Underwater vehicle radiation noise generation and control method, system and device based on characteristic modeling and storage medium

Abstract

The invention provides an underwater vehicle radiation noise generation and control method, system and device based on characteristic modeling and a storage medium, and belongs to the field of underwater vehicle radiation noise simulation. According to the method, an underwater vehicle radiation noise source is simplified into a multi-point sound source model; acquiring a radiation noise signal of the underwater vehicle; a multi-resolution time-frequency analysis and deep learning technology is introduced by combining a passing characteristic rule of the radiation noise of the underwater vehicle, so that efficient feature extraction and accurate modeling of a non-stationary noise signal are realized, and a radiation noise simulation theoretical model of the underwater vehicle is established; through frequency domain analysis, a frequency domain curve of the radiation noise simulation theoretical model is compared with a measured data curve so as to evaluate the accuracy and effectiveness of the method. According to the method, the control capability of the radiation noise of the underwater vehicle is effectively improved, and the method has important theoretical breakthrough and wide engineering application value.

Description

Technical Field

[0001] This invention relates to the field of underwater vehicle radiated noise simulation technology, and in particular to a method, system, device and storage medium for generating and controlling underwater vehicle radiated noise based on characteristic modeling. Background Technology

[0002] With the increasing demand for marine resource development and scientific research, underwater vehicles are being used more and more widely in the civilian sector. However, their radiated noise significantly interferes with the acoustic equipment they carry (such as multibeam echo sounders and side-scan sonar), leading to a decrease in measurement accuracy. In addition, the International Maritime Organization (IMO) is gradually strengthening its control over underwater noise from ships, requiring a reduction in acoustic interference to marine mammals.

[0003] Noise sources in underwater vehicles can be mainly classified into three categories: mechanical vibration noise, generated by the operation of equipment such as motors and steering gears, transmitted to the water through the hull structure, with a frequency range concentrated in the 10–500 Hz range, and is the dominant noise during low-speed navigation; propeller noise, including cavitation noise and low-frequency line spectrum generated by blade vortex shedding, with a frequency band typically below 100 Hz; and hydrodynamic noise, generated by the interaction between the fluid and the hull, which is particularly significant at high speeds, including turbulent pulsating pressure and flow-induced structural noise. During navigation, the variation of noise sound pressure level at the observation point with time or distance exhibits a trend of increasing noise level with distance, and decreasing noise level with distance, reflecting the combined effects of sound source intensity, propagation loss, and environmental factors; this is known as the transit characteristic.

[0004] The purpose of simulating ship radiated noise is to study the acoustic characteristics generated during ship operation and analyze its potential impact on the marine environment, biological ecology, and related technological fields. By simulating noise, the characteristics of major noise sources such as ship propellers, engines, and hull vibrations can be quantified, and their behavioral disturbances and ecological impacts on marine life (such as whales and dolphins) can be assessed, providing a scientific basis for the development of noise control standards. Simultaneously, simulation results help optimize ship design, reduce noise emissions, and improve the environmental friendliness of shipping. Furthermore, on a technical level, noise simulation can support the development of underwater acoustic detection and monitoring technologies, providing crucial data support for marine environmental protection, shipping safety, and related research. Summary of the Invention

[0005] The purpose of this invention is to provide a method, system, device, and storage medium for generating and controlling radiated noise from underwater vehicles based on characteristic modeling, in order to solve the problems of complex radiated noise sources of underwater vehicles and the difficulty in establishing theoretical models for simulating the acoustic signature of underwater vehicles.

[0006] This invention proposes a method, system, device, and storage medium for generating and controlling radiated noise from underwater vehicles based on characteristic modeling. The core technical solutions include the following:

[0007] A method for generating and controlling radiated noise from underwater vehicles based on characteristic modeling includes the following steps:

[0008] Step 1: Obtain the noise source of the underwater vehicle, measured noise data, structural parameters of the underwater vehicle, and the distribution location of mechanical equipment.

[0009] Step 2: Combining the structural parameters of the underwater vehicle and the distribution of mechanical equipment, simplify the radiated noise source of the underwater vehicle into a point source model, and generate a synthetic noise signal containing continuous spectrum and line spectrum.

[0010] Step 3: Calculate the sound pressure level of the synthesized noise signal at the observation point based on the sound wave propagation model.

[0011] Step 4: Separate the synthesized noise signal to obtain multiple independent noise components.

[0012] Step 5: Based on each noise component and combined with navigation state parameters, establish a simulation model of the radiated noise of the underwater vehicle;

[0013] Step 6: Run the underwater vehicle radiated noise simulation model and compare the output simulated noise data with the measured noise data for verification.

[0014] Step 7: Dynamically adjust the model parameters based on the verification results and output the optimized noise control strategy.

[0015] Furthermore, the expression for the synthesized noise signal in step 2 specifically includes:

[0016]

[0017] in, In time The synthesized noise signal value, For broadband signals, For the first The amplitude of a discrete line spectrum For the first The frequency of a discrete line spectrum For the first The phase of a discrete line spectrum.

[0018] Furthermore, the method for calculating the sound pressure level of the synthesized noise signal at the observation point in step 3 specifically includes:

[0019]

[0020]

[0021] in, For time The sound pressure level at the observation point At the source level, It is a constant. For time The distance between the ship and the observation point For reference distance, The frequency-dependent absorption coefficient, To observe the water depth at the hydrophone point, The speed of the ship.

[0022] Furthermore, the method for separating and processing the radiated noise signal of the underwater vehicle described in step 4 specifically includes:

[0023] Step 4.1: Use a multimodal noise separation method to separate the synthetic noise signal.

[0024] Step 4.2: Perform time-frequency analysis on each noise component to extract line spectrum frequency, power spectral density, instantaneous frequency, and amplitude modulation characteristics;

[0025]

[0026] in, The original signal, For the first One modal function, This is the remaining signal.

[0027] Furthermore, step 6 specifically includes:

[0028] Calculate the power spectral density of simulated noise data and measured noise data. Analyze the energy distribution of the signal at different frequencies;

[0029]

[0030] in, For the signal duration Fourier transform within.

[0031] Calculate the speaker similarity between simulated noise data and measured noise data. ;like The closer the similarity is to 1, the higher the voiceprint similarity; if The closer the similarity is to -1, the lower the voiceprint similarity.

[0032]

[0033] in, For simulating noise data vectors, This is the measured noise data vector.

[0034] Calculate the correlation coefficient between simulated noise data and measured noise data. ;

[0035]

[0036] in, For the first in the simulated noise data vector One element, The first element in the measured noise data vector One element, This is the arithmetic mean of all elements in the simulated noise data vector. This is the arithmetic mean of all elements in the measured noise data vector.

[0037] Calculate the line spectrum coverage to assess the degree of coverage of the characteristic line spectrum in the actual measured sound pressure level spectrum relative to the expected sound pressure level spectrum.

[0038] In frequency range Within, identify the desired sound pressure level spectrum. and measuring sound pressure level spectrum The effective characteristic line spectrum; for each characteristic line spectrum frequency in the desired sound pressure level spectrum. Check if there are matching characteristic line spectral frequencies in the measured spectrum. The matching condition is .

[0039] Line spectrum coverage is defined as the number of effective characteristic lines in the measured sound pressure level spectrum. Number of characteristic lines in the expected spectrum percentage;

[0040]

[0041] Calculate sound pressure level and total sound pressure level .

[0042] Single-frequency or narrowband sound pressure level Used to characterize a specific frequency The sound pressure intensity at that location;

[0043]

[0044] in, For frequency The effective sound pressure level at that location, This is the underwater standard reference sound pressure level. This indicator reflects the local spectral energy, making it easy to identify characteristic spectral lines.

[0045] Total sound pressure level The overall sound pressure level is obtained by superimposing the effective sound pressure levels (RMS) of all frequency components within a specified frequency range.

[0046]

[0047] in, For the first The sound pressure level of a 1Hz narrowband or 1 / 3 octave band, where M is the total number of frequency bands.

[0048] Furthermore, the method for dynamically adjusting model parameters described in step 7 specifically includes:

[0049] An adaptive filter is introduced, and the sound wave propagation model parameters are updated based on the verification results.

[0050] A reinforcement learning mechanism is introduced, and a reward function is calculated. ;

[0051]

[0052] in, Output as the target. Output for the model.

[0053] Based on the reward function, the optimized noise control strategy is obtained. ;

[0054]

[0055] in, For learning rate, This is the discount factor.

[0056] A computer device includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described above.

[0057] A computer-readable storage medium having a computer program stored thereon, characterized in that: when the computer program is executed by a processor, it implements the steps of the above-described method.

[0058] A computer program product includes computer instructions that, when executed by a processor, implement the steps of the method described above.

[0059] The beneficial effects of this invention are as follows:

[0060] Compared with existing technologies, this invention simplifies the underwater radiated noise source into a multi-point sound source model, significantly simplifying the calculation and analysis process. This allows for a focus on key factors such as sound power, thus more easily and accurately reflecting actual load conditions. Based on this, multi-resolution time-frequency analysis and deep learning techniques are introduced to achieve efficient feature extraction and accurate modeling of non-stationary noise signals, providing precise frequency domain analysis that reveals the main frequency distribution of radiated noise, aiding in the identification of key dynamic characteristics. Comparison of verification steps with simulation results ensures the effectiveness of the simplified model and verifies the accuracy and reliability of the method. Furthermore, the provided underwater vehicle radiated noise generation and control system based on transit characteristics can be easily integrated with existing control systems and acoustic equipment, reducing the difficulty and cost of technology upgrades. In addition, this method improves the intelligence level of the design process, accelerates design and analysis speed, and the system can serve as a decision support tool, helping engineers and designers make more scientific and rational decisions in the design and operation of underwater vehicles. Attached Figure Description

[0061] Figure 1 This is an overall flowchart of an embodiment of the present invention.

[0062] Figure 2 This is a schematic diagram of radiated noise signal monitoring in an embodiment of the present invention.

[0063] Figure 3 This is a block diagram of the system in an embodiment of the present invention.

[0064] Figure 4 This is a schematic diagram of the structure of the radiated noise generation control device in an embodiment of the present invention.

[0065] Figure 5 This is a time-domain waveform diagram of the radiated noise characteristics in an embodiment of the present invention. Detailed Implementation

[0066] The following is in conjunction with the appendix Figure 1 The present invention will be further described below.

[0067] Step 1: Obtain the noise source of the underwater vehicle, measured noise data, structural parameters of the underwater vehicle, and the distribution location of mechanical equipment.

[0068] Step 2: Combining the structural parameters of the underwater vehicle and the distribution of mechanical equipment, simplify the radiated noise source of the underwater vehicle into a point source model, and generate a synthetic noise signal containing continuous spectrum and line spectrum.

[0069] The expression for the synthesized noise signal specifically includes:

[0070]

[0071] in, In time The synthesized noise signal value, For broadband signals, For the first The amplitude of a discrete line spectrum For the first The frequency of a discrete line spectrum For the first The phase of a discrete line spectrum.

[0072] Step 3: Calculate the sound pressure level of the synthesized noise signal at the observation point based on the sound wave propagation model.

[0073] The method for calculating the sound pressure level of the synthesized noise signal at the observation point specifically includes:

[0074]

[0075]

[0076] in, For time The sound pressure level at the observation point At the source level, It is a constant. For time The distance between the ship and the observation point For reference distance, The frequency-dependent absorption coefficient, To observe the water depth at the hydrophone point, The speed of the ship.

[0077] Step 4: Separate the synthesized noise signal to obtain multiple independent noise components.

[0078] The method for separating and processing radiated noise signals from underwater vehicles specifically includes:

[0079] Step 4.1: Use a multimodal noise separation method to separate the synthetic noise signal.

[0080] Step 4.2: Perform time-frequency analysis on each noise component to extract line spectrum frequency, power spectral density, instantaneous frequency, and amplitude modulation characteristics;

[0081]

[0082] in, The original signal, For the first One modal function, This is the remaining signal.

[0083] Step 5: Based on each noise component and combined with navigation state parameters, establish a simulation model of the radiated noise of the underwater vehicle;

[0084] Step 6: Run the underwater vehicle radiated noise simulation model and compare the output simulated noise data with the measured noise data for verification.

[0085] Step 6 specifically includes:

[0086] Calculate the power spectral density of simulated noise data and measured noise data. Analyze the energy distribution of the signal at different frequencies;

[0087]

[0088] in, For the signal duration Fourier transform within.

[0089] Calculate the speaker similarity between simulated noise data and measured noise data. ;like The closer the similarity is to 1, the higher the voiceprint similarity; if The closer the similarity is to -1, the lower the voiceprint similarity.

[0090]

[0091] in, For simulating noise data vectors, This is the measured noise data vector.

[0092] Calculate the correlation coefficient between simulated noise data and measured noise data. ;

[0093]

[0094] in, For the first in the simulated noise data vector One element, The first element in the measured noise data vector One element, This is the arithmetic mean of all elements in the simulated noise data vector. This is the arithmetic mean of all elements in the measured noise data vector.

[0095] Calculate the line spectrum coverage to assess the degree of coverage of the characteristic line spectrum in the actual measured sound pressure level spectrum relative to the expected sound pressure level spectrum.

[0096] In frequency range Within, identify the desired sound pressure level spectrum. and measuring sound pressure level spectrum The effective characteristic line spectrum; for each characteristic line spectrum frequency in the desired sound pressure level spectrum. Check if there are matching characteristic line spectral frequencies in the measured spectrum. The matching condition is .

[0097] Line spectrum coverage is defined as the number of effective characteristic lines in the measured sound pressure level spectrum. Number of characteristic lines in the expected spectrum percentage;

[0098]

[0099] Calculate sound pressure level and total sound pressure level .

[0100] Single-frequency or narrowband sound pressure level Used to characterize a specific frequency The sound pressure intensity at that location;

[0101]

[0102] in, For frequency The effective sound pressure level at that location, This is the underwater standard reference sound pressure level. This indicator reflects the local spectral energy, making it easy to identify characteristic spectral lines.

[0103] Total sound pressure level The overall sound pressure level is obtained by superimposing the effective sound pressure values ​​of all frequency components within a specified frequency range.

[0104]

[0105] in, For the first The sound pressure level of a 1Hz narrowband or 1 / 3 octave band, where M is the total number of frequency bands.

[0106] Step 7: Dynamically adjust the model parameters based on the verification results and output the optimized noise control strategy.

[0107] Example

[0108] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0109] The following is a reference appendix. Figure 1 To be continued Figure 5 Embodiments of the present invention are described below. Addressing the problem mentioned in the background art regarding the establishment of a theoretical model for simulating acoustic signatures of underwater vehicles under maneuvering conditions, the present invention provides a method for generating and controlling radiated noise from underwater vehicles based on characteristic modeling. In this method, by identifying the main noise sources of the underwater vehicle, the radiated noise sources are simplified into a multi-point sound source model. The radiated noise of the underwater vehicle before simplification is compared with the characteristic frequency domain curves after simplification, proving the effectiveness of the simplification and reducing the amount of statistical calculation. Thus, the problem of establishing a theoretical model for simulating acoustic signatures of underwater vehicles under maneuvering conditions is solved.

[0110] Specifically, Figure 1 This is a flowchart illustrating a method for generating and controlling radiated noise from an underwater vehicle based on characteristic modeling, as provided in an embodiment of the present invention.

[0111] like Figure 1 As shown, the underwater vehicle radiated noise generation and control method based on its transit characteristics includes the following steps:

[0112] In S101, based on the structural and layout information of the underwater vehicle, the radiated noise sources of the underwater vehicle are simplified into point sound sources. This simplification generates a sound source signal containing both continuous and line spectra.

[0113]

[0114] in,

[0115] For broadband signals, , , This represents the amplitude, frequency, and phase of the line spectrum.

[0116] Broadband noise can be generated by a Gaussian random process, and the spectral shape is based on an empirical PSD.

[0117] When the size of the sound source is much smaller than the distance from the measuring point to the sound source, the sound source can be considered equivalent to a point source. The sound wave radiates relatively uniformly in all directions as a spherical wave. The sound pressure level generated by the sound wave at a point is inversely proportional to the distance from that point to the center of the sound source. The sound pressure level at a location r away from the sound source is...

[0118]

[0119] in

[0120] Sound pressure level at the observation point (unit: dB re 1) )

[0121] Sound source level (reference distance) (sound pressure level at the location).

[0122] : The distance between the ship and the observation point.

[0123] Reference distance (usually 1 meter)

[0124] Frequency-dependent absorption coefficient (unit: dB / m).

[0125] Considering the relative motion and the amplitude changes caused by the motion speed, the actual simulated signal is obtained, simulating the sound pressure change process from far to near and from near to far at different speeds.

[0126] like Figure 1 and Figure 2 The diagram illustrates the monitoring of radiated noise signals from an underwater vehicle. The formula for the distance from the ship to the hydrophone can be derived from the ship's speed. ,time Therefore, the coordinates of the hydrophone can be determined by the water depth at which the hydrophone is located, thus yielding the distance between the ship and the hydrophone.

[0127]

[0128] in,

[0129] Distance from the ship to the hydrophone (unit: meters).

[0130] : Water depth of the hydrophone (unit: meter).

[0131] Ship speed (unit: meters per second).

[0132] Time (unit: seconds).

[0133] In step S102, the radiated noise signal of the underwater vehicle is acquired. A hydrophone array is used to collect the radiated noise signal of the underwater vehicle under different maneuvering conditions, and the corresponding navigation parameters are recorded to construct an underwater vehicle radiated noise dataset.

[0134] Multimodal noise separation is performed, as underwater vehicle noise comprises three coupled components: mechanical noise, propulsion noise, and hydrodynamic noise. A condition-based decoupling method is employed for separation.

[0135] Specifically, mechanical noise measurement: the aircraft is suspended and stationary (gravity). (Buoyancy), only the motor / servo motor is running:

[0136]

[0137] in, For structure transfer function, This is the spectrum of the vibration reference signal.

[0138] Thruster noise measurement: With the propeller blades disconnected while suspended, only the propulsion motor is running:

[0139]

[0140] Hydrodynamic noise calculation: Measure total noise during navigation. Subtracting the first two:

[0141]

[0142] Signal acquisition and preprocessing were performed, and the time-domain waveform of the radiated noise is as follows:

[0143]

[0144] in, For modulation spectrum, It is a continuous spectrum. It is a line spectrum.

[0145] The preprocessing procedure is as follows: First, frequency domain averaging is performed, and then power spectrum estimation is performed on the N-segment signal to reduce the impact of random noise.

[0146]

[0147] Propagation loss correction: adjust the measured value Converted to a 1-meter reference distance:

[0148]

[0149] in, This is the seawater absorption coefficient.

[0150] Line spectrum extraction: Based on DEMON spectrum demodulation analysis, the modulation spectrum is separated.

[0151]

[0152] Specifically, taking the measured noise data of an underwater vehicle during its passage as a case study, we will analyze its time-frequency characteristics in depth.

[0153] like Figure 1 and Figure 5The time-domain waveform diagram shows a significant increase in sound pressure amplitude with fluctuations between 9 and 16 seconds when the underwater vehicle passes through the underwater acoustic monitoring area. Analysis indicates this phenomenon is attributed to the superposition effect of multiple noise source devices of various types, located far apart, passing sequentially through the monitoring point.

[0154] In S103, the characteristics of radiated noise from underwater vehicles are revealed, and a theoretical model for simulating radiated noise from underwater vehicles under maneuvering conditions is established.

[0155] In S104, the effectiveness of the radiated noise generation control method is verified. The radiated noise of the underwater vehicle before simplification is compared with the characteristic spectrum curves after simplification.

[0156] Figure 3 This is an embodiment of the present invention of an underwater vehicle radiated noise generation and control system based on its transit characteristics.

[0157] like Figure 3 As shown, the radiated noise generation and control system includes:

[0158] Multimodal noise separation module: Separates the coupled components in radiated noise (such as main engine noise, thruster noise, and fluid noise), clarifies the contribution of each sound source to the transmission characteristics, and improves the accuracy of sound source modeling.

[0159] The time-frequency characteristic analysis module analyzes the time-frequency characteristics of radiated noise signals, uses Fourier transform (FFT) to generate time spectrum, reveals the frequency components of the signal that change over time, and extracts the time evolution law and frequency distribution characteristics of non-stationary signals, such as line spectrum frequency (e.g., propeller blade frequency) and power spectral density (PSD).

[0160] Radiated noise signal generation module: Based on the operating conditions (simulated distance, sailing speed, sailing status) and the characteristics of the noise source, it generates a realistic radiated noise signal with passing characteristics to simulate changes in sound pressure level.

[0161] Noise Source Characteristics Database Module: Stores and manages noise source characteristics that are strongly correlated with the operating conditions of the aircraft (speed, depth, load), providing parameter support for signal generation and modeling.

[0162] The control system execution module receives instructions from the control decision module, coordinates the operation of each module, and manages input parameters and output results.

[0163] The verification and visualization module is used to compare the actual generated radiated noise signal with the radiated noise data collected in the experiment in the frequency domain, verify the accuracy of the simulation results, and display the time-frequency curves and analysis results of the radiated noise.

[0164] Figure 4This is a schematic diagram of a device provided in an embodiment of the present invention. The device may include:

[0165] The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.

[0166] When the processor 402 executes the program, it implements the underwater vehicle radiated noise generation and control method based on characteristic modeling provided in the above embodiments.

[0167] Furthermore, this device also includes:

[0168] Communication interface 403 is used for communication between memory 401 and processor 402.

[0169] The memory 401 is used to store computer programs that can run on the processor 402.

[0170] Memory 401 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0171] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for generating and controlling radiated noise from an underwater vehicle based on characteristic modeling.

[0172] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0173] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0174] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0175] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

[0176] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for generating and controlling radiated noise of underwater vehicles based on characteristic modeling, characterized in that... Includes the following steps: Step 1: Obtain the noise source of the underwater vehicle, measured noise data, structural parameters of the underwater vehicle, and the distribution location of its mechanical equipment; Step 2: Combining the structural parameters of the underwater vehicle and the distribution of mechanical equipment, simplify the radiated noise source of the underwater vehicle into a point source model, and generate a synthetic noise signal containing continuous spectrum and line spectrum; Step 3: Calculate the sound pressure level of the synthesized noise signal at the observation point based on the sound wave propagation model; Step 4: Separate the synthesized noise signal to obtain multiple independent noise components; Step 5: Based on each noise component and combined with navigation state parameters, establish a simulation model of the radiated noise of the underwater vehicle; Step 6: Run the underwater vehicle radiated noise simulation model and compare the output simulated noise data with the measured noise data for verification; Step 7: Dynamically adjust the model parameters based on the verification results and output the optimized noise control strategy.

2. The method for generating and controlling radiated noise of underwater vehicles based on characteristic modeling according to claim 1, characterized in that, The expression for the synthesized noise signal in step 2 specifically includes: in, In time The synthesized noise signal value, For broadband signals, For the first The amplitude of a discrete line spectrum For the first The frequency of a discrete line spectrum For the first The phase of a discrete line spectrum.

3. The method for generating and controlling radiated noise of underwater vehicles based on characteristic modeling according to claim 2, characterized in that, The method for calculating the sound pressure level of the synthesized noise signal at the observation point in step 3 specifically includes: in, For time The sound pressure level at the observation point At the sound source level, It is a constant. For time The distance between the ship and the observation point For reference distance, The frequency-dependent absorption coefficient, To observe the water depth at the hydrophone point, The speed of the ship.

4. The method for generating and controlling radiated noise of underwater vehicles based on characteristic modeling according to claim 3, characterized in that, Step 4, the method for separating and processing the radiated noise signal of an underwater vehicle, specifically includes: Step 4.1: Use a multimodal noise separation method to separate the synthetic noise signal; Step 4.2: Perform time-frequency analysis on each noise component to extract line spectrum frequency, power spectral density, instantaneous frequency, and amplitude modulation characteristics; in, The original signal, For the first One modal function, This is the remaining signal.

5. The method for generating and controlling radiated noise of underwater vehicles based on characteristic modeling according to claim 4, characterized in that, Step 6 specifically includes: Calculate the power spectral density of simulated noise data and measured noise data. Analyze the energy distribution of the signal at different frequencies; in, For the signal duration Fourier transform within; Calculate the speaker similarity between simulated noise data and measured noise data. ;like The closer the similarity is to 1, the higher the voiceprint similarity; if The closer the similarity is to -1, the lower the voiceprint similarity. in, For simulating noise data vectors, This is the measured noise data vector; Calculate the correlation coefficient between simulated noise data and measured noise data. ; in, For the first in the simulated noise data vector One element, The first element in the measured noise data vector One element, This is the arithmetic mean of all elements in the simulated noise data vector. This is the arithmetic mean of all elements in the measured noise data vector; Calculate the line spectrum coverage and evaluate the degree of coverage of the characteristic line spectrum in the actual measured sound pressure level spectrum relative to the expected sound pressure level spectrum; In frequency range Within, identify the desired sound pressure level spectrum. and measuring sound pressure level spectrum The effective characteristic line spectrum; for each characteristic line spectrum frequency in the desired sound pressure level spectrum. Check if there are matching characteristic line spectral frequencies in the measured spectrum. The matching condition is ; Line spectrum coverage is defined as the number of effective characteristic lines in the measured sound pressure level spectrum. Number of characteristic lines in the expected spectrum percentage; Calculate sound pressure level and total sound pressure level ; Single-frequency or narrowband sound pressure level Used to characterize a specific frequency The sound pressure intensity at that location; in, For frequency The effective sound pressure level at that location, This is the underwater standard reference sound pressure level. This indicator reflects the local spectral energy, facilitating the identification of characteristic spectral lines; Total sound pressure level The overall sound pressure level is obtained by superimposing the effective sound pressure values ​​of all frequency components within a specified frequency range. in, For the first The sound pressure level of a 1Hz narrowband or 1 / 3 octave band, where M is the total number of frequency bands.

6. The method for generating and controlling radiated noise of underwater vehicles based on characteristic modeling according to claim 5, characterized in that, The method for dynamically adjusting model parameters described in step 7 specifically includes: An adaptive filter is introduced, and the sound wave propagation model parameters are updated based on the verification results. A reinforcement learning mechanism is introduced, and a reward function is calculated. ; in, Output as the target. Output for the model; Based on the reward function, the optimized noise control strategy is obtained. ; in, For learning rate, This is the discount factor.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method of claim 6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the steps of the method of claim 6.

9. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by the processor, they implement the steps of the method of claim 6.

Images