage sag determination: AI determines whether a voltage sag event occurs in the power grid; S73, average power calculation: AI calculates the average power of a fundamental wave cycle before the grid voltage sag occurs and the average power of a fundamental wave cycle during the grid voltage sag; S74, active power difference calculation: calculate the difference between the two average powers to obtain the active power difference; S75. Determine the location of the voltage sag source: Based on the flow direction of the active power difference and a predefined reference direction, the AI ​​determines the location of the voltage sag source in the power grid relative to the monitoring point.

2. The AI-based voltage monitoring and voltage sag determination method according to claim 1, characterized in that: The voltage sag source determination device of step S1 further includes the following steps: S15, sampling unit calibration: the sampling unit is calibrated regularly to ensure that it can accurately collect voltage data. The calibration process includes adjusting the sampling frequency and calibrating the sampling accuracy. S16, data processing unit verification: verify the data processing unit to ensure that it can correctly process and analyze the data collected by the sampling unit. The verification process includes testing the data processing algorithm and verifying the accuracy of the data processing results; S17. Self-diagnosis function configuration: configure the self-diagnosis function of the device so that it can monitor the operating status of the device in real time and promptly detect and report potential faults or abnormalities.

3. The voltage monitoring and voltage sag determination method based on AI as claimed in claim 2, characterized in that: In the monitoring point setting of step S21, the same polarity direction of the internal voltage and current transformer of the monitoring point is used as the positive direction of the reference direction. If the bus active power measured by the voltage and current transformers after installation is positive, the reference direction is the same as the active power flow direction; conversely, if the measured bus active power is negative, the reference direction is opposite to the active power flow direction.

4. The AI-based voltage monitoring and voltage sag determination method according to claim 3, characterized in that: In the voltage sag determination of step S31, the voltages relative to the neutral point of the power grid, i.e., the difference between the phase voltage and the zero-sequence voltage of the power grid, are monitored. When the voltage of any phase of the three-phase power grid neutral point is less than 90% of the rated phase voltage, it is determined that a voltage sag occurs.

5. The AI-based voltage monitoring and voltage sag determination method according to claim 4, characterized in that: In the difference calculation of step S42, the disturbance voltage and disturbance current monitored by the monitoring point are defined as: (1) Where: The solution method for disturbance voltage and disturbance current is: (2) Where: is the number of sampling points in a single cycle, Take a positive integer to represent the fundamental wave period number of the sampling interval during the disturbance and before the disturbance, and the disturbance power is obtained as: (3) Where: is the instantaneous disturbance power; is the average disturbance power.

6. The AI-based voltage monitoring and voltage sag determination method according to claim 5, characterized in that: The cause determination in step S64 includes the following specific steps: S641. Analysis of the propagation path of disturbance power: Use power grid simulation software to establish a power grid model including generators, transformers, lines, and loads; simulate the injection of disturbance power in the model, set the size, polarity, and position of the disturbance power; use the power grid model to track the propagation path of the disturbance power in the power grid and record the power changes of each node; S642, attenuation characteristics analysis: calculation of attenuation coefficient: according to the resistance, inductance and capacitance of the power grid, calculate the attenuation coefficient of the disturbance power during the propagation process; The attenuation coefficient is applied to each node on the propagation path to simulate the actual attenuation of the disturbance power; S643, load and line parameter correction: according to the actual load of the power grid, adjust the load size of each node in the model to reflect the actual power grid operation status; According to the actual line parameter measurement values ​​or calibration results, the line parameters in the model are corrected to improve the accuracy of the model; S644, correction and optimization of determination results: comparing the disturbance power distribution obtained by simulation with the actual monitoring data to find out the area with large differences; According to the comparison results, the line length and impedance of the power grid model are adjusted to reduce the difference between simulation and reality; the simulation calculation is re-performed using the corrected model to obtain a more accurate disturbance power distribution, and then determine the location of the voltage sag source.

7. The AI-based voltage monitoring and voltage sag determination method according to claim 6, characterized in that: The step S75 of determining the voltage sag source position includes the following specific steps: S751. Use the training set data to train the AI ​​model, and optimize the model parameters through the back propagation algorithm so that the model can accurately determine the source of the voltage sag; S752. Evaluation indicators include the proportion of correctly identified voltage sag sources to the total number, the proportion of correctly identified voltage sag events that actually occurred, and the harmonic mean of accuracy and recall, which can fully reflect the model's determination ability and performance; S753. According to the evaluation results, adjust the learning rate, network structure, and activation function of the model until the optimal parameter combination is found; S754, removing features irrelevant to the determination of the voltage sag source, and increasing the disturbance power, the amplitude and duration of the voltage sag; S755. Integrate the trained AI model into the power grid monitoring system, collect voltage, current, and power, and input them into the AI ​​model to achieve real-time monitoring of the power grid operation status and determine the source of voltage sag; S756. Use AI models to process and analyze real-time data of the power grid to predict potential voltage sag events; the prediction results include the time, location, fault type and fault location of the voltage sag event.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the AI-based voltage monitoring and voltage sag determination method according to any one of claims 1 to 7 is implemented.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the AI-based voltage monitoring and voltage sag determination method according to any one of claims 1 to 7 is implemented.

Images