Intelligent piling underwater noise monitoring method and system

Abstract

The application discloses an intelligent piling underwater noise monitoring method and system, which comprises the following steps: receiving and preprocessing original underwater sound pressure signals of multiple monitoring sites to obtain multiple underwater sound pressure signals; detecting and extracting the underwater sound pressure signals of each monitoring site based on short-time energy analysis and adaptive threshold judgment to obtain candidate pulse signals; performing spectrum analysis on the candidate pulse signals to obtain time-frequency distribution diagrams, log-mel spectrograms and frequency domain characteristic parameters; inputting the log-mel spectrogram into a deep learning model to obtain a piling pulse signal; performing post-processing on the piling pulse signal to calculate acoustic evaluation parameters of piling underwater noise; and inversely calculating the average sound source level of the piling operation based on the acoustic evaluation parameters of the multiple monitoring sites and corresponding monitoring position information and in combination with an ocean underwater sound propagation model. The application meets the demand of modern ocean engineering for rapid response and automatic monitoring of underwater noise pollution.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of marine environment monitoring, and particularly relates to an intelligent piling underwater noise monitoring method and system. BACKGROUND

[0002] Traditional underwater noise monitoring methods mostly use fixed acoustic monitoring systems or manually deployed hydrophone arrays, which have significant defects. In terms of data processing, existing methods usually rely on offline processing mode, and the collected acoustic data need to be analyzed by humans or later to extract effective information, which leads to serious lag in data processing and makes it impossible to realize real-time feedback and rapid warning.

[0003] In addition, due to the lack of efficient automatic identification and extraction algorithms, the existing technology is difficult to accurately distinguish and extract piling pulse signals from complex marine environmental noise, further reducing the accuracy and reliability of underwater noise monitoring.

[0004] Therefore, the existing technology cannot meet the urgent need for rapid response and automatic monitoring of underwater noise pollution in modern marine engineering. SUMMARY

[0005] To solve the above technical problems, the present application provides an intelligent piling underwater noise monitoring method, which comprises the following steps:

[0006] Receiving and preprocessing the original underwater sound pressure signals of multiple monitoring sites to obtain multiple underwater sound pressure signals;

[0007] Based on short-time energy analysis and adaptive threshold determination, the underwater sound pressure signals of each monitoring site are detected and extracted to obtain candidate pulse signals;

[0008] Performing spectral analysis on the candidate pulse signals to obtain time-frequency distribution diagrams, log-mel spectrograms and frequency domain feature parameters;

[0009] Inputting the log-mel spectrogram into a deep learning model for identification and classification to obtain piling pulse signals from the candidate pulse signals;

[0010] Post-processing the piling pulse signals and calculating the acoustic evaluation parameters of piling underwater noise;

[0011] Based on the acoustic evaluation parameters of multiple monitoring sites and their corresponding monitoring location information, combined with a marine underwater sound propagation model, the average sound source level of piling operations is calculated by inversion.

[0012] Optionally, based on short-time energy analysis and adaptive threshold determination, the underwater sound pressure signals of each monitoring site are detected and extracted to obtain candidate pulse signals, comprising the following steps:

[0013] calculating a short-time energy of the underwater sound pressure signal based on the preset window length and the preset overlap rate;

[0014] calculating a corresponding adaptive threshold value based on the energy mean value, the standard deviation of the background noise of each monitoring site, and a preset sensitivity factor;

[0015] comparing the short-time energy of each monitoring site with the adaptive threshold value to identify a candidate pulse signal; the short-time energy of the candidate pulse signal is greater than the adaptive threshold value;

[0016] extracting an envelope line of the candidate pulse signal;

[0017] performing low-pass filtering and smoothing processing on the envelope line, and determining the start and end time of the candidate pulse signal based on an envelope detection threshold value;

[0018] based on the start and end time, the complete waveform of the candidate pulse signal is obtained by extending a preset filling time length before and after.

[0019] Optionally, the frequency domain feature parameters include in-band energy distribution, peak frequency and bandwidth parameters;

[0020] performing spectral analysis on the candidate pulse signal to obtain a time-frequency distribution map, a log-mel spectrogram and frequency domain feature parameters, including the following steps:

[0021] based on the complete waveform of the candidate pulse signal, performing fast Fourier transform or short-time Fourier transform to obtain a time-frequency distribution map;

[0022] convert the time-frequency distribution map into a log-mel spectrogram, and based on the time-frequency distribution map, calculate the in-band energy distribution, peak frequency and bandwidth parameters of each candidate pulse signal.

[0023] Optionally, after obtaining the candidate pulse signal, it further includes:

[0024] performing time domain feature extraction on the candidate pulse signal to obtain time domain feature parameters; the time domain feature parameters include peak sound pressure, peak-to-peak sound pressure, pulse duration, rise time, fall time, pulse interval and pulse rate.

[0025] Optionally, inputting the log-mel spectrogram into a deep learning model for identification and classification to obtain a pile driving pulse signal from the candidate pulse signal, including the following steps:

[0026] inputting the log-mel spectrogram into a two-dimensional convolutional neural network model to perform feature learning and classification on the log-mel spectrogram;

[0027] Based on the feature learning result, a class label and a confidence corresponding to each of the candidate pulse signals are outputted to obtain a pile-driving pulse signal from the candidate pulse signals; the class label at least includes a pile-driving sound and a ship machinery noise.

[0028] Optionally, the method further comprises:

[0029] Based on the pile-driving pulse signal, an average sound pressure level in a period is calculated;

[0030] The average sound pressure level in the period is compared with a preset frequency band threshold value, and when the average sound pressure level in the period is greater than the frequency band threshold value, a first alarm signal is generated and outputted.

[0031] Optionally, the method further comprises:

[0032] Based on the pile-driving pulse signal, a single-event sound exposure level is calculated; the single event is a single pile-driving impact;

[0033] The single-event sound exposure level is compared with a preset sound exposure level threshold value, and when the single-event sound exposure level is greater than the sound exposure level threshold value, a second alarm signal is generated and outputted.

[0034] Optionally, the pile-driving pulse signal is post-processed, and an acoustic evaluation parameter of pile-driving underwater noise is calculated, including the following steps:

[0035] The pile-driving pulse signal is time-smoothed;

[0036] Based on the propagation distance of each pile-driving pulse signal and a marine acoustic propagation model, the pile-driving pulse signal is corrected for propagation loss;

[0037] Based on the sound pressure level after the correction for propagation loss, an acoustic evaluation parameter of pile-driving underwater noise is calculated, and the acoustic evaluation parameter includes a root mean square sound pressure level, an instantaneous peak sound pressure level, a single sound exposure level, and a cumulative sound exposure level.

[0038] Optionally, based on the acoustic evaluation parameters of multiple monitoring sites and corresponding monitoring position information, an average sound source level of pile-driving operation is calculated by inversion in combination with a marine acoustic propagation model, including the following steps:

[0039] Single sound exposure levels of multiple monitoring sites and corresponding monitoring position information are obtained, and a straight-line distance between each monitoring position and a pile-driving sound source is calculated;

[0040] Based on a spherical or cylindrical marine acoustic propagation model, a propagation loss corresponding to each monitoring site is calculated;

[0041] Add the single sound exposure level of each monitoring site to the corresponding propagation loss to calculate the sound source level of each monitoring site corresponding to 1m away from the piling operation respectively;

[0042] Calculate the arithmetic mean value of the sound source level of 1m away from the piling operation based on the sound source level of 1m away from the piling operation calculated by all monitoring sites, and take the arithmetic mean value as the average sound source level of the piling operation.

[0043] Corresponding to the intelligent piling underwater noise monitoring method, the application provides an intelligent piling underwater noise monitoring system, which comprises:

[0044] A signal acquisition module is configured to acquire original underwater sound pressure signals of a plurality of monitoring sites.

[0045] A preprocessing module is configured to receive and preprocess the original underwater sound pressure signals of the plurality of monitoring sites to obtain a plurality of underwater sound pressure signals.

[0046] A signal extraction module is configured to detect and extract the underwater sound pressure signals of each monitoring site based on short-time energy analysis and adaptive threshold determination to obtain candidate impulse signals.

[0047] A spectrum analysis module is configured to perform spectrum analysis on the candidate impulse signals to obtain a time-frequency distribution diagram, a log-mel spectrogram and a frequency domain feature parameter.

[0048] A classification module is configured to input the log-mel spectrogram into a deep learning model for identification and classification to obtain a piling impulse signal from the candidate impulse signals.

[0049] An acoustic evaluation parameter calculation module is configured to perform post-processing on the piling impulse signal and calculate acoustic evaluation parameters of the piling underwater noise.

[0050] A sound source level inversion module is configured to calculate the average sound source level of the piling operation based on the acoustic evaluation parameters of the plurality of monitoring sites and the corresponding monitoring position information in combination with an ocean underwater sound propagation model.

[0051] Compared with the prior art, the application has the following beneficial effects:

[0052] (1) By receiving the original underwater sound pressure signals of multiple monitoring stations and preprocessing, combining short-time energy analysis and adaptive threshold determination to realize automatic real-time detection and extraction of pulse signals, the data processing lag problem caused by the dependence of the prior art on offline manual analysis is solved; through deep learning model for automatic identification and classification of log-mel spectrogram, the efficiency and accuracy of the automatic identification algorithm in the prior art are overcome; through the fusion of multi-point acoustic evaluation parameters and marine acoustic propagation model to invert the sound source level, the whole process automation of data acquisition, signal recognition and sound source intensity evaluation is realized, which meets the needs of modern marine engineering for rapid response and automatic monitoring, and significantly improves the real-time, accuracy and reliability of monitoring.

[0053] (2) By presetting the window length and overlap rate to calculate the short-time energy and dynamically generating the adaptive threshold based on the statistical characteristics of the background noise, the sensitivity of pulse detection can be automatically adjusted according to the actual environmental noise level, avoiding the problem of missed detection or false detection caused by fixed threshold; by low-pass filtering, smoothing and front and rear extension filling of the envelope line, noise interference is effectively suppressed, and the complete waveform boundary of the candidate pulse signal is accurately extracted, improving the accuracy and robustness of candidate pulse signal extraction.

[0054] (3) By fast Fourier transform or short-time Fourier transform, the candidate pulse signal is converted into a time-frequency distribution diagram, and a log-mel spectrogram is further generated, realizing the visualization and logarithmic perception scale representation of signal spectrum characteristics; at the same time, the in-band energy distribution, peak frequency and bandwidth parameters are calculated, providing input data for the deep learning model and improving the feature learning efficiency and recognition accuracy of the classification model.

[0055] (4) By inputting the log-mel spectrogram into the two-dimensional convolutional neural network model for end-to-end feature learning and classification, the powerful nonlinear feature extraction capability of deep learning is utilized to realize high-precision automatic differentiation of complex interference sources such as piling sound and ship noise; by outputting the class label and confidence, a quantitative basis is provided for the screening of piling pulse signals, greatly reducing the workload and misjudgment risk of manual discrimination.

[0056] (5) By calculating the average sound pressure level in a cycle and comparing it with the frequency band threshold, the first alarm signal can be generated immediately when the noise intensity exceeds the standard, realizing the function of rapid early warning of persistent strong noise and providing timely decision support for on-site construction of biological protection measures.

[0057] (6) By calculating the sound exposure level of a single piling impact event and comparing it with the sound exposure level threshold, the second alarm signal is generated when the energy of a single pulse exceeds the standard, realizing accurate monitoring and graded early warning of high-intensity transient noise events.

[0058] (7) Through time smoothing processing of the piling pulse signal and propagation loss correction based on the ocean acoustic propagation model, the influence of distance and propagation path on sound pressure measurement is eliminated, making the data of different monitoring sites comparable; by calculating the standardized acoustic evaluation parameters such as root mean square sound pressure level, instantaneous peak sound pressure level, single sound exposure level and cumulative sound exposure level, standardized and normalized quantitative indicators are provided for objective evaluation of piling noise and environmental protection.

[0059] (8) Through multi-point monitoring data fusion, the influence of single-point measurement error and environmental uncertainty is effectively reduced, and the accuracy and robustness of sound source level estimation are significantly improved. BRIEF DESCRIPTION OF DRAWINGS

[0060] The drawings described herein are used to provide further understanding of the present application, and form a part of the present application. The illustrative embodiments of the present application and their descriptions serve to explain the present application, and do not constitute an improper limitation on the present application. In the drawings:

[0061] Figure 1 a flowchart of an embodiment of the intelligent piling underwater noise monitoring method of the present application;

[0062] Figure 2 a framework diagram of an embodiment of the intelligent piling underwater noise monitoring system of the present application. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme of the embodiments of the present application will be described clearly and completely below in conjunction with the drawings of the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the specific embodiments described herein are only used to explain the present application, and do not limit the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0064] As shown in Figure 1 , an intelligent piling underwater noise monitoring method of the present application includes the following steps:

[0065] Receive the original underwater sound pressure signals of multiple monitoring sites and pre-process to obtain multiple underwater sound pressure signals; preferably, the pre-processing includes converting the original underwater sound pressure signals into digital signals, and performing band-pass filtering (10Hz-100kHz), gain adjustment processing, removing direct current, environmental low-frequency and high-frequency noise;

[0066] Based on short-time energy analysis and adaptive threshold determination, the underwater sound pressure signals of each monitoring site are detected and extracted respectively to obtain candidate pulse signals;

[0067] spectrum analysis is performed on the candidate pulse signal to obtain a time-frequency distribution diagram, a log-mel spectrum diagram and frequency domain characteristic parameters;

[0068] The log-mel spectrum diagram is input into a deep learning model for identification and classification to obtain a pile-driving pulse signal from the candidate pulse signal;

[0069] The pile-driving pulse signal is post-processed, and an acoustic evaluation parameter of pile-driving underwater noise is calculated;

[0070] Based on the acoustic evaluation parameters of multiple monitoring sites and the corresponding monitoring position information, combined with a marine acoustic propagation model, the average sound source level of pile-driving operation is calculated by inversion.

[0071] Preferably, the multiple monitoring sites form an underwater acoustic sensor array, which has high sensitivity and a wide frequency band, and the cable length is adjustable (adjustment range is 1-50 meters); the underwater acoustic sensor array is composed of multiple underwater acoustic sensors arranged according to water depth layers (such as 5m, 15m, 30m); the layout point can be adjusted within a radius range of 100-5000m from the pile-driving point.

[0072] The present application realizes automatic real-time detection and extraction of pulse signals by receiving and preprocessing the original underwater sound pressure signals of multiple monitoring sites, combining short-time energy analysis and adaptive threshold determination, solves the data processing lag problem caused by the dependence of the prior art on offline manual analysis; the log-mel spectrum diagram is automatically identified and classified by a deep learning model, effectively distinguishing pile-driving pulse signals from complex marine environmental noise, overcoming the defects of low efficiency and poor accuracy of automatic identification algorithms in the prior art; the sound source level is obtained by fusion inversion of multi-point acoustic evaluation parameters and a marine acoustic propagation model, realizing full-process automatic processing from data acquisition, signal identification to sound source intensity evaluation, meeting the needs of modern marine engineering for rapid response and automatic monitoring, and significantly improving the real-time, accuracy and reliability of monitoring.

[0073] In the present embodiment, based on short-time energy analysis and adaptive threshold determination, the underwater sound pressure signals of each monitoring site are detected and extracted to obtain candidate pulse signals, including the following steps:

[0074] The short-time energy of the underwater sound pressure signal is calculated based on a preset window length and a preset overlap rate; the preferred range of the preset window length is 10-50ms, and the preset overlap rate is preferably 50%;

[0075] The adaptive threshold is calculated based on the average energy, the standard deviation of the background noise of each monitoring site, and a preset sensitivity factor. Preferably, the product of the standard deviation of the background noise and the sensitivity factor is calculated first, and the adaptive threshold is the sum of the product and the average energy of the background noise.

[0076] The short-time energy of each monitoring site is compared with the adaptive threshold to identify candidate impulse signals. The short-time energy of the candidate impulse signals is greater than the adaptive threshold.

[0077] The envelope of the candidate impulse signal is extracted.

[0078] The envelope is subjected to low-pass filtering and smoothing processing, and the start and end times of the candidate impulse signal are determined based on an envelope detection threshold.

[0079] Based on the start and end times, the complete waveform of the candidate impulse signal is obtained by extending the preset filling time forward and backward. Preferably, the filling time extended forward is preferably 50 ms, and the filling time extended backward is preferably 200 ms to ensure the capture of the envelope and the afterglow. Further, the time start and end points, the peak time, and the duration of each candidate impulse signal are also recorded.

[0080] It should be noted that the calculation of the adaptive threshold depends on the statistical characteristics of the background noise of each monitoring site. In a preferred embodiment, the system automatically learns the background noise for not less than 30 seconds before formally starting monitoring, during which signals without piling work are collected, and the average and standard deviation of the (short-time) energy are calculated. The sensitivity factor is preferably 3-6. To further adapt to the changes in environmental noise during long-term monitoring, the system supports dynamic updating of the background noise statistics.

[0081] Preferably, the envelope of the candidate impulse signal is extracted by the following steps:

[0082] Taking the absolute value: the part of the candidate impulse signal below the horizontal axis is "folded" above the horizontal axis to obtain a V-shaped signal that is always positive, which is equivalent to obtaining the "amplitude" of the signal first.

[0083] Low-pass filtering: the candidate impulse signal after taking the absolute value is subjected to low-pass filtering to filter out high-frequency, rapid fluctuations and burrs, and retain the overall, slowly changing trend to obtain the envelope.

[0084] The present application calculates short-time energy by presetting window length and overlap rate, and dynamically generates an adaptive threshold based on background noise statistical characteristics, so that the pulse detection can automatically adjust the sensitivity according to the actual environmental noise level, and avoids the problems of missed detection or false detection caused by the fixed threshold; through low-pass filtering, smoothing processing and front and rear extension filling of the envelope line, the noise interference is effectively suppressed, the complete waveform boundary of the candidate pulse signal is accurately extracted, and the accuracy and robustness of the candidate pulse signal extraction are improved.

[0085] In the embodiment, the frequency domain feature parameters include in-band energy distribution, peak frequency and bandwidth parameters.

[0086] The candidate pulse signal is subjected to spectrum analysis to obtain a time-frequency distribution diagram, a log-mel spectrum diagram and frequency domain feature parameters, including the following steps:

[0087] Based on the complete waveform of the candidate pulse signal, fast Fourier transform or short-time Fourier transform is performed to obtain a time-frequency distribution diagram.

[0088] The time-frequency distribution diagram is converted into a log-mel spectrum diagram, and based on the time-frequency distribution diagram, the in-band energy (low frequency / middle frequency / high frequency band) distribution, peak frequency and bandwidth (-3dB) parameters of each candidate pulse signal are calculated.

[0089] The present application converts the candidate pulse signal into a time-frequency distribution diagram by fast Fourier transform or short-time Fourier transform, and further generates a log-mel spectrum diagram, realizes the visualization and logarithmic perception scale representation of signal spectrum features; at the same time, the in-band energy distribution, peak frequency and bandwidth parameters are calculated, which provides input data for the deep learning model, and improves the feature learning efficiency and recognition accuracy of the classification model.

[0090] In the embodiment, the log-mel spectrum diagram is input into a deep learning model for recognition and classification to obtain a pile driving pulse signal from the candidate pulse signal, including the following steps:

[0091] The log-mel spectrum diagram is input into a two-dimensional convolutional neural network model to perform feature learning and classification on the log-mel spectrum diagram.

[0092] Based on the feature learning result, the class label and confidence corresponding to each candidate pulse signal are output to obtain a pile driving pulse signal from the candidate pulse signal; the class label at least includes pile driving sound and ship machine noise.

[0093] The application realizes high-precision automatic distinguishing of complex interference sources such as piling sound and ship machine noise by inputting a log-mel spectrogram into a two-dimensional convolutional neural network model for end-to-end feature learning and classification, using the powerful nonlinear feature extraction capability of deep learning; and provides a quantitative basis for the screening of piling pulse signals by outputting a category label and a confidence level, greatly reducing the workload and misjudgment risk of manual discrimination.

[0094] In the embodiment, after obtaining the candidate pulse signal, the method further includes:

[0095] The time-domain feature extraction is performed on the candidate pulse signal to obtain time-domain feature parameters; the time-domain feature parameters include a peak sound pressure, a peak-to-peak sound pressure, a pulse duration (T90 / T50 / T10), a rise time, a fall time, a pulse interval and a pulse rate;

[0096] Further, in the embodiment, the method further includes: displaying the time-domain feature extraction result and / or the spectrum analysis result in a chart form.

[0097] In the embodiment, the method further includes:

[0098] Based on the piling pulse signal, an average sound pressure level in a cycle is calculated;

[0099] The average sound pressure level in the cycle is compared with a preset frequency band threshold value, and when the average sound pressure level in the cycle is greater than the frequency band threshold value, a first alarm signal is generated and output.

[0100] The application can generate the first alarm signal immediately when the noise intensity exceeds the standard by calculating the average sound pressure level in a cycle and comparing it with the frequency band threshold value, thereby realizing the rapid early warning function of persistent strong noise and providing timely decision support for the biological protection measures of the site construction.

[0101] In the embodiment, the method further includes:

[0102] Based on the piling pulse signal, a sound exposure level of a single event is calculated; the single event is a single piling impact;

[0103] The sound exposure level of the single event is compared with a preset sound exposure level threshold value, and when the sound exposure level of the single event is greater than the sound exposure level threshold value, a second alarm signal is generated and output.

[0104] The application realizes the accurate monitoring and hierarchical early warning of high-intensity transient noise events by calculating the sound exposure level of the single piling impact event and comparing it with the sound exposure level threshold value, and generating the second alarm signal when the single pulse energy exceeds the standard.

[0105] Preferably, the first alarm signal and the second alarm signal are sent to the administrator through short message, email or APP push.

[0106] Further, in the embodiment, the method further comprises: recording the alarm event based on the first alarm signal and / or the second alarm signal.

[0107] In the embodiment, the pile driving pulse signals are post-processed, and the acoustic evaluation parameters of the pile driving underwater noise are calculated, including the following steps:

[0108] The pile driving pulse signals are time-smoothed;

[0109] Based on the propagation distance of each pile driving pulse signal and the ocean acoustic propagation model, the pile driving pulse signals are corrected for propagation loss;

[0110] Based on the sound pressure level corrected for propagation loss, the acoustic evaluation parameters of the pile driving underwater noise are calculated, including the root mean square sound pressure level, the instantaneous peak sound pressure level, the single sound exposure level and the cumulative sound exposure level.

[0111] Preferably, the root mean square sound pressure level is calculated according to the following formula:

[0112] ; wherein, is the root mean square sound pressure, is the reference sound pressure, and = 1 μPa.

[0113] The instantaneous peak sound pressure level is calculated according to the following formula:

[0114] ; wherein, is the peak sound pressure.

[0115] The single sound exposure level is calculated according to the following formula:

[0116] ; wherein, T is the time of the pile driving pulse signal, in seconds (s), is the original underwater sound pressure signal, is the reference integration time (usually 1 s).

[0117] The cumulative sound exposure level is calculated according to the following formula:

[0118] ; wherein, i is the i-th pile driving pulse signal, and N is the total number of pile driving pulse signals.

[0119] This invention eliminates the influence of distance and propagation path on sound pressure measurement by performing time smoothing processing on pile driving pulse signals and propagation loss correction based on an ocean underwater acoustic propagation model, making data from different monitoring stations comparable. By calculating standardized acoustic evaluation parameters such as root mean square sound pressure level, instantaneous peak sound pressure level, single sound exposure level, and cumulative sound exposure level, it provides standardized and regulated quantitative indicators for the objective evaluation of pile driving noise and environmental protection.

[0120] In this embodiment, based on the acoustic evaluation parameters of multiple monitoring stations and their corresponding monitoring location information, combined with the ocean underwater acoustic propagation model, the average sound source level of the pile driving operation is calculated by inversion, including the following steps:

[0121] The individual sound exposure levels and corresponding monitoring location information of multiple monitoring stations are obtained, and the straight-line distance between each monitoring location and the pile driving sound source is calculated.

[0122] Based on the spherical or cylindrical expansion ocean acoustic propagation model, the propagation loss corresponding to each monitoring station is calculated; the specific formula for calculating the propagation loss TL is as follows: Where k is the extended loss factor and r is the straight-line distance between the monitoring location and the pile driving sound source, in meters (m). The absorption attenuation coefficient (unit: dB / m);

[0123] By adding the individual sound exposure level of each monitoring station to the corresponding propagation loss, the sound source level SL at a distance of 1m from the pile driving operation at each monitoring station can be calculated; that is:

[0124] SL ;in, The single sound exposure level (in dB) is measured at a monitoring location r away from the sound source of the pile driving operation. This formula can be used to inversely estimate the original intensity of the sound source given the sound pressure level at the monitoring site, or to predict the range of noise impact at different distances.

[0125] The arithmetic mean of the sound source level SL at a distance of 1m from the pile driving operation was calculated based on all monitoring stations, and this arithmetic mean was taken as the average sound source level of the pile driving operation. .

[0126] Specifically, if at a distance M received sound pressure levels were measured. And estimate the propagation loss TL(j) corresponding to the j-th monitoring station. The average sound source level of the pile driving operation is then... It can be obtained through the following formula:

[0127] ; wherein, M is the total number of monitoring stations participating in the inversion calculation; j is the jth monitoring station, is the received sound pressure level, i.e., the sound pressure level actually measured at the jth monitoring station; is the straight-line distance between the jth monitoring station and the piling sound source; is the propagation loss of the sound wave from the sound source to the jth monitoring station.

[0128] The present application effectively reduces the single-point measurement error and environmental uncertainty by fusing multi-point monitoring data, and significantly improves the accuracy and robustness of the sound source level estimation.

[0129] Further, the method further comprises: in response to a user query instruction, deriving user query data from the historical monitoring data. Preferably, the user query instruction includes time, location, and other query conditions.

[0130] The method further comprises: generating a compliance determination report according to the average sound source level of the piling operation, directly monitoring the environmental protection limit standard and generating a compliance determination report, and improving the supervision efficiency.

[0131] As shown in Figure 2 The present application also provides an intelligent piling underwater noise monitoring system, which comprises:

[0132] The signal acquisition module 10 is used for acquiring the original underwater sound pressure signals of the plurality of monitoring stations; preferably, the signal acquisition module 10 is an underwater acoustic sensor array, which has high sensitivity and wide frequency band, and the cable length is adjustable (adjustment range is 1-50 meters); the underwater acoustic sensor array is composed of a plurality of underwater acoustic sensors arranged according to water depth layers (such as 5m, 15m, 30m); the layout point can be adjusted within a radius range of 100-5000m from the piling point;

[0133] The preprocessing module 20 is used for receiving and preprocessing the original underwater sound pressure signals of the plurality of monitoring stations to obtain a plurality of underwater sound pressure signals; preferably, the preprocessing module 20 includes an analog-to-digital converter (ADC) and a microcontroller (MCU), which are used for converting the analog signals collected by the hydrophone into digital signals, and performing band-pass filtering and gain adjustment processing;

[0134] The signal extraction module 30 is used for detecting and extracting the underwater sound pressure signals of each monitoring station based on short-time energy analysis and adaptive threshold determination to obtain candidate pulse signals;

[0135] The spectrum analysis module 40 is used for performing spectrum analysis on the candidate pulse signals to obtain time-frequency distribution diagrams, log-mel spectrograms, and frequency domain feature parameters;

[0136] The classification module 50 is configured to input the log-mel spectrogram into a deep learning model for identification and classification, so as to obtain the pile-driving pulse signal from the candidate pulse signals.

[0137] The acoustic evaluation parameter calculation module 60 is configured to post-process the pile-driving pulse signal and calculate the acoustic evaluation parameter of the pile-driving underwater noise.

[0138] The sound source level inversion module 70 is configured to calculate the average sound source level of the pile-driving operation based on the acoustic evaluation parameters of the plurality of monitoring sites and the corresponding monitoring position information, and in combination with an ocean acoustic propagation model.

[0139] Preferably, the system further comprises:

[0140] The time-domain feature extraction module is configured to perform time-domain feature extraction on the candidate pulse signal to obtain time-domain feature parameters.

[0141] The alarm module is configured to calculate the average sound pressure level in a period based on the pile-driving pulse signal, compare the average sound pressure level in the period with a preset frequency band threshold, and generate and output a first alarm signal when the average sound pressure level in the period is greater than the frequency band threshold; and / or, calculate the sound exposure level of a single event based on the pile-driving pulse signal, wherein the single event is a single pile-driving impact; compare the sound exposure level of the single event with a preset sound exposure level threshold, and generate and output a second alarm signal when the sound exposure level of the single event is greater than the sound exposure level threshold.

[0142] The visualization module is configured to display the time-domain feature extraction result and / or the spectrum analysis result in a chart form; further, the visualization module also supports GIS map superposition to display the noise propagation range.

[0143] The data query module is configured to export user query data from the historical monitoring data in response to a user query instruction; preferably, the user query instruction includes time, location, and other query conditions.

[0144] The alarm event recording module is configured to record an alarm event based on the first alarm signal and / or the second alarm signal.

[0145] The wireless communication module is configured to transmit the pre-processed underwater sound pressure signal to the signal extraction module 30 in real time, for example, a 4G / 5G module, a LoRa module.

[0146] The energy management unit includes a rechargeable battery module and an interface module reserving a solar panel interface (which needs to be installed according to the actual buoy), to ensure the continuous power supply of the system under long-time operation.

[0147] In the embodiment, the system can be arranged in a buoy / submarine main body, which has good water tightness and stability.

[0148] When the system can be arranged on the buoy body, the system further comprises:

[0149] a Beidou position module, configured to locate a position of the buoy to obtain a drift track of the buoy;

[0150] Further, the visualization module is further configured to visually display the drift track of the buoy.

[0151] It should be noted that each of the embodiments in the specification adopts a progressive manner for description, and each embodiment focuses on the difference from other embodiments, and the same and similar parts of each embodiment can be referred to each other. For the system embodiment, since it is basically similar to the method embodiment, it is described more simply, and the relevant part can be referred to the part of the method embodiment.

[0152] Also, in this document, the terms "comprise", "comprising", or any other variant thereof are intended to cover non-exclusive inclusions, so that processes, methods, articles, or devices that include a series of elements not only include those elements, but also include other elements not explicitly listed, or include elements inherent to such processes, methods, articles, or devices. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of other identical elements in the process, method, article, or device that includes the element.

[0153] The above description shows and describes the preferred embodiments of the present application, it should be understood that the present application is not limited to the forms disclosed herein, should not be regarded as excluding other embodiments, and can be used in various other combinations, modifications and environments, and can be modified by the above teaching or related art or knowledge within the scope of the present application. The modifications and changes made by those skilled in the art without departing from the spirit and scope of the present application shall be within the protection scope of the appended claims of the present application.

Claims

1. An intelligent underwater noise monitoring method for pile driving, characterized in that, Includes the following steps: The system receives raw underwater acoustic pressure signals from multiple monitoring stations and preprocesses them to obtain multiple underwater acoustic pressure signals. Based on short-time energy analysis and adaptive threshold determination, the underwater sound pressure signals of each monitoring station are detected and extracted to obtain candidate pulse signals; The candidate pulse signal is subjected to spectral analysis to obtain the time-frequency distribution diagram, log-mel energy spectrum diagram and frequency domain characteristic parameters; The log-mel energy spectrum is input into a deep learning model for identification and classification in order to obtain the pile driving pulse signal from the candidate pulse signals; The pile driving pulse signal is post-processed, and the acoustic evaluation parameters of underwater pile driving noise are calculated. Based on the acoustic evaluation parameters of multiple monitoring stations and their corresponding monitoring location information, the average sound source level of the pile driving operation is obtained by inversion calculation using the marine underwater acoustic propagation model. The post-processing of the pile driving pulse signal and the calculation of acoustic evaluation parameters for underwater pile driving noise include the following steps: The pile driving pulse signal is subjected to time smoothing processing; Based on the propagation distance of each of the pile driving pulse signals and the ocean acoustic propagation model, the propagation loss of the pile driving pulse signals is corrected. Based on the sound pressure level corrected for propagation loss, acoustic evaluation parameters for underwater pile driving noise are calculated. These acoustic evaluation parameters include root mean square sound pressure level, instantaneous peak sound pressure level, single sound exposure level, and cumulative sound exposure level. Root mean square sound pressure level The calculation formula is as follows: ;in, The root mean square sound pressure level is... For reference sound pressure, and =1μPa; Instantaneous peak sound pressure level The calculation formula is as follows: ;in, Peak sound pressure level; Single sound exposure level The calculation formula is as follows: Where T is the duration of the piling pulse signal. This is the original underwater sound pressure signal. The baseline integration time; Cumulative sound exposure level The calculation formula is as follows: Where i is the i-th piling pulse signal, and N is the total number of piling pulse signals; Based on the acoustic evaluation parameters of multiple monitoring stations and their corresponding monitoring location information, combined with the ocean underwater acoustic propagation model, the average sound source level of the pile driving operation is calculated by inversion, including the following steps: The individual sound exposure levels and corresponding monitoring location information of multiple monitoring stations are obtained, and the straight-line distance between each monitoring location and the pile driving sound source is calculated. Based on the spherical or cylindrical expansion ocean acoustic propagation model, the propagation loss corresponding to each monitoring station is calculated; the specific formula for calculating the propagation loss TL is as follows: Where k is the extended loss factor, and r is the straight-line distance between the monitoring location and the pile driving sound source. The absorption attenuation coefficient; By adding the individual sound exposure level of each monitoring station to the corresponding propagation loss, the sound source level SL at a distance of 1m from the pile driving operation at each monitoring station can be calculated; that is: SL ;in, The single sound exposure level measured at a monitoring location r away from the sound source of the pile driving operation; The arithmetic mean of the sound source level SL at a distance of 1m from the pile driving operation was calculated based on all monitoring stations, and this arithmetic mean was taken as the average sound source level of the pile driving operation. .

2. The intelligent underwater noise monitoring method for pile driving according to claim 1, characterized in that, Based on short-time energy analysis and adaptive threshold determination, the underwater acoustic pressure signals of each monitoring station are detected and extracted to obtain candidate pulse signals, including the following steps: The short-time energy of the underwater acoustic pressure signal is calculated based on a preset window length and a preset overlap rate. Based on the mean energy and standard deviation of the background noise at each monitoring station, as well as the preset sensitivity factor, the corresponding adaptive threshold is calculated. The short-time energy of each monitoring station is compared with an adaptive threshold to identify candidate pulse signals; the short-time energy of the candidate pulse signal is greater than the adaptive threshold. Extract the envelope of the candidate pulse signal; The envelope is subjected to low-pass filtering and smoothing, and the start and end times of the candidate pulse signal are determined based on the envelope detection threshold. Based on the start and end times, the complete waveform of the candidate pulse signal is obtained by extending the preset fill time before and after.

3. The intelligent underwater noise monitoring method for pile driving according to claim 2, characterized in that, The frequency domain characteristic parameters include in-band energy distribution, peak frequency, and bandwidth parameters; The candidate pulse signal is subjected to spectral analysis to obtain the time-frequency distribution map, log-mel energy spectrum map and frequency domain characteristic parameters, including the following steps: Based on the complete waveform of the candidate pulse signal, perform a fast Fourier transform or a short-time Fourier transform to obtain a time-frequency distribution map; The time-frequency distribution map is converted into a log-mel energy spectrum map, and based on the time-frequency distribution map, the in-band energy distribution, peak frequency and bandwidth parameters of each candidate pulse signal are calculated.

4. The intelligent underwater noise monitoring method for pile driving according to claim 1, characterized in that, After obtaining the candidate pulse signal, the process also includes: The candidate pulse signal is subjected to time-domain feature extraction to obtain time-domain feature parameters; the time-domain feature parameters include peak sound pressure, peak-to-peak sound pressure, pulse duration, rise time, fall time, pulse interval, and pulse rate.

5. The intelligent underwater noise monitoring method for pile driving according to claim 1, characterized in that, The log-mel energy spectrum is input into a deep learning model for identification and classification to obtain the piling pulse signal from the candidate pulse signals, including the following steps: The log-mel energy spectrum is input into a two-dimensional convolutional neural network model to perform feature learning and classification on the log-mel energy spectrum. Based on the feature learning results, a category label and confidence level corresponding to each candidate pulse signal are output to obtain the pile driving pulse signal from the candidate pulse signals; the category label includes at least pile driving sound and ship engine noise.

6. The intelligent underwater noise monitoring method for pile driving according to claim 5, characterized in that, Also includes: Based on the pile driving pulse signal, calculate the average sound pressure level within one cycle; The average sound pressure level within one cycle is compared with a preset frequency band threshold. When the average sound pressure level within one cycle is greater than the frequency band threshold, a first alarm signal is generated and output.

7. The intelligent underwater noise monitoring method for pile driving according to claim 5, characterized in that, Also includes: Based on the pile driving pulse signal, calculate the acoustic exposure level of a single event; The single event refers to a single pile driving impact. The sound exposure level of the single event is compared with a preset sound exposure level threshold. When the sound exposure level of the single event is greater than the sound exposure level threshold, a second alarm signal is generated and output.

8. An intelligent underwater noise monitoring system for pile driving, characterized in that, include: The signal acquisition module is used to acquire raw underwater acoustic pressure signals from multiple monitoring stations; The preprocessing module is used to receive raw underwater acoustic pressure signals from multiple monitoring stations and preprocess them to obtain multiple underwater acoustic pressure signals; The signal extraction module is used to detect and extract the underwater sound pressure signals of each monitoring station based on short-time energy analysis and adaptive threshold determination to obtain candidate pulse signals. The spectrum analysis module is used to perform spectrum analysis on the candidate pulse signal to obtain the time-frequency distribution map, log-mel energy spectrum map and frequency domain characteristic parameters; The classification module is used to input the log-mel energy spectrum into the deep learning model for identification and classification, so as to obtain the pile driving pulse signal from the candidate pulse signal; The acoustic evaluation parameter calculation module is used to post-process the pile driving pulse signal and calculate the acoustic evaluation parameters of the underwater pile driving noise, including the following steps: The pile driving pulse signal is subjected to time smoothing processing; Based on the propagation distance of each of the pile driving pulse signals and the ocean acoustic propagation model, the propagation loss of the pile driving pulse signals is corrected. Based on the sound pressure level corrected for propagation loss, acoustic evaluation parameters for underwater pile driving noise are calculated. These acoustic evaluation parameters include root mean square sound pressure level, instantaneous peak sound pressure level, single sound exposure level, and cumulative sound exposure level. Root mean square sound pressure level The calculation formula is as follows: ;in, The root mean square sound pressure level is... For reference sound pressure, and =1μPa; Instantaneous peak sound pressure level The calculation formula is as follows: ;in, Peak sound pressure level; Single sound exposure level The calculation formula is as follows: Where T is the duration of the piling pulse signal. This is the original underwater sound pressure signal. The baseline integration time; Cumulative sound exposure level The calculation formula is as follows: Where i is the i-th piling pulse signal, and N is the total number of piling pulse signals; The sound source level inversion module is used to calculate the average sound source level of the piling operation based on the acoustic evaluation parameters of multiple monitoring stations and their corresponding monitoring location information, combined with the ocean underwater acoustic propagation model. The steps include: obtaining the individual sound exposure level and corresponding monitoring location information of multiple monitoring stations; calculating the straight-line distance between each monitoring location and the piling sound source; and calculating the propagation loss corresponding to each monitoring station based on a spherical or cylindrical underwater acoustic propagation model. The specific formula for calculating the propagation loss TL is as follows: Where k is the extended loss factor, and r is the straight-line distance between the monitoring location and the pile driving sound source. The absorption attenuation coefficient is used; the individual sound exposure level at each monitoring station is added to the corresponding propagation loss to calculate the sound source level SL at 1m away from the pile driving operation for each monitoring station; SL ;in, The individual sound exposure level is measured at a monitoring location r away from the sound source of the pile driving operation. The arithmetic mean of the sound source levels SL at a distance of 1 m from the pile driving operation, calculated from all monitoring stations, is used as the average sound source level for the pile driving operation. .

Images