A method for evaluating and processing electromagnetic radiation of communication signals and a storage medium

Abstract

The present invention provides a method, a system and a storage medium for evaluating and processing electromagnetic radiation of communication signals. Among them, real-time monitored electromagnetic radiation data is acquired; the pre-trained anomaly detection model is used to analyze the pre-processed electromagnetic radiation data to identify electromagnetic radiation signals with abnormal intensity; characteristic parameters of the electromagnetic radiation signals with abnormal intensity are calculated; according to the characteristic parameters, the anomaly level of the electromagnetic radiation signals with abnormal intensity is evaluated through a preset evaluation rule; an evaluation result is output, and the evaluation result at least includes the anomaly level and the corresponding treatment measures for the anomaly level. The technical solution provided by the present invention can automatically identify and evaluate electromagnetic radiation signals with abnormal intensity, reduce the need for manual intervention, and improve work efficiency and processing speed.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of data processing, and in particular, to a method, a system and a storage medium for evaluating and processing electromagnetic radiation of communication signals. Background Art

[0002] In communication technology, communication signals refer to electromagnetic waves carrying information. These signals can be analog or digital, and they propagate in space in the form of radio waves for wireless communication. With the development of modern technology, electromagnetic radiation has become an inevitable part of people's daily lives. In application scenarios such as communication base stations, radar systems, and industrial equipment, the monitoring of electromagnetic radiation has become increasingly important. The reason for the generation of electromagnetic radiation is as follows: Any accelerating charge will generate an electromagnetic field, and when these electromagnetic fields propagate in the form of waves, electromagnetic radiation is formed. In communication base stations, radar systems, industrial equipment, etc., the operation of electronic devices will generate electromagnetic radiation.

[0003] Monitoring electromagnetic radiation is to ensure that its level is within a safe range and to avoid affecting human health and electronic devices. However, traditional electromagnetic radiation evaluation methods often rely on the detection and judgment of simple electromagnetic radiation intensity. Even if abnormal signals can be identified, there are no targeted treatment measures, resulting in the inability to effectively control risks. Summary of the Invention

[0004] The embodiments of the present invention provide a method, a system and a storage medium for evaluating and processing electromagnetic radiation of communication signals, so as to solve the problem of poor effect in automatically identifying and evaluating electromagnetic radiation signals with abnormal intensity in the prior art.

[0005] In a first aspect, the embodiments of the present invention provide a method for evaluating and processing electromagnetic radiation of communication signals, including:

[0006] Obtaining real-time monitored electromagnetic radiation data;

[0007] Using a pre-trained anomaly detection model to analyze the preprocessed electromagnetic radiation data to identify electromagnetic radiation signals with abnormal intensity, where the preprocessing at least includes: denoising, smoothing processing, and frequency transformation;

[0008] Calculating characteristic parameters of the electromagnetic radiation signals with abnormal intensity, where the characteristic parameters at least include time-weighted average radiation intensity, peak intensity, energy density, and spectral entropy;

[0009] Evaluating the anomaly level of the electromagnetic radiation signals with abnormal intensity according to the characteristic parameters through a preset evaluation rule;

[0010] Outputting an evaluation result, where the evaluation result at least includes the anomaly level and the corresponding treatment measures for the anomaly level.

[0011] Optionally, the preprocessing at least includes: denoising, smoothing, and frequency transformation;

[0012] Before analyzing the preprocessed electromagnetic radiation data using a pre-trained anomaly detection model to identify electromagnetic radiation signals of abnormal intensity, it further includes:

[0013] Performing a Fourier transform on the electromagnetic radiation data to convert it into a frequency-domain signal;

[0014] Using a band-pass filter to filter out noise signals outside a specified frequency range, where the specified frequency range is determined according to the frequency range of electromagnetic radiation signals of normal intensity, and is used to retain frequency components related to electromagnetic radiation signals of abnormal intensity;

[0015] Applying a sliding window smoothing algorithm to reduce the signal fluctuations of the electromagnetic radiation data.

[0016] Optionally, the using a pre-trained anomaly detection model to analyze the preprocessed electromagnetic radiation data to identify electromagnetic radiation signals of abnormal intensity includes:

[0017] Using a long short-term memory network for time series prediction to identify electromagnetic radiation signals of abnormal intensity by capturing long-term dependencies in the electromagnetic radiation data; and / or,

[0018] Combining with an autoencoder to identify electromagnetic radiation signals of abnormal intensity by reconstructing the difference between the electromagnetic radiation signals of normal intensity and the electromagnetic radiation data; and / or,

[0019] Using a support vector machine for classification to distinguish between electromagnetic radiation signals of normal intensity and electromagnetic radiation signals of abnormal intensity by constructing an optimal hyperplane.

[0020] Optionally, the calculating the characteristic parameters of the electromagnetic radiation signals of abnormal intensity includes:

[0021] By the formula: , calculating the time-weighted average radiation intensity of the electromagnetic radiation signals of abnormal intensity; where, represents the time-weighted average radiation intensity, represents the radiation intensity at the i-th moment, N represents the number of sampling points, represents a time-based weight function, where, , represents the attenuation coefficient, represents the time difference between the i-th moment and the reference moment;

[0022] By the formula: , calculate the peak intensity of the electromagnetic radiation signal with abnormal intensity, where P represents the peak intensity, represents the radiation intensity at the i-th moment, i = {1, 2,..., N};

[0023] Through the formula: , calculate the energy density of the electromagnetic radiation signal with abnormal intensity; where E represents the energy density, represents the sampling interval, represents the energy-based weight function, where, ;

[0024] Through the formula: , calculate the spectral entropy of the electromagnetic radiation signal with abnormal intensity; where S represents the spectral entropy, represents the power ratio of the j-th frequency component, and M represents the total number of frequency components.

[0025] Optionally, evaluating the abnormality level of the electromagnetic radiation signal with abnormal intensity according to the characteristic parameters through a preset evaluation rule includes:

[0026] When the time-weighted average radiation intensity of the electromagnetic radiation signal with abnormal intensity exceeds the preset threshold T1, it is determined as a first-level abnormality;

[0027] When the peak intensity of the electromagnetic radiation signal with abnormal intensity exceeds the preset threshold T2, it is determined as a second-level abnormality;

[0028] When the energy density of the electromagnetic radiation signal with abnormal intensity exceeds the preset threshold T3, it is determined as a third-level abnormality;

[0029] When the spectral entropy of the electromagnetic radiation signal with abnormal intensity is lower than the preset threshold T4, it is determined as a fourth-level abnormality.

[0030] Optionally, evaluating the abnormality level of the electromagnetic radiation signal with abnormal intensity according to the characteristic parameters through a preset evaluation rule includes:

[0031] Define the abnormality level calculation formula: ;

[0032] Among them, G represents the abnormality level, w1, w2, w3, and w4 respectively represent the importance weights of the time-weighted average radiation intensity, peak intensity, energy density, and spectral entropy, and T1, T2, T3, and T4 respectively represent the preset thresholds of the corresponding characteristic parameters.

[0033] Optionally, the calculation formulas for the importance weights w1, w2, w3, and w4 are:

[0034] ;

[0035] Among them, λ is a parameter for adjusting the steepness of the curve, and σ1, σ2, σ3, and σ4 are calibration factors for the corresponding characteristic parameters respectively. 、 、 、 respectively represent the average values of the corresponding characteristic parameters. represents the time-weighted average radiation intensity, P represents the peak intensity, E represents the energy density, and S represents the spectral entropy.

[0036] In a second aspect, an embodiment of the present invention provides a communication signal electromagnetic radiation evaluation and processing system, including:

[0037] An acquisition module for acquiring real-time monitored electromagnetic radiation data;

[0038] A detection module for analyzing the preprocessed electromagnetic radiation data using a pre-trained anomaly detection model to identify electromagnetic radiation signals with abnormal intensities, where the preprocessing at least includes: denoising, smoothing processing, and frequency transformation;

[0039] A calculation module for calculating characteristic parameters of the electromagnetic radiation signal with abnormal intensity, where the characteristic parameters at least include time-weighted average radiation intensity, peak intensity, energy density, and spectral entropy;

[0040] An evaluation module for evaluating the anomaly level of the electromagnetic radiation signal with abnormal intensity according to the characteristic parameters through a preset evaluation rule;

[0041] An output module for outputting an evaluation result, where the evaluation result at least includes the anomaly level and the corresponding processing measures for the anomaly level.

[0042] In a third aspect, an embodiment of the present invention provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the communication signal electromagnetic radiation evaluation and processing method as described in the first aspect above.

[0043] In a fourth aspect, an embodiment of the present invention provides a storage medium storing a computer program, and when the computer program is executed by a computer, it implements the communication signal electromagnetic radiation evaluation and processing method as described in the first aspect above.

[0044] In an embodiment of the present invention, real-time monitored electromagnetic radiation data is acquired; the preprocessed electromagnetic radiation data is analyzed using a pre-trained anomaly detection model to identify electromagnetic radiation signals with abnormal intensities, wherein the preprocessing at least includes: denoising, smoothing, and frequency transformation; characteristic parameters of the electromagnetic radiation signals with abnormal intensities are calculated, and the characteristic parameters at least include time-weighted average radiation intensity, peak intensity, energy density, and spectral entropy; according to the characteristic parameters, the anomaly level of the electromagnetic radiation signals with abnormal intensities is evaluated through a preset evaluation rule; and an evaluation result is output, where the evaluation result at least includes the anomaly level and the corresponding handling measures for the anomaly level.

[0045] A communication signal electromagnetic radiation evaluation and processing method proposed by the present invention has the following remarkable beneficial effects:

[0046] By preprocessing the electromagnetic radiation data, including denoising, smoothing, and frequency transformation, the detection accuracy of electromagnetic radiation signals with abnormal intensities is effectively improved. Denoising in the preprocessing process can filter out irrelevant noise signals, smoothing can reduce signal fluctuations, and frequency transformation helps to identify abnormal frequency components in the signals.

[0047] The technical solution of the embodiment of the present invention adopts a comprehensive evaluation index, that is, characteristic parameters of electromagnetic radiation signals with abnormal intensities are calculated, including time-weighted average radiation intensity, peak intensity, energy density, and spectral entropy. These parameters can comprehensively evaluate the abnormality degree of the signals from multiple perspectives, improving the accuracy and comprehensiveness of the evaluation. By evaluating the electromagnetic radiation signals with abnormal intensities through a preset evaluation rule, different thresholds can be flexibly configured to distinguish abnormal signals of different levels, making the evaluation more accurate and reliable.

[0048] The technical solution of the embodiment of the present invention implements targeted handling measures: the output evaluation result not only includes the anomaly level, but also includes the corresponding handling measures for the anomaly level, which helps to take timely and effective response measures and reduce potential risks. This method can automatically identify and evaluate electromagnetic radiation signals with abnormal intensities, reducing the need for manual intervention and improving work efficiency and processing speed.

[0049] These aspects or other aspects of the present invention will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or in the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0051] Figure 1 Flowchart of a communication signal electromagnetic radiation evaluation and processing method provided by an embodiment of the present invention;

[0052] Figure 2 Structural schematic diagram of an electromagnetic radiation evaluation and processing provided by an embodiment of the present invention;

[0053] Figure 3 Structural schematic diagram of a computing device provided by an embodiment of the present invention. Detailed implementation manners

[0054] In order to enable those skilled in the art of the present technology to better understand the solution of the present invention, 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.

[0055] In some processes described in the specification, claims and above-mentioned drawings of the present invention, a plurality of operations that appear in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order in which they appear in this document or may be executed in parallel. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are different types.

[0056] 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 of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0057] Figure 1 A flowchart of a communication signal electromagnetic radiation evaluation and processing method provided by an embodiment of the present invention, as Figure 1 shown, the method includes:

[0058] 101. Obtain real-time monitored electromagnetic radiation data;

[0059] This step refers to the process of obtaining real-time electromagnetic radiation data from sensors or monitoring devices. These data usually include the intensity, frequency and other related parameters of the electromagnetic field. The electromagnetic radiation data can be analog signals or digital signals, depending on the type and configuration of the monitoring device.

[0060] In an embodiment of the present invention, it is assumed that the application scenario is an electromagnetic radiation monitoring system in an industrial production environment. The system aims to monitor the electromagnetic radiation level around production equipment in real time to ensure the safety of employees and the normal operation of equipment.

[0061] Monitoring equipment: The system is equipped with multiple electromagnetic radiation monitoring sensors, which are distributed at key positions in the production facility, such as around equipment, at entrances, etc. These sensors can monitor the electromagnetic radiation intensity in real time and send the data to the central processing unit.

[0062] Data acquisition: The monitoring sensors continuously collect electromagnetic radiation data and transmit the data to the central processing unit at a certain sampling frequency (e.g., once per second). This data usually includes the change trend of electromagnetic radiation intensity over time, as well as information such as frequency components.

[0063] Data format: The collected data can be a digital signal, such as stored in the form of a CSV file or a database record, or it can be an analog signal, which needs to be converted into a digital signal by an analog-to-digital converter for processing.

[0064] Specific embodiment: Suppose 5 electromagnetic radiation monitoring sensors are installed in a factory workshop, and these sensors collect data every 1 second. The monitoring system continuously collects data within 24 hours a day. After the central processing unit receives the data from these sensors, it preprocesses the data, including denoising and smoothing processing, to reduce noise interference and improve the accuracy of subsequent analysis.

[0065] In this way, the system can monitor the electromagnetic radiation level in real time, ensure that abnormal situations can be detected in a timely manner, and take corresponding measures.

[0066] 102. Use a pre-trained anomaly detection model to analyze the preprocessed electromagnetic radiation data to identify electromagnetic radiation signals with abnormal intensity;

[0067] Wherein, the preprocessing at least includes: denoising, smoothing processing, and frequency transformation;

[0068] Before performing step 102, it further includes: performing a Fourier transform on the electromagnetic radiation data to convert it into a frequency-domain signal; using a band-pass filter to filter out noise signals outside a specified frequency range, wherein the specified frequency range is determined according to the frequency range of normal-intensity electromagnetic radiation signals and is used to retain frequency components related to electromagnetic radiation signals with abnormal intensity; applying a sliding window smoothing algorithm to reduce the signal fluctuation of the electromagnetic radiation data.

[0069] Among them, the Fourier transform is a mathematical tool used to convert a time-domain signal into a frequency-domain signal. Through the Fourier transform, electromagnetic radiation data can be converted from the time domain to the frequency domain, making it easier to identify different frequency components in the signal.

[0070] A band-pass filter is a type of filter that allows signals within a specified frequency range to pass through while suppressing signals of other frequencies. In the present invention, the band-pass filter is used to filter out noise signals outside the specified frequency range and retain the frequency components related to the electromagnetic radiation signals of abnormal intensity.

[0071] The sliding window smoothing algorithm is an algorithm used to reduce signal fluctuations. By moving a window over the data and averaging the data within the window, random fluctuations in the signal can be reduced, improving the smoothness of the signal.

[0072] In an embodiment of the present invention, it is assumed that the application scenario is an electromagnetic radiation monitoring system in an industrial production environment. The system aims to monitor the electromagnetic radiation level around production equipment in real time to ensure the safety of employees and the normal operation of the equipment.

[0073] The system is equipped with multiple electromagnetic radiation monitoring sensors, which are distributed at key locations in the production facility. The original electromagnetic radiation data collected by the sensors is first converted into a frequency-domain signal through the Fourier transform to analyze the frequency components of the signal. Then, a band-pass filter is used to filter out noise signals outside the specified frequency range, where the specified frequency range is determined according to the frequency range of the electromagnetic radiation signals of normal intensity to ensure that the frequency components related to the electromagnetic radiation signals of abnormal intensity are retained. Finally, the sliding window smoothing algorithm is applied to reduce the signal fluctuations of the electromagnetic radiation data, improving the smoothness and continuity of the signal.

[0074] Based on the above, when performing step 102, it may specifically include: using a long short-term memory network for time series prediction to identify electromagnetic radiation signals of abnormal intensity by capturing long-term dependencies in the electromagnetic radiation data; and / or, combining with an autoencoder to identify electromagnetic radiation signals of abnormal intensity by reconstructing the difference between the electromagnetic radiation signals of normal intensity and the electromagnetic radiation data; and / or, using a support vector machine for classification to distinguish between electromagnetic radiation signals of normal intensity and abnormal intensity by constructing an optimal hyperplane.

[0075] In this step, the long short-term memory network (LSTM) is a special type of recurrent neural network (RNN) that can capture long-term dependencies in data. In the present invention, the LSTM is used to capture long-term dependencies in the electromagnetic radiation data to identify electromagnetic radiation signals of abnormal intensity.

[0076] An autoencoder (AE) is an unsupervised learning model that can be used for data dimensionality reduction and feature learning. In the present invention, the autoencoder identifies electromagnetic radiation signals with abnormal intensities by reconstructing the difference between electromagnetic radiation signals with normal intensities and electromagnetic radiation data.

[0077] A support vector machine (SVM) is a supervised learning model used for classification and regression analysis. In the present invention, the SVM distinguishes electromagnetic radiation signals with normal intensities from those with abnormal intensities by constructing an optimal hyperplane.

[0078] In an embodiment of the present invention, after the above data collection and preprocessing, the system analyzes the preprocessed electromagnetic radiation data using a pre-trained anomaly detection model. Specifically, a long short-term memory network (LSTM) is used for time series prediction to identify electromagnetic radiation signals with abnormal intensities by capturing long-term dependencies in the electromagnetic radiation data. At the same time, an autoencoder (AE) is combined to identify electromagnetic radiation signals with abnormal intensities by reconstructing the difference between electromagnetic radiation signals with normal intensities and electromagnetic radiation data. In addition, a support vector machine (SVM) is adopted for classification to distinguish electromagnetic radiation signals with normal intensities from those with abnormal intensities by constructing an optimal hyperplane.

[0079] For example, assume that 5 electromagnetic radiation monitoring sensors are installed in a factory workshop, and these sensors collect data every 1 second. The monitoring system continuously collects data within 24 hours a day. After the central processing unit receives the data from these sensors, it preprocesses the data, including Fourier transform, band-pass filtering, and sliding window smoothing. Then, a pre-trained anomaly detection model is used for analysis, and this model includes components such as LSTM, AE, and SVM. Through the joint work of these components, the system can identify electromagnetic radiation signals with abnormal intensities and evaluate them.

[0080] In this way, the system can monitor the electromagnetic radiation level in real time, ensure that abnormal situations can be detected in a timely manner, and take corresponding measures.

[0081] 103. Calculate the characteristic parameters of the electromagnetic radiation signal with abnormal intensity;

[0082] In this step, the characteristic parameters at least include time-weighted average radiation intensity, peak intensity, energy density, and spectral entropy;

[0083] The specific execution process of step 103 may include:

[0084] Through the formula: , calculate the time-weighted average radiation intensity of the electromagnetic radiation signal with abnormal intensity; where, represents the time-weighted average radiation intensity, represents the radiation intensity at the i-th moment, and N represents the number of sampling points, represents the weight function based on time, where, , represents the attenuation coefficient, represents the time difference between the i-th moment and the reference moment;

[0085] Through the formula: , calculate the peak intensity of the electromagnetic radiation signal with abnormal intensity, where P represents the peak intensity, represents the radiation intensity at the i-th moment, i = {1, 2,..., N};

[0086] Through the formula: , calculate the energy density of the electromagnetic radiation signal with abnormal intensity; where E represents the energy density, represents the sampling interval, represents the weight function based on energy, where, ;

[0087] Through the formula: , calculate the spectral entropy of the electromagnetic radiation signal with abnormal intensity; where S represents the spectral entropy, represents the power ratio of the j-th frequency component, and M represents the total number of frequency components.

[0088] In this step, the time-weighted average radiation intensity is the weighted average of the radiation intensities of the electromagnetic radiation data at different time points to consider the importance of different time points. The weight function decays according to the time difference from the reference moment, where represents the attenuation coefficient.

[0089] The peak intensity refers to the maximum radiation intensity value in the electromagnetic radiation data, which reflects the maximum intensity of the signal.

[0090] The energy density calculates the energy of the electromagnetic radiation data, considering the radiation intensity and sampling interval of each sampling point. The weight function based on energy is weighted according to the ratio of the radiation intensity to the time-weighted average radiation intensity.

[0091] The spectral entropy is a statistic based on the spectral distribution, used to measure the uniformity of the spectral distribution. It is obtained by calculating the logarithm weighted sum of the power ratios of different frequency components.

[0092] In an embodiment of the present invention, it is assumed that the application scenario is an electromagnetic radiation monitoring system in an industrial production environment. The system aims to monitor the electromagnetic radiation level around production equipment in real time to ensure the safety of employees and the normal operation of equipment.

[0093] First, the system is equipped with multiple electromagnetic radiation monitoring sensors, which are distributed at key positions in the production facility. The original electromagnetic radiation data collected by the sensors is first converted into a frequency-domain signal through Fourier transform to analyze the frequency components of the signal. Then, a band-pass filter is used to filter out noise signals outside the specified frequency range, where the specified frequency range is determined according to the frequency range of electromagnetic radiation signals with normal intensity to ensure that the frequency components related to electromagnetic radiation signals with abnormal intensity are retained. Finally, a sliding window smoothing algorithm is applied to reduce the signal fluctuations of the electromagnetic radiation data and improve the smoothness and continuity of the signal.

[0094] Furthermore, after the preprocessed electromagnetic radiation data is analyzed using a pre-trained anomaly detection model, the characteristic parameters of the electromagnetic radiation signal with abnormal intensity are further calculated. The specific steps are as follows:

[0095] Time-weighted average radiation intensity: Through the formula: , calculate the time-weighted average radiation intensity of the electromagnetic radiation signal with abnormal intensity; where , represents the attenuation coefficient, represents the time difference between the i-th moment and the reference moment;

[0096] Peak intensity: Through the formula: , calculate the peak intensity of the electromagnetic radiation signal with abnormal intensity;

[0097] Energy density: Through the formula: , calculate the energy density of the electromagnetic radiation signal with abnormal intensity; where ;

[0098] Spectral entropy: Through the formula: , calculate the spectral entropy of the electromagnetic radiation signal with abnormal intensity, where represents the power ratio of the j-th frequency component;

[0099] For example, assume that 5 electromagnetic radiation monitoring sensors are installed in a factory workshop, and these sensors collect data every 1 second. The monitoring system continuously collects data within 24 hours a day. After the central processing unit receives the data from these sensors, it preprocesses the data, including Fourier transform, band-pass filtering, and moving window smoothing. Then, it uses a pre-trained anomaly detection model for analysis. For each electromagnetic radiation signal with abnormal intensity, the system calculates its characteristic parameters, including time-weighted average radiation intensity, peak intensity, energy density, and spectral entropy.

[0100] Time-weighted average radiation intensity: Assume the attenuation coefficient λ = 0.1, and calculate the time-weighted average radiation intensity of each abnormal signal.

[0101] Peak intensity: Directly calculate the maximum radiation intensity of each abnormal signal.

[0102] Energy density: Considering the sampling interval Δt = 1 second, calculate the energy density of each abnormal signal.

[0103] Spectral entropy: Calculate the spectral entropy of each abnormal signal to evaluate the uniformity of the spectral distribution.

[0104] In this way, the system can calculate the characteristic parameters of the electromagnetic radiation signals with abnormal intensity, providing data support for subsequent evaluation and processing.

[0105] 104. According to the characteristic parameters, evaluate the anomaly level of the electromagnetic radiation signal with abnormal intensity through a preset evaluation rule;

[0106] As a possible implementation method, step 104 may include: when the time-weighted average radiation intensity of the electromagnetic radiation signal with abnormal intensity exceeds the preset threshold T1, it is determined as a first-level anomaly; when the peak intensity of the electromagnetic radiation signal with abnormal intensity exceeds the preset threshold T2, it is determined as a second-level anomaly; when the energy density of the electromagnetic radiation signal with abnormal intensity exceeds the preset threshold T3, it is determined as a third-level anomaly; when the spectral entropy of the electromagnetic radiation signal with abnormal intensity is lower than the preset threshold T4, it is determined as a fourth-level anomaly.

[0107] In this implementation method, the preset threshold is a value set according to specific criteria and is used to determine whether the electromagnetic radiation signal reaches an abnormal state. These thresholds can be determined based on historical data, industry standards, or other factors.

[0108] The anomaly level is determined based on the comparison result between the characteristic parameters and the preset threshold and is used to represent the abnormal degree of the electromagnetic radiation signal. Different anomaly levels represent different degrees of abnormal states.

[0109] As another possible implementation, step 104 may include: defining an abnormal level calculation formula: ;

[0110] where G represents the abnormal level, w1, w2, w3, and w4 respectively represent the importance weights of the time-weighted average radiation intensity, peak intensity, energy density, and spectral entropy, and T1, T2, T3, and T4 respectively represent the preset thresholds of the corresponding characteristic parameters.

[0111] where the calculation formulas for the importance weights w1, w2, w3, and w4 are:

[0112] ;

[0113] where λ is a parameter for adjusting the steepness of the curve, and σ1, σ2, σ3, and σ4 are respectively the calibration factors of the corresponding characteristic parameters, , , , respectively represent the averages of the corresponding characteristic parameters, represents the time-weighted average radiation intensity, P represents the peak intensity, E represents the energy density, and S represents the spectral entropy.

[0114] In this implementation, the importance weights are used to represent the relative importance of different characteristic parameters when evaluating the abnormal level. These weights can be calculated by formulas to ensure that the evaluation results are more reasonable.

[0115] The abnormal level calculation formula is a method for calculating the abnormal level based on the thresholds and importance weights of the characteristic parameters. Through this formula, multiple characteristic parameters can be comprehensively considered to determine the abnormal level.

[0116] In the embodiments of the present invention, it is assumed that the application scenario is an electromagnetic radiation monitoring system in an industrial production environment. The system aims to monitor the electromagnetic radiation level around production equipment in real time to ensure the safety of employees and the normal operation of equipment.

[0117] The system is equipped with multiple electromagnetic radiation monitoring sensors, which are distributed at key positions of the production facility. The original electromagnetic radiation data collected by the sensors is first converted into a frequency-domain signal through Fourier transform to analyze the frequency components of the signal. Then, a band-pass filter is used to filter out the noise signals outside the specified frequency range, where the specified frequency range is determined according to the frequency range of the electromagnetic radiation signal with normal intensity to ensure that the frequency components related to the electromagnetic radiation signal with abnormal intensity are retained. Finally, a sliding window smoothing algorithm is applied to reduce the signal fluctuation of the electromagnetic radiation data and improve the smoothness and continuity of the signal.

[0118] After the system analyzes the preprocessed electromagnetic radiation data using a pre-trained anomaly detection model, it further calculates the characteristic parameters of the electromagnetic radiation signals with abnormal intensity, including the time-weighted average radiation intensity, peak intensity, energy density, and spectral entropy.

[0119] Based on the calculated characteristic parameters, the system evaluates the anomaly level of the electromagnetic radiation signals with abnormal intensity through a preset evaluation rule. The specific steps are as follows:

[0120] Threshold comparison: The system sets preset thresholds T1, T2, T3, and T4 for the time-weighted average radiation intensity, peak intensity, energy density, and spectral entropy respectively. When the characteristic parameters exceed these thresholds, the system determines the corresponding anomaly level.

[0121] Anomaly level calculation formula: The system can also use the anomaly level calculation formula: ;

[0122] where G represents the anomaly level, w1, w2, w3, and w4 represent the importance weights of the time-weighted average radiation intensity, peak intensity, energy density, and spectral entropy respectively. The system calculates the importance weights w1, w2, w3, and w4 according to the above weight calculation formula, and T1, T2, T3, and T4 represent the preset thresholds of the corresponding characteristic parameters.

[0123] For example, assume that 5 electromagnetic radiation monitoring sensors are installed in a factory workshop, and these sensors collect data every 1 second. The monitoring system continuously collects data within 24 hours a day. After the central processing unit receives the data from these sensors, it preprocesses them, including Fourier transform, band-pass filtering, and sliding window smoothing. Then, it uses a pre-trained anomaly detection model for analysis and calculates the characteristic parameters of the electromagnetic radiation signals with abnormal intensity. Then, the system evaluates the anomaly level based on these characteristic parameters.

[0124] Threshold comparison: Assume that the preset thresholds are T1 = 10, T2 = 20, T3 = 500, and T4 = 0.5, and the system determines the anomaly level according to these thresholds.

[0125] Anomaly level calculation formula: The system calculates the importance weights according to the formula. Assume that λ = 0.5, σ1 = 1.2, σ2 = 1.1, σ3 = 1.0, and σ4 = 0.9, and the average values of the corresponding characteristic parameters are = 5, = 15, = 300, = 0.7. Substitute these values into the above importance weight calculation formula to obtain the importance weights w1 = 0.4, w2 = 0.3, w3 = 0.2, and w4 = 0.1. Then, the system uses the anomaly level calculation formula again: Calculate the anomaly level.

[0126] In this way, the system can evaluate the anomaly level based on the characteristic parameters and preset thresholds, and take corresponding measures according to the anomaly level.

[0127] 105. Output the evaluation result, where the evaluation result at least includes the anomaly level and the corresponding handling measures for the anomaly level.

[0128] In this step, outputting the evaluation result means presenting the evaluated anomaly level and the corresponding handling measures in an appropriate form. This step is the last step of the entire evaluation process, aiming to enable relevant personnel to clearly understand the monitoring results and their corresponding measures.

[0129] The anomaly level is determined based on the comparison result between the characteristic parameters and the preset thresholds, and is used to represent the anomaly degree of the electromagnetic radiation signal. Different anomaly levels represent different degrees of abnormal states.

[0130] The handling measures are the corresponding measures taken for different anomaly levels. These measures aim to mitigate or eliminate the potential risks brought by the abnormal situation.

[0131] In the embodiment of the present invention, it is assumed that the application scenario is an electromagnetic radiation monitoring system in an industrial production environment. This system aims to monitor the electromagnetic radiation level around production equipment in real time to ensure the safety of employees and the normal operation of equipment.

[0132] The system outputs the anomaly level and the corresponding handling measures according to the evaluation result. The specific steps are as follows:

[0133] Anomaly level output: The system outputs the corresponding level information according to the evaluated anomaly level, for example: "Level 1 anomaly", "Level 2 anomaly", etc.

[0134] Handling measures: The system outputs the corresponding handling measures according to the anomaly level. For example, for a "Level 1 anomaly", it is recommended to take emergency measures such as shutting down relevant equipment and evacuating personnel; for a "Level 2 anomaly", it is recommended to strengthen monitoring and regularly check the equipment status; for a "Level 3 anomaly", it is recommended to perform equipment maintenance and inspection; for a "Level 4 anomaly", it is recommended to adjust the equipment working state or parameter settings.

[0135] In this way, the system can evaluate the anomaly level based on the characteristic parameters and preset thresholds, and take corresponding measures according to the anomaly level to ensure that abnormal situations can be detected in time and appropriate actions can be taken.

[0136] Figure 2 The following is a schematic structural diagram of a communication signal electromagnetic radiation evaluation and processing system provided by an embodiment of the present invention, as Figure 2 shown, the device includes:

[0137] An acquisition module 21 for acquiring electromagnetic radiation data monitored in real time;

[0138] A detection module 22 for analyzing the preprocessed electromagnetic radiation data using a pre-trained anomaly detection model to identify electromagnetic radiation signals with abnormal intensities, wherein the preprocessing at least includes: denoising, smoothing, and frequency transformation;

[0139] A calculation module 23 for calculating characteristic parameters of the electromagnetic radiation signals with abnormal intensities, where the characteristic parameters at least include time-weighted average radiation intensity, peak intensity, energy density, and spectral entropy;

[0140] An evaluation module 24 for evaluating the anomaly level of the electromagnetic radiation signals with abnormal intensities according to the characteristic parameters through a preset evaluation rule;

[0141] An output module 25 for outputting an evaluation result, where the evaluation result at least includes the anomaly level and the corresponding handling measures for the anomaly level.

[0142] In an embodiment of the present invention, the preprocessing at least includes: denoising, smoothing, and frequency transformation; the device further includes: a preprocessing module 26;

[0143] The preprocessing module 26 is used to perform a Fourier transform on the electromagnetic radiation data to convert it into a frequency-domain signal; use a band-pass filter to filter out noise signals outside a specified frequency range, where the specified frequency range is determined according to the frequency range of electromagnetic radiation signals with normal intensities and is used to retain frequency components related to electromagnetic radiation signals with abnormal intensities; apply a sliding window smoothing algorithm to reduce the signal fluctuations of the electromagnetic radiation data.

[0144] In an embodiment of the present invention, the detection module 22 is specifically used to perform time series prediction using a long short-term memory network to identify electromagnetic radiation signals with abnormal intensities by capturing long-term dependencies in the electromagnetic radiation data; and / or, in combination with an autoencoder, identify electromagnetic radiation signals with abnormal intensities by reconstructing the difference between the electromagnetic radiation signals with normal intensities and the electromagnetic radiation data; and / or, use a support vector machine for classification to distinguish electromagnetic radiation signals with normal intensities from electromagnetic radiation signals with abnormal intensities by constructing an optimal hyperplane.

[0145] In an embodiment of the present invention, the calculation module 23 is specifically used to calculate the time-weighted average radiation intensity of the electromagnetic radiation signals with abnormal intensities through the formula: , where represents the time-weighted average radiation intensity, represents the radiation intensity at the i-th moment, and N represents the number of sampling points. is expressed as a time-based weight function, where , is expressed as an attenuation coefficient, is expressed as the time difference between the i-th moment and the reference moment;

[0146] Through the formula: , calculate the peak intensity of the electromagnetic radiation signal with abnormal intensity, where P is expressed as the peak intensity, is expressed as the radiation intensity at the i-th moment, i = {1, 2,..., N};

[0147] Through the formula: , calculate the energy density of the electromagnetic radiation signal with abnormal intensity; where E is expressed as the energy density, is expressed as the sampling interval, is expressed as an energy-based weight function, where ;

[0148] Through the formula: , calculate the spectral entropy of the electromagnetic radiation signal with abnormal intensity; where S is expressed as the spectral entropy, is expressed as the power ratio of the j-th frequency component, and M is expressed as the total number of frequency components.

[0149] In the embodiment of the present invention, the evaluation module 24 is specifically configured to determine a first-level anomaly when the time-weighted average radiation intensity of the electromagnetic radiation signal with abnormal intensity exceeds a preset threshold T1; determine a second-level anomaly when the peak intensity of the electromagnetic radiation signal with abnormal intensity exceeds a preset threshold T2; determine a third-level anomaly when the energy density of the electromagnetic radiation signal with abnormal intensity exceeds a preset threshold T3; and determine a fourth-level anomaly when the spectral entropy of the electromagnetic radiation signal with abnormal intensity is lower than a preset threshold T4.

[0150] In the embodiment of the present invention, the evaluation module 24 is specifically configured to define an abnormal level calculation formula: ;

[0151] Where G represents the abnormal level, w1, w2, w3, and w4 respectively represent the importance weights of the time-weighted average radiation intensity, peak intensity, energy density, and spectral entropy, and T1, T2, T3, and T4 respectively represent the preset thresholds of the corresponding characteristic parameters;

[0152] Among them, the calculation formulas for the importance weights w1, w2, w3, and w4 are:

[0153] ;

[0154] Among them, λ is a parameter for adjusting the steepness of the curve, and σ1, σ2, σ3, and σ4 are calibration factors for the corresponding characteristic parameters respectively. and 、 、 respectively represent the average values of the corresponding characteristic parameters. represents the time-weighted average radiation intensity, P represents the peak intensity, E represents the energy density, and S represents the spectral entropy.

[0155] Figure 3 The communication signal electromagnetic radiation evaluation and processing system described above can execute Figure 1 the communication signal electromagnetic radiation evaluation and processing method described in the embodiment shown. The implementation principle and technical effects will not be elaborated here. For the communication signal electromagnetic radiation evaluation and processing system in the above embodiment, the specific ways in which each module and unit perform operations have been described in detail in the embodiment related to this method, and will not be elaborated here.

[0156] In a possible design, Figure 2 the communication signal electromagnetic radiation evaluation and processing system of the embodiment shown can be implemented as a computing device, as Figure 3 shown, this computing device can include a storage component 31 and a processing component 32;

[0157] The storage component 31 stores one or more computer instructions, and among them, the one or more computer instructions are called and executed by the processing component 32.

[0158] The processing component 32 is used for: obtaining real-time monitored electromagnetic radiation data; using a pre-trained anomaly detection model to analyze the preprocessed electromagnetic radiation data to identify electromagnetic radiation signals with abnormal intensity, where the preprocessing at least includes: denoising, smoothing processing, and frequency transformation; calculating characteristic parameters of the electromagnetic radiation signals with abnormal intensity, and the characteristic parameters at least include time-weighted average radiation intensity, peak intensity, energy density, and spectral entropy; evaluating the anomaly level of the electromagnetic radiation signals with abnormal intensity according to the characteristic parameters; outputting an evaluation result, and the evaluation result at least includes the anomaly level and the corresponding processing measures for the anomaly level.

[0159] Among them, the processing component 32 can include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component can also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for executing the above method.

[0160] The storage component 31 is configured to store various types of data to support the operation of the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0161] Of course, the computing device may also necessarily include other components, such as input / output interfaces, display components, communication components, etc.

[0162] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above-mentioned peripheral interface module can be an output device, an input device, etc.

[0163] The communication component is configured to facilitate communication between the computing device and other devices in a wired or wireless manner, etc.

[0164] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. At this time, the computing device can refer to a cloud server, and the above-mentioned processing component, storage component, etc. can be basic server resources leased or purchased from a cloud computing platform.

[0165] An embodiment of the present invention also provides a storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the communication signal electromagnetic radiation evaluation and processing method of the above-mentioned Figure 1 shown embodiment.

[0166] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0167] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0168] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0169] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A communication signal electromagnetic radiation evaluation and processing method, characterized in that: include: Obtain real-time monitoring of electromagnetic radiation data; Using a pre-trained anomaly detection model to analyze the pre-processed electromagnetic radiation data to identify electromagnetic radiation signals of abnormal intensity, wherein the pre-processing at least includes: denoising, smoothing and frequency conversion; Calculating characteristic parameters of the electromagnetic radiation signal of abnormal intensity, wherein the characteristic parameters at least include time-weighted average radiation intensity, peak intensity, energy density and spectrum entropy; According to the characteristic parameters, evaluating the abnormal level of the electromagnetic radiation signal of abnormal intensity by using a preset evaluation rule; Outputting an evaluation result, wherein the evaluation result at least includes an abnormality level and a treatment measure corresponding to the abnormality level; The step of calculating the characteristic parameter of the electromagnetic radiation signal of abnormal intensity comprises: By formula: , calculate the time-weighted average radiation intensity of the electromagnetic radiation signal of abnormal intensity; wherein, represents the time-weighted average radiation intensity, It is represented as the radiation intensity at the i-th moment, N is the number of sampling points, is expressed as a time-based weight function, where , Expressed as the attenuation coefficient, It is expressed as the time difference between the i-th moment and the reference moment; By formula: , calculate the peak intensity of the electromagnetic radiation signal of abnormal intensity, where P represents the peak intensity, It is expressed as the radiation intensity at the i-th moment, i={1,2,…,N}; By formula: , calculate the energy density of the electromagnetic radiation signal of abnormal intensity; where E represents the energy density, is the sampling interval, It is expressed as an energy-based weight function, where ; By formula: , calculate the spectrum entropy of the electromagnetic radiation signal of abnormal intensity; where S represents the spectrum entropy, It is expressed as the power ratio of the jth frequency component, and M is expressed as the total number of frequency components; The step of evaluating the abnormal level of the electromagnetic radiation signal of abnormal intensity according to the characteristic parameter by using a preset evaluation rule includes: When the time-weighted average radiation intensity of the electromagnetic radiation signal of abnormal intensity exceeds the preset threshold value T1, it is determined to be a first-level abnormality; When the peak intensity of the electromagnetic radiation signal of abnormal intensity exceeds the preset threshold value T2, it is determined to be a secondary abnormality; When the energy density of the electromagnetic radiation signal of abnormal intensity exceeds the preset threshold value T3, it is determined as a third-level abnormality; When the spectrum entropy of the electromagnetic radiation signal of abnormal intensity is lower than the preset threshold value T4, it is determined to be a level 4 abnormality.

2. The method according to claim 1, characterized in that The preprocessing at least includes: denoising, smoothing and frequency conversion; Before using the pre-trained anomaly detection model to analyze the pre-processed electromagnetic radiation data to identify electromagnetic radiation signals of abnormal intensity, the method further includes: Performing Fourier transformation on the electromagnetic radiation data to convert it into a frequency domain signal; Using a bandpass filter to filter out noise signals outside a specified frequency range, wherein the specified frequency range is determined according to the frequency range of an electromagnetic radiation signal of normal intensity, and is used to retain frequency components related to the electromagnetic radiation signal of abnormal intensity; A sliding window smoothing algorithm is applied to reduce signal fluctuations of the electromagnetic radiation data.

3. The method according to claim 2, characterized in that The method of using a pre-trained anomaly detection model to analyze the pre-processed electromagnetic radiation data to identify electromagnetic radiation signals of abnormal intensity includes: Using a long short-term memory network for time series prediction to capture long-term dependencies in the electromagnetic radiation data to identify electromagnetic radiation signals of abnormal intensity; and / or, In combination with an autoencoder, the electromagnetic radiation signal of abnormal intensity is identified by reconstructing the difference between the electromagnetic radiation signal of normal intensity and the electromagnetic radiation data; and / or, Support vector machine is used for classification, and the optimal hyperplane is constructed to distinguish electromagnetic radiation signals of normal intensity from electromagnetic radiation signals of abnormal intensity.

4. The method according to claim 1, characterized in that: The step of evaluating the abnormal level of the electromagnetic radiation signal of abnormal intensity according to the characteristic parameter by using a preset evaluation rule includes: Define the abnormal level calculation formula: ; Among them, G represents the abnormality level, w1, w2, w3 and w4 represent the importance weights of time-weighted average radiation intensity, peak intensity, energy density and spectral entropy respectively, and T1, T2, T3 and T4 represent the preset thresholds of the corresponding characteristic parameters respectively.

5. The method according to claim 4, characterized in that The calculation formula of the importance weights w1, w2, w3 and w4 is: ； Among them, λ is the parameter for adjusting the steepness of the curve, σ1, σ2, σ3 and σ4 are the calibration factors of the corresponding characteristic parameters, , , , are respectively expressed as the average values ​​of the corresponding characteristic parameters, represents the time-weighted average radiation intensity, P represents the peak intensity, E represents the energy density, and S represents the spectral entropy.

6. A storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, the communication signal electromagnetic radiation evaluation and processing method as described in any one of claims 1 to 5 is implemented.

Images