Power grid environment monitoring system and method based on intelligent sensor

Abstract

The invention relates to the technical field of intelligent power grid monitoring, in particular to a power grid environment monitoring system and method based on an intelligent sensor, and the system comprises a data collection module which is used for collecting power grid monitoring data; the data processing module is used for processing the power grid monitoring data; the monitoring operation module is used for monitoring the electromagnetic environment state of the power grid according to the electromagnetic intensity and optimizing the electromagnetic intensity according to the rated voltage of the equipment; the prediction model construction module is used for constructing a prediction model according to the electromagnetic intensity historical data; the prediction result analysis module is used for monitoring the future electromagnetic intensity state according to the predicted maximum peak value of the future electromagnetic intensity; and the decision execution module is used for judging the equipment fault reason according to the judgment result of the future electromagnetic intensity state and processing the equipment. According to the invention, the electromagnetic intensity influence in the future power grid environment is automatically monitored, so that communication interruption is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of smart grid monitoring, and particularly to a power grid environment monitoring system and method based on intelligent sensors. Background Art

[0002] In a complex power grid environment, there are limitations in technical implementation. The monitoring range and data accuracy of the smart grid monitoring system need to be improved. The existing technology optimizes resource allocation, resulting in low monitoring efficiency and the inability to fully utilize the advantages of the smart grid. A large number of electrical equipment and electronic systems are close to each other, which easily generates electromagnetic interference. The high-frequency electromagnetic signals generated by power electronic equipment will interfere with nearby communication equipment and control equipment. At the same time, the stability and reliability of the system need to be improved. In addition, it is impossible to automatically monitor the impact of electromagnetic intensity in the future power grid environment, resulting in the inability to replace and maintain power grid equipment in advance, thereby causing communication interruption.

[0003] Chinese Patent Publication No.: CN110375789B discloses a power grid operation environment monitoring device. Aiming at the problem that the existing monitoring device is not convenient for monitoring the environment from multiple angles and cannot adjust the height of the monitoring device, resulting in dead corners in monitoring, the following solution is proposed. It includes a fixing plate. A fixing groove is opened at the top of the fixing plate. A motor groove is opened on the bottom inner wall of the fixing groove. A servo motor is fixedly installed on the bottom inner wall of the motor groove. The output shaft of the servo motor extends to the outside of the motor groove and is fixedly installed with a first roller. Two symmetrically arranged fixing blocks are fixedly installed on the bottom inner wall of the fixing groove. A circular hole is opened on one side of the fixing block. A rotating seat is rotatably installed in the circular hole. A square plate is fixedly installed on one side of one of the two fixing blocks. A square hole is opened on the top of the square plate. It can be seen that this solution cannot automatically monitor the impact of electromagnetic intensity in the future power grid environment, resulting in interference of high-frequency electromagnetic signals to nearby communication equipment and control equipment, thereby causing communication interruption. Summary of the Invention

[0004] Therefore, the present invention provides a power grid environment monitoring system and method based on intelligent sensors to overcome the problem in the prior art that it is impossible to automatically monitor the impact of electromagnetic intensity in the future power grid environment, resulting in interference of high-frequency electromagnetic signals to nearby communication equipment and control equipment, thereby causing communication interruption.

[0005] To achieve the above object, on the one hand, the present invention provides a power grid environment monitoring system based on intelligent sensors. The system includes: A data acquisition module for collecting power grid monitoring data; A data processing module for processing the power grid monitoring data to obtain standard power grid monitoring data, including equipment rated voltage, equipment current, current element, equipment fault status coefficient, and environmental parameters; A monitoring and calculation module for calculating the electromagnetic intensity according to the current element, monitoring the power grid electromagnetic environment status according to the electromagnetic intensity, optimizing the electromagnetic intensity according to the equipment rated voltage, adjusting the equipment rated voltage according to the equipment fault status coefficient, calculating the environmental index according to the environmental parameters, and optimizing the equipment fault status coefficient according to the environmental index; A prediction model construction module for constructing a prediction model according to the historical electromagnetic intensity data and outputting an electromagnetic prediction result, including predicting the highest peak value of the future electromagnetic intensity and predicting the duration of the future strong electromagnetic field; A prediction result analysis module for monitoring the future electromagnetic intensity status according to the predicted highest peak value of the future electromagnetic intensity, optimizing the predicted highest peak value of the future electromagnetic intensity according to the predicted duration of the future strong electromagnetic field, and adjusting the predicted duration of the future strong electromagnetic field according to the equipment current; A decision execution module for judging the cause of equipment failure according to the judgment result of the future electromagnetic intensity status and processing the equipment according to the cause of equipment failure.

[0006] Further, when the monitoring and calculation module monitors the standard power grid monitoring data, it calculates the electromagnetic intensity B according to the current element idl, and sets , where r is the distance at which the electromagnetic intensity B is generated in the current element idl, and μ 0 is the vacuum permeability, and μ 0 = 4π×10 -7 T·m / A. Compare the electromagnetic intensity B with the preset electromagnetic intensity B0, and judge the electromagnetic environment status of the power grid equipment according to the comparison result, where: When B ≤ B0, it is determined that the electromagnetic environment status of the power grid equipment is normal; When B > B0, it is determined that the electromagnetic environment status of the power grid equipment is abnormal.

[0007] Further, when the monitoring and calculation module optimizes the electromagnetic intensity B, it compares the equipment rated voltage U with the preset equipment rated voltage U0, judges the voltage area where the equipment is located according to the comparison result, and optimizes the electromagnetic intensity B according to the judgment result, where: When U ≤ U0, it is determined that the voltage area where the equipment is located is the low-voltage area, and at this time, the electromagnetic intensity B is not optimized; When U > U0, it is determined that the voltage region where the device is located is the high-voltage region. At this time, the electromagnetic intensity B is optimized, and the optimized electromagnetic intensity is B1. It is set that B1 = U1 × B, where U1 is the voltage parameter, and U1 = U0 × e -1.23U , and e is the base of the natural logarithm.

[0008] Further, when the monitoring operation module adjusts the rated voltage U of the device, it compares the device fault status coefficient G with the preset device fault status coefficient G0, judges the device fault status according to the comparison result, and adjusts the rated voltage U of the device according to the judgment result, where: When G ≤ G0, it is determined that the device fault status is normal and has no impact on the rated voltage U of the device. At this time, the rated voltage U of the device is not adjusted; When G > G0, it is determined that the device fault status is abnormal and has an impact on the rated voltage U of the device. At this time, the rated voltage U of the device is adjusted, and the adjusted rated voltage of the device is U2. It is set that U2 = 0.5 × g × U, where g is the device status value, and g = 1.38 × G0 / G.

[0009] Further, when the monitoring operation module optimizes the device fault status coefficient G, it calculates the environmental index H according to the weather influence coefficient T, the temperature influence coefficient W, the humidity influence coefficient S, and the geographical environment influence coefficient D. It is set that H = 0.35T + 0.3W + 0.2S + 0.15D, compares the environmental index H with the preset environmental index H0, judges the environmental temperature range of the power grid device according to the comparison result, and optimizes the device fault status coefficient G according to the judgment result, where: When H ≤ H0, it is determined that the environmental temperature range of the power grid device is normal and has no impact on the power grid device. At this time, the device status coefficient G is not optimized; When H > H0, it is determined that the environmental temperature range of the power grid device is abnormal and has an impact on the power grid device. At this time, the device status coefficient G is optimized, and the optimized device status coefficient is G1. It is set that G1 = α × G, where α is the environmental coefficient, and 0.38 < α < 1.45.

[0010] Further, when constructing the prediction model, the prediction model construction module predicts the historical electromagnetic intensity data through the prediction model, inputs the historical electric field intensity data into the prediction model to obtain the electromagnetic prediction result, where the electromagnetic prediction result includes the predicted future maximum peak dB of the electromagnetic intensity and the predicted future duration dT of the strong electromagnetic field. A prediction model is constructed. Specifically, the historical electric field intensity data is divided into a 70% prediction training set, a 15% prediction validation set, and a 15% prediction test set. The prediction training set is input into the LSTM model for training the LSTM model, and the prediction validation set is input into the trained LSTM model to perform hyperparameter iterative optimization on the trained LSTM model. Then, the prediction test set is input into the iteratively optimized LSTM model to perform prediction testing on the iteratively optimized LSTM model, obtaining the electromagnetic prediction test result. Let the total number of samples in the prediction test set be f0, the number of correctly predicted test samples be f, and the prediction test accuracy be F. Set F = f / f0. Compare the prediction test accuracy F with the preset prediction test accuracy F0, judge the training compliance of the iteratively optimized LSTM model according to the comparison result, and output according to the judgment result. Among them: When F≥F0, it is determined that the training of the iteratively optimized LSTM model is qualified, and the iteratively optimized LSTM model is output as the prediction model; When F<F0, it is determined that the training of the iteratively optimized LSTM model is unqualified. Update the historical electric field intensity database to obtain the updated historical electric field intensity database, and use the historical electric field intensity database to train, perform hyperparameter iterative optimization, and prediction testing on the LSTM model until the training of the LSTM model is qualified.

[0011] Further, when monitoring the future electromagnetic intensity state, the prediction result analysis module compares the predicted future maximum peak dB of the electromagnetic intensity with the electromagnetic intensity B, and judges the future electromagnetic intensity state according to the comparison result. Among them: When dB≤B, it is determined that the future electromagnetic intensity state is normal; When dB>B, it is determined that the future electromagnetic intensity state is abnormal; When the prediction result analysis module optimizes the predicted future maximum peak dB of the electromagnetic intensity, it compares the predicted future duration dT of the strong electromagnetic field with the preset duration dT0 of the strong electromagnetic field, judges the abnormal change range of the future electromagnetic intensity in the predicted power grid environment according to the comparison result, and optimizes the predicted future maximum peak dB of the electromagnetic intensity according to the judgment result. Among them: When dT≤dT0, it is determined that the abnormal change range of the future electromagnetic intensity in the predicted power grid environment is a reasonable range, and at this time, the predicted future maximum peak dB of the electromagnetic intensity is not optimized; When dT > dT0, it is determined that the predicted abnormal change range of the future electromagnetic intensity in the power grid environment is an unreasonable range. At this time, the predicted highest peak value dB of the future electromagnetic intensity is optimized, and the predicted highest peak value of the future electromagnetic intensity after optimization is dB1. It is set that dB1 = (dT - dT0) × dB; Further, when the prediction result analysis module adjusts the predicted future strong electromagnetic duration dT, it compares the device current I with the preset device current I0, judges the state of the device current according to the comparison result, and adjusts the predicted future strong electromagnetic duration dT according to the judgment result, where: When I ≤ I0, it is determined that the state of the device current is in the normal range, and at this time, the predicted future strong electromagnetic duration dT is not adjusted; When I > I0, it is determined that the state of the device current is in the abnormal range. At this time, the predicted future strong electromagnetic duration dT is adjusted, and the adjusted predicted future strong electromagnetic duration is dT1. It is set that dT1 = i × dT, where i is the current change coefficient and 0.78 < i < 1.

[0012] Further, when the decision execution module processes the device, it judges the device failure cause according to the judgment result of the future electromagnetic intensity state, and processes the device according to the judgment result, where: When the judgment result of the future electromagnetic intensity state is that the predicted abnormal change range of the future electromagnetic intensity in the power grid environment is in the unreasonable range, it is determined that the device failure cause is a device failure. At this time, the device is processed by adjusting the load distribution and increasing the device capacity; When the judgment result of the future electromagnetic intensity state is that the state of the device current is in the abnormal range, it is determined that the device failure cause is a grounding failure. At this time, electromagnetic shielding measures are adopted to reduce the abnormal electromagnetic intensity. For sensitive devices and personnel activity areas in the substation, electromagnetic shielding covers are installed to reduce electromagnetic radiation.

[0013] On the other hand, the present invention also provides a power grid environment monitoring method based on intelligent sensors, and the method includes: Step S1, collecting power grid monitoring data; Step S2, processing the power grid monitoring data to obtain standard power grid monitoring data, which includes device rated voltage, device current, current element, device failure state coefficient, and environmental parameters; Step S3, calculating the electromagnetic intensity according to the current element, and monitoring the power grid electromagnetic environment state according to the electromagnetic intensity; Step S4, optimizing the electromagnetic intensity according to the device rated voltage; Step S5: Adjust the rated voltage of the device according to the device fault status coefficient; Step S6: Calculate the environment index according to the environment parameters, and optimize the device fault status coefficient according to the environment index; Step S7: Construct a prediction model based on the historical electromagnetic intensity data, and output the electromagnetic prediction results, including predicting the highest peak value of the future electromagnetic intensity and predicting the duration of the future strong electromagnetic field; Step S8: Monitor the future electromagnetic intensity status according to the predicted highest peak value of the future electromagnetic intensity, and optimize the predicted highest peak value of the future electromagnetic intensity according to the predicted duration of the future strong electromagnetic field; Step S9: Adjust the predicted duration of the future strong electromagnetic field according to the device current; Step S10: Judge the device fault cause according to the judgment result of the future electromagnetic intensity status, and process the device according to the device fault cause.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows. The system ensures the timeliness and accuracy of data through the real-time collection of power grid monitoring data by the data collection module. The system standardizes the power grid monitoring data through the data processing module, extracts key device parameters and environment parameters, so as to provide a clear data view for subsequent analysis and operation. The system accurately calculates the electromagnetic intensity and accurately judges the power grid electromagnetic environment status through the monitoring operation module, optimizes the electromagnetic intensity according to the rated voltage of the device, thereby improving the operation efficiency and safety of the device, dynamically adjusts and optimizes the rated voltage and environment index of the device, and further improves the adaptability and stability of the power grid. The system constructs an accurate prediction model through the prediction model construction module, so as to accurately predict the highest peak value of the future electromagnetic intensity and the duration of the strong electromagnetic field, thereby providing a scientific basis for the preventive maintenance of the power grid. The system deeply analyzes and optimizes the prediction results through the prediction result analysis module, realizes the automatic monitoring of the influence of the electromagnetic intensity in the future power grid environment, thereby improving the accuracy and practicality of the prediction results, avoiding communication interruption, and ensuring the safe and stable operation of the power grid. The system realizes the rapid judgment and effective processing of the device fault cause through the decision execution module, improves the operation efficiency of the power grid communication equipment and control equipment, reduces the influence of electromagnetic radiation, and thus avoids communication interruption.

[0015] In particular, the data collection module collects power grid monitoring data through intelligent sensors, realizes the real-time monitoring of the power grid operation status, and improves the automation degree and accuracy of data collection.

[0016] In particular, the data processing module processes the power grid monitoring data, combines time-domain feature extraction and frequency-domain feature conversion technologies, realizes the analysis and optimization of the power grid monitoring data, improves the reliability and security of the power grid, and thus ensures the stable operation of the power system.

[0017] In particular, the monitoring and operation module realizes the accurate evaluation and optimization of the power grid equipment status and environmental factors through comprehensive monitoring and optimization algorithms, and improves the safety and stability of the power grid operation.

[0018] In particular, the prediction model construction module constructs a prediction model, trains the historical data of electromagnetic intensity using the LSTM model, realizes the accurate prediction of the highest peak dB of future electromagnetic intensity and the strong electromagnetic duration dT, improves the accuracy of electromagnetic prediction, and thus ensures the reliability of the prediction model.

[0019] In particular, the prediction result analysis module realizes the accurate prediction of the future electromagnetic intensity state through comprehensive judgment and optimization adjustment, improves the accuracy and practicality of the prediction result, and ensures the safe and stable operation of the power grid.

[0020] In particular, the decision execution module realizes the rapid judgment and effective processing of the causes of equipment failures through accurate prediction and intelligent decision-making, improves the operation efficiency of power grid communication equipment and control equipment, reduces the influence of electromagnetic radiation, and thus avoids communication interruption. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a schematic structural diagram of the power grid environment monitoring system based on intelligent sensors in this embodiment; Figure 2 It is a schematic flow diagram of the power grid environment monitoring method based on intelligent sensors in this embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0022] In order to make the objectives and advantages of the present invention clearer and more understandable, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0023] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and do not limit the protection scope of the present invention.

[0024] It should be noted that in the description of the present invention, the terms indicating directions or positional relationships such as "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention.

[0025] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and defined, the terms "installation", "connection", and "coupling" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0026] Please refer to Figure 1 as shown, which is a schematic structural diagram of the power grid environment monitoring system based on intelligent sensors in this embodiment. The system includes: A data acquisition module for acquiring power grid monitoring data; A data processing module for processing the power grid monitoring data to obtain standard power grid monitoring data, which includes the rated voltage of the device, the device current, the current element, the device fault status coefficient, and the environmental parameters. The data processing module is connected to the data acquisition module; A monitoring operation module for calculating the electromagnetic intensity according to the current element, monitoring the power grid electromagnetic environment status according to the electromagnetic intensity, optimizing the electromagnetic intensity according to the rated voltage of the device, adjusting the rated voltage of the device according to the device fault status coefficient, calculating the environmental index according to the environmental parameters, and optimizing the device fault status coefficient according to the environmental index. The monitoring operation module is connected to the data processing module; A prediction model construction module for constructing a prediction model according to the historical electromagnetic intensity data and outputting an electromagnetic prediction result, which includes predicting the highest peak value of the future electromagnetic intensity and predicting the duration of the future strong electromagnetic field. The prediction model construction module is connected to the monitoring operation module; A prediction result analysis module for monitoring the future electromagnetic intensity status according to the predicted highest peak value of the future electromagnetic intensity, optimizing the predicted highest peak value of the future electromagnetic intensity according to the predicted duration of the future strong electromagnetic field, and adjusting the predicted duration of the future strong electromagnetic field according to the device current. The prediction result analysis module is connected to the prediction model construction module; A decision execution module, which is used to judge the cause of equipment failure according to the judgment result of the future electromagnetic intensity state, and process the equipment according to the cause of equipment failure. The decision execution module is connected to the prediction result analysis module.

[0027] Specifically, the system is set in the power grid environment monitoring terminal of the intelligent sensor. By integrating the data acquisition, processing, monitoring, prediction model construction, prediction result analysis and decision execution modules, the system can comprehensively and accurately monitor and analyze the electromagnetic environment state of the power grid, further realize the automatic monitoring of the impact of electromagnetic intensity in the future power grid environment, and then effectively judge the cause of equipment failure and take corresponding treatment measures, so as to improve the safety and stability of power grid operation, reduce the risks and losses brought by equipment failure, improve the operation efficiency of power grid communication equipment and control equipment, reduce the impact of electromagnetic radiation, and thus avoid communication interruption. Among them, the system ensures the timeliness and accuracy of data by real-time collecting power grid monitoring data through the data acquisition module. The system standardizes the power grid monitoring data through the data processing module and extracts key equipment parameters and environmental parameters to provide a clear data view for subsequent analysis and operation. The system accurately calculates the electromagnetic intensity and accurately judges the electromagnetic environment state of the power grid through the monitoring operation module, optimizes the electromagnetic intensity according to the rated voltage of the equipment, improves the operation efficiency and safety of the equipment, dynamically adjusts and optimizes the rated voltage of the equipment and the environmental index, and further improves the adaptability and stability of the power grid. The system constructs an accurate prediction model through the prediction model construction module to accurately predict the highest peak value of future electromagnetic intensity and the duration of strong electromagnetic, providing a scientific basis for the preventive maintenance of the power grid. The system deeply analyzes and optimizes the prediction results through the prediction result analysis module, realizes the automatic monitoring of the impact of electromagnetic intensity in the future power grid environment, improves the accuracy and practicability of the prediction results, and thus avoids communication interruption, ensuring the safe and stable operation of the power grid. The system realizes the rapid judgment and effective treatment of the cause of equipment failure through the decision execution module, improves the operation efficiency of power grid communication equipment and control equipment, reduces the impact of electromagnetic radiation, and thus avoids communication interruption.

[0028] Specifically, when the data acquisition module collects power grid monitoring data, it collects the power grid monitoring data through an intelligent sensor.

[0029] Specifically, the power grid monitoring data refers to the set of power grid environment data collected by intelligent sensors, including device voltage, device current I, device power, ambient temperature, and ambient humidity. The device voltage refers to the potential difference across the device in the power grid. The device current I refers to the rate of charge flow through the device in the power grid. The device power refers to the work done by the device per unit time. The ambient temperature refers to the temperature of the surrounding environment where the power grid device is located. The ambient humidity refers to the content of water vapor in the air of the surrounding environment where the power grid device is located. The intelligent sensors refer to the set of sensors used to collect power grid monitoring data, including voltage sensors, current sensors, power sensors, temperature sensors, and humidity sensors. The data acquisition module collects the device voltage through the voltage sensor, such as the rated voltage of the device. The data acquisition module collects the device current I through the current sensor, such as the current element idl. The data acquisition module collects the device power through the power sensor. The data acquisition module collects the ambient temperature through the temperature sensor, such as the weather influence coefficient and the temperature influence coefficient. The data acquisition module collects the ambient humidity through the humidity sensor, such as the humidity coefficient and the geographical environment influence coefficient.

[0030] Specifically, the data acquisition module collects the power grid monitoring data through intelligent sensors to achieve real-time monitoring of the power grid operation status and improve the automation degree and accuracy of data acquisition.

[0031] Specifically, when processing the power grid monitoring data, the data processing module processes the power grid monitoring data through data processing methods to obtain the processed power grid monitoring data, extracts the time-domain features of the processed power grid monitoring data, and uses the fast Fourier transform FFT to convert the data from the time-domain features to the frequency-domain features to obtain the standard power grid monitoring data, which includes the rated voltage of the device, the device current, the current element idl, the device fault status coefficient, and the environmental parameters.

[0032] Specifically, the data processing method refers to a method for cleaning, sorting, and converting original power grid monitoring data, including outlier processing, missing value processing, and normalization processing. The outlier processing refers to setting reasonable thresholds to identify and remove outliers. The missing value processing refers to the process of processing missing data in the dataset. The normalization processing refers to converting data in different ranges to the same scale. The processed power grid monitoring data refers to the data processed by the data processing method. The time-domain feature extraction refers to extracting time-related features from the processed power grid monitoring data, such as waveforms, peaks, and periods. The fast Fourier transform (FFT) refers to a mathematical algorithm for converting a signal from the time domain to the frequency domain. The frequency-domain feature refers to the performance of the signal in the frequency domain, such as frequency distribution, main frequency, and secondary frequency. The standard power grid monitoring data refers to the dataset after processing and feature extraction. The rated voltage of the device refers to the highest voltage value that the device can withstand under normal working conditions. The device current refers to the magnitude of the current flowing through the device during operation. The current element idl refers to a component of the current signal. The device fault status coefficient refers to an index for evaluating the degree and possibility of device faults. The environmental parameters refer to environmental factors affecting the operating state of power grid devices, including the weather influence coefficient T, the temperature influence coefficient W, the humidity influence coefficient S, and the geographical environment influence coefficient D. The weather influence coefficient T refers to the coefficient for quantifying the impact of weather conditions on power grid devices. The temperature influence coefficient W refers to the coefficient for quantifying the impact of temperature on power grid devices. The humidity influence coefficient S refers to the coefficient for quantifying the impact of humidity on power grid devices. The geographical environment influence coefficient D refers to the coefficient for quantifying the impact of geographical environment factors on power grid devices.

[0033] Specifically, the data processing module processes the power grid monitoring data and combines time-domain feature extraction and frequency-domain feature conversion technologies to analyze and optimize the power grid monitoring data, improve the reliability and security of the power grid, and thus ensure the stable operation of the power system.

[0034] Specifically, when the monitoring operation module monitors the standard power grid monitoring data, it calculates the electromagnetic intensity B based on the current element idl, and sets , where r is the distance at which the electromagnetic intensity B is generated in the current element idl, and μ 0 is the vacuum permeability, and μ 0 = 4π×10-7 T·m / A. It compares the electromagnetic intensity B with the preset electromagnetic intensity B0 and judges the electromagnetic environment state of the power grid device according to the comparison result, where: When B ≤ B0, it is determined that the electromagnetic environment state of the power grid device is normal; When B > B0, it is determined that the electromagnetic environment state of the power grid device is abnormal; When the monitoring and computing module optimizes the electromagnetic intensity B, it compares the rated voltage U of the device with the preset rated voltage U0 of the device, determines the voltage region where the device is located according to the comparison result, and optimizes the electromagnetic intensity B according to the determination result, where: When U ≤ U0, it is determined that the voltage region where the device is located is the low-voltage region, and at this time, the electromagnetic intensity B is not optimized; When U > U0, it is determined that the voltage region where the device is located is the high-voltage region, and at this time, the electromagnetic intensity B is optimized. The optimized electromagnetic intensity is B1, and it is set that B1 = U1 × B, where U1 is the voltage parameter, and U1 = U0 × e -1.23U , and e is the base of the natural logarithm; When the monitoring and computing module adjusts the rated voltage U of the device, it compares the device fault status coefficient G with the preset device fault status coefficient G0, determines the device fault status according to the comparison result, and adjusts the rated voltage U of the device according to the determination result, where: When G ≤ G0, it is determined that the device fault status is normal and has no effect on the rated voltage U of the device, and at this time, the rated voltage U of the device is not adjusted; When G > G0, it is determined that the device fault status is abnormal and has an effect on the rated voltage U of the device, and at this time, the rated voltage U of the device is adjusted. The adjusted rated voltage of the device is U2, and it is set that U2 = 0.5 × g × U, where g is the device status value, and g = 1.38 × G0 / G; When the monitoring and computing module optimizes the device fault status coefficient G, it calculates the environmental index H according to the weather influence coefficient T, the temperature influence coefficient W, the humidity influence coefficient S, and the geographical environment influence coefficient D, and sets H = 0.35T + 0.3W + 0.2S + 0.15D. It compares the environmental index H with the preset environmental index H0, determines the environmental temperature range of the power grid device according to the comparison result, and optimizes the device fault status coefficient G according to the determination result, where: When H ≤ H0, it is determined that the environmental temperature range of the power grid device is normal and has no effect on the power grid device, and at this time, the device status coefficient G is not optimized; When H > H0, it is determined that the environmental temperature range of the power grid device is abnormal and has an effect on the power grid device, and at this time, the device status coefficient G is optimized. The optimized device status coefficient is G1, and it is set that G1 = α × G, where α is the environmental coefficient, and 0.38 < α < 1.45.

[0035] Specifically, the electromagnetic intensity B refers to the magnetic field intensity generated by the current element idl at a point in space. The preset electromagnetic intensity B0 is used to determine whether the electromagnetic environment state of the power grid equipment is normal. In this embodiment, the value of the preset electromagnetic intensity B0 is not limited, and those skilled in the relevant art can freely set it according to the actual situation, as long as it meets the requirement of comparison with the electromagnetic intensity B. For example, the value of the preset electromagnetic intensity B0 can be set to 50 μT. The electromagnetic environment state of the power grid equipment refers to the state of the electromagnetic field environment in which the power grid equipment is located during operation. The preset rated voltage U0 of the equipment is used as a reference for judging the voltage area where the power grid equipment is located. In this embodiment, the value of the preset rated voltage U0 of the equipment is not limited, and those skilled in the relevant art can freely set it according to the actual situation, as long as it meets the requirement of comparison with the rated voltage U of the equipment. For example, the value of the preset rated voltage U0 of the equipment can be set to 220 V. The voltage area where the equipment is located refers to the voltage environment range where the power grid equipment is currently located. The preset equipment fault state coefficient G0 is used to judge the fault state of the power grid equipment. In this embodiment, the range of the preset equipment fault state coefficient G0 is not limited, and those skilled in the relevant art can freely set it according to the actual situation, as long as it meets the requirement of judging the fault state of the power grid equipment. For example, the range of the preset equipment fault state coefficient G0 can be set to 0.7 - 0.9. The equipment fault state refers to the fault situation that occurs during the operation of the power grid equipment. The preset environment index H0 is used to evaluate whether the environment where the power grid equipment is located is in a normal state. In this embodiment, the value of the preset environment index H0 is not limited, and those skilled in the relevant art can freely set it according to the actual situation, as long as it meets the requirement of evaluating whether the environment where the power grid equipment is located is in a normal state. For example, the value of the preset environment index H0 can be set to 0.4. The ambient temperature range of the power grid equipment refers to the safe range of the ambient temperature around the power grid equipment during normal operation.

[0036] Specifically, the monitoring and operation module realizes the accurate evaluation and optimization of the power grid equipment status and environmental factors through comprehensive monitoring and optimization algorithms, improving the safety and stability of power grid operation.

[0037] Specifically, when constructing the prediction model, the prediction model construction module predicts the historical electromagnetic intensity data through the prediction model, inputs the historical electric field intensity data into the prediction model, and obtains the electromagnetic prediction result. The electromagnetic prediction result includes the predicted maximum peak dB of the future electromagnetic intensity and the predicted duration dT of the strong electromagnetic field in the future. A prediction model is constructed. Among them, the historical electric field intensity data is divided into a 70% prediction training set, a 15% prediction validation set, and a 15% prediction test set. The prediction training set is input into the LSTM model to train the LSTM model, and the prediction validation set is input into the trained LSTM model to perform hyperparameter iterative optimization on the trained LSTM model. Then, the prediction test set is input into the iteratively optimized LSTM model to perform prediction testing on the iteratively optimized LSTM model, and the electromagnetic prediction test result is obtained. Set the total number of samples in the prediction test set as f0, the number of correctly predicted test samples as f, and the prediction test accuracy as F. Set F = f / f0. Compare the prediction test accuracy F with the preset prediction test accuracy F0, judge the training compliance of the iteratively optimized LSTM model according to the comparison result, and output according to the judgment result. Among them: When F ≥ F0, it is determined that the training of the iteratively optimized LSTM model is qualified, and the iteratively optimized LSTM model is output as the prediction model; When F < F0, it is determined that the training of the iteratively optimized LSTM model is unqualified. Update the historical electric field intensity database to obtain the updated historical electric field intensity database, and use the historical electric field intensity database to train, perform hyperparameter iterative optimization, and prediction testing on the LSTM model until the training of the LSTM model is qualified.

[0038] Specifically, the prediction model refers to a mathematical model constructed using historical data and algorithms. The historical electromagnetic intensity data refers to the electric field intensity data recorded in the past time, such as the electromagnetic intensity at each time point, the device power change rate, the ambient temperature, and the ambient humidity. The electromagnetic prediction result refers to the value of the future electromagnetic intensity predicted by the prediction model based on the input historical data. The predicted maximum peak dB of the future electromagnetic intensity refers to the maximum value of the electromagnetic intensity predicted by the prediction model within the future time period. The predicted duration dT of the future strong electromagnetic field refers to the duration during which the electromagnetic intensity exceeds the safety threshold within the future time period predicted by the prediction model. The historical electric field intensity database refers to the database storing the historical electromagnetic intensity data. The prediction training set refers to the data set used to train the prediction model. The prediction validation set refers to the data set used to verify the performance of the prediction model. The prediction test set refers to the data set used to test the performance of the prediction model. The LSTM model refers to a special type of recurrent neural network model. The hyperparameter iterative optimization refers to the iterative process of continuously adjusting the hyperparameters of the LSTM model. The electromagnetic prediction test result refers to the prediction result obtained after testing the trained LSTM model using the prediction test set, including the electromagnetic prediction result, the prediction test accuracy F, and the model training compliance status. The prediction test accuracy being F refers to the proportion of the number of correctly predicted test samples to the total number of samples in the prediction test set. The model training compliance status refers to the state of measuring whether the model performance meets the preset standard through evaluation indicators. The total number of samples in the prediction test set refers to the total number of data samples contained in the prediction test set. The number of correctly predicted test samples refers to the number of data samples used for correct prediction. The preset prediction test accuracy F0 refers to the threshold of the prediction test accuracy used to determine whether the LSTM model is trained. In this embodiment, the range of the preset prediction test accuracy F0 is not limited. Those skilled in the relevant art can freely set it according to the actual situation, as long as it meets the requirement of determining whether the LSTM model is trained. For example, the range of the preset prediction test accuracy F0 can be set to 85% - 95%. The training compliance status refers to whether the preset prediction test accuracy F0 is achieved during the training process. The iteratively optimized LSTM model refers to the LSTM model whose prediction test accuracy reaches the preset value F0 after multiple hyperparameter iterative optimizations. The update refers to the update of the historical electric field intensity database. In this embodiment, the specific update method is not limited. Those skilled in the relevant art can freely set it according to the actual situation, as long as it meets the requirement of updating the historical electric field intensity database. For example, the specific update method can be set to big data network update.

[0039] Specifically, the prediction model construction module builds a prediction model and uses the LSTM model to train the historical data of electromagnetic intensity, so as to accurately predict the highest peak dB of future electromagnetic intensity and the strong electromagnetic duration dT, improve the accuracy of electromagnetic prediction, and thus ensure the reliability of the prediction model.

[0040] Specifically, when monitoring the future electromagnetic intensity state, the prediction result analysis module compares the predicted highest peak dB of future electromagnetic intensity with the electromagnetic intensity B, and judges the future electromagnetic intensity state according to the comparison result, where: When dB ≤ B, it is determined that the future electromagnetic intensity state is normal; When dB > B, it is determined that the future electromagnetic intensity state is abnormal; When the prediction result analysis module optimizes the predicted highest peak dB of future electromagnetic intensity, it compares the predicted strong electromagnetic duration dT with the preset strong electromagnetic duration dT0, judges the abnormal change range of the future electromagnetic intensity of the predicted power grid environment according to the comparison result, and optimizes the predicted highest peak dB of future electromagnetic intensity according to the judgment result, where: When dT ≤ dT0, it is determined that the abnormal change range of the future electromagnetic intensity of the predicted power grid environment is a reasonable range, and at this time, the predicted highest peak dB of future electromagnetic intensity is not optimized; When dT > dT0, it is determined that the abnormal change range of the future electromagnetic intensity of the predicted power grid environment is an unreasonable range. At this time, the predicted highest peak dB of future electromagnetic intensity is optimized, and the optimized predicted highest peak of future electromagnetic intensity is dB1, and it is set that dB1 = (dT - dT0) × dB; When the prediction result analysis module adjusts the predicted strong electromagnetic duration dT, it compares the device current I with the preset device current I0, judges the state of the device current according to the comparison result, and adjusts the predicted strong electromagnetic duration dT according to the judgment result, where: When I ≤ I0, it is determined that the state of the device current is in the normal range, and at this time, the predicted strong electromagnetic duration dT is not adjusted; When I > I0, it is determined that the state of the device current is in the abnormal range. At this time, the predicted strong electromagnetic duration dT is adjusted, and the adjusted predicted strong electromagnetic duration is dT1, and it is set that dT1 = i × dT, where i is the current change coefficient and 0.78 < i < 1.

[0041] Specifically, the future electromagnetic intensity state refers to the electromagnetic intensity state within a future time period predicted by the prediction module based on current data and algorithms. The preset strong electromagnetic duration dT0 refers to the normal range for measuring the duration of strong electromagnetic phenomena in the power grid environment. In this embodiment, the range of the preset strong electromagnetic duration dT0 is not limited, and those skilled in the relevant art can freely set it according to the actual situation, as long as it meets the requirement of comparing with the predicted future strong electromagnetic duration dT. For example, the range of the preset strong electromagnetic duration dT0 can be set to 50 ms - 200 ms. The predicted abnormal change range of the future electromagnetic intensity in the power grid environment refers to the possible abnormal change range of the electromagnetic intensity in the power grid environment in the future. The preset device current I0 refers to the reference value used for comparison with the real-time device current I. In this embodiment, the value of the preset device current I0 is not limited, and those skilled in the relevant art can freely set it according to the actual situation, as long as it meets the requirement of comparing with the real-time device current I. For example, the value of the preset device current I0 can be set to 100 A. The state of the device current refers to the state of the current level shown by the device during actual operation relative to the preset device current I0. The current change coefficient is a factor used to adjust the predicted future strong electromagnetic duration dT.

[0042] Specifically, the prediction result analysis module realizes the accurate prediction of the future electromagnetic intensity state through comprehensive judgment and optimization adjustment, improves the accuracy and practicality of the prediction result, and ensures the safe and stable operation of the power grid.

[0043] Specifically, when the decision execution module processes the device, it judges the cause of the device failure according to the judgment result of the future electromagnetic intensity state, and processes the device according to the judgment result, where: When the judgment result of the future electromagnetic intensity state is that the predicted abnormal change range of the future electromagnetic intensity in the power grid environment is within an unreasonable range, it is determined that the cause of the device failure is a device failure. At this time, the device is processed by adjusting the load distribution and increasing the device capacity; When the judgment result of the future electromagnetic intensity state is that the state of the device current is within an abnormal range, it is determined that the cause of the device failure is a grounding failure. At this time, electromagnetic shielding measures are adopted to reduce the abnormal electromagnetic intensity. For sensitive devices and personnel activity areas in the substation, electromagnetic shielding covers are installed to reduce electromagnetic radiation.

[0044] Specifically, the equipment refers to various electrical equipment in the power grid, including transformers and switchgear cabinets. The transformer refers to a device that uses the principle of electromagnetic induction to change the AC voltage. The switchgear cabinet refers to a cabinet in which all internal electrical and mechanical connections are completed by the manufacturer, such as circuit breakers, disconnectors, load switches, operating mechanisms, and instrument transformers. The cause of equipment failure refers to the specific reason that causes the performance of the equipment to decline due to failure. The equipment failure refers to the abnormal state that occurs during the normal operation of the equipment. The load distribution refers to the reasonable distribution of power loads in the power grid. Increasing the equipment capacity refers to increasing the rated capacity of the equipment. The ground fault refers to the electrical connection between the electrical equipment and the ground, resulting in the abnormal operation of the equipment. The electromagnetic shielding measure refers to the use of shielding materials to prevent the electromagnetic field from affecting specific areas and equipment. The sensitive equipment in the substation refers to the equipment whose performance declines and is damaged due to electromagnetic interference, such as measuring instruments, control devices, and communication equipment. The personnel activity area refers to the area where personnel work and move in the substation. The electromagnetic shielding cover refers to a shielding structure used to reduce the impact of electromagnetic radiation on specific areas and equipment. The structure of the electromagnetic shielding cover is not limited in this embodiment, and those skilled in the relevant art can freely set it according to the actual situation, as long as it meets the shielding requirements for reducing the impact of electromagnetic radiation on specific areas and equipment. For example, the structure of the electromagnetic shielding cover can be set as an openable shielding cover. The electromagnetic radiation refers to the propagation and distribution of the electromagnetic field in space.

[0045] Specifically, the decision execution module realizes the rapid judgment and effective processing of the cause of equipment failure through accurate prediction and intelligent decision-making, improves the operation efficiency of power grid communication equipment and control equipment, reduces the impact of electromagnetic radiation, and thus avoids communication interruption.

[0046] Please refer to Figure 2 as shown, which is a schematic flow chart of the power grid environment monitoring method based on intelligent sensors in this embodiment. The method includes: Step S1: Collect power grid monitoring data; Step S2: Process the power grid monitoring data to obtain standard power grid monitoring data, which includes equipment rated voltage, equipment current, current element, equipment failure status coefficient, and environmental parameters; Step S3: Calculate the electromagnetic intensity according to the current element, and monitor the power grid electromagnetic environment status according to the electromagnetic intensity; Step S4: Optimize the electromagnetic intensity according to the equipment rated voltage; Step S5: Adjust the equipment rated voltage according to the equipment failure status coefficient; Step S6: Calculate the environmental index according to the environmental parameters, and optimize the equipment failure status coefficient according to the environmental index; Step S7: Construct a prediction model based on the historical data of electromagnetic intensity and output the electromagnetic prediction results, including predicting the highest peak value of future electromagnetic intensity and predicting the duration of future strong electromagnetic fields. Step S8: Monitor the future electromagnetic intensity state based on the predicted highest peak value of future electromagnetic intensity and optimize the predicted highest peak value of future electromagnetic intensity according to the predicted duration of future strong electromagnetic fields. Step S9: Adjust the predicted duration of future strong electromagnetic fields according to the device current. Step S10: Judge the cause of the device failure based on the judgment result of the future electromagnetic intensity state and process the device according to the cause of the device failure.

[0047] So far, the technical solution of the present invention has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the protection scope of the present invention.

Claims

1. A power grid environment monitoring system based on intelligent sensors, characterized in that: The system comprises: Data acquisition module, used to collect power grid monitoring data; A data processing module, used to process the power grid monitoring data to obtain standard power grid monitoring data, which includes equipment rated voltage, equipment current, current element, equipment fault state coefficient and environmental parameters; A monitoring operation module, used to calculate the electromagnetic intensity according to the current element, and monitor the electromagnetic environment state of the power grid according to the electromagnetic intensity, and to optimize the electromagnetic intensity according to the rated voltage of the equipment, and to adjust the rated voltage of the equipment according to the equipment fault state coefficient, and to calculate the environmental index according to the environmental parameters, and to optimize the equipment fault state coefficient according to the environmental index; A prediction model building module is used to build a prediction model based on the historical data of electromagnetic intensity and output the electromagnetic prediction results, including the prediction of the highest peak value of electromagnetic intensity in the future and the prediction of the duration of strong electromagnetic intensity in the future; A prediction result analysis module is used to monitor the future electromagnetic intensity state according to the predicted maximum peak value of the future electromagnetic intensity, optimize the predicted maximum peak value of the future electromagnetic intensity according to the predicted future strong electromagnetic duration, and adjust the predicted future strong electromagnetic duration according to the equipment current; The decision-making execution module is used to judge the cause of equipment failure based on the judgment result of the future electromagnetic intensity state, and to handle the equipment according to the cause of the equipment failure.

2. The power grid environment monitoring system based on intelligent sensors according to claim 1 is characterized in that: When the monitoring operation module monitors the standard power grid monitoring data, it calculates the electromagnetic intensity B according to the current element idl and sets , where r is the distance where the electromagnetic intensity B is generated in the current element idl, μ0 is the magnetic permeability of vacuum, and μ0=4π×10 -7 T·m / A, compare the electromagnetic intensity B with the preset electromagnetic intensity B0, and judge the electromagnetic environment state of the power grid equipment according to the comparison result, where: When B≤B0, it is determined that the electromagnetic environment state of the power grid equipment is normal; When B>B0, it is determined that the electromagnetic environment state of the power grid equipment is abnormal.

3. The power grid environment monitoring system based on intelligent sensors according to claim 2 is characterized in that: When optimizing the electromagnetic intensity B, the monitoring operation module compares the equipment rated voltage U with the preset equipment rated voltage U0, and judges the voltage area where the equipment is located according to the comparison result, and optimizes the electromagnetic intensity B according to the judgment result, wherein: When U≤U0, the voltage area where the device is located is determined to be a low-voltage area, and the electromagnetic intensity B is not optimized at this time; When U>U0, the voltage area where the device is located is determined to be a high voltage area. At this time, the electromagnetic intensity B is optimized. The optimized electromagnetic intensity is B1. Set B1=U1×B, where U1 is the voltage parameter, and set U1=U0×e -1.23U , e is the natural number base.

4. The power grid environment monitoring system based on intelligent sensors according to claim 3 is characterized in that: When adjusting the rated voltage U of the equipment, the monitoring operation module compares the equipment fault state coefficient G with the preset equipment fault state coefficient G0, and judges the equipment fault state according to the comparison result, and adjusts the rated voltage U of the equipment according to the judgment result, wherein: When G≤G0, the fault state of the equipment is determined to be normal, and the rated voltage U of the equipment is not affected. In this case, the rated voltage U of the equipment is not adjusted; When G>G0, the equipment fault state is determined to be abnormal, which affects the rated voltage U of the equipment. At this time, the rated voltage U of the equipment is adjusted. After adjustment, the rated voltage of the equipment is U2, and U2=0.5×g×U is set, where g is the equipment state value, and g=1.38×G0 / G is set.

5. The power grid environment monitoring system based on intelligent sensors according to claim 4 is characterized in that: When optimizing the equipment fault state coefficient G, the monitoring operation module calculates the environmental index H according to the weather influence coefficient T, the temperature influence coefficient W, the humidity influence coefficient S and the geographical environment influence coefficient D, sets H=0.35T+0.3W+0.2S+0.15D, compares the environmental index H with the preset environmental index H0, and judges the environmental temperature range of the power grid equipment according to the comparison result, and optimizes the equipment fault state coefficient G according to the judgment result, wherein: When H≤H0, the ambient temperature range of the power grid equipment is determined to be normal and has no impact on the power grid equipment. At this time, the equipment state coefficient G is not optimized; When H>H0, the ambient temperature range of the power grid equipment is determined to be abnormal, which affects the power grid equipment. At this time, the equipment state coefficient G is optimized. The optimized equipment state coefficient is G1, and G1=α×G is set. α is the environmental coefficient, and 0.38<α<1.

45.

6. The power grid environment monitoring system based on intelligent sensors according to claim 1 is characterized in that: When constructing the prediction model, the prediction model building module predicts the electromagnetic intensity historical data through the prediction model, inputs the electric field intensity historical data into the prediction model, obtains the electromagnetic prediction result, and the electromagnetic prediction result includes the predicted maximum peak value dB of the future electromagnetic intensity and the predicted future strong electromagnetic duration dT, and constructs the prediction model, wherein the electric field intensity historical data is divided into a 70% prediction training set, a 15% prediction verification set and a 15% prediction test set, the prediction training set is input into the LSTM model to train the LSTM model, and the prediction verification set is input into the trained LSTM In the model, the hyperparameters of the trained LSTM model are iteratively optimized, and the prediction test set is input into the iteratively optimized LSTM model to perform prediction test on the iteratively optimized LSTM model to obtain the electromagnetic prediction test result. The total number of samples in the prediction test set is set to f0, the number of correct prediction test samples is set to f, the prediction test accuracy is set to F, and F=f / f0. The prediction test accuracy F is compared with the preset prediction test accuracy F0. According to the comparison result, the training compliance of the iteratively optimized LSTM model is judged, and the judgment result is output, where: When F≥F0, it is determined that the iteratively optimized LSTM model training has reached the standard, and the iteratively optimized LSTM model is output as a prediction model; When F<F0, it is determined that the training of the iteratively optimized LSTM model does not meet the standards, the electric field strength historical database is updated to obtain an updated electric field strength historical database, and the electric field strength historical database is used to train the LSTM model, iteratively optimize hyperparameters and perform prediction tests until the LSTM model training meets the standards.

7. The power grid environment monitoring system based on intelligent sensors according to claim 1 is characterized in that: When monitoring the future electromagnetic intensity state, the prediction result analysis module compares the predicted future electromagnetic intensity highest peak value dB with the electromagnetic intensity B, and judges the future electromagnetic intensity state according to the comparison result, wherein: When dB≤B, the future electromagnetic intensity state is determined to be normal; When dB>B, the future electromagnetic intensity state is determined to be abnormal; When optimizing the predicted future electromagnetic intensity maximum peak value dB, the prediction result analysis module compares the predicted future strong electromagnetic duration dT with the preset strong electromagnetic duration dT0, judges the abnormal change range of the predicted future electromagnetic intensity of the power grid environment according to the comparison result, and optimizes the predicted future electromagnetic intensity maximum peak value dB according to the judgment result, wherein: When dT≤dT0, it is determined that the predicted abnormal change range of the future electromagnetic intensity of the power grid environment is within a reasonable range, and at this time, the predicted maximum peak value dB of the future electromagnetic intensity is not optimized; When dT>dT0, it is determined that the predicted abnormal change range of the future electromagnetic intensity of the power grid environment is unreasonable. At this time, the predicted maximum peak value dB of the future electromagnetic intensity is optimized. After optimization, the predicted maximum peak value of the future electromagnetic intensity is dB1, and dB1=(dT-dT0)×dB is set.

8. The power grid environment monitoring system based on intelligent sensors according to claim 7 is characterized in that: When adjusting the predicted future strong electromagnetic duration dT, the prediction result analysis module compares the device current I with the preset device current I0, and judges the state of the device current according to the comparison result, and adjusts the predicted future strong electromagnetic duration dT according to the judgment result, wherein: When I≤I0, the current state of the device is determined to be within the normal range, and the predicted future strong electromagnetic duration dT is not adjusted at this time; When I>I0, the state of the current of the equipment is determined to be in an abnormal range. At this time, the predicted future strong electromagnetic duration dT is adjusted. The adjusted predicted future strong electromagnetic duration is dT1. Set dT1=i×dT, where i is the current variation coefficient, and 0.78<i<1.

9. The power grid environment monitoring system based on intelligent sensors according to claim 1 is characterized in that: When processing the equipment, the decision execution module determines the cause of the equipment failure according to the judgment result of the future electromagnetic intensity state, and processes the equipment according to the judgment result, wherein: When the result of the judgment of the future electromagnetic intensity state is that the range of abnormal change of the predicted future electromagnetic intensity of the power grid environment is in an unreasonable range, it is determined that the cause of the equipment failure is equipment failure, and the equipment is processed by adjusting the load distribution and increasing the equipment capacity; When the future electromagnetic intensity status judgment result is that the status of the equipment current is within an abnormal range, it is determined that the cause of the equipment failure is a grounding fault. At this time, electromagnetic shielding measures are taken to reduce the abnormal electromagnetic intensity. For sensitive equipment and personnel activity areas in the substation, electromagnetic shielding covers are installed to reduce electromagnetic radiation.

10. A method applied to a power grid environment monitoring system based on an intelligent sensor as claimed in any one of claims 1 to 9, characterized in that: The method comprises: Step S1, collecting power grid monitoring data; Step S2, processing the power grid monitoring data to obtain standard power grid monitoring data, which includes equipment rated voltage, equipment current, current element, equipment fault state coefficient and environmental parameters; Step S3, calculating the electromagnetic intensity according to the current element, and monitoring the electromagnetic environment state of the power grid according to the electromagnetic intensity; Step S4, optimizing the electromagnetic intensity according to the rated voltage of the equipment; Step S5, adjusting the rated voltage of the device according to the device fault state coefficient; Step S6, calculating the environmental index according to the environmental parameters, and optimizing the equipment fault state coefficient according to the environmental index; Step S7, constructing a prediction model based on the historical data of electromagnetic intensity, and outputting the electromagnetic prediction results, which include predicting the highest peak value of electromagnetic intensity in the future and predicting the duration of strong electromagnetic intensity in the future; Step S8, monitoring the future electromagnetic intensity state according to the predicted future electromagnetic intensity peak value, and optimizing the predicted future electromagnetic intensity peak value according to the predicted future strong electromagnetic duration; Step S9, adjusting the predicted future strong electromagnetic duration according to the device current; Step S10, judging the cause of the equipment failure according to the judgment result of the future electromagnetic intensity state, and processing the equipment according to the cause of the equipment failure.

Images