Online monitoring method and system for lightning invasion path

Abstract

The invention discloses a lightning invasion path online monitoring method and system, and relates to the technical field of lightning monitoring. Comprising the following steps: acquiring electromagnetic field data by using a sensor, and transmitting the acquired electromagnetic field data to a central monitoring area of the system; preprocessing the electromagnetic field data transmitted to the central monitoring area; and establishing a lightning intrusion mode library, automatically learning path data of a lightning intrusion path according to the established lightning intrusion mode library, and completing monitoring of the lightning intrusion path. According to the invention, the accuracy and real-time performance of lightning invasion path monitoring are effectively improved, accurate identification and monitoring of lightning paths are realized, the possibility of false alarm and missing alarm is reduced, the reliability and stability of the system are improved, in addition, an automatic learning and optimization mechanism provided by the invention can continuously update a monitoring model, and the monitoring efficiency is improved. And the adaptability of the system to novel thunder and lightning signals is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of lightning monitoring, and in particular to an online monitoring method and system for lightning intrusion pathways. Background Art

[0002] With the development of society and the advancement of technology, wind farms and other new energy facilities are growing rapidly around the world. However, these facilities are often damaged by lightning, resulting in equipment damage and downtime, causing huge economic losses and potential safety hazards. Therefore, accurate and real-time monitoring of lightning intrusion paths has become an important technical means to ensure the normal operation of key infrastructure such as wind farms.

[0003] The existing technology has problems such as low detection accuracy and delayed response time in lightning monitoring. Especially in complex electromagnetic environments, it is difficult to accurately distinguish lightning signals from background noise. The present invention improves the recognition accuracy of lightning signals and the system response speed by introducing a multi-band sensor array, a dynamically adjusted noise processing method, and an intelligent analysis and feedback mechanism, thereby effectively solving the defects of the existing technology. Summary of the invention

[0004] In view of the problems existing in the existing online monitoring method and system for lightning intrusion pathways, the present invention is proposed.

[0005] Therefore, the purpose of the present invention is to provide an online monitoring method and system for lightning intrusion paths. In view of the problems of low detection accuracy and slow response time in the prior art for lightning monitoring, the present invention introduces a multi-band sensor array and an intelligent analysis and feedback mechanism, dynamically adjusts the noise processing method, and improves the accuracy of lightning signal recognition and the system response speed.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides an online monitoring method for lightning intrusion paths, which includes deploying sensors around a wind farm where lightning is generated, collecting electromagnetic field data using the sensors, and transmitting the collected electromagnetic field data to a central monitoring area of ​​the system;

[0008] Pre-process the electromagnetic field data transmitted to the central monitoring area, and introduce the electromagnetic field path recognition model to identify the lightning intrusion path;

[0009] A lightning intrusion pattern library is established, and path data of lightning intrusion pathways are automatically learned based on the established lightning intrusion pattern library. The path data is detected through automated intelligent protection technology to complete the monitoring of lightning intrusion pathways.

[0010] As a preferred solution of the online monitoring method for lightning intrusion path of the present invention, wherein: the deployment of sensors around the wind farm where lightning is generated includes deploying sensors of different frequency bands using a multi-band sensor array, calculating the correlation coefficient between different frequency bands by cross-correlation analysis of multi-band data, calculating the noise amplitude between different frequency bands according to the correlation coefficient, setting a dynamically adjusted noise amplitude threshold, and dynamically adjusting the noise amplitude for updating;

[0011] The specific calculation formula of the correlation coefficient is:

[0012]

[0013] Among them, R(f i , f j ) represents the frequency band f i and f j The correlation coefficient between represents the frequency band f at time t i The signal value on represents the frequency band f at time t j The signal value on Indicates frequency band f i The average value of the upper signal, Indicates frequency band f j The average value of the upper signal;

[0014] The specific calculation formula of the noise amplitude is:

[0015]

[0016] Where RMS represents the noise amplitude, N represents the number of samples, and R(f i , f j ) represents the frequency band f i and f j The correlation coefficient between them is that when the RMS becomes larger, the noise amplitude increases.

[0017] As a preferred solution of the online monitoring method for lightning intrusion path of the present invention, the dynamically adjusting the noise amplitude for updating includes taking statistics on the initial value of the noise amplitude to obtain the average value safety margin of the noise amplitude under a normal signal environment;

[0018] When signal processing is performed under a normal signal environment, if it is detected that the average safety margin of the current signal is greater than the noise amplitude threshold, the filter parameters of the sensor are automatically adjusted; the automatic adjustment of the filter parameters of the sensor includes increasing the step size factor of the filter;

[0019] If it is detected that the average safety margin of the current signal is less than or equal to the noise amplitude threshold, the filter parameters are reduced; the reducing the filter parameters includes reducing the step size factor of the filter.

[0020] As a preferred solution of the online monitoring method for lightning intrusion path of the present invention, wherein: the collecting electromagnetic field data includes analyzing the initial value of the noise amplitude, calculating the initial value root mean square of the noise amplitude, and setting the initial value root mean square as the reference value of the noise amplitude;

[0021] The specific calculation formula of the initial value root mean square of the noise amplitude is:

[0022]

[0023] Among them, RMSRMS noise_initial represents the initial value of the noise amplitude, RMS, N represents the number of samples, represents the mean value of noise amplitude;

[0024] The adjustment of the step size factor includes noise dominance and signal dominance;

[0025] If the noise amplitude mean is greater than the initial value of the noise amplitude root mean square, the signal contains information. At this time, the signal dominance is used for analysis. The specific calculation formula for the signal dominance is:

[0026] α new =α old -Δα

[0027] Among them, α old represents the old step size factor, Δα represents the adjustment increment, α new Represents the new step size factor after adjustment;

[0028] If the noise amplitude mean is less than or equal to the initial value of the noise amplitude root mean square, the signal contains noise. At this time, the noise dominance is used for analysis. The specific calculation formula of the noise dominance is:

[0029] α new =α old +Δα

[0030] Among them, α old represents the old step size factor, Δα represents the adjustment increment, α new Represents the new step size factor after adjustment.

[0031] As a preferred solution of the online monitoring method for lightning intrusion paths of the present invention, wherein: the transmitting of the collected electromagnetic field data to the central monitoring area of ​​the system includes packaging the collected electromagnetic field data according to the timestamp and sensor number, generating a symmetric key and an encrypted data packet, and when the system detects that the encrypted data packet contains sensitive information, the encryption mode is enabled;

[0032] The generating of the symmetric key includes the system automatically selecting an unobstructed communication link for data transmission, and when the bandwidth of one of the selected links is insufficient for the transmitted data to pass, the system automatically switches to the backup link and records the switching event;

[0033] Establishing a contact station between the sensor and the central monitoring area through the layer protocol of the link, and detecting the state of the transmitted data using the error checking mechanism of the contact station;

[0034] If a packet loss or error is detected in the transmitted data, the system automatically requests retransmission of the lost packet; if no difference in the packet is detected, the packet is decrypted through the central monitoring area, the original state of the data is restored, the packet content is decrypted using the symmetric key, and the data integrity is verified;

[0035] If decryption fails, the system will log the error and notify the administrator for manual intervention.

[0036] As a preferred solution of the online monitoring method for lightning intrusion path of the present invention, the preprocessing of the electromagnetic field data includes cleaning the restored original state data, and standardizing the cleaned original state data, wherein the standardization includes eliminating the scale difference between sensors and adjusting the original state data according to the filter;

[0037] Compare and analyze the data before and after filtering. If the data after filtering is lower than the data before filtering, filter the filter parameters after automatic sensor adjustment, focus on the main signal frequency band, and use a single secondary filtering classification to perform spectrum analysis on the filtered data.

[0038] If the filtered data is higher than the unfiltered data, the filter parameters after the automatic adjustment of the sensor are filtered twice to disperse the main signal frequency band, and the spectrum analysis of the filtered data is performed using a combined multi-stage filtering classification to complete the data integrity processing.

[0039] As a preferred solution of the online monitoring method for lightning intrusion pathways of the present invention, wherein: the establishment of a lightning intrusion pattern library includes establishing unidentified data using the results of the comparative analysis;

[0040] When the filtered data is equal to the unfiltered data, it is in an unrecognized state;

[0041] Calculate the similarity between the unidentified data and the existing lightning signal data. If the similarity is higher than the dynamically adjusted filter data threshold, they will be regarded as the same type of signals. At this time, the path data will be detected through the automated intelligent protection technology.

[0042] If the similarity is lower than or equal to the dynamically adjusted filter data threshold, a feedback mechanism is established to update and optimize the existing lightning signal data using the established lightning intrusion pattern library to complete the monitoring of lightning intrusion paths.

[0043] In the second aspect, an embodiment of the present invention provides an online monitoring system for lightning intrusion paths, which includes: an acquisition module, which uses the sensor to collect electromagnetic field data and transmits the collected electromagnetic field data to a central monitoring area of ​​the system; an establishment module, which pre-processes the electromagnetic field data transmitted to the central monitoring area; and a monitoring module, which establishes a lightning intrusion pattern library, automatically learns the path data of the lightning intrusion path according to the established lightning intrusion pattern library, and completes the monitoring of the lightning intrusion path.

[0044] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the online monitoring method for lightning intrusion paths as described in the first aspect of the present invention are implemented.

[0045] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of the online monitoring method for lightning intrusion paths as described in the first aspect of the present invention are implemented.

[0046] The beneficial effects of the present invention are as follows: the present invention effectively improves the accuracy and real-time performance of lightning intrusion path monitoring by deploying a multi-band sensor array and utilizing a method for dynamically adjusting noise amplitude; by establishing a lightning intrusion pattern library and automated intelligent protection technology, the present invention achieves accurate identification and monitoring of lightning paths, reduces the possibility of false alarms and missed alarms, and improves the reliability and stability of the system; in addition, the automatic learning and optimization mechanism provided by the present invention can continuously update the monitoring model, thereby improving the system's adaptability to new lightning signals. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 A flowchart of a method and system for online monitoring of lightning intrusion pathways provided by an embodiment of the present invention.

[0049] Figure 2 A schematic diagram of a monitoring method of an online monitoring method and system for lightning intrusion pathways provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0051] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0052] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0053] Example 1

[0054] Reference Figure 1-2 , which is the first embodiment of the present invention, provides an online monitoring method for lightning intrusion path, comprising:

[0055] S1: Deploy sensors around wind farms where lightning occurs, use the sensors to collect electromagnetic field data, and transmit the collected electromagnetic field data to the central monitoring area of ​​the system.

[0056] Among them, deploying sensors around wind farms that generate lightning includes deploying sensors of different frequency bands using a multi-band sensor array, calculating the correlation coefficients between different frequency bands using cross-correlation analysis of multi-band data, calculating the noise amplitudes between different frequency bands based on the correlation coefficients, setting a dynamically adjusted noise amplitude threshold, and dynamically adjusting the noise amplitude for updating;

[0057] The specific calculation formula of the correlation coefficient is:

[0058]

[0059] Among them, R(f i , f j ) represents the frequency band f i and f jThe correlation coefficient between represents the frequency band f at time t i The signal value on represents the frequency band f at time t j The signal value on Indicates frequency band f i The average value of the upper signal, Indicates frequency band f j The average value of the upper signal;

[0060] The specific calculation formula for the noise amplitude is:

[0061]

[0062] Where RMS represents the noise amplitude, N represents the number of samples, and R(f i , f j ) represents the frequency band f i and f j The correlation coefficient between them is that when the RMS becomes larger, the noise amplitude increases.

[0063] S1.1: Dynamically adjusting the noise amplitude for updating includes taking statistics on the initial value of the noise amplitude to obtain an average safety margin of the noise amplitude under a normal signal environment.

[0064] When signal processing is performed under a normal signal environment, if it is detected that the average safety margin of the current signal is greater than the noise amplitude threshold, the filter parameters of the sensor are automatically adjusted; the automatic adjustment of the filter parameters of the sensor includes increasing the step size factor of the filter;

[0065] If it is detected that the average safety margin of the current signal is less than or equal to the noise amplitude threshold, the filter parameters are reduced; reducing the filter parameters includes reducing the step size factor of the filter.

[0066] Furthermore, a multi-band sensor array is deployed around wind farms with active lightning activity to obtain electromagnetic field data in different frequency bands. For example, sensor A captures low-frequency signals of 0-30 Hz, sensor B captures medium-frequency signals of 30-60 Hz, and sensor C captures high-frequency signals of 60-100 Hz. These sensors monitor changes in the electromagnetic field in real time and transmit the data to the central monitoring area of ​​the system. By performing cross-correlation analysis on these multi-band data, the correlation coefficients between different frequency bands are calculated. For example, if at time t1, the signal value of frequency band A is 5 μT, the signal value of frequency band B is 7 μT, and their respective average values ​​are 4 μT and 6 μT, respectively, then the correlation coefficient between the two frequency bands is calculated to be 0.8.

[0067] Furthermore, based on the calculated correlation coefficient, the noise amplitude between each frequency band is estimated. For example, in a normal signal environment, when the number of samples is 1000, if the average correlation coefficient is 0.8, the initial noise amplitude is 1.5μT. The system sets a dynamically adjusted noise amplitude threshold, such as 2μT, as a benchmark for adjusting the filter parameters. When it is detected that the average noise amplitude safety margin of the current signal exceeds 2μT, for example, it reaches 2.5μT, the system automatically increases the step size factor of the filter to enhance the signal processing capability; if it is detected that the noise amplitude safety margin drops below 2μT, the system reduces the step size factor to reduce the impact of noise on the signal. Through these precise data and dynamic adjustment mechanisms, the system can effectively process and analyze complex electromagnetic field data, providing an accurate and reliable basis for monitoring lightning intrusion pathways. The lightning monitoring data analysis is shown in Table 1 below:

[0068] Table 1 Lightning monitoring data analysis table

[0069]

[0070] The table shows the electromagnetic field data collected by sensors in different frequency bands around the wind farm, including the mean, correlation coefficient and noise amplitude of the signals in each frequency band. By calculating the correlation coefficient and noise amplitude, the noise amplitude threshold can be dynamically adjusted, and the filter parameters of the sensor can be optimized accordingly to ensure accurate identification of lightning intrusion paths.

[0071] S1.2: Collecting electromagnetic field data includes analyzing the initial value of the noise amplitude, calculating the initial value root mean square of the noise amplitude, and setting the initial value root mean square as the reference value of the noise amplitude;

[0072] The specific calculation formula of the initial value root mean square of the noise amplitude is:

[0073]

[0074] Among them, RMSRMS noise_initial represents the initial value of the noise amplitude, RMS, N represents the number of samples, represents the mean value of noise amplitude;

[0075] The adjustment of step size factor includes noise dominance and signal dominance;

[0076] If the mean value of the noise amplitude is greater than the root mean square of the initial value of the noise amplitude, the signal contains information. At this time, signal dominance is used for analysis. The specific calculation formula for signal dominance is:

[0077] α new =α old -Δα

[0078] Among them, α oldrepresents the old step size factor, Δα represents the adjustment increment, α new Represents the new step size factor after adjustment;

[0079] If the mean value of the noise amplitude is less than or equal to the root mean square of the initial value of the noise amplitude, the signal contains noise. In this case, noise dominance is used for analysis. The specific calculation formula for noise dominance is:

[0080] α new =α old +Δα

[0081] Among them, α old represents the old step size factor, Δα represents the adjustment increment, α new Represents the new step size factor after adjustment.

[0082] Furthermore, in the electromagnetic field data collected by the sensors deployed around the wind farm, the initial value of the noise amplitude is first analyzed. Assuming that the number of samples collected is 1000, the calculated mean value of the noise amplitude is 0.5. Using these data, the initial root mean square value of the noise amplitude is calculated to be 0.45, which is used as the baseline value of the noise amplitude.

[0083] In data processing, if the real-time noise amplitude average is detected to be 0.6, which is higher than the initial root mean square value of 0.45, it indicates that the signal contains information. At this time, the signal-dominant analysis method is selected, and the step factor is adjusted from the original 0.1 to 0.2. On the contrary, if the noise amplitude average is 0.4, which is lower than or equal to the initial root mean square value of 0.45, the signal is mainly noise. The system selects the noise-dominant analysis method and reduces the step factor from 0.2 to 0.1. This adjustment method ensures flexible response in different noise environments and optimizes the accuracy and efficiency of data processing.

[0084] S1.3: Transmitting the collected electromagnetic field data to the central monitoring area of ​​the system includes packaging the collected electromagnetic field data according to the timestamp and sensor number, generating a symmetric key and an encrypted data packet, and enabling encryption mode when the system detects that the encrypted data packet contains sensitive information;

[0085] Generating the symmetric key includes the system automatically selecting an unobstructed communication link for data transmission, and when the bandwidth of one of the selected links is insufficient for the transmitted data to pass, the system automatically switches to the backup link and records the switching event;

[0086] Establish a contact station between the sensor and the central monitoring area through the link layer protocol, and use the error checking mechanism of the contact station to detect the status of the transmitted data;

[0087] If a packet loss or error is detected in the transmitted data, the system automatically requests retransmission of the lost packet; if no difference in the packet is detected, the packet is decrypted through the central monitoring area, the original state of the data is restored, the packet content is decrypted using the symmetric key, and the data integrity is verified;

[0088] If decryption fails, the system will log the error and notify the administrator for manual intervention.

[0089] The electromagnetic field data collected by the sensors deployed around the wind farm will be packaged according to the timestamp and sensor number, and an encrypted data packet will be generated. For example, if the amount of data collected at a certain moment is 500MB, these data will be encrypted and packaged into an encrypted data packet of approximately 510MB in size. Considering the increased size due to encryption, the system will automatically select the optimal communication link for data transmission. If the bandwidth of the main link is 100Mbps, but it is detected in real time that the network bandwidth drops to 80Mbps, the system will automatically switch to the backup link with a bandwidth of 150Mbps to ensure the stability and speed of data transmission. Each link switching event will be recorded for subsequent analysis.

[0090] During the transmission process, the integrity of the data packet is monitored through the error checking mechanism of the contact station. If data packet loss or transmission error is detected, for example, 2 out of 10 data packets are lost, the system will automatically request retransmission of the lost data packets to ensure data integrity. After the transmission is completed, the central monitoring area uses the symmetric key to decrypt the data packet content. If a failure occurs during the decryption process, for example, 1 out of 10 decryption attempts fails, the system will record the error and notify the administrator to intervene manually to ensure data security and integrity.

[0091] S2: Pre-process the electromagnetic field data transmitted to the central monitoring area, introduce the electromagnetic field path recognition model to identify the lightning intrusion path, and establish a lightning intrusion pattern library.

[0092] The preprocessing of the electromagnetic field data includes cleaning the restored original state data, and standardizing the cleaned original state data. The standardization includes eliminating the scale difference between sensors and adjusting the original state data according to the filter.

[0093] Compare and analyze the data before and after filtering. If the data after filtering is lower than the data before filtering, filter the filter parameters after automatic sensor adjustment, focus on the main signal frequency band, and use a single secondary filtering classification to perform spectrum analysis on the filtered data.

[0094] If the filtered data is higher than the unfiltered data, the filter parameters after the automatic adjustment of the sensor are filtered twice to disperse the main signal frequency band, and the spectrum analysis of the filtered data is performed using a combined multi-stage filtering classification to complete the data integrity processing.

[0095] In the central monitoring area, the received electromagnetic field data is first preprocessed to ensure the accuracy and consistency of the data. The preprocessing step includes cleaning the recovered raw data. For example, in a data collection process, the 1GB of data collected may contain 10% noise data, which will be removed through the data cleaning process. Next, the cleaned data is standardized to eliminate the scale differences between different sensors. For example, if the signal strength range collected by different sensors is 0-5V and 0-10V, the standardization process will unify it into a common range, such as 0-1V.

[0096] During filter adjustment, the system will adjust the filter parameters based on the cleaned and standardized data. If the amplitude of the filtered data is lower than the data before filtering, for example, the signal amplitude before filtering is 2V and drops to 1.5V after filtering, it indicates that the signal is mainly concentrated in the main frequency band. At this time, the system will use a single secondary filtering to focus on the spectrum analysis of the main signal frequency band to ensure that the core information of the signal is not lost. On the contrary, if the amplitude of the filtered data is higher than the data before filtering, such as increasing from 2V to 2.5V, it indicates that there are multi-band signals. At this time, the system will use combined multi-stage filtering for more detailed spectrum analysis to disperse and detect signals of all frequency bands in detail to ensure the integrity and accuracy of the data. These processing steps ensure the quality of the data and provide a reliable data basis for the subsequent identification of lightning intrusion pathways and the establishment of a lightning intrusion pattern library.

[0097] S3: Establish a lightning intrusion pattern library, automatically learn the path data of the lightning intrusion path according to the established lightning intrusion pattern library, detect the path data through automated intelligent protection technology, and complete the monitoring of the lightning intrusion path.

[0098] Among them, establishing a lightning intrusion pattern library includes using the results of comparative analysis to establish unidentified data;

[0099] When the filtered data is equal to the unfiltered data, it is in an unrecognized state;

[0100] Calculate the similarity between the unidentified data and the existing lightning signal data. If the similarity is higher than the dynamically adjusted filter data threshold, they will be regarded as the same type of signal. At this time, the path data will be detected through automated intelligent protection technology.

[0101] If the similarity is lower than or equal to the dynamically adjusted filter data threshold, a feedback mechanism is established to update and optimize the existing lightning signal data using the established lightning intrusion pattern library to complete the monitoring of lightning intrusion paths.

[0102] Furthermore, in the process of establishing a lightning intrusion pattern library, the system will compare and analyze the collected electromagnetic field data. If some signals in the pre-processed data do not match the known lightning signal patterns, these signals will be marked as unidentified. For example, suppose that the unidentified signals detected by a system contain 10,000 data, and these data will be further analyzed for their characteristics.

[0103] The system will calculate the similarity between these unidentified data and the existing lightning signal data. For example, if it finds that 30% of the data has a similarity of more than 70%, and these data may represent a specific type of lightning activity, the system will automatically classify the data with a similarity higher than the threshold as the same lightning intrusion path signal and monitor it in real time through automated intelligent protection technology. These data will be further used to update and optimize the existing lightning intrusion pattern library, so that the system can more accurately identify future lightning events.

[0104] For data with a similarity lower than or equal to the dynamically adjusted filter data threshold, for example, the remaining 70% of the data with a similarity lower than 50%, the system will establish a feedback mechanism. These data will be recorded in detail and incorporated into the learning database to facilitate the identification of similar new or unknown lightning signals in the future. By continuously updating and optimizing the lightning intrusion pattern library, the system can continuously improve its monitoring capabilities for lightning intrusion pathways and ensure the safety and stability of wind farm equipment.

[0105] In a preferred embodiment, a lightning intrusion path online monitoring system includes an acquisition module, which uses a sensor to collect electromagnetic field data and transmits the collected electromagnetic field data to a central monitoring area of ​​the system; an establishment module, which preprocesses the electromagnetic field data transmitted to the central monitoring area; and a monitoring module, which establishes a lightning intrusion pattern library, automatically learns the path data of the lightning intrusion path according to the established lightning intrusion pattern library, and completes the monitoring of the lightning intrusion path.

[0106] The above-mentioned unit modules may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above-mentioned modules.

[0107] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0108] In summary, the present invention effectively improves the accuracy and real-time performance of lightning intrusion path monitoring by deploying a multi-band sensor array and utilizing a method for dynamically adjusting the noise amplitude. By establishing a lightning intrusion pattern library and automated intelligent protection technology, the present invention achieves accurate identification and monitoring of lightning paths, reduces the possibility of false alarms and missed alarms, and improves the reliability and stability of the system. In addition, the automatic learning and optimization mechanism provided by the present invention can continuously update the monitoring model, thereby improving the system's adaptability to new lightning signals.

[0109] Example 2

[0110] Reference Figure 1-2 , which is the second embodiment of the present invention, and this embodiment provides an online monitoring method for lightning intrusion paths. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0111] First, a multi-band sensor array is deployed around the wind farm. These sensors can capture electromagnetic field data in different frequency bands. The experiment sets up 100 sensor nodes, covering a radius of 5 kilometers around the wind farm. The data collected by each sensor is transmitted to the central monitoring area in real time via a wireless network. During the data transmission process, the system generates a symmetric key and uses AES encryption technology to ensure data security. In the experiment, 10MB of data is collected per second, and the integrity of the data packet is monitored during transmission to ensure that there is no data loss or error.

[0112] In the central monitoring area, the system pre-processes the electromagnetic field data, including data cleaning and standardization, eliminates the scale differences between different sensors, and conducts in-depth analysis of the data through filter adjustment and spectrum analysis to screen out possible lightning intrusion signals. In the experiment, for 5 million raw data, the system successfully screened out 500,000 possible lightning intrusion path data. For these data, the system calculated their similarity with the data in the existing lightning pattern library. The results showed that about 30% of the data was highly similar to the existing patterns. This part of the data was used to further verify the lightning intrusion path.

[0113] The experiment also set up a feedback mechanism to record the data with similarity below the threshold in detail for subsequent learning. During the experiment, the system continuously optimized the lightning intrusion pattern library and finally established a detailed database containing 100,000 different lightning intrusion paths. The entire experiment lasted for 3 months. The system successfully issued warnings in many lightning activities, verifying its effectiveness and reliability in practical applications. The experimental data is summarized in Table 2 below:

[0114] Table 2 Experimental data summary

[0115]

[0116] The table summarizes the experimental data of the online monitoring technology solution for lightning intrusion paths. The main data include the electromagnetic field strength values ​​collected after the deployment of multi-band sensors, the residual noise level after standardization, and the signal amplitude change before and after filtering, as well as the similarity threshold of the comparative analysis after the establishment of the pattern library. The experiment shows that the electromagnetic field strength values ​​collected by the sensor range from 1000 to 5000 μV / m, the residual noise level is maintained at 0.05 to 0.2 μV / m, the signal amplitude change rate before and after filtering is maintained at 5% to 15%, and the threshold of the similarity analysis is 0.75, ensuring high-precision lightning path identification. The comparison between the present invention and the prior art is shown in Table 3 below:

[0117] Table 3 Comparison between the present invention and the prior art

[0118]

[0119] This table shows the main differences and advantages of the technical solution of the present invention over the prior art. The present invention is superior to the prior art in terms of sensor deployment, data preprocessing, data transmission security, path identification accuracy, intelligent protection, pattern library establishment, and system flexibility, and provides higher accuracy, reliability, and security.

[0120] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for online monitoring of lightning intrusion paths, characterized in that: include, Deploy sensors around wind farms where lightning is generated, collect electromagnetic field data using the sensors, and transmit the collected electromagnetic field data to a central monitoring area of ​​the system; Pre-process the electromagnetic field data transmitted to the central monitoring area, and introduce the electromagnetic field path recognition model to identify the lightning intrusion path; A lightning intrusion pattern library is established, and path data of lightning intrusion pathways are automatically learned based on the established lightning intrusion pattern library. The path data is detected through automated intelligent protection technology to complete the monitoring of lightning intrusion pathways.

2. The method for online monitoring of lightning intrusion paths according to claim 1, characterized in that: The deployment of sensors around the wind farm where lightning is generated includes deploying sensors of different frequency bands using a multi-band sensor array, calculating correlation coefficients between different frequency bands using cross-correlation analysis of multi-band data, calculating noise amplitudes between different frequency bands based on the correlation coefficients, setting a dynamically adjusted noise amplitude threshold, and dynamically adjusting the noise amplitude for updating; The specific calculation formula of the correlation coefficient is: Among them, R(f i , f j ) represents the frequency band f i and f j The correlation coefficient between represents the frequency band f at time t i The signal value on represents the frequency band f at time t j The signal value on Indicates frequency band f i The average value of the upper signal, Indicates frequency band f j The average value of the upper signal; The specific calculation formula of the noise amplitude is: Where RMS represents the noise amplitude, N represents the number of samples, and R(f i , f j ) represents the frequency band f i and f j The correlation coefficient between them is that when the RMS becomes larger, the noise amplitude increases.

3. The method for online monitoring of lightning intrusion paths according to claim 2, characterized in that: The dynamically adjusting the noise amplitude for updating includes taking statistics on the initial value of the noise amplitude to obtain a safety margin of the average value of the noise amplitude under a normal signal environment; When signal processing is performed under a normal signal environment, if it is detected that the average safety margin of the current signal is greater than the noise amplitude threshold, the filter parameters of the sensor are automatically adjusted; the automatic adjustment of the filter parameters of the sensor includes increasing the step size factor of the filter; If it is detected that the average safety margin of the current signal is less than or equal to the noise amplitude threshold, the filter parameters are reduced; the reducing the filter parameters includes reducing the step size factor of the filter.

4. The method for online monitoring of lightning intrusion paths according to claim 3, characterized in that: The collecting of electromagnetic field data includes analyzing the initial value of the noise amplitude, calculating the initial value root mean square of the noise amplitude, and setting the initial value root mean square as the reference value of the noise amplitude; The specific calculation formula of the initial value root mean square of the noise amplitude is: Among them, RMSRMS noise_initial represents the initial value of the noise amplitude, RMS, N represents the number of samples, represents the mean value of noise amplitude; The adjustment of the step size factor includes noise dominance and signal dominance; If the noise amplitude mean is greater than the initial value of the noise amplitude root mean square, the signal contains information. At this time, the signal dominance is used for analysis. The specific calculation formula for the signal dominance is: a new =a old -Yes Among them, α old represents the old step size factor, Δα represents the adjustment increment, α new Represents the new step size factor after adjustment; If the noise amplitude mean is less than or equal to the initial value of the noise amplitude root mean square, the signal contains noise. At this time, the noise dominance is used for analysis. The specific calculation formula of the noise dominance is: a new =a old +Da Among them, α old represents the old step size factor, Δα represents the adjustment increment, α new Represents the new step size factor after adjustment.

5. The method for online monitoring of lightning intrusion paths according to claim 4, characterized in that: The transmitting of the collected electromagnetic field data to the central monitoring area of ​​the system includes packaging the collected electromagnetic field data according to the timestamp and sensor number, generating a symmetric key and an encrypted data packet, and enabling encryption mode when the system detects that the encrypted data packet contains sensitive information; The generating of the symmetric key includes the system automatically selecting an unobstructed communication link for data transmission, and when the bandwidth of one of the selected links is insufficient for the transmitted data to pass, the system automatically switches to the backup link and records the switching event; Establishing a contact station between the sensor and the central monitoring area through the layer protocol of the link, and detecting the state of the transmitted data using the error checking mechanism of the contact station; If a packet loss or error is detected in the transmitted data, the system automatically requests retransmission of the lost packet; If no difference in the data packet is detected, the data packet is decrypted through the central monitoring area, the original state of the data is restored, the content of the data packet is decrypted using the symmetric key, and the data integrity is verified; If decryption fails, the system will log the error and notify the administrator for manual intervention.

6. The method for online monitoring of lightning intrusion paths according to claim 5, characterized in that: The electromagnetic field data preprocessing includes cleaning the restored original state data and standardizing the cleaned original state data, wherein the standardization includes eliminating the scale difference between sensors and adjusting the original state data according to the filter; Compare and analyze the data before and after filtering. If the data after filtering is lower than the data before filtering, filter the filter parameters after automatic sensor adjustment, focus on the main signal frequency band, and use a single secondary filtering classification to perform spectrum analysis on the filtered data. If the filtered data is higher than the unfiltered data, the filter parameters after the automatic adjustment of the sensor are filtered twice to disperse the main signal frequency band, and the spectrum analysis of the filtered data is performed using a combined multi-stage filtering classification to complete the data integrity processing.

7. The method for online monitoring of lightning intrusion paths according to claim 6, characterized in that: The establishing of the lightning intrusion pattern library includes establishing the unidentified data using the result of the comparative analysis; When the filtered data is equal to the unfiltered data, it is in an unrecognized state; Calculate the similarity between the unidentified data and the existing lightning signal data. If the similarity is higher than the dynamically adjusted filter data threshold, they will be regarded as the same type of signals. At this time, the path data will be detected through the automated intelligent protection technology. If the similarity is lower than or equal to the dynamically adjusted filter data threshold, a feedback mechanism is established to update and optimize the existing lightning signal data using the established lightning intrusion pattern library to complete the monitoring of lightning intrusion paths.

8. A lightning intrusion path online monitoring system, based on the lightning intrusion path online monitoring method according to any one of claims 1 to 7, characterized in that: Also includes, A collection module, which uses the sensor to collect electromagnetic field data and transmits the collected electromagnetic field data to a central monitoring area of ​​the system; Establishing a module that pre-processes electromagnetic field data transmitted to a central monitoring area; The monitoring module establishes a lightning intrusion pattern library, automatically learns the path data of the lightning intrusion path according to the established lightning intrusion pattern library, and completes the monitoring of the lightning intrusion path.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for online monitoring of lightning intrusion paths according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for online monitoring of lightning intrusion paths according to any one of claims 1 to 7 are implemented.

Images