Machine Learning-Based Method for Quality Control of Meteorological Radar Electromagnetic Interference Data

Abstract

The present invention discloses a method for quality control of meteorological radar electromagnetic interference data based on machine learning, belonging to the technical field of meteorological data processing. The present invention extracts feature parameters related to electromagnetic interference from echo signal data, constructs an interference recognition model and deploys it into the meteorological radar data processing flow to identify electromagnetic interference data, classifies and identifies the interference types and interference modes of the electromagnetic interference data, identifies external interference sources and internal interference sources. By modularly embedding the interference recognition model into the meteorological radar data processing flow, real-time discrimination and automatic marking of interference data are realized. By identifying and marking the interference type and mode characteristics of electromagnetic interference data, the classification accuracy is effectively improved. By comparing with the known type library, accurate identification of typical interference types is realized. By identifying external interference sources and internal interference sources, the two-way traceability mechanism improves the operation and maintenance efficiency of radar stations and the abnormal response ability, and reduces the false alarm and miss rate.

Description

Technical Field

[0001] The present invention relates to the technical field of meteorological data processing, and particularly to a method for quality control of meteorological radar electromagnetic interference data based on machine learning. Background Art

[0002] As an important device for obtaining the three-dimensional structure of the atmosphere and precipitation information, meteorological radars are widely used in fields such as weather monitoring, meteorological forecasting, and disaster warning. The quality of their observed data is directly related to the scientific nature and accuracy of meteorological analysis and decision-making. However, with the frequent occurrence of electromagnetic activities such as wireless communication, power transmission, and radar navigation, the electromagnetic environment in which meteorological radar systems are located has become increasingly complex, and various electromagnetic interference events occur frequently, seriously affecting the accuracy and stability of radar echo data, and may even lead to missed or false alarms of key weather processes.

[0003] Traditional methods for identifying radar electromagnetic interference mainly rely on rule setting and manual experience judgment. For example, interference is identified by setting signal intensity thresholds, spectral change characteristics, or time series outliers. Such methods are usually applicable to interference situations with known patterns, have limited ability to identify non-atypical or highly concealed interference, and are difficult to meet the actual needs of the increasingly complex form of electromagnetic interference. In addition, although some methods introduce an automatic detection mechanism, they lack further classification and traceability analysis of interference types and sources, resulting in incomplete data marking and making it difficult to form a closed-loop quality control system. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for quality control of meteorological radar electromagnetic interference data based on machine learning to solve the problems raised in the above background art.

[0005] To achieve the above purpose, the present invention provides the following technical solution: A method for quality control of meteorological radar electromagnetic interference data based on machine learning, including:

[0006] Based on the echo signal data collected by the weather radar, extract the characteristic parameters related to electromagnetic interference through multi-dimensional analysis, construct and train an interference recognition model, deploy the interference recognition model into the weather radar data processing flow to identify electromagnetic interference data, receive the characteristic parameters extracted from the radar signal as input for interference discrimination, output the determination result of whether each frame or each group of data contains electromagnetic interference data, and explicitly mark the electromagnetic interference data. Based on the electromagnetic interference data, construct an interference index, and determine the quality level of the electromagnetic interference data according to the interference index. Compare the interference index corresponding to the electromagnetic interference data with a preset index threshold. When the interference index corresponding to the electromagnetic interference data exceeds the preset index threshold, it is determined that the quality of the electromagnetic interference data is high, and an interference anomaly alarm is issued. When the interference index corresponding to the electromagnetic interference data does not exceed the preset index threshold, it is determined that the level of the electromagnetic interference data is general, and the interference mode and interference type of the electromagnetic interference data are identified;

[0007] After classifying and identifying the interference type and interference mode of the electromagnetic interference data, perform interference source tracing analysis on the identified different types of electromagnetic interference data to identify external interference sources and internal interference sources.

[0008] Furthermore, based on the original echo signal data collected by the weather radar, extract the characteristic parameters related to electromagnetic interference through multi-dimensional analysis, specifically including:

[0009] The weather radar system collects and preprocesses the original echo signal data in the conventional detection working mode. Based on the preprocessed echo signal data, extract characteristic parameters in multiple dimensions, and the dimensions include the time domain, frequency domain, and statistical dimension;

[0010] In the time domain dimension, the extracted characteristic parameters include signal duration, amplitude mutation rate, and intermittent distribution characteristics; in the frequency domain dimension, convert the echo signal from the time domain to the frequency domain, and the extracted characteristic parameters include spectral energy distribution, spectral mutation points, and bandwidth broadening degree; in the statistical dimension, the characteristic parameters extracted based on the sliding window include extreme anomaly rate, variance change amplitude, skewness, and kurtosis.

[0011] Furthermore, construct and train an interference recognition model, specifically including:

[0012] Construct a sample set for model training, and the sample set includes normal echo data and abnormal echo data containing electromagnetic interference;

[0013] Among them, the normal echo data is selected from the radar observation data segments that have been confirmed by artificial or expert systems to be free of interference; the abnormal echo data is selected from the echo data including the interference events marked in the historical records;

[0014] Build an interference recognition model based on a convolutional neural network, use a sample set to train the interference recognition model, and after the training process is completed, solidify and save the model parameters;

[0015] Based on an independent validation set that does not overlap with the sample set, perform performance evaluation on the trained interference recognition model. During the performance evaluation process, use multiple classification metrics to comprehensively analyze the model effect. The classification metrics include accuracy, recall rate, false alarm rate, and F1-score.

[0016] Further, deploy the interference recognition model to the meteorological radar data processing flow and identify electromagnetic interference data, specifically including:

[0017] Embed the trained and verified interference recognition model into the data processing flow of the meteorological radar system in a modular form. During the model deployment process, build a data interaction interface for receiving feature parameters;

[0018] Input the feature parameters into the interference recognition model, perform interference discrimination operations, and output the interference recognition results corresponding to each frame or each group of echo signal data. The interference recognition results include at least one binary decision label. When the label value of the binary decision label is "1", it indicates that there is electromagnetic interference data in the echo signal data, and when it is "0", it indicates that the echo signal data is normal data;

[0019] Explicitly mark the echo signal data determined by the model to contain electromagnetic interference data. The explicit marking includes the following marking information: label information on the presence or absence of interference, frame number range where interference occurs, interference duration length, interference intensity level, and affected beam or elevation layer.

[0020] Further, build an interference index based on the electromagnetic interference data and determine the quality level of the electromagnetic interference data according to the interference index, including:

[0021] Extract the frame number range and duration of interference occurrence corresponding to each electromagnetic interference data;

[0022] Extract the interference frame number range where the interference signal intensity exceeds the preset interference signal intensity threshold from the frame number range of interference occurrence;

[0023] Normalize the interference frame number range and duration of interference occurrence corresponding to each electromagnetic interference data to obtain the normalized interference frame number range parameter and duration parameter;

[0024] Perform a difference operation on the normalized interference frame number range parameter and duration parameter to obtain the difference between the normalized interference frame number range parameter and duration parameter;

[0025] Compare the difference between the interference frame number range parameter and the duration parameter after the normalization process with a preset difference threshold;

[0026] Filter out the electromagnetic interference data with the difference between the interference frame number range parameter and the duration parameter after the normalization process lower than the difference threshold as the first electromagnetic interference data set;

[0027] Filter out the electromagnetic interference data with the difference between the interference frame number range parameter and the duration parameter after the normalization process not lower than the difference threshold as the second electromagnetic interference data set;

[0028] Determine the quality level of the meteorological radar electromagnetic interference data according to the first electromagnetic interference data and the second electromagnetic interference data.

[0029] Further, determining the quality level of the meteorological radar electromagnetic interference data according to the first electromagnetic interference data and the second electromagnetic interference data includes:

[0030] Extract the affected beam or elevation layer corresponding to each first electromagnetic interference data and second electromagnetic interference data in the first electromagnetic interference data set and the second electromagnetic interference data set;

[0031] Normalize the affected beam using the standard beam to obtain the normalized beam parameters corresponding to each first electromagnetic interference data and second electromagnetic interference data; or, normalize each elevation layer corresponding to each first electromagnetic interference data and second electromagnetic interference data using the elevation range corresponding to the standard elevation layer to obtain the normalized elevation parameters corresponding to each first electromagnetic interference data and second electromagnetic interference data;

[0032] Unify the beam parameters or elevation parameters corresponding to the first electromagnetic interference data as the spatial coefficient, and obtain the first spatial coefficient standard deviation corresponding to the first electromagnetic interference data set according to the spatial coefficient corresponding to the first electromagnetic interference data;

[0033] Unify the beam parameters or elevation parameters corresponding to the second electromagnetic interference data as the spatial coefficient, and obtain the second spatial coefficient standard deviation corresponding to the second electromagnetic interference data set according to the spatial coefficient corresponding to the second electromagnetic interference data;

[0034] Extract the average value of the difference between the interference frame number range parameter and the duration parameter after the normalization process corresponding to the first electromagnetic interference data set;

[0035] Extract the average value of the difference between the interference frame number range parameter and the duration parameter after the normalization process corresponding to the second electromagnetic interference data set;

[0036] The interference index corresponding to the overall electromagnetic interference data is obtained by combining the standard deviation of the first spatial coefficient and the standard deviation of the second spatial coefficient with the average difference corresponding to the first electromagnetic interference data set and the average difference corresponding to the second electromagnetic interference data set.

[0037] Further, the interference types and interference patterns of the electromagnetic interference data are classified and identified, specifically including:

[0038] Based on the marked electromagnetic interference data, the characteristic parameter vector set corresponding to the electromagnetic interference data is extracted and sorted out;

[0039] A classification library for interference types is constructed. The classification library for interference types includes the reference characteristic distribution range and category labels of interference types. The interference types include periodic interference, broadband interference, pulse interference, and frequency modulation interference.

[0040] Further, the interference types and interference patterns of the electromagnetic interference data are classified and identified, and specifically also include:

[0041] For the extracted electromagnetic interference data, an unsupervised clustering method is used for interference pattern aggregation analysis. The electromagnetic interference data is divided into several clustering clusters according to the feature similarity. Each clustering cluster corresponds to an interference category. Based on the established classification library for interference types, the interference category of each clustering cluster is discriminated, and a support vector machine classification model is used to complete the marking;

[0042] The interference type information that has been classified and identified is appended to the original echo signal data to form a triple marking structure of "observed data - interference presence - interference type".

[0043] Further, interference source tracing analysis is performed on the identified different types of electromagnetic interference data, specifically including:

[0044] Correlation analysis is performed on the detection time, spatial position, and radar operating status corresponding to the electromagnetic interference data, and heterogeneous information including radar system operation logs, site geographical information, electromagnetic environment monitoring data, and meteorological condition records is collected;

[0045] The radar system operation logs include radar power status, beam pointing, scanning mode, equipment self - inspection records, and alarm events; the electromagnetic environment monitoring data includes electromagnetic spectrum scanning results around the radar site, distribution of radio transmitting stations, and operating status of adjacent equipment;

[0046] Data fusion is used to align and map the heterogeneous information on the time axis and spatial coordinates to construct a basic data set for interference analysis;

[0047] Based on the interference analysis basic data set, a spatio-temporal distribution map of interference events is constructed using a geographic information system. The spatio-temporal distribution map is centered on a radar station, marking the time period when the interference event occurs, the azimuth angle and elevation angle layers of the corresponding beam, and representing the distribution density and change trend of the interference in space through a heat map and a trajectory map.

[0048] Furthermore, perform interference source tracing analysis on the identified different types of electromagnetic interference data, which specifically includes:

[0049] According to the interference type, its occurrence frequency and intensity, count the occurrence frequency, interference duration and intensity level distribution of each type of interference in different time periods, and output statistical charts;

[0050] Based on the spatio-temporal distribution map, trace the path of each type of interference and infer the potential interference radiation source area, match the known external electromagnetic interference source with the potential interference radiation source area, and if the spatial distance, interference frequency band and interference type match, mark it as an external interference source;

[0051] Identify the interference caused by abnormal internal equipment of the meteorological radar system. According to the change trend of the equipment status recorded in the operation log, judge whether there is an internal system abnormality that highly coincides with the occurrence of the interference, and mark the identified abnormal internal equipment of the meteorological radar system as an internal interference source.

[0052] Compared with the prior art, the beneficial effects of the present invention are:

[0053] 1. By modularly embedding the interference recognition model into the meteorological radar data processing flow, the present invention realizes the real-time discrimination and automatic marking of interference data, significantly improves the intelligent level and data processing efficiency of the system. During operation, the model can output a clear interference presence label for each frame or each group of echo data, and mark the key parameters of the interference in a structured manner, enabling subsequent data users to clearly identify the contaminated area, avoid misusing abnormal data, and improve data credibility.

[0054] 2. By performing clustering analysis and classification recognition on the marked electromagnetic interference data, the present invention further identifies the type and pattern characteristics of the interference, thereby realizing more fine-grained interference control. The interference type classification library is based on the characteristic statistical data of a large number of interference samples, combines clustering algorithms and support vector machine classifiers to discriminate unknown interference samples, effectively improves the classification accuracy, automatically divides the interference samples into several pattern categories through unsupervised clustering algorithms, and then compares them with the known type library to achieve accurate identification of typical interference types, providing support for the system to further identify the interference source and formulate countermeasures.

[0055] 3. By integrating multi-source heterogeneous data such as the operating logs of the radar system, electromagnetic environment monitoring data, and geographic information system, the present invention conducts traceability analysis on the identified electromagnetic interference data to achieve precise positioning of external interference sources, and can also identify the interference caused by internal system anomalies, greatly improving the system's comprehensive discrimination ability for the causes of interference. Based on the spatio-temporal tag information of the interference data, combined with the azimuth angle, elevation layer of the radar site, and the radar beam scanning trajectory, the geographic information system is used to draw the interference distribution heat map and trajectory map. By comparing with parameters such as the location of known interference sources and electromagnetic spectrum, rapid matching and identification of external interference sources are achieved. Combining data such as beam control, power supply status, and alarm records in the equipment operating logs, internal anomalies with high coincidence are investigated to identify possible internal interference sources. The two-way traceability mechanism improves the operation and maintenance efficiency and anomaly response ability of the radar site, and reduces the false alarm and missed alarm rates. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a schematic flow chart of the method for controlling the quality of electromagnetic interference data of the meteorological radar of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0058] Please refer to Figure 1 , the present invention provides the following technical solutions:

[0059] A method for controlling the quality of electromagnetic interference data of a meteorological radar based on machine learning, including:

[0060] Based on the echo signal data collected by the weather radar, extract feature parameters related to electromagnetic interference through multi-dimensional analysis, construct and train an interference recognition model, deploy the interference recognition model into the weather radar data processing flow to identify electromagnetic interference data, receive the feature parameters extracted from the radar signal as input for interference discrimination, output the determination result of whether each frame or each group of data contains electromagnetic interference data, and explicitly mark the electromagnetic interference data. Construct an interference index based on the electromagnetic interference data, and determine the quality level of the electromagnetic interference data according to the interference index. Compare the interference index corresponding to the electromagnetic interference data with a preset index threshold. When the interference index corresponding to the electromagnetic interference data exceeds the preset index threshold, it is determined that the quality of the electromagnetic interference data is high, and an interference anomaly alarm is issued. When the interference index corresponding to the electromagnetic interference data does not exceed the preset index threshold, it is determined that the level of the electromagnetic interference data is general, and the interference mode and interference type of the electromagnetic interference data are identified;

[0061] After classifying and identifying the interference type and interference mode of the electromagnetic interference data, perform interference source tracing analysis on the identified different types of electromagnetic interference data to identify external interference sources and internal interference sources.

[0062] Based on the original echo signal data collected by the weather radar, extract feature parameters related to electromagnetic interference through multi-dimensional analysis, specifically including:

[0063] The weather radar system collects and preprocesses the original echo signal data in the conventional detection working mode. Based on the preprocessed echo signal data, feature parameters are extracted in multiple dimensions, and the dimensions include the time domain, frequency domain, and statistical dimension;

[0064] In the time domain dimension, the extracted feature parameters include signal duration, amplitude mutation rate, and intermittent distribution characteristics; in the frequency domain dimension, the echo signal is transformed from the time domain to the frequency domain, and the extracted feature parameters include spectral energy distribution, spectral mutation points, and bandwidth broadening degree; in the statistical dimension, the feature parameters extracted based on the sliding window include extreme anomaly rate, variance change amplitude, skewness, and kurtosis.

[0065] In the above embodiments, by extracting multi-dimensional characteristic parameters from the original echo signal data collected by the meteorological radar, the recognition accuracy and anti-interference ability of the system against electromagnetic interference are effectively improved. Typical interference characteristics are extracted in the time domain, frequency domain, and statistical dimension respectively, enabling the system to understand the abnormal manifestations of interference signals from different signal representation levels. For example, time domain characteristics such as signal mutation and intermittency reflect the suddenness and discontinuity of interference, frequency domain characteristics such as abnormal spectral energy distribution reveal the abnormal occupation of frequency resources, while the statistical dimension reveals the overall distribution law of interference signals and the differences from normal signals. This multi-dimensional and all-round characteristic parameter extraction method avoids the recognition blind spots and false judgment risks caused by relying on single-dimensional signal characteristics, and enhances the discriminant ability of the model for complex interference samples.

[0066] Construct and train an interference recognition model, specifically including:

[0067] Construct a sample set for model training, where the sample set includes normal echo data and abnormal echo data containing electromagnetic interference;

[0068] Among them, the normal echo data is selected from radar observation data segments confirmed to be interference-free by artificial or expert systems; the abnormal echo data is selected from echo data including marked interference events in historical records;

[0069] Construct an interference recognition model based on a convolutional neural network, use the sample set to train the interference recognition model, and after the training process is completed, solidify and save the model parameters;

[0070] Based on an independent validation set that does not overlap with the sample set, perform performance evaluation on the trained interference recognition model. During the performance evaluation process, use multiple classification metrics to comprehensively analyze the model effect, and the classification metrics include accuracy, recall rate, false alarm rate, and F1-score.

[0071] In the above embodiments, an interference recognition model based on a convolutional neural network is constructed and trained, which not only effectively realizes the automatic recognition and classification of electromagnetic interference data, but also breaks through the technical bottlenecks of low recognition accuracy and weak generalization ability of traditional rule- or threshold-based methods. By introducing manually annotated normal and interference samples to construct a high-quality training set and combining it with a non-overlapping validation set for performance evaluation, the scientificity and robustness of model training can be guaranteed. Especially on the basis of adopting the convolutional neural network (CNN) structure, the model has the ability to efficiently learn local feature structures, can quickly locate the feature regions of electromagnetic interference in large-scale echo signals, and achieve high-precision classification and discrimination. In addition, during the model training process, multiple evaluation criteria such as accuracy, recall rate, false alarm rate, and F1-score are comprehensively used, which helps to comprehensively analyze the model performance and facilitate subsequent optimization and adjustment. The finally trained model parameters are solidified and saved, providing a stable and reliable technical guarantee for actual deployment, and effectively supporting the real-time determination requirement of electromagnetic interference data in the actual operation of the radar system.

[0072] Deploy the interference recognition model into the meteorological radar data processing flow and identify electromagnetic interference data, specifically including:

[0073] Embed the trained and verified interference recognition model into the data processing flow of the meteorological radar system in a modular form. During the model deployment process, construct a data interaction interface for receiving feature parameters;

[0074] Input the feature parameters into the interference recognition model, perform interference discrimination operations, and output the interference recognition results corresponding to each frame or each group of echo signal data. The interference recognition results at least include one binary decision label. When the label value of the binary decision label is "1", it indicates that there is electromagnetic interference data in the echo signal data, and when it is "0", it indicates that the echo signal data is normal data;

[0075] Explicitly mark the echo signal data determined by the model to contain electromagnetic interference data. The explicit marking includes the following marking information: label information on the presence or absence of interference, the frame number range where the interference occurs, the interference duration length, the interference intensity level, and the affected beam or elevation layer.

[0076] In the above embodiments, by modularly embedding the interference recognition model into the meteorological radar data processing flow, real-time discrimination and automatic marking of interference data are achieved, significantly improving the intelligent level and data processing efficiency of the system. During operation, the model can output clear interference presence tags for each frame or each set of echo data, and mark the key parameters of interference in a structured manner, such as interference duration, intensity level, and affected beam range, etc., enabling subsequent data users to clearly identify the contaminated areas, avoid misusing abnormal data, and improve data credibility. In addition, the explicitly marked interference information also provides a necessary basis for subsequent interference classification recognition and traceability analysis, forming a complete interference recognition closed-loop, greatly reducing the workload of manual interference recognition, and improving the automation and intelligent level of the radar system.

[0077] Specifically, an interference index is constructed based on the electromagnetic interference data, and the quality level of the electromagnetic interference data is determined according to the interference index, including:

[0078] Extract the frame number range and duration of interference occurrence corresponding to each electromagnetic interference data;

[0079] Extract the frame number range of interference signals whose intensity exceeds the preset dry signal intensity threshold from the frame number range of interference occurrence;

[0080] Normalize the frame number range of interference occurrence and the duration of interference corresponding to each electromagnetic interference data to obtain the normalized frame number range parameter and duration parameter;

[0081] Perform a difference process on the normalized frame number range parameter and duration parameter to obtain the difference between the normalized frame number range parameter and duration parameter;

[0082] Compare the difference between the normalized frame number range parameter and duration parameter with a preset difference threshold;

[0083] Select the electromagnetic interference data with the difference between the normalized frame number range parameter and duration parameter lower than the difference threshold as the first electromagnetic interference data set;

[0084] Select the electromagnetic interference data with the difference between the normalized frame number range parameter and duration parameter not lower than the difference threshold as the second electromagnetic interference data set;

[0085] Determine the quality level of the meteorological radar electromagnetic interference data according to the first electromagnetic interference data and the second electromagnetic interference data.

[0086] The technical effects of the above technical solution are as follows: By extracting the frame number range and duration of interference occurrence corresponding to each electromagnetic interference data, and further screening out the frame number range of interference signals with an intensity exceeding the preset interference signal intensity threshold, the effective interference data range can be determined more accurately, excluding some interference data with low interference intensity and less likely to affect meteorological radar data, making the subsequent processed interference data more representative and accurate, thereby improving the accuracy of meteorological radar electromagnetic interference data. Normalizing the frame number range and duration of interference eliminates the influence of different dimensions and numerical ranges of the original data, providing a more scientific basis for subsequent difference processing, facilitating improving the accuracy of data processing and analysis, and further enhancing the reliability of the quality assessment of meteorological radar electromagnetic interference data. By comparing the difference between the normalized frame number range parameter and the duration parameter with a preset difference threshold, the electromagnetic interference data is screened into a first electromagnetic interference data set (the difference is lower than the difference threshold) and a second electromagnetic interference data set (the difference is not lower than the difference threshold), realizing effective classification of the electromagnetic interference data. This classification method helps to more clearly understand the characteristics of electromagnetic interference data of different quality levels, facilitating subsequent targeted measures according to the data characteristics of different sets. For example, the data in the first electromagnetic interference data set may be more trusted and used for more important analysis, while the data in the second electromagnetic interference data set may need further verification or supplementation, improving the efficiency and pertinence of meteorological radar data processing. Determining the quality level of meteorological radar electromagnetic interference data based on the first electromagnetic interference data and the second electromagnetic interference data, this method of determining the quality level is more scientific and reasonable based on the previous accurate data extraction, standardization processing, and reasonable data classification, can more accurately reflect the quality of meteorological radar electromagnetic interference data, providing a reliable basis for the performance evaluation, interference analysis, and possible improvement measures of the meteorological radar system, and ultimately contributing to improving the overall performance and reliability of the meteorological radar system.

[0087] Specifically, determining the quality level of meteorological radar electromagnetic interference data according to the first electromagnetic interference data and the second electromagnetic interference data includes:

[0088] Extracting the affected beam or elevation layer corresponding to each first electromagnetic interference data and second electromagnetic interference data in the first electromagnetic interference data set and the second electromagnetic interference data set;

[0089] Normalize the influence beam using the standard beam to obtain the beam parameters after normalization corresponding to each first electromagnetic interference data and second electromagnetic interference data; or, normalize the elevation layer corresponding to each first electromagnetic interference data and second electromagnetic interference data using the elevation range corresponding to the standard elevation layer to obtain the elevation parameters after normalization corresponding to each first electromagnetic interference data and second electromagnetic interference data;

[0090] Unify the beam parameters or elevation parameters corresponding to the first electromagnetic interference data as spatial coefficients, and obtain the standard deviation of the first spatial coefficient corresponding to the set of first electromagnetic interference data according to the spatial coefficients corresponding to the first electromagnetic interference data;

[0091] Unify the beam parameters or elevation parameters corresponding to the second electromagnetic interference data as spatial coefficients, and obtain the standard deviation of the second spatial coefficient corresponding to the set of second electromagnetic interference data according to the spatial coefficients corresponding to the second electromagnetic interference data;

[0092] Extract the average value of the difference between the interference frame number range parameter and the duration parameter after normalization corresponding to the set of first electromagnetic interference data;

[0093] Extract the average value of the difference between the interference frame number range parameter and the duration parameter after normalization corresponding to the set of second electromagnetic interference data;

[0094] Use the standard deviation of the first spatial coefficient and the standard deviation of the second spatial coefficient, combined with the average value of the difference corresponding to the set of first electromagnetic interference data and the average value of the difference corresponding to the set of second electromagnetic interference data, to obtain the interference index corresponding to the overall electromagnetic interference data;

[0095] Among them, the interference index corresponding to the overall electromagnetic interference data is obtained through the following formula:

[0096] ;

[0097] Among them, Q represents the interference index corresponding to the overall electromagnetic interference data; k 01 and k 02 respectively represent the standard deviation of the first spatial coefficient and the standard deviation of the second spatial coefficient; C 01 and C 02 respectively represent the average value of the difference corresponding to the set of first electromagnetic interference data and the average value of the difference corresponding to the set of second electromagnetic interference data; C represents a preset difference threshold, which can be set by itself according to the actual application situation, combined with the historical data empirical value; specifically, k 01 and k 02 reflect the discrete degree of interference in space, C 01 、C 02Reflect the average deviation of the difference in time-related parameters (range of interference frames and duration). C is a preset reference standard. Multiplying the standard deviation by their ratio is to comprehensively consider the spatial interference feature (standard deviation) and time interference features (average difference value, difference threshold) in one calculation step. This can comprehensively reflect the impact of the comprehensive characteristics of electromagnetic interference in the space-time dimension on the interference index, because the electromagnetic interference of the weather radar is not determined by a single dimension of space or time alone, but the result of the combined action of both. The smaller the value of this logarithmic part, it indicates that the degree of discrete interference of the first electromagnetic interference data set in space (k 01 ) is relatively small, and the comprehensive deviation degree of the average difference value of the interference frame number range parameter and the duration parameter in time (C 01 ) and the preset difference threshold (C) is also small. That is, the interference in the first electromagnetic interference data set is relatively stable and regular in space-time, so the data quality corresponding to the first electromagnetic interference data set is better; conversely, the larger the value of the logarithmic part, the worse the data quality. The smaller the value of this logarithmic part, it means that the second electromagnetic interference data set performs better in terms of the degree of discrete interference in space (k 02 ) and the degree of deviation of time interference features (reflected by the relationship between C 02 and C). The interference is relatively stable and orderly in space-time, and the data quality corresponding to the second electromagnetic interference data set is better; the larger the value of the logarithmic part, the worse the data quality. The two logarithmic functions respectively represent the quantization results of the comprehensive interference features of the first and second electromagnetic interference data sets. The subtraction operation is to compare the differences in space-time interference features between these two types of data sets. Through subtraction, the differences in the degree of discrete interference in space and the degree of deviation of time interference features between the two can be highlighted, so as to more clearly understand the differences in the interference of different types of electromagnetic interference data sets on the weather radar, and provide a basis for comprehensively evaluating the overall electromagnetic interference data quality of the weather radar. There are some common factors (such as environmental background interference, etc.) in the electromagnetic interference received by the weather radar, which may act on both types of electromagnetic interference data sets at the same time. Subtracting the logarithmic functions can, to a certain extent, eliminate the influence of these common factors, and focus more on the differences in the unique interference features of the two types of data sets themselves, making the interference index more accurately reflect the differences in the impact of different data sets on the weather radar data quality. The smaller the difference value (i.e., the Q value) after subtraction, it indicates that the differences in space-time interference features between the first electromagnetic interference data set and the second electromagnetic interference data set are smaller, and overall, the interference is relatively stable and regular in space-time, and the electromagnetic interference data quality of the weather radar is better; the larger the difference value, it indicates that the differences in space-time interference features between the two types of data sets are large, the interference situation is complex and changeable, and the electromagnetic interference data quality of the weather radar is worse.

[0098] Compare the interference index corresponding to the overall electromagnetic interference data with a preset index threshold;

[0099] When the interference index corresponding to the overall electromagnetic interference data exceeds the preset index threshold, it is determined that the quality level of the meteorological radar electromagnetic interference data is high, and an interference anomaly alarm is issued;

[0100] When the interference index corresponding to the overall electromagnetic interference data does not exceed the preset index threshold, it is determined that the quality level of the meteorological radar electromagnetic interference data is general, and the interference types and interference modes of the electromagnetic interference data are classified and identified.

[0101] The technical effects of the above technical solution are as follows: Extract the affected beam or elevation layer corresponding to the interference data, and perform normalization processing to obtain beam parameters and elevation parameters, and unify them into spatial coefficients. This enables the characteristics of electromagnetic interference data to be accurately measured from the spatial dimension. Considering the interference conditions of different beams and elevation layers helps to comprehensively and accurately evaluate the interference effects on the meteorological radar at different spatial positions, improve the accuracy of the analysis of the interference spatial distribution characteristics, and further improve the reliability of the meteorological radar data quality assessment. Calculate the standard deviation of the spatial coefficients corresponding to the first and second electromagnetic interference data sets. The standard deviation can reflect the degree of dispersion of the data. Through this operation, the fluctuation of the spatial coefficients in the two data sets can be quantitatively understood, that is, the degree of dispersion or concentration of the interference in the spatial dimension. This provides a quantitative index for evaluating the stability of the interference in space, making the analysis of the meteorological radar electromagnetic interference situation more scientific and assisting in judging the degree of influence of the interference on the radar spatial detection performance. Extract the average value of the difference between the normalized interference frame number range parameter and the duration parameter in the two data sets. This average value reflects the average difference in the time-related characteristics (frame number range and duration) of the two types of interference data, which helps to comprehensively analyze the characteristics of the interference data from the time dimension. Combining with the standard deviation of the spatial coefficients, the characteristics of the electromagnetic interference data can be more comprehensively grasped from multiple time-space dimensions, improving the accuracy of the meteorological radar interference assessment. Use the standard deviation of the spatial coefficients and the average value of the difference to obtain the interference index corresponding to the overall electromagnetic interference data. By comprehensively considering multiple key indicators to obtain the interference index, the severity of the electromagnetic interference suffered by the meteorological radar can be quantitatively characterized as a whole, providing a simple and comprehensive evaluation index, which is convenient for quickly and intuitively judging the interference situation, providing a clear basis for subsequent quality level determination and countermeasures, and improving the efficiency and effectiveness of the meteorological radar interference assessment. Compare the interference index with the preset index threshold to determine the quality level of the meteorological radar electromagnetic interference data, and adopt different countermeasures (interference anomaly alarm or interference type and mode classification and identification). This hierarchical determination and targeted processing method enable the meteorological radar to make reasonable responses according to the severity of the interference, promptly alarm and prompt attention for high-level interference, and further analyze its type and mode for general-level interference, which helps to improve the ability of the meteorological radar system to cope with electromagnetic interference and ensure the quality of radar data and the stable operation of the system.

[0102] On the other hand, the standard deviation k of the first spatial coefficient is incorporated into the formula 01 , the standard deviation k of the second spatial coefficient 02 , the average difference C corresponding to the first electromagnetic interference data set 01 the interference frame number range parameter, the average difference C corresponding to the second electromagnetic interference data set 02 and the preset difference threshold C. By performing logarithmic operations to fuse these factors, the dispersion degree (standard deviation) of interference in the spatial dimension and the average difference (average difference value) in the time-related dimension are comprehensively considered, enabling the interference index to comprehensively reflect various characteristics of meteorological radar electromagnetic interference, avoiding the one-sidedness of single-factor evaluation, and improving the accuracy and comprehensiveness of the description of the interference situation by the interference index. Using a logarithmic function for calculation, the non-linear characteristics of the logarithmic function can perform non-linear transformation on the input parameters, compress large values and stretch small values to a certain extent, so that parameters of different magnitudes can be comprehensively calculated on a relatively balanced scale. At the same time, the operation form of each parameter in the formula with the preset difference threshold C is similar to a normalization method, which transforms parameters from different sources and magnitudes into a comparable and comprehensively calculable form, helping to eliminate the influence of the dimension and magnitude differences between parameters, making the calculated interference index more reasonable and comparable, and being able to more scientifically measure the interference degree. The formula highlights the differences between the first and second electromagnetic interference data sets in terms of the standard deviation of the spatial coefficient and the average difference value through the form of logarithmic subtraction. The logarithmic subtraction operation makes the relative differences between the corresponding parameters of the two data sets more obvious, can effectively capture the differences in the spatio-temporal characteristics of the two types of interference data, and further enables the interference index to more sensitively reflect the differences between the meteorological radar electromagnetic interference data sets, providing a more powerful quantitative basis for accurately evaluating the interference situation.

[0103] Classify and identify the interference types and interference patterns of electromagnetic interference data, specifically including:

[0104] Based on the marked electromagnetic interference data, extract and organize the set of characteristic parameter vectors corresponding to the electromagnetic interference data;

[0105] Construct an interference type classification library, which includes the reference characteristic distribution range and category labels of interference types, and the interference types include periodic interference, broadband interference, pulse interference, and frequency modulation interference;

[0106] For the extracted electromagnetic interference data, use an unsupervised clustering method to perform interference pattern aggregation analysis, divide the electromagnetic interference data into several clustering clusters according to the feature similarity, each clustering cluster corresponds to an interference category, and based on the established interference type classification library, perform interference category discrimination on each clustering cluster, and complete the marking using a support vector machine classification model;

[0107] Attach the classified and identified interference type information to the original echo signal data to form a triple-tag structure of "observed data - interference presence - interference type".

[0108] In the above embodiment, by performing cluster analysis and classification identification on the marked electromagnetic interference data, the system can further identify the type and pattern characteristics of the interference, thereby achieving more fine-grained interference control. The interference type classification library is based on the feature statistical data of a large number of interference samples, and combines the clustering algorithm and the support vector machine classifier to discriminate unknown interference samples, effectively improving the classification accuracy. By using the unsupervised clustering algorithm, the interference samples are automatically divided into several pattern categories, and then compared with the known type library, it is possible to accurately identify typical interference types such as periodic, pulsed, broadband, and frequency modulation interference, providing support for the system to further identify the interference source and formulate countermeasures. In addition, the classification and identification results are attached to the original observation data to form a triple structure of "observed data - interference presence - interference type", which not only improves the integrity and systematicness of data annotation, but also helps to construct a high-quality interference training data set for the continuous optimization of future models.

[0109] Perform interference source tracing analysis on the identified different types of electromagnetic interference data, specifically including:

[0110] Perform correlation analysis on the detection time, spatial position, and radar operating status corresponding to the electromagnetic interference data, and collect heterogeneous information including radar system operation logs, site geographical information, electromagnetic environment monitoring data, and meteorological condition records;

[0111] The radar system operation logs include radar power status, beam pointing, scanning mode, equipment self-check records, and alarm events; the electromagnetic environment monitoring data includes the electromagnetic spectrum scanning results around the radar site, the distribution of radio transmitting stations, and the operating status of adjacent equipment;

[0112] Use data fusion to align and map the heterogeneous information on the time axis and spatial coordinates to construct a basic data set for interference analysis;

[0113] Based on the basic data set for interference analysis, use a geographic information system to construct a spatio-temporal distribution map of interference events. The spatio-temporal distribution map is centered on the radar station, marking the time period when the interference event occurs, the azimuth angle and elevation angle layers of the corresponding beam, and representing the distribution density and change trend of the interference in space through a heat map and a trajectory map;

[0114] According to the interference type, its occurrence frequency and intensity, count the distribution of the occurrence frequency, interference duration, and intensity level of each type of interference in different time periods, and output statistical charts;

[0115] Based on the spatio-temporal distribution map, trace the path of each type of interference and infer the potential interference radiation source area. Match the known external electromagnetic interference sources with the potential interference radiation source area. If the spatial distance, interference frequency band, and interference type match, mark it as an external interference source;

[0116] Identify the interference caused by the abnormal operation of internal equipment in the meteorological radar system. According to the trend of equipment status changes recorded in the operation log, determine whether there is an internal system abnormality that highly coincides with the occurrence of interference, and mark the identified abnormal internal equipment of the meteorological radar system as an internal interference source

[0117] In the above embodiment, by integrating multi-source heterogeneous data such as the operation log of the radar system, electromagnetic environment monitoring data, and geographic information system, the source analysis of the identified electromagnetic interference data is carried out. It not only realizes the accurate positioning of external interference sources, but also can identify the interference caused by internal system abnormalities, greatly improving the system's comprehensive discrimination ability of interference causes. Based on the spatio-temporal tag information of interference data, combined with the azimuth angle, elevation layer of the radar site, and the radar beam scanning trajectory, use the geographic information system to draw the interference distribution heat map and trajectory map, visually display the evolution trend of interference in time and space, effectively assist the interference diagnosis decision-making, and realize the rapid matching and identification of external interference sources by comparing with parameters such as the position and electromagnetic spectrum of known interference sources; at the same time, combined with data such as beam control, power supply status, and alarm records in the equipment operation log, check for highly coincident internal abnormalities and identify possible internal interference sources. This two-way source tracing mechanism improves the operation and maintenance efficiency and abnormal response ability of the radar site, reduces the false alarm and missed alarm rates, and provides strong support for ensuring the quality of radar observation data.

[0118] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution of the present invention and its inventive concept, makes equivalent substitutions or changes, and should be covered by the protection scope of the present invention.

Claims

1. A method for quality control of electromagnetic interference data of meteorological radar based on machine learning, characterized in that: include: Based on the echo signal data collected by the meteorological radar, characteristic parameters related to electromagnetic interference are extracted through multi-dimensional analysis, an interference identification model is constructed and trained, the interference identification model is deployed in the meteorological radar data processing flow and electromagnetic interference data is identified, the characteristic parameters extracted from the radar signal are received as input for interference discrimination, and the judgment result of whether each frame or each group of data contains electromagnetic interference data is output, and the electromagnetic interference data is explicitly marked, an interference index is constructed based on the electromagnetic interference data, and the quality level of the electromagnetic interference data is determined according to the interference index, and the interference index corresponding to the electromagnetic interference data is compared with a preset index threshold. When the interference index corresponding to the electromagnetic interference data exceeds the preset index threshold, the electromagnetic interference data quality is determined to be high, and an interference abnormality alarm is issued. When the interference index corresponding to the electromagnetic interference data does not exceed the preset index threshold, the electromagnetic interference data level is determined to be general, and the interference mode and interference type of the electromagnetic interference data are identified; After classifying and identifying the interference types and interference patterns of the electromagnetic interference data, interference source tracing analysis is performed on the identified different types of electromagnetic interference data to identify external and internal interference sources.

2. The method for controlling the quality of electromagnetic interference data of a meteorological radar based on machine learning according to claim 1, characterized in that: Based on the original echo signal data collected by the meteorological radar, characteristic parameters related to electromagnetic interference are extracted through multi-dimensional analysis, including: The meteorological radar system collects and preprocesses raw echo signal data in a conventional detection working mode, and extracts characteristic parameters in multiple dimensions based on the preprocessed echo signal data, wherein the dimensions include time domain, frequency domain and statistical dimensions; In the time domain dimension, the extracted characteristic parameters include signal duration, amplitude mutation rate and intermittent distribution characteristics; in the frequency domain dimension, the echo signal is converted from the time domain to the frequency domain, and the extracted characteristic parameters include spectral energy distribution, spectrum mutation point and bandwidth broadening degree; in the statistical dimension, the characteristic parameters extracted based on the sliding window include extreme value anomaly rate, variance change amplitude, skewness and kurtosis.

3. The method for controlling the quality of electromagnetic interference data of a meteorological radar based on machine learning as claimed in claim 1, characterized in that: Build and train the interference recognition model, including: Constructing a sample set for model training, wherein the sample set includes normal echo data and abnormal echo data containing electromagnetic interference; The normal echo data is selected from the radar observation data segment confirmed to be free of interference by manual or expert system; the abnormal echo data is selected from the echo data including the interference events marked in the historical records; An interference recognition model is built based on a convolutional neural network. The interference recognition model is trained using a sample set. After the training process is completed, the model parameters are solidified and saved. Based on an independent validation set that does not overlap with the sample set, the performance of the trained interference recognition model is evaluated. During the performance evaluation process, a variety of classification indicators are used to comprehensively analyze the model effect. The classification indicators include accuracy, recall rate, false alarm rate and F1-score.

4. The method for controlling the quality of electromagnetic interference data of a weather radar based on machine learning according to claim 1, characterized in that: Deploy interference identification models into the weather radar data processing flow and identify electromagnetic interference data, including: The interference identification model that has been trained and verified is embedded in the data processing flow of the meteorological radar system in a modular form. During the model deployment process, a data interaction interface for receiving characteristic parameters is constructed; Input the characteristic parameters into the interference recognition model, perform interference discrimination operation, and output the interference recognition result corresponding to each frame or each group of echo signal data, wherein the interference recognition result includes at least one binary judgment label, and when the label value of the binary judgment label is "1", it indicates that the echo signal data has electromagnetic interference data, and when it is "0", it indicates that the echo signal data is normal data; The echo signal data determined by the model to contain electromagnetic interference data is explicitly marked, and the explicit marking includes the following marking information: label information of whether interference exists, the frame number range in which the interference occurs, the duration of the interference, the interference intensity level and the affected beam or elevation layer.

5. The method for quality control of meteorological radar electromagnetic interference data based on machine learning as claimed in claim 4, characterized in that: Constructing an interference index based on the electromagnetic interference data, and determining the quality level of the electromagnetic interference data according to the interference index, including: Extract the frame number range and duration of interference corresponding to each electromagnetic interference data; Extracting, from the frame number range where the interference occurs, an interference frame number range in which the interference signal strength exceeds a preset interference signal strength threshold; Normalizing the interference frame number range and duration of interference corresponding to each electromagnetic interference data, and obtaining interference frame number range parameters and duration parameters after normalization; Performing difference processing on the interference frame number range parameter and the duration parameter after the normalization processing to obtain the difference between the interference frame number range parameter and the duration parameter after the normalization processing; Comparing the difference between the interference frame number range parameter and the duration parameter after the normalization process with a preset difference threshold; Filter out electromagnetic interference data whose difference between the interference frame number range parameter and the duration parameter after normalization is lower than the difference threshold as the first electromagnetic interference data set; Filter out electromagnetic interference data whose difference between the interference frame number range parameter and the duration parameter after normalization is not less than the difference threshold as the second electromagnetic interference data set; The quality level of the meteorological radar electromagnetic interference data is determined according to the first electromagnetic interference data and the second electromagnetic interference data.

6. The method for controlling the quality of electromagnetic interference data of a meteorological radar based on machine learning as claimed in claim 5, characterized in that: Determining the quality level of the meteorological radar electromagnetic interference data according to the first electromagnetic interference data and the second electromagnetic interference data includes: Extracting an impact beam or elevation layer corresponding to each first electromagnetic interference data and second electromagnetic interference data in the first electromagnetic interference data set and the second electromagnetic interference data set; Normalizing the affected beam using a standard beam to obtain normalized beam parameters corresponding to each first electromagnetic interference data and the second electromagnetic interference data; or, normalizing the elevation layer corresponding to each first electromagnetic interference data and the second electromagnetic interference data using the elevation range corresponding to the standard elevation layer to obtain normalized elevation parameters corresponding to each first electromagnetic interference data and the second electromagnetic interference data; Marking the beam parameters or elevation parameters corresponding to the first electromagnetic interference data as spatial coefficients, and obtaining a first spatial coefficient standard deviation corresponding to the first electromagnetic interference data set according to the spatial coefficients corresponding to the first electromagnetic interference data; Marking the beam parameters or elevation parameters corresponding to the second electromagnetic interference data as spatial coefficients, and obtaining a second spatial coefficient standard deviation corresponding to the second electromagnetic interference data set according to the spatial coefficients corresponding to the second electromagnetic interference data; Extracting the average value of the difference between the interference frame number range parameter and the duration parameter after normalization corresponding to the first electromagnetic interference data set; Extracting the average value of the difference between the interference frame number range parameter and the duration parameter after normalization corresponding to the second electromagnetic interference data set; The interference index corresponding to the overall electromagnetic interference data is obtained by using the first space coefficient standard deviation and the second space coefficient standard deviation in combination with the difference average corresponding to the first electromagnetic interference data set and the difference average corresponding to the second electromagnetic interference data set.

7. The method for controlling the quality of electromagnetic interference data of a weather radar based on machine learning according to claim 1, characterized in that: Classify and identify the interference types and interference patterns of electromagnetic interference data, including: Based on the marked electromagnetic interference data, extract and organize the characteristic parameter vector set corresponding to the electromagnetic interference data; An interference type classification library is constructed, wherein the interference type classification library includes reference feature distribution ranges and category labels of interference types, and the interference types include periodic interference, broadband interference, pulse interference, and frequency modulation interference.

8. The method for controlling the quality of electromagnetic interference data of a meteorological radar based on machine learning as claimed in claim 7, characterized in that: Classify and identify the interference type and interference mode of electromagnetic interference data, including: For the extracted electromagnetic interference data, an unsupervised clustering method is used to perform interference pattern aggregation analysis. The electromagnetic interference data is divided into several clusters based on feature similarity. Each cluster corresponds to an interference category. Based on the established interference type classification library, the interference category of each cluster is identified and the support vector machine classification model is used to complete the labeling. The classified and identified interference type information is added to the original echo signal data to form a triple labeling structure of "observation data-interference existence-interference type".

9. The method for controlling the quality of electromagnetic interference data of a weather radar based on machine learning according to claim 1, characterized in that: Conduct interference source tracing analysis on the identified different types of electromagnetic interference data, including: Conduct correlation analysis on the detection time, spatial location and radar operation status corresponding to the electromagnetic interference data, and collect heterogeneous information including radar system operation logs, site geographic information, electromagnetic environment monitoring data, and meteorological condition records; The radar system operation log includes radar power status, beam pointing, scanning mode, equipment self-test records and alarm events; the electromagnetic environment monitoring data includes electromagnetic spectrum scanning results around the radar site, distribution of radio transmitters and operating status of nearby equipment; Data fusion is used to align and map heterogeneous information on the time axis and spatial coordinates to construct a basic data set for interference analysis; Based on the basic data set for interference analysis, a geographic information system is used to construct a spatiotemporal distribution map of interference events. The spatiotemporal distribution map is centered on the radar station, marking the time period when the interference event occurred, the azimuth and elevation layers of the corresponding beam, and the distribution density and change trend of the interference in space are represented by heat maps and trajectory maps.

10. The method for controlling the quality of electromagnetic interference data of a weather radar based on machine learning according to claim 9, characterized in that: Conduct interference source tracing analysis on the identified different types of electromagnetic interference data, including: According to the interference type, frequency and intensity, statistics are compiled on the frequency of each type of interference in different time periods, the duration of interference and the distribution of intensity levels, and statistical charts are output; Based on the time-space distribution map, the path of each type of interference is traced and the potential interference radiation source area is inferred. The known external electromagnetic interference source is matched with the potential interference radiation source area. If the spatial distance, interference frequency band and interference type are consistent, it is marked as an external interference source. Identify the interference caused by abnormal equipment inside the weather radar system. Based on the equipment status change trend recorded in the operation log, determine whether there is an internal system abnormality that highly overlaps with the interference, and mark the identified abnormal equipment inside the weather radar system as an internal interference source.

Images