Scanning observation method and system based on multi-radar cooperation

Abstract

The invention relates to the field of radar speed measurement, and discloses a scanning observation method and system based on multi-radar collaboration.The system comprises a radar wave band speed measurement module, a wave band flow velocity judgment module, a wave band flow velocity processing module and a sea wave early warning module, and the radar wave band speed measurement module is used for obtaining electromagnetic wave signals reflected by different wave bands of multiple radars; fourier transform is adopted to convert a target radar signal into a frequency domain signal value, an initial sea wave flow velocity is obtained based on a comparison result, a wave band flow velocity judgment module compares the sea wave flow velocity with historical data and judges whether to correct the initial sea wave flow velocity, and a wave band flow velocity processing module establishes a convolutional neural network model and processes the wave band flow velocity. According to the convolutional neural network model, a sea wave flow velocity prediction value is obtained, the initial sea wave flow velocity to be corrected is corrected according to the flow velocity correction coefficient, the target sea wave flow velocity is obtained, and the sea wave early warning module determines a sea wave early warning alarm according to the sea wave early warning score.

Description

Technical Field

[0001] This invention relates to the field of radar speed measurement technology, and more specifically, to a scanning observation method and system based on multi-radar cooperation. Background Technology

[0002] With the development of radar technology, radar is widely used to observe ocean wave data. By scanning the reflected electromagnetic waves, radar can detect the movement of ocean waves and thus observe the current speed of ocean waves in real time.

[0003] However, current wave observations typically rely on a single radar to acquire current velocity data over a given area. A single radar struggles to comprehensively capture changes in wave velocity, and its coverage is limited by waveband and environmental factors. In a dynamic ocean environment, wave velocity varies due to factors such as tides, wind speed, and temperature changes. This necessitates real-time acquisition and processing of multiple velocity data points, a goal that a single radar cannot achieve. Furthermore, the accuracy of traditional radar measurements of wave velocity is often affected by environmental factors, such as atmospheric refraction, sea surface fluctuations, and weather conditions. These factors influence the accuracy of wave velocity measurements, making it impossible to obtain precise wave velocity readings for effective early warning.

[0004] Therefore, how to provide a scanning observation method and system based on multi-radar cooperation is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] In view of this, the present invention proposes a scanning observation method and system based on multi-radar cooperation, which aims to solve the problem that a single radar cannot fully capture the changes in the flow velocity of ocean waves and cannot accurately determine the flow velocity of ocean waves for effective early warning.

[0006] In one aspect, the present invention proposes a scanning observation system based on multi-radar cooperation, comprising: Radar band velocity measurement module, band current velocity judgment module, band current velocity processing module, and wave warning module; The radar band velocity measurement module is configured to acquire electromagnetic wave signals reflected from multiple radars in different bands, preprocess the electromagnetic wave signals, obtain the target radar signal based on the preprocessing results, convert the target radar signal into a frequency domain signal value using Fourier transform, set a standard spectrum threshold, compare the standard spectrum threshold with the frequency domain signal value, and obtain the initial wave current speed based on the comparison results. The wave velocity determination module is configured to compare the wave velocity with historical data to determine whether the initial wave velocity needs to be corrected. The wave velocity processing module is configured to establish a convolutional neural network model, obtain a predicted wave velocity value based on the convolutional neural network model, determine a velocity correction coefficient based on the ratio of the predicted wave velocity value to the initial wave velocity to be corrected, and correct the initial wave velocity to be corrected using the velocity correction coefficient to obtain the target wave velocity. The wave warning module is configured to determine a wave warning score based on the target wave velocity and to issue a wave warning alarm based on the wave warning score.

[0007] Furthermore, when acquiring electromagnetic wave signals reflected from multiple radars at different frequency bands and preprocessing the electromagnetic wave signals, the process includes: The different bands include the first radar band and the second radar band; The preprocessing includes signal noise reduction and signal normalization.

[0008] 3. The scanning observation system based on multi-radar cooperation according to claim 2, characterized in that, when converting the target radar signal into a frequency domain signal value using Fourier transform, it includes:

[0009] Where X(f) represents the frequency domain signal value, x(t) represents the time domain signal of the target radar signal, t represents the sampling point of the signal in the discrete time domain, T represents the number of discrete time points, f represents the frequency of the target radar signal, i represents the imaginary number, and e represents the natural constant.

[0010] 4. The scanning observation system based on multi-radar cooperation according to claim 3, characterized in that, when setting a standard spectrum threshold, comparing the standard spectrum threshold with the frequency domain signal value, and determining the initial wave current velocity based on the comparison result, the following steps are included: When the frequency domain signal value is equal to the standard spectrum threshold, it is determined that the waves have not fluctuated and the current wave speed is maintained. When the frequency domain signal value is not equal to the standard spectrum threshold, it is determined that the ocean wave is fluctuating, and the initial ocean wave velocity is calculated based on the frequency domain signal value and the standard spectrum threshold.

[0011] 5. The scanning observation system based on multi-radar cooperation according to claim 4, characterized in that, when calculating the initial wave current velocity based on the frequency domain signal value and the standard spectrum threshold, it includes: The frequency shift F is calculated by taking the difference between the frequency domain signal value and the standard spectral threshold. The initial wave velocity is derived from the frequency shift, and the initial wave velocity is obtained by the following formula:

[0012] Where V represents the initial wave velocity, F represents the frequency shift, and λ represents the mean radar wavelength. This represents the average radar transmission frequency.

[0013] Furthermore, when comparing the wave velocity with historical data to determine whether the initial wave velocity needs correction, the process includes: The historical data represents the average of historical qualified data; When the initial wave velocity is greater than or equal to the average of the historical qualified data, it is determined that the initial wave velocity will not be corrected and the initial wave velocity will be determined as the target wave velocity. If the initial wave velocity is less than the average of the historical qualified data, then it is determined that the initial wave velocity should be corrected.

[0014] Furthermore, in establishing a convolutional neural network model and deriving predicted wave current speeds based on the convolutional neural network model, the following steps are included: Historical initial wave velocity data is obtained from the initial wave velocity data, and the historical initial wave velocity data is divided into a wave training set and a wave test set. Cross-validation and grid search are used to find the parameters of the convolutional neural network model, and a convolutional neural network model is established. The wave training set is used to fit the neural network model, and the wave test set is used to input the convolutional neural network model to calculate the accuracy of the wave velocity prediction value. When the accuracy reaches a preset accuracy threshold, the predicted value of the current wave velocity is obtained based on the initial wave velocity.

[0015] Furthermore, when determining a velocity correction coefficient based on the ratio of the predicted wave velocity to the initial wave velocity to be corrected, and then correcting the initial wave velocity to be corrected using the velocity correction coefficient to obtain the target wave velocity, the process includes: The ratio of the wave velocity to be corrected to the predicted wave velocity is denoted as Q; The first preset correction coefficient, the second preset correction coefficient, and the third preset correction coefficient are preset. When Q≤1, the first preset correction coefficient is used as the velocity correction coefficient of the wave velocity to be corrected. When 1 < Q ≤ 1.5, the second preset correction coefficient is used as the velocity correction coefficient for the wave velocity to be corrected. When 1.5 < Q, the third preset correction coefficient is used as the velocity correction coefficient for the wave velocity to be corrected. The target wave velocity is the product of the initial wave velocity to be corrected and the velocity correction coefficient.

[0016] Furthermore, when determining a wave warning score based on the target wave current speed, and determining a wave warning alert based on the wave warning score, the process includes: The wave warning score is derived from the following formula:

[0017] Where S represents the wave warning score, The target wave velocity is represented by α, e is represented by the natural constant, and α and β are represented by the weighting coefficients, with α+β=1. The wave warning alert is divided into three levels: Level 1, Level 2, and Level 3. When 4 < S, the wave warning module issues a level one alarm; When 2 < S ≤ 4, the wave warning module issues a level two alarm; When S≤2, the wave warning module issues a level three alarm; The urgency levels of the Level 1 alarm, Level 2 alarm, and Level 3 alarm decrease sequentially.

[0018] Compared with existing technologies, the advantages of this invention are as follows: By coordinating the operation of multiple radars in different bands, it can acquire wave and current velocity data over a wider sea area, improving the accuracy of wave and current velocity measurement. Especially under complex sea conditions, it provides comprehensive wave and current velocity information. Furthermore, the preprocessing process ensures the filtering of signal noise and the extraction of data. By using Fourier transform to convert the target radar signal into a frequency domain signal, and comparing it with standard spectral thresholds, measurement errors caused by environmental interference or signal attenuation are avoided, improving the accuracy of the initial wave and current velocity. By comparing with historical data, it can determine whether the initial wave and current velocity needs correction. Combining a convolutional neural network model for prediction and comparison, the system can automatically derive the current velocity correction coefficient based on the ratio between the predicted velocity and the initial velocity, and accurately correct the initial wave and current velocity. This improves the reliability of wave and current velocity measurement results and can meet the requirements of different marine environments. After wave warning scoring, an early warning alarm is automatically triggered. It can identify and predict abnormal wave changes in a timely manner, providing key data support for offshore operations, shipping, and marine disaster early warning, which helps reduce marine disaster risks and improve emergency response capabilities.

[0019] On the other hand, this application also provides a multi-radar cooperative scanning observation method for applying the above-mentioned multi-radar cooperative scanning observation system, including: Electromagnetic wave signals reflected from multiple radars at different frequency bands are acquired and preprocessed. The target radar signal is obtained based on the preprocessing results. The target radar signal is converted into a frequency domain signal value using Fourier transform. A standard spectrum threshold is set, and the standard spectrum threshold is compared with the frequency domain signal value. The initial wave velocity is obtained based on the comparison results. The wave velocity is compared with historical data to determine whether the initial wave velocity needs to be corrected. A convolutional neural network model is established, and a predicted value of the ocean wave velocity is obtained based on the convolutional neural network model. A velocity correction coefficient is determined based on the ratio of the predicted value of the ocean wave velocity to the initial ocean wave velocity to be corrected. The velocity correction coefficient is used to correct the initial ocean wave velocity to be corrected to obtain the target ocean wave velocity. A wave warning score is determined based on the target wave velocity, and a wave warning alert is issued based on the wave warning score.

[0020] It is understandable that the aforementioned scanning observation method and system based on multi-radar collaboration have the same beneficial effects, and will not be elaborated further here. Attached Figure Description

[0021] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A functional block diagram of a multi-radar cooperative scanning observation system provided for an embodiment of the present invention; Figure 2 A flowchart of a multi-radar collaborative scanning observation method provided for an embodiment of the present invention. Detailed Implementation

[0022] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the disclosure to those skilled in the art. It should be noted that, unless otherwise specified, embodiments and features in the embodiments of the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0023] In some embodiments of this application, see Figure 1 As shown, a scanning observation system based on multi-radar cooperation includes: Radar band velocity measurement module, band current velocity judgment module, band current velocity processing module, and wave warning module; The radar band velocity measurement module is configured to acquire electromagnetic wave signals reflected from multiple radars in different bands, preprocess the electromagnetic wave signals, obtain the target radar signal based on the preprocessing results, convert the target radar signal into a frequency domain signal value using Fourier transform, set a standard spectrum threshold, compare the standard spectrum threshold with the frequency domain signal value, and obtain the initial wave current speed based on the comparison results. The wave velocity determination module is configured to compare wave velocity with historical data to determine whether the initial wave velocity needs to be corrected. The wave velocity processing module is configured to establish a convolutional neural network model, obtain the predicted wave velocity based on the convolutional neural network model, determine the velocity correction coefficient based on the ratio of the predicted wave velocity to the initial wave velocity to be corrected, and correct the initial wave velocity to be corrected using the velocity correction coefficient to obtain the target wave velocity. The wave warning module is configured to determine a wave warning score based on the target wave velocity and to issue a wave warning alert based on the wave warning score.

[0024] Specifically, the radar band velocity measurement module is the core of the system, responsible for acquiring electromagnetic wave signals reflected from multiple radars at different frequency bands. The preferred number of radars is three, but this can be adjusted according to actual needs. Since electromagnetic waves of different frequency bands exhibit varying reflection and propagation characteristics on the sea surface, acquiring signals from different bands can comprehensively reflect the sea surface fluctuations. Preprocessing the reflected electromagnetic wave signals improves signal quality, laying the foundation for subsequent analysis. Based on the preprocessed signals, the system uses Fourier transform to convert them into frequency domain signal values, allowing observation of the frequency composition of the target radar signal. By setting a standard spectral threshold and comparing it with the obtained frequency domain signal values, the initial wave velocity can be inferred. This facilitates a comprehensive analysis of the wave velocity at the current moment, improves the system's observation capabilities, and provides a data foundation for subsequent early warning systems. Because the initial wave velocity is affected by various factors, such as wind speed, tidal changes, seabed topography, and the accuracy of reflected electromagnetic waves, there will be a certain degree of error in the initial wave velocity. Therefore, the wave velocity judgment module compares the wave velocity with historical data to determine whether the initial wave velocity needs correction, ensuring the reliability of the target wave velocity. The wave velocity processing module predicts the initial wave velocity using a convolutional neural network (CNN) model. A CNN is a deep learning algorithm that can automatically extract features from data and make predictions. After obtaining the predicted wave velocity value, a velocity correction coefficient is calculated based on the ratio of the predicted wave velocity value to the initial wave velocity to be corrected. This correction coefficient is used to correct the initial wave velocity, thus obtaining the target wave velocity. This correction eliminates errors in the initial wave velocity, improving the accuracy and reliability of the target wave velocity. The wave warning module then determines the wave warning score in real time based on the target wave velocity, triggering the corresponding wave warning alarm to remind relevant personnel to take appropriate preventative measures.

[0025] Understandably, by combining electromagnetic wave signals reflected from multiple radars at different frequency bands, the system comprehensively captures subtle changes in ocean waves, enabling all-round measurement and analysis of ocean current speed. Multi-radar collaborative observation and signal processing improve the accuracy of ocean observation. Convolutional neural network models enhance the accuracy of handling nonlinear and complex wave changes, leading to precise predictions and further improving the accuracy of ocean observation. By acquiring electromagnetic wave signals, comparing and correcting them, the target ocean wave current speed is determined, improving the accuracy and precision of target ocean wave current speed observation. Triggering early warning alarms ensures the timeliness of target ocean wave current speed warnings, helping coastal areas, ships, and offshore platforms to take timely evasive action and reduce disaster losses. Due to the collaborative operation of multiple radars, the system can adapt to different sea conditions and environmental changes. Whether in stormy weather or calm waters, the system can monitor ocean wave current speed in real time, providing effective early warnings and improving the system's adaptability and reliability.

[0026] In some embodiments of this application, when acquiring electromagnetic wave signals reflected from multiple radars at different frequency bands and preprocessing the electromagnetic wave signals, the process includes: Different bands include radar band 1 and radar band 2; Preprocessing includes signal denoising and signal normalization.

[0027] In some embodiments of this application, when converting the target radar signal into a frequency domain signal value using Fourier transform, the following steps are included:

[0028] Where X(f) represents the frequency domain signal value, x(t) represents the time domain signal of the target radar signal, t represents the sampling point of the signal in the discrete time domain, T represents the number of discrete time points, f represents the frequency of the target radar signal, i represents the imaginary number, and e represents the natural constant.

[0029] It is understandable that the first and second radar bands are the low-frequency and high-frequency bands, respectively. The low-frequency band is suitable for general wave observation, while the high-frequency band is suitable for precise wave detail observation. By using different radar bands for reflection, both coarse and precise wave data can be obtained. Combining the radar signals from both bands provides comprehensive wave observation and enhances signal robustness. Noise reduction processing of the electromagnetic wave signals effectively removes external noise and interference signals, improving the quality of the target radar signal. Standardization eliminates signal amplitude differences between different radar devices caused by hardware variations or environmental changes, ensuring data consistency across different bands and facilitating subsequent analysis and processing. Fourier transform is used to convert the target radar signal from the time domain to the frequency domain. This frequency domain transformation decomposes the different frequency components in the target radar signal, facilitating signal analysis and feature extraction.

[0030] In some embodiments of this application, when setting a standard spectral threshold, comparing the standard spectral threshold with the frequency domain signal value, and determining the initial wave current velocity based on the comparison result, the process includes: When the frequency domain signal value is equal to the standard spectrum threshold, it is determined that the waves have not fluctuated and the current wave speed is maintained. When the frequency domain signal value is not equal to the standard spectrum threshold, it is determined that the ocean wave is fluctuating, and the initial ocean wave velocity is calculated based on the frequency domain signal value and the standard spectrum threshold.

[0031] In some embodiments of this application, calculating the initial wave velocity based on the frequency domain signal value and a standard spectral threshold includes: The frequency shift F is calculated by subtracting the frequency domain signal value from the standard spectral threshold. The initial wave velocity is derived from the frequency shift, and is obtained by the following formula:

[0032] Where V represents the initial wave velocity, F represents the frequency shift, and λ represents the mean radar wavelength. This represents the average radar transmission frequency.

[0033] Understandably, the standard spectral threshold is a benchmark set based on the frequency changes of reflected electromagnetic wave signals in the current sea area. It represents the typical spectral characteristics of ocean waves in the absence of fluctuations. In actual observations, the obtained signal spectral values ​​will change due to wave fluctuations. Therefore, by comparing the difference between the frequency domain signal value and the standard spectral threshold, it can be determined whether the waves have fluctuated. If the frequency domain signal value and the standard spectral threshold are equal, it indicates that the waves are in a stable state, i.e., without significant fluctuations. Therefore, the current wave velocity remains unchanged, and the waves are in a stable state. When there is a difference between the frequency domain signal value and the standard spectral threshold, it indicates that the waves have fluctuated, and the wave velocity has changed. The frequency shift is calculated by the difference between the frequency domain signal and the standard spectral threshold, which allows the calculation of the initial wave velocity. The radar wavelength and radar transmission frequency are selected as averages. The system observes the waves through multiple radars and multiple bands, each with different wavelengths and frequencies. By using the average value calculation, the influence of frequency and wavelength differences on the initial wave velocity is avoided, improving the accuracy and precision of the initial wave velocity calculation. By calculating the frequency shift, the dynamic changes of the ocean waves are reflected, providing real-time data support for the ocean current velocity in the observed sea area. The standard spectrum threshold can be adjusted according to different environmental conditions, thus ensuring the adaptability of the system.

[0034] In some embodiments of this application, when comparing wave velocity with historical data to determine whether to correct the initial wave velocity, the following steps are included: Historical data represents the average of historical qualified data; If the initial wave velocity is greater than or equal to the average of historical qualified data, it is determined that the initial wave velocity will not be corrected and will be set as the target wave velocity. If the initial wave velocity is less than the average of historical qualified data, then it is determined that the initial wave velocity should be corrected.

[0035] Understandably, the historical average of qualified data can be set based on the current wave changes in the sea area and used as a judgment indicator. Its specific value can be changed in actual application. By introducing the historical average of qualified data as a reference benchmark, the accuracy and automation of the initial wave velocity correction are improved. If it is greater than or equal to the historical average of qualified data, it indicates that the calculated initial wave velocity conforms to the reference benchmark. If it is less than or equal to the historical average of qualified data, it indicates that the calculated initial wave velocity deviates from the reference benchmark and needs to be corrected. The system makes automatic judgments, reducing the interference and error of human judgment and enhancing the system's adaptability to different sea environments.

[0036] In some embodiments of this application, the process of establishing a convolutional neural network model and deriving predicted wave velocity values ​​based on the convolutional neural network model includes: Historical initial wave velocity data is obtained from the initial wave velocity data. The historical initial wave velocity data is divided into wave training set and wave test set. Cross-validation and grid search are used to find the parameters of the convolutional neural network model. The convolutional neural network model is established. The wave training set is used to fit the neural network model. The wave test set is input into the convolutional neural network model and the accuracy of the wave velocity prediction value is calculated. When the accuracy reaches the preset accuracy threshold, the predicted value of the current wave velocity is obtained based on the initial wave velocity.

[0037] Understandably, historical initial wave velocity data is obtained from initial wave currents, including key factors such as time, weather, and ocean conditions. This historical initial wave velocity data is divided into a wave training set and a wave test set. 40%-80% of the data is used as the wave training set, and the remainder as the wave test set. This ensures that both sets contain multiple key factors, thereby improving the generalization ability of the convolutional neural network (CNN) model. Cross-validation combined with grid search is used to find the model parameters of the CNN. Cross-validation divides the data into several parts and trains the CNN model multiple times to verify its stability and performance. Grid search searches for parameter combinations of the CNN model in the parameter space, such as batch size and kernel size. The CNN model is fitted using the wave training set data. The CNN model integrates different types of layers, such as convolutional layers, activation layers, and pooling layers, reducing the risk of overfitting and improving the accuracy and stability of the CNN model. The test set data of ocean waves is fed into the convolutional neural network model after multiple training sessions, and the accuracy of the ocean current velocity prediction value of the convolutional neural network model is calculated. The accuracy reflects the performance of the convolutional neural network model on unknown data and serves as a reference benchmark for evaluating the performance of the convolutional neural network model. After reaching the preset accuracy threshold, the initial ocean current velocity is substituted into the convolutional neural network model to obtain the ocean current velocity prediction value at the current time, providing a benchmark for subsequent correction.

[0038] In some embodiments of this application, when determining a velocity correction coefficient based on the ratio of the predicted wave velocity to the initial wave velocity to be corrected, and correcting the initial wave velocity to be corrected using the velocity correction coefficient to obtain the target wave velocity, the process includes: The ratio of the wave velocity to be corrected to the predicted wave velocity is denoted as Q; The first preset correction coefficient, the second preset correction coefficient, and the third preset correction coefficient are preset. When Q≤1, the first preset correction coefficient is used as the velocity correction coefficient for the wave velocity to be corrected. When 1 < Q ≤ 1.5, the second preset correction coefficient is used as the velocity correction coefficient for the wave velocity to be corrected. When 1.5 < Q, the third preset correction coefficient is used as the velocity correction coefficient for the wave velocity to be corrected. The target wave velocity is the product of the initial wave velocity to be corrected and the velocity correction coefficient.

[0039] It is understood that the first preset correction coefficient is preferably 1.5, the second preset correction coefficient is preferably 0.8, and the third preset correction coefficient is preferably 0.5. The corresponding preset correction coefficient is selected according to the ratio of the wave velocity to be corrected to the predicted wave velocity. This enables dynamic correction of the initial wave velocity to be corrected, ensuring the accuracy of the correction and improving the precision of the target wave velocity.

[0040] In some embodiments of this application, when determining a wave warning score based on a target wave current velocity and determining a wave warning alarm based on the wave warning score, the process includes: The wave warning score is derived from the following formula:

[0041] Where S represents the wave warning score, The target wave velocity is represented by α, e is represented by the natural constant, and α and β are represented by the weighting coefficients, with α+β=1. Sea wave warnings are divided into three levels: Level 1, Level 2, and Level 3. When 4 < S, the wave warning module issues a Level 1 alarm; When 2 < S ≤ 4, the wave warning module issues a level 2 alarm; When S≤2, the wave warning module issues a level 3 alarm; The urgency level decreases sequentially from Level 1 to Level 2 and Level 3.

[0042] Understandably, precise target wave velocity allows for real-time calculation of wave warning scores, for example: when... β is 0.5, and β is 0.5. In other words, when the speed is 1 meter per second, The score was 2.31 minutes, and the wave warning module issued a level-two alarm. β is 0.5, and β is 0.5. In other words, when the speed is 2 meters per second, A score of 4.71 indicates that the wave warning module issues a Level 1 alarm. The alarm level is dynamically adjusted based on the real-time wave warning score, reducing the possibility of false alarms and missed alarms. The flexible adjustment of the weighting coefficients allows the system to dynamically adjust the weights for triggering graded alarms according to different marine environments and sea area characteristics, adapting to various wave conditions and improving the scientific nature of wave observation and the accuracy of warnings.

[0043] In summary, the beneficial effects of this invention are as follows: By coordinating the operation of multiple radars across different bands, it is possible to acquire wave and current velocity data over a wider sea area, improving the accuracy of wave and current velocity measurements. Especially under complex sea conditions, it provides comprehensive wave and current velocity information. Furthermore, the preprocessing process ensures the filtering of signal noise and the extraction of data. By employing Fourier transform to convert the target radar signal into a frequency domain signal, and comparing it with standard spectral thresholds, measurement errors caused by environmental interference or signal attenuation are avoided, thus improving the accuracy of the initial wave and current velocity. By comparing with historical data, it is possible to determine whether the initial wave and current velocity needs correction. Combining a convolutional neural network model for prediction and comparison, the system can automatically derive the current velocity correction coefficient based on the ratio between the predicted velocity and the initial velocity, and accurately correct the initial wave and current velocity. This improves the reliability of wave and current velocity measurement results and can meet the requirements of varying marine environments. Finally, it performs wave warning scoring and automatically triggers warning alarms. It can identify and predict abnormal wave changes in a timely manner, providing key data support for offshore operations, shipping, and marine disaster early warning, which helps reduce marine disaster risks and improve emergency response capabilities.

[0044] In another preferred embodiment based on the above embodiments, see [reference] Figure 2 As shown, this embodiment provides a scanning observation method based on multi-radar cooperation, used to apply the above-mentioned scanning observation system based on multi-radar cooperation, including: S100: Acquire electromagnetic wave signals reflected from multiple radars at different frequency bands, preprocess the electromagnetic wave signals, obtain the target radar signal based on the preprocessing results, convert the target radar signal into a frequency domain signal value using Fourier transform, set a standard spectrum threshold, compare the standard spectrum threshold with the frequency domain signal value, and obtain the initial wave velocity based on the comparison results. S200: Compare the wave velocity with historical data to determine whether the initial wave velocity needs to be corrected; S300: Establish a convolutional neural network model, obtain the predicted value of the wave current velocity based on the convolutional neural network model, determine the velocity correction coefficient based on the ratio of the predicted value of the wave current velocity to the initial wave current velocity to be corrected, correct the initial wave current velocity to be corrected using the velocity correction coefficient, and obtain the target wave current velocity. S400: Determine the wave warning score based on the target wave current speed, and issue a wave warning alert based on the wave warning score.

[0045] Understandably, by preprocessing electromagnetic wave signals reflected from multiple radars at different frequency bands and combining them with Fourier transform, the target radar signal can be accurately obtained and converted into a frequency domain signal to derive the initial wave current velocity. This effectively avoids errors caused by environmental changes or interference, providing a reliable initial wave current velocity. By comparing it with historical data, it can be determined whether the initial wave current velocity needs correction, helping to improve the accuracy and precision of the target wave current velocity and ensuring that it conforms to the actual situation. A convolutional neural network model is established to derive the predicted wave current velocity value. The ratio of the predicted wave current velocity value to the initial wave current velocity is used to derive the correction coefficient, thus realizing an automated correction process and improving the accuracy of the target wave current velocity. The wave warning score derived from the target wave current velocity can provide real-time warning information. This provides scientific data support for marine activities, shipping, and safety protection, enabling timely detection of abnormal wave conditions and prevention of disasters or dangers.

[0046] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program goods. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program goods embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0047] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program goods according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0048] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0049] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0050] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A scanning observation system based on multi-radar cooperation, characterized in that, include: Radar band velocity measurement module, band current velocity judgment module, band current velocity processing module, and wave warning module; The radar band velocity measurement module is configured to acquire electromagnetic wave signals reflected from multiple radars in different bands, preprocess the electromagnetic wave signals, obtain the target radar signal based on the preprocessing results, convert the target radar signal into a frequency domain signal value using Fourier transform, set a standard spectrum threshold, compare the standard spectrum threshold with the frequency domain signal value, and obtain the initial wave current speed based on the comparison results. The wave velocity determination module is configured to compare the wave velocity with historical data to determine whether the initial wave velocity needs to be corrected. The wave velocity processing module is configured to establish a convolutional neural network model, obtain a predicted wave velocity value based on the convolutional neural network model, determine a velocity correction coefficient based on the ratio of the predicted wave velocity value to the initial wave velocity to be corrected, and correct the initial wave velocity to be corrected using the velocity correction coefficient to obtain the target wave velocity. The wave warning module is configured to determine a wave warning score based on the target wave velocity and to issue a wave warning alarm based on the wave warning score.

2. The scanning observation system based on multi-radar cooperation according to claim 1, characterized in that, When acquiring electromagnetic wave signals reflected from multiple radars at different frequency bands and preprocessing the electromagnetic wave signals, the process includes: The different bands include the first radar band and the second radar band; The preprocessing includes signal noise reduction and signal normalization.

3. The scanning observation system based on multi-radar cooperation according to claim 2, characterized in that, When converting the target radar signal into a frequency domain signal value using Fourier transform, the process includes: ； Where X(f) represents the frequency domain signal value, x(t) represents the time domain signal of the target radar signal, t represents the sampling point of the signal in the discrete time domain, T represents the number of discrete time points, f represents the frequency of the target radar signal, i represents the imaginary number, and e represents the natural constant.

4. The scanning observation system based on multi-radar cooperation according to claim 3, characterized in that, When setting a standard spectral threshold, comparing the standard spectral threshold with the frequency domain signal value, and determining the initial wave current velocity based on the comparison result, the process includes: When the frequency domain signal value is equal to the standard spectrum threshold, it is determined that the waves have not fluctuated and the current wave speed is maintained. When the frequency domain signal value is not equal to the standard spectrum threshold, it is determined that the ocean wave is fluctuating, and the initial ocean wave velocity is calculated based on the frequency domain signal value and the standard spectrum threshold.

5. The scanning observation system based on multi-radar cooperation according to claim 4, characterized in that, Calculating the initial wave current velocity based on the frequency domain signal value and the standard spectral threshold includes: The frequency shift F is calculated by taking the difference between the frequency domain signal value and the standard spectral threshold. The initial wave velocity is derived from the frequency shift, and the initial wave velocity is obtained by the following formula: ； Where V represents the initial wave velocity, F represents the frequency shift, and λ represents the mean radar wavelength. This represents the average radar transmission frequency.

6. The scanning observation system based on multi-radar cooperation according to claim 5, characterized in that, When comparing the wave velocity with historical data to determine whether the initial wave velocity needs correction, the following steps are included: The historical data represents the average of historical qualified data; When the initial wave velocity is greater than or equal to the average of the historical qualified data, it is determined that the initial wave velocity will not be corrected and the initial wave velocity will be determined as the target wave velocity. If the initial wave velocity is less than the average of the historical qualified data, then it is determined that the initial wave velocity should be corrected.

7. The scanning observation system based on multi-radar cooperation according to claim 6, characterized in that, When establishing a convolutional neural network model and deriving predicted wave current speeds based on the convolutional neural network model, the following steps are included: Historical initial wave velocity data is obtained from the initial wave velocity data, and the historical initial wave velocity data is divided into a wave training set and a wave test set. Cross-validation and grid search are used to find the parameters of the convolutional neural network model, and a convolutional neural network model is established. The wave training set is used to fit the neural network model, and the wave test set is used to input the convolutional neural network model to calculate the accuracy of the wave velocity prediction value. When the accuracy reaches a preset accuracy threshold, the predicted value of the current wave velocity is obtained based on the initial wave velocity.

8. The scanning observation system based on multi-radar cooperation according to claim 7, characterized in that, When determining a velocity correction coefficient based on the ratio of the predicted wave velocity to the initial wave velocity to be corrected, and then correcting the initial wave velocity to be corrected using the velocity correction coefficient to obtain the target wave velocity, the process includes: The ratio of the wave velocity to be corrected to the predicted wave velocity is denoted as Q; The first preset correction coefficient, the second preset correction coefficient, and the third preset correction coefficient are preset. When Q≤1, the first preset correction coefficient is used as the velocity correction coefficient of the wave velocity to be corrected. When 1 < Q ≤ 1.5, the second preset correction coefficient is used as the velocity correction coefficient for the wave velocity to be corrected. When 1.5 < Q, the third preset correction coefficient is used as the velocity correction coefficient for the wave velocity to be corrected. The target wave velocity is the product of the initial wave velocity to be corrected and the velocity correction coefficient.

9. The scanning observation system based on multi-radar cooperation according to claim 8, characterized in that, When determining a wave warning score based on the target wave current speed, and when determining a wave warning alert based on the wave warning score, the process includes: The wave warning score is derived from the following formula: ； Where S represents the wave warning score, The target wave velocity is represented by α, e is represented by the natural constant, and α and β are represented by the weighting coefficients, with α+β=1. The wave warning alert is divided into three levels: Level 1, Level 2, and Level 3. When 4 < S, the wave warning module issues a level one alarm; When 2 < S ≤ 4, the wave warning module issues a level two alarm; When S≤2, the wave warning module issues a level three alarm; The urgency levels of the Level 1 alarm, Level 2 alarm, and Level 3 alarm decrease sequentially.

10. A scanning observation method based on multi-radar cooperation, used in applying the multi-radar cooperative scanning observation system as described in any one of claims 1-9, characterized in that, include: Electromagnetic wave signals reflected from multiple radars at different frequency bands are acquired and preprocessed. The target radar signal is obtained based on the preprocessing results. The target radar signal is converted into a frequency domain signal value using Fourier transform. A standard spectrum threshold is set, and the standard spectrum threshold is compared with the frequency domain signal value. The initial wave velocity is obtained based on the comparison results. The wave velocity is compared with historical data to determine whether the initial wave velocity needs to be corrected. A convolutional neural network model is established, and a predicted value of the ocean wave velocity is obtained based on the convolutional neural network model. A velocity correction coefficient is determined based on the ratio of the predicted value of the ocean wave velocity to the initial ocean wave velocity to be corrected. The velocity correction coefficient is used to correct the initial ocean wave velocity to be corrected to obtain the target ocean wave velocity. A wave warning score is determined based on the target wave velocity, and a wave warning alert is issued based on the wave warning score.

Images