A method and system for monitoring noise of a low altitude aircraft

Abstract

The application provides a low-altitude aircraft noise monitoring method and system. The method comprises the following steps: collecting low-altitude flight noise and environmental information, and obtaining total noise values after pretreatment; dynamically calculating the total noise limit value of the region, and judging the number of aircrafts if the total noise exceeds the limit; when there is a single aircraft, directly classifying and disposing; when there are multiple aircrafts, separating the aliasing signals, extracting the noise characteristics and measured values of each aircraft; obtaining flight parameters and matching the aircraft type with the voiceprint feature library; inputting the noise characteristics, environment, flight parameters and aircraft type into a pre-trained model to obtain the noise prediction limit value of each aircraft; comparing the measured value with the prediction limit value, and classifying and disposing if any aircraft exceeds the limit, otherwise outputting a cooperative alarm instruction; and binding the processing results, flight parameters, environment and aircraft type into a database for model updating. Through dynamic limit value, multi-target separation, aircraft type identification and prediction model, the application realizes accurate evaluation and efficient supervision of noise in multiple airport scenes.

Description

Technical Field

[0001] This invention relates to the field of low-altitude aircraft noise monitoring technology, and in particular to a method and system for monitoring low-altitude aircraft noise. Background Technology

[0002] With the booming development of the low-altitude economy, various low-altitude aircraft, such as drones and helicopters, are increasingly widely used in logistics, emergency rescue, aerial photography, and tourism, and their numbers are growing rapidly. However, the noise problem generated by low-altitude aircraft during operation is becoming increasingly prominent. This noise not only interferes with the lives, work, and studies of nearby residents, affecting their quality of life, but may also adversely affect the normal operation of sound-sensitive locations such as hospitals, schools, and research institutions. Furthermore, the noise characteristics of different types of low-altitude aircraft and their operating conditions vary, and are influenced by various factors such as the surrounding environment and weather conditions, making the monitoring and management of low-altitude aircraft noise a significant challenge. Therefore, conducting effective low-altitude aircraft noise monitoring is urgently needed.

[0003] Currently, in low-altitude aircraft noise monitoring, there is a lack of efficient and accurate multi-target separation technology when facing aliased noise signals generated by multiple low-altitude aircraft flying simultaneously. It is difficult to accurately extract the independent noise characteristic parameters of each aircraft, thus making it impossible to accurately assess and effectively monitor the noise situation of each aircraft, which greatly limits the scientific nature and effectiveness of low-altitude aircraft noise monitoring. Summary of the Invention

[0004] In view of this, the present invention proposes a method and system for monitoring noise of low-altitude aircraft, which can effectively deal with the aliased noise signals generated by multiple low-altitude aircraft flying at the same time, accurately extract the independent noise characteristic parameters of each aircraft, thereby realizing accurate assessment and effective supervision of the noise situation of each aircraft, and greatly improving the scientificity and effectiveness of low-altitude aircraft noise monitoring.

[0005] The technical solution of the present invention is implemented as follows: In a first aspect, the present invention provides a method for monitoring noise of low-altitude aircraft, comprising the following sub-steps: S1, collect low-altitude flight noise signals and surrounding environmental information of the monitoring area, preprocess the collected data, and obtain the total low-altitude flight noise value; S2. Calculate the total noise limit of the monitoring area dynamically based on the surrounding environmental information. If the total noise value of low-altitude flight exceeds the total noise limit of the monitoring area, determine the number of low-altitude aircraft in the monitoring area. If there are multiple low-altitude aircraft, perform multi-target separation on the low-altitude flight noise signal, extract the noise characteristic parameters and measured flight noise values ​​corresponding to each low-altitude aircraft. If there is only one low-altitude aircraft, determine the noise level according to the preset grading strategy and output the corresponding handling action. S3. Obtain the flight parameter information of each low-altitude aircraft, and perform similarity matching between the noise characteristic parameters corresponding to each low-altitude aircraft and the data in the pre-built aircraft model voiceprint feature library to obtain the aircraft model corresponding to each low-altitude aircraft. S4. Input the noise characteristic parameters, surrounding environment information, flight parameter information and aircraft model of each low-altitude aircraft into the pre-trained noise limit prediction model. The model outputs the noise prediction limit corresponding to each low-altitude aircraft. S5 compares the measured flight noise value of each low-altitude aircraft with the noise prediction limit. If the measured flight noise value of any low-altitude aircraft exceeds the corresponding noise prediction limit, the noise level of the corresponding aircraft is determined according to the preset classification strategy, and the corresponding handling action is output. If none of them exceed the corresponding noise prediction limit, a coordinated alarm command is output. S6 binds the current noise processing results with the aircraft's flight parameters, surrounding environment information, and aircraft model, and stores them in the historical flight monitoring database for updating the noise limit prediction model.

[0006] Based on the above technical solutions, preferably, step S1 includes the following sub-steps: S11, continuously collect low-altitude flight noise signals through a distributed acoustic sensor array, and simultaneously obtain surrounding environmental information of the monitoring area through temperature and humidity sensors, wind speed sensors and air pressure sensors. The surrounding environmental information includes ambient background noise, wind speed, wind direction, temperature, humidity and atmospheric pressure. S12 performs DC rejection, anti-aliasing filtering, wind noise suppression, A-weighting calibration and meteorological sound propagation compensation preprocessing on the low-altitude flight noise signal to obtain the standard flight noise signal. S13, calculate the A-weighted equivalent continuous sound level based on the standard flight noise signal, and use the A-weighted equivalent continuous sound level as the total noise value for low-altitude flight.

[0007] Based on the above technical solutions, preferably, step S2 includes the following sub-steps: S21. Determine the basic limit based on the area type and time period of the monitoring area, and calculate the meteorological propagation correction value and background noise correction value based on the surrounding environmental information. Add the meteorological propagation correction value and background noise correction value to the basic limit to obtain the dynamic total noise limit. S22, compare the total noise value of low-altitude flight with the dynamic total noise limit. If the total noise value of low-altitude flight does not exceed the dynamic total noise limit, the current determination ends; if it exceeds the limit, proceed to step S23. S23, perform frequency domain analysis on the preprocessed low-altitude flight noise signal, extract significant peaks in the spectrum, count the number of significant peaks, and determine the number of low-altitude aircraft in the current monitoring area based on the number of significant peaks; If the number of significant peaks is equal to 1, then the number of low-altitude aircraft is determined to be 1, and the total noise value of low-altitude flight is taken as the measured flight noise value. The noise level is determined according to the preset classification strategy and the corresponding handling action is output. If the number of significant peaks is greater than 1, it is determined that there are multiple low-altitude aircraft, and the process proceeds to step S24. If the number of significant peaks is 0, it is determined to be a no-flying event, and the current determination ends; S24 performs multi-target separation on the low-altitude flight noise signal, decomposes it into multiple independent signals, and extracts the noise characteristic parameters and measured flight noise values ​​of each independent signal.

[0008] Based on the above technical solution, preferably, step S24, which involves multi-target separation of the low-altitude flight noise signal into multiple independent signals, includes the following sub-steps: Microphone array beamforming technology is used to perform spatial filtering on sound sources arriving at different azimuth angles to obtain spatially decoupled direction signals of multiple sound sources. The blind source separation and independent component analysis techniques are used to decompose the signals from each sound source direction into multiple statistically independent acoustic signals, each of which corresponds to the noise emitted by an aircraft. Spectral analysis was performed on each of the decomposed independent acoustic signals to extract the blade passage frequency fundamental frequency component in the spectrum. Multiple distinct blade fundamental frequency components were identified using multi-peak detection and clustering algorithms to verify whether the number of separated independent acoustic signals was consistent with the number of significant peaks. If they match, the blade fundamental frequency component of each independent acoustic signal is associated with the corresponding spatial orientation, and a unique identifier is assigned to each independent acoustic signal to complete the separation of aliased noise signals; if they do not match, the process returns to the step of using microphone array beamforming technology to re-execute the separation.

[0009] Based on the above technical solutions, preferably, the noise characteristic parameters include: A-weighted equivalent continuous sound level, maximum sound level, noise duration, 1 / 3 octave band spectrum with a frequency range of 20Hz to 20kHz, blade passing frequency, background noise, signal-to-noise ratio, time-domain rise slope and fall slope; the corresponding background noise is subtracted from the A-weighted equivalent continuous sound level to obtain the measured flight noise value.

[0010] Based on the above technical solutions, preferably, step S3 includes the following sub-steps: S31, Obtain flight parameter information for each low-altitude aircraft, including the flight altitude, area type, time period, flight speed, and heading of the low-altitude aircraft; S32, construct a voiceprint feature library for low-altitude aircraft. The voiceprint feature library stores standard voiceprint templates for various aircraft models. The standard voiceprint template for each aircraft model includes the blade passing frequency fundamental frequency and harmonic frequency of the corresponding aircraft model under normal flight conditions, 1 / 3 octave band standard spectrum, time domain envelope and modulation features. S33, calculate the similarity between the blade passing frequency, 1 / 3 octave band spectrum and time domain envelope features corresponding to each signal and the corresponding features of the standard voiceprint templates of each model in the voiceprint feature library. S34. Select the model template with the highest similarity that exceeds the preset candidate threshold as the matching result and output the corresponding model number; if all similarities are lower than the preset threshold, output the unknown model identifier and store the noise feature parameters corresponding to the current acoustic signal as new template candidates in the pending review queue of the voiceprint feature library.

[0011] Based on the above technical solutions, preferably, the training process of the noise determination model in step S4 includes the following sub-steps: Flight event information is extracted from the historical flight status database. Each flight event information includes noise characteristic parameters, surrounding environment information, aircraft model, flight parameter information, measured flight noise value, and reasonable noise limit label. The noise feature parameters, flight parameter information, surrounding environment information and aircraft model in each flight event information are combined into an input feature vector, and the corresponding reasonable noise limit label is used as the output target to form a training sample set. An initial noise determination model is constructed based on a neural network structure. The training sample set is divided into a training set and a validation set. The input feature vector is used as the model input, and the mean square error between the noise prediction limit and the reasonable noise limit label is used as the loss function. The gradient descent algorithm is used to iteratively update the model parameters until the preset maximum number of iterations is reached and training stops. The performance of the trained model is evaluated on the validation set, and the mean absolute error is calculated. If the model performance meets the preset performance threshold, the current model parameters are saved as the final noise judgment model.

[0012] Based on the above technical solutions, preferably, the preset classification strategy determines the noise level of the corresponding aircraft and outputs corresponding handling actions, including: When the measured flight noise value is lower than the noise prediction limit, it is determined to be silent flight, the noise level is 0 and no alarm action is executed. When the measured flight noise value exceeds the noise prediction limit by a margin within the first threshold range, it is judged as a slight exceedance, the noise level is 1, and local recording is executed. When the measured flight noise value exceeds the noise prediction limit by a margin within the second threshold range, it is judged as a general exceedance, the noise level is 2, and an early warning is pushed to the monitoring platform. If the measured flight noise value exceeds the noise prediction limit by a margin within the third threshold range, it is judged as a serious exceedance, with a noise level of 3, and a strong alarm and evidence capture are triggered. If the measured flight noise value exceeds the noise prediction limit by more than the upper limit of the third threshold, or if the maximum sound level exceeds the fourth threshold, it is judged as extremely disturbing the peace, with a noise level of 4, and a mandatory alarm and enforcement work order are triggered.

[0013] Secondly, the present invention also provides a low-altitude aircraft noise monitoring system, implemented using a low-altitude aircraft noise monitoring method, comprising: The data acquisition module is used to collect low-altitude flight noise signals and surrounding environmental information of the monitoring area, preprocess the collected data, and obtain the total low-altitude flight noise value. The primary determination and separation module is used to dynamically calculate the total noise limit of the monitoring area based on the surrounding environmental information. If the total noise value of low-altitude flight exceeds the total noise limit of the monitoring area, the number of low-altitude aircraft in the monitoring area is determined. If there are multiple low-altitude flight noise signals, multi-target separation is performed on the low-altitude flight noise signal to extract the noise characteristic parameters and measured flight noise values ​​corresponding to each low-altitude aircraft. If the number is 1, the noise level is determined according to the preset classification strategy, and the corresponding handling action is output. The aircraft identification module is used to obtain the flight parameter information of each low-altitude aircraft, and to perform similarity matching between the noise characteristic parameters corresponding to each low-altitude aircraft and the data in the pre-built aircraft model voiceprint feature library to obtain the aircraft model corresponding to each low-altitude aircraft. The noise limit prediction module is used to input the noise characteristic parameters, surrounding environment information, flight parameter information and aircraft model of each low-altitude aircraft into the pre-trained noise limit prediction model. The model outputs the noise prediction limit corresponding to each low-altitude aircraft. The noise level determination module is used to compare the measured flight noise value of each low-altitude aircraft with the noise prediction limit. If the measured flight noise value of any low-altitude aircraft exceeds the corresponding noise prediction limit, the noise level of the corresponding aircraft is determined according to the preset classification strategy, and the corresponding handling action is output. If none of them exceed the corresponding noise prediction limit, a coordinated alarm command is output. The data binding and storage module is used to bind the current noise processing results with the aircraft's flight parameters, surrounding environment information, and aircraft model, and store them in the historical flight monitoring database for updating the noise limit prediction model.

[0014] Thirdly, the present invention also provides a computer-readable storage medium storing a program for a low-altitude aircraft noise monitoring method, wherein the program, when executed, implements the low-altitude aircraft noise monitoring method.

[0015] The low-altitude aircraft noise monitoring method of the present invention has the following advantages over the prior art: (1) By collecting low-altitude flight noise and environmental information and performing preprocessing to obtain the total noise value, the total noise limit of the monitoring area is dynamically calculated, and corresponding processing strategies are adopted according to the number of low-altitude aircraft; at the same time, flight parameters are acquired and matched with aircraft models, and the noise limit prediction model is used to output the noise prediction limit of each aircraft. After comparing it with the measured value, the noise level is determined and the handling action is output. This method can effectively deal with the aliased noise signal generated by multiple low-altitude aircraft flying at the same time, accurately extract the independent noise characteristic parameters of each aircraft, thereby realizing the accurate assessment and effective supervision of the noise situation of each aircraft, and significantly improving the accuracy and efficiency of noise monitoring and treatment; (2) By dynamically calculating the total noise limit of the monitoring area through the surrounding environmental information, the judgment criteria can be flexibly adjusted in combination with actual environmental changes, making the judgment more reasonable and accurate. At the same time, corresponding processing strategies are adopted for different numbers of low-altitude aircraft, avoiding the blindness of uniform processing, thereby effectively improving the efficiency of noise monitoring and processing. (3) By inputting multi-dimensional information into the noise limit prediction model, the model outputs the noise prediction limit corresponding to each aircraft, providing a scientific basis for judging whether the aircraft exceeds the standard and improving the accuracy of low-altitude aircraft noise monitoring. (4) By comparing the measured flight noise values ​​of each low-altitude aircraft with the noise prediction limits one by one, the aircraft that exceed the limits can be accurately located, and the noise level can be determined according to the preset classification strategy and the corresponding handling action can be output. In this way, effective control measures can be taken against the non-compliant aircraft in a timely manner to avoid the expansion of noise pollution. If all aircraft do not exceed the limits, a coordinated alarm command is output to ensure that multiple aircraft fly together within a reasonable noise range, effectively maintain the order of low-altitude flight, and improve the safety and comfort of the low-altitude flight environment. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1This is a flowchart of the low-altitude aircraft noise monitoring method of the present invention; Figure 2 This is a schematic diagram of the noise level identification and classification process of the low-altitude aircraft noise monitoring method of the present invention. Figure 3 This is a schematic diagram of the architecture of the low-altitude aircraft noise monitoring system of the present invention. Detailed Implementation

[0018] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0019] like Figure 1-2 As shown, in a first aspect, the present invention provides a method for monitoring noise in low-altitude aircraft, comprising the following sub-steps: S1 collects low-altitude flight noise signals and surrounding environmental information of the monitoring area, preprocesses the collected data, and obtains the total low-altitude flight noise value.

[0020] Step S1 includes the following sub-steps: S11, continuously collect low-altitude flight noise signals through a distributed acoustic sensor array, and simultaneously obtain surrounding environmental information of the monitoring area through temperature and humidity sensors, wind speed sensors and air pressure sensors. The surrounding environmental information includes ambient background noise, wind speed, wind direction, temperature, humidity and atmospheric pressure. Among them, low-altitude flight noise signals are continuously collected through a distributed acoustic sensor array, which is usually composed of multiple MEMS microphones arranged in a certain geometric shape to achieve spatial sound source localization and subsequent beamforming; at the same time, the surrounding environmental information of the monitoring area is acquired through temperature and humidity sensors, wind speed sensors, and air pressure sensors. The surrounding environmental information includes ambient background noise, wind speed, wind direction, temperature, humidity, and atmospheric pressure; the background noise can be measured in advance when no aircraft is flying.

[0021] S12 performs DC rejection, anti-aliasing filtering, wind noise suppression, A-weighting calibration and meteorological sound propagation compensation preprocessing on the low-altitude flight noise signal to obtain the standard flight noise signal. The raw low-altitude flight noise signal collected needs to undergo several preprocessing steps. First, DC rejection is performed to remove the DC bias introduced by the sensor or acquisition circuit. Then, anti-aliasing filtering is performed, using a low-pass filter to filter out frequency components higher than the Nyquist frequency. Next, digital high-pass filtering or adaptive algorithms are used to suppress wind noise and eliminate low-frequency turbulence noise. Then, A-weighted calibration is performed according to the IEC61672 standard to simulate the sensitivity of the human ear to different frequencies. Finally, based on the measured wind speed, wind direction, temperature, humidity, and atmospheric pressure, atmospheric absorption attenuation and sound ray bending correction are calculated according to standards such as ISO9613-1 to complete meteorological sound propagation compensation. The signal obtained after the above preprocessing is called the standard flight noise signal.

[0022] S13, calculate the A-weighted equivalent continuous sound level based on the standard flight noise signal, and use the A-weighted equivalent continuous sound level as the total noise value for low-altitude flight.

[0023] Based on the standard flight noise signal, the A-weighted equivalent continuous sound level is calculated using time-weighted methods. Specifically, within a specified measurement time interval T, the square of the instantaneous A-weighted sound pressure is integrated or averaged, and then the logarithm to base 10 is taken to obtain the equivalent continuous A-weighted sound level. This calculation result is directly used as the total low-altitude flight noise value, without deducting background noise. This total noise value reflects the actual acoustic environment of the monitoring area, including aircraft noise and background sound sources, and is used for subsequent comparison with the dynamic total noise limit.

[0024] The expression for the A-weighted equivalent continuous sound level is: ; In the formula, L eq,A,T To be in the time interval T The A-weighted equivalent continuous sound level within the range, T For time intervals, p A ( t () represents the instantaneous A-weighted sound pressure level. p 0 The reference sound pressure level is used.

[0025] S2. Calculate the total noise limit of the monitoring area dynamically based on the surrounding environmental information. If the total noise value of low-altitude flight exceeds the total noise limit of the monitoring area, determine the number of low-altitude aircraft in the monitoring area. If there are multiple low-altitude aircraft, perform multi-target separation on the low-altitude flight noise signal, extract the noise characteristic parameters and measured flight noise values ​​corresponding to each low-altitude aircraft. If there is only one low-altitude aircraft, determine the noise level according to the preset grading strategy and output the corresponding handling action.

[0026] Step S2 includes the following sub-steps: S21. Determine the basic limit based on the area type and time period of the monitoring area, and calculate the meteorological propagation correction value and background noise correction value based on the surrounding environmental information. Add the meteorological propagation correction value and background noise correction value to the basic limit to obtain the dynamic total noise limit. The basic limits are determined based on the area type and the current time period of the monitoring area. The area types include residential areas, cultural and educational sensitive areas, commercial areas and industrial areas. The time periods are divided into daytime 6:00-22:00 and nighttime 22:00-6:00, as shown in Table 1 below. Table 1 is the basic limit table;

[0027] The meteorological propagation correction value and the background noise correction value are calculated based on the surrounding environment information obtained in step S1. The meteorological propagation correction value includes atmospheric absorption attenuation, wind-induced sound ray bending, and temperature gradient correction. The calculation expression for atmospheric absorption attenuation correction is as follows: ; In the formula, α is the atmospheric absorption attenuation coefficient. d The horizontal distance from the sound source to the receiving point; The calculation expression for wind-induced sound ray bending correction is: ; In the formula, C w This is an empirical coefficient, typically taken as 0.02~0.05 dB·s / m·Hz. -0.5 , v Wind speed; θ The angle between the wind direction and the sound propagation direction; f c The center frequency; The calculation expression for temperature gradient correction is as follows: ; In the formula, C t This is an empirical coefficient, measured in dB·m / K, and is typically taken as 0.01~0.02. The vertical temperature gradient can be determined by monitoring multiple temperature sensors at the monitoring nodes or by assessing atmospheric stability. d This is the horizontal distance from the sound source to the receiving point.

[0028] The expression for the weather propagation correction value is: ; In this embodiment, to reduce computational complexity, a lookup table of meteorological propagation correction values ​​under different combinations of wind speed, temperature, and humidity can be pre-calculated and obtained through real-time interpolation.

[0029] The calculation expression for background noise correction is: ; In the formula, L bg The A-weighted equivalent continuous sound level of the ambient background noise was measured when no aircraft was in flight. L ref For reference background noise values, K bg This is a correction factor.

[0030] The expression for the dynamic total noise limit is: .

[0031] S22, compare the total noise value of low-altitude flight with the dynamic total noise limit. If the total noise value of low-altitude flight does not exceed the dynamic total noise limit, the current determination ends; if it exceeds the limit, proceed to step S23. S23, perform frequency domain analysis on the preprocessed low-altitude flight noise signal, extract significant peaks in the spectrum, count the number of significant peaks, and determine the number of low-altitude aircraft in the current monitoring area based on the number of significant peaks; Specifically, in this embodiment, a fast Fourier transform is performed on the preprocessed standard flight noise signal to obtain the frequency domain spectrum; candidate peak frequencies with amplitudes exceeding the background noise threshold are extracted from the spectrum, with the frequency range limited to 20Hz to 20kHz, covering the blade passage frequency range of common rotary-wing UAVs; the fundamental frequency and harmonic frequency range of blade passage frequencies of all aircraft types are extracted from the pre-built acoustic signature feature library of low-altitude aircraft models through the library; the candidate peak frequencies are matched with these frequency ranges; significant peaks that conform to the blade passage frequency distribution characteristics of at least one aircraft type are selected; and the number of significant peaks is counted.

[0032] If the number of significant peaks is equal to 1, then the number of low-altitude aircraft is determined to be 1, and the total noise value of low-altitude flight is taken as the measured flight noise value. The noise level is determined according to the preset classification strategy and the corresponding handling action is output. If the number of significant peaks is greater than 1, it is determined that there are multiple low-altitude aircraft, and the process proceeds to step S24. If the number of significant peaks is 0, it is determined to be a no-flying event, and the current determination ends; S24 performs multi-target separation on the low-altitude flight noise signal, decomposes it into multiple independent signals, and extracts the noise characteristic parameters and measured flight noise values ​​of each independent signal.

[0033] Step S24, which describes multi-target separation of the low-altitude flight noise signal into multiple independent signals, includes the following sub-steps: Microphone array beamforming technology is used to perform spatial filtering on sound sources arriving at different azimuth angles to obtain spatially decoupled direction signals of multiple sound sources. Specifically, using a delay summation or MVDR beamformer, weighting coefficients are calculated based on the microphone array geometry and the direction of sound source arrival to enhance the signal in the desired direction and suppress other directions.

[0034] Using the signals from each sound source direction as input, blind source separation and independent component analysis techniques are used to decompose the signals from each sound source direction into multiple statistically independent acoustic signals. Independent component analysis assumes that the source signals are statistically independent and at most only one of them is Gaussian distributed. The unmixing matrix is ​​obtained by maximizing the non-Gaussianity index. Each output corresponds to the noise emitted by an aircraft. Spectral analysis was performed on each of the decomposed independent acoustic signals to extract the blade passage frequency fundamental frequency component in the spectrum. Multiple distinct blade fundamental frequency components were identified using multi-peak detection and clustering algorithms to verify whether the number of separated independent acoustic signals was consistent with the number of significant peaks. If they match, the blade fundamental frequency component of each independent acoustic signal is associated with the corresponding spatial orientation, and a unique identifier is assigned to each independent acoustic signal to complete the separation of aliased noise signals; if they do not match, the process returns to the step of using microphone array beamforming technology to re-execute the separation; until they match or the preset number of retries is exceeded, if they still do not match, the separation is marked as failed and the aliased signal is treated as a whole.

[0035] The noise characteristic parameters include: A-weighted equivalent continuous sound level, maximum sound level, noise duration, 1 / 3 octave band spectrum with a frequency range of 20Hz to 20kHz, blade passing frequency, background noise, signal-to-noise ratio, and time-domain rise and fall slopes; the measured flight noise value is obtained by subtracting the corresponding background noise from the A-weighted equivalent continuous sound level.

[0036] In this embodiment, a dynamic total noise limit is first calculated and compared with the measured total noise. Subsequent multi-target separation and single-aircraft determination are only triggered when the total noise exceeds the limit, thereby significantly reducing unnecessary calculations and resource consumption. At the same time, the dynamic total noise limit integrates multi-dimensional information such as regional type, time period, meteorological propagation, and background noise, making regional noise alarms more consistent with actual environmental changes. After the total noise exceeds the limit, the number of aircraft is quickly determined by using spectrum peak statistics. A multi-target separation method combining beamforming, blind source separation, and blade frequency verification is adopted to ensure accurate decoupling of aliased signals and reliable extraction of independent signals. This provides a high-quality data foundation for subsequent accurate single-aircraft identification and law enforcement, improving the monitoring reliability and regulatory efficiency in multi-aircraft scenarios.

[0037] S3. Obtain the flight parameter information of each low-altitude aircraft, and perform similarity matching between the noise characteristic parameters corresponding to each low-altitude aircraft and the data in the pre-built aircraft model voiceprint feature library to obtain the aircraft model corresponding to each low-altitude aircraft. Step S3 includes the following sub-steps: S31, Obtain flight parameter information for each low-altitude aircraft, including the flight altitude, area type, time period, flight speed, and heading of the low-altitude aircraft; The flight parameter information of each low-altitude aircraft is obtained. The flight parameter information includes the flight altitude, area type, time period, flight speed and heading of the low-altitude aircraft. These parameters can be obtained through at least one of the following methods: ADS-B / BeiDou positioning data from the low-altitude monitoring platform, photoelectric tracking data from monitoring nodes or flight control reporting data.

[0038] S32, construct a voiceprint feature library for low-altitude aircraft. The voiceprint feature library stores standard voiceprint templates for various aircraft models. The standard voiceprint template for each aircraft model includes the blade passing frequency fundamental frequency and harmonic frequency of the corresponding aircraft model under normal flight conditions, 1 / 3 octave band standard spectrum, time domain envelope and modulation features. S33, calculate the similarity between the blade pass frequency, 1 / 3 octave band spectrum, and time domain envelope features corresponding to each signal and the corresponding features of the standard voiceprint templates for each aircraft model in the voiceprint feature database; the expression is: ; In the formula, Sim i The similarity score is calculated between the i-th model's standard voiceprint template in the voiceprint feature database. f BPF The extracted signals correspond to the blade passing frequencies. f i,BPF Let be the propeller passing frequency of the standard voiceprint template for the i-th model in the voiceprint feature library; cos(·,·) is the cosine similarity; S is the 1 / 3 octave band spectrum vector corresponding to each extracted signal. i is the 1 / 3 octave band spectrum vector of the standard voiceprint template of the i-th model in the voiceprint feature library; E is the time-domain envelope feature vector corresponding to each extracted signal. E i Let be the temporal envelope feature vector of the standard voiceprint template for the i-th model in the voiceprint feature library. w f , w s , w e For the corresponding weight coefficients, and w f + w s+ w e =1.

[0039] S34, select the model template with the highest similarity that exceeds the preset candidate threshold as the matching result, and output the corresponding model number; if all similarities are lower than the preset threshold, output the unknown model identifier, and store the noise feature parameters corresponding to the current acoustic signal as new template candidates in the pending review queue of the voiceprint feature library; after manual review, it is included in the feature library. In this way, the model voiceprint feature library can be continuously enriched during use, improving the coverage and accuracy of subsequent recognition.

[0040] In this embodiment, a multi-dimensional aircraft voiceprint feature library containing blade passage frequency, 1 / 3 octave band spectrum, and time domain envelope features is constructed. Combined with weighted similarity calculation and dual threshold judgment mechanism, accurate identification of specific models of low-altitude aircraft is achieved. At the same time, the introduction of unknown aircraft identification and pending review queue enables the voiceprint library to have online expansion capability, continuously adapt to new aircraft, and improve the intelligent monitoring level of complex low-altitude flight scenarios.

[0041] S4. Input the noise characteristic parameters, surrounding environment information, flight parameter information and aircraft model of each low-altitude aircraft into the pre-trained noise limit prediction model. The model outputs the noise prediction limit corresponding to each low-altitude aircraft.

[0042] The training process of the noise determination model in step S4 includes the following sub-steps: Flight event information is extracted from the historical flight status database. Each flight event information includes noise characteristic parameters, surrounding environment information, aircraft model, flight parameter information, measured flight noise value, and reasonable noise limit label. The reasonable noise limit labels are generated by experts based on the actual level of disturbance, regional standards, and historical complaint data. For each event, noise characteristic parameters, surrounding environmental information, flight parameters, and aircraft model are combined into an input feature vector, with the corresponding reasonable noise limit label serving as the output target. Missing values ​​in the input feature vector are filled in, continuous features are normalized or standardized, and categorical features are one-hot encoded to form a training sample set.

[0043] The noise feature parameters, flight parameter information, surrounding environment information and aircraft model in each flight event information are combined into an input feature vector, and the corresponding reasonable noise limit label is used as the output target to form a training sample set. An initial noise determination model is constructed based on a neural network structure. The training sample set is divided into a training set and a validation set. The input feature vector is used as the model input, and the mean square error between the noise prediction limit and the reasonable noise limit label is used as the loss function. The gradient descent algorithm is used to iteratively update the model parameters until the preset maximum number of iterations is reached and training stops. The neural network structure in this embodiment adopts a three-layer fully connected feedforward network. The number of nodes in the input layer is equal to the dimension of the input feature vector. The first hidden layer contains 128 neurons, uses the ReLU activation function, and adds a Dropout layer (dropout rate of 0.2) to prevent overfitting. The second hidden layer contains 64 neurons, uses the ReLU activation function, and the third hidden layer contains 32 neurons, uses the ReLU activation function. The output layer contains one linear neuron, which directly outputs the noise prediction limit.

[0044] The performance of the trained model is evaluated on the validation set, and the mean absolute error is calculated. If the model performance meets the preset performance threshold, the current model parameters are saved as the final noise judgment model.

[0045] By constructing a multi-dimensional feature input noise limit prediction model based on neural networks, personalized noise prediction limits can be dynamically output according to the noise characteristics, environmental information, flight parameters and aircraft model of each aircraft, thereby improving the accuracy of noise supervision for low-altitude aircraft.

[0046] S5. Compare the measured flight noise values ​​of each low-altitude aircraft with the noise prediction limits. If the measured flight noise value of any low-altitude aircraft exceeds the corresponding noise prediction limit, determine the noise level of the corresponding aircraft according to the preset classification strategy and output the corresponding handling action. If none of them exceed the corresponding noise prediction limits, output a collaborative alarm command. The collaborative alarm command includes at least one of the following prompts: suggesting adjusting the flight path, reducing the flight altitude, or reducing the number of aircraft at the same time. This is used to remind the air traffic control or flight scheduling system to optimize the flight plan and avoid regional disturbance caused by multiple aircraft overlapping.

[0047] The preset classification strategy determines the noise level of the corresponding aircraft and outputs the corresponding handling action, including: When the measured flight noise value is lower than the noise prediction limit, it is determined to be silent flight, the noise level is 0 and no alarm action is executed. When the measured flight noise value exceeds the noise prediction limit by a margin within the first threshold range, it is determined to be a slight exceedance, the noise level is 1, and local recording is performed; the first threshold range is preferably (0,3).

[0048] When the measured flight noise value exceeds the noise prediction limit by a margin within the second threshold range, it is determined to be a general exceedance, with a noise level of 2, and an early warning is pushed to the monitoring platform; the second threshold range is preferably (3, 6).

[0049] If the measured flight noise value exceeds the noise prediction limit by a margin within the third threshold range, it is determined to be a serious over-limit, with a noise level of 3, and a strong alarm and image capture are triggered for evidence preservation; the preferred range of the third threshold is (6, 10).

[0050] If the measured flight noise value exceeds the noise prediction limit by more than the upper limit of the third threshold, or when the maximum sound level S d If the noise level exceeds the fourth threshold, it is determined to be extremely disturbing to the public, with a noise level of 4, and a mandatory alarm and law enforcement work order are triggered; the fourth threshold is preferably 80dB.

[0051] This embodiment directly compares the measured noise value of each aircraft with the dynamically predicted limit and uses a multi-level gradient threshold to achieve refined graded handling from silent to extremely disturbing noise. It matches different enforcement methods such as local recording, platform warning, photo capture and evidence preservation, and law enforcement work orders to different levels of exceeding the limit, thereby improving the accuracy and efficiency of supervision. At the same time, in multi-aircraft scenarios, when all individual aircraft do not exceed the limit, a coordinated alarm command is output, filling the regulatory blind spot of legal but superimposed disturbances, and providing a basis for proactive scheduling and flight optimization. The threshold can be adaptively adjusted according to regional sensitivity and historical data, making noise level determination more flexible and scientific, and strongly supporting the control and data support of low-altitude aircraft noise.

[0052] S6 binds the current noise processing results with the aircraft's flight parameters, surrounding environment information, and aircraft model, and stores them in the historical flight monitoring database for updating the noise limit prediction model.

[0053] The stored historical data is used to update the noise limit prediction model. When the amount of new data added to the historical flight monitoring database reaches a preset threshold, the incremental training or retraining process of the model is automatically triggered: the system extracts the latest event records from the database, fine-tunes or fully retrains the current model, generates new model parameters and replaces the old model. Through this continuous iteration, the noise limit prediction model can continuously adapt to new aircraft types, new weather conditions and new flight scenarios, maintain prediction accuracy and adaptability, and improve the accuracy and efficiency of low-altitude aircraft noise monitoring.

[0054] like Figure 3 As shown, in a second aspect, the present invention also provides a low-altitude aircraft noise monitoring system, implemented using a low-altitude aircraft noise monitoring method, comprising: The data acquisition module is used to collect low-altitude flight noise signals and surrounding environmental information of the monitoring area, preprocess the collected data, and obtain the total low-altitude flight noise value. The primary determination and separation module is used to dynamically calculate the total noise limit of the monitoring area based on the surrounding environmental information. If the total noise value of low-altitude flight exceeds the total noise limit of the monitoring area, the number of low-altitude aircraft in the monitoring area is determined. If there are multiple low-altitude flight noise signals, multi-target separation is performed on the low-altitude flight noise signal to extract the noise characteristic parameters and measured flight noise values ​​corresponding to each low-altitude aircraft. If the number is 1, the noise level is determined according to the preset classification strategy, and the corresponding handling action is output. The aircraft identification module is used to obtain the flight parameter information of each low-altitude aircraft, and to perform similarity matching between the noise characteristic parameters corresponding to each low-altitude aircraft and the data in the pre-built aircraft model voiceprint feature library to obtain the aircraft model corresponding to each low-altitude aircraft. The noise limit prediction module is used to input the noise characteristic parameters, surrounding environment information, flight parameter information and aircraft model of each low-altitude aircraft into the pre-trained noise limit prediction model. The model outputs the noise prediction limit corresponding to each low-altitude aircraft. The noise level determination module is used to compare the measured flight noise value of each low-altitude aircraft with the noise prediction limit. If the measured flight noise value of any low-altitude aircraft exceeds the corresponding noise prediction limit, the noise level of the corresponding aircraft is determined according to the preset classification strategy, and the corresponding handling action is output. If none of them exceed the corresponding noise prediction limit, a coordinated alarm command is output. The data binding and storage module is used to bind the current noise processing results with the aircraft's flight parameters, surrounding environment information, and aircraft model, and store them in the historical flight monitoring database for updating the noise limit prediction model.

[0055] It should be noted that this system corresponds to the aforementioned method for monitoring noise in low-altitude aircraft. All implementation methods in the above method embodiments are applicable to the embodiments of this system and can achieve the same technical effect.

[0056] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0057] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the system and modules described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0058] In the embodiments provided by this invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0059] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0060] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0061] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0062] Furthermore, it should be noted that in the system and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent solutions of the present invention. Moreover, the steps performing the above series of processes can naturally be executed in the order described, but are not necessarily required to be executed in chronological order; some steps can be executed in parallel or independently of each other. Those skilled in the art will understand that all or any step or component of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or network of computing devices, in hardware, firmware, software, or a combination thereof. This is something that those skilled in the art can achieve by using their basic programming skills after reading the description of the present invention.

[0063] Therefore, the object of the present invention can also be achieved by running a program or a set of programs on any computing system. The computing system can be a known general-purpose system. Therefore, the object of the present invention can also be achieved simply by providing a program product containing program code implementing the method or apparatus. That is, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any known storage medium or any storage medium developed in the future. It should also be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent to the present invention. Furthermore, the steps performing the above series of processes can naturally be performed in the order described, but are not necessarily required to be performed in chronological order. Some steps can be performed in parallel or independently of each other.

[0064] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for monitoring noise in low-altitude aircraft, characterized in that, Includes the following sub-steps: S1, collect low-altitude flight noise signals and surrounding environmental information of the monitoring area, preprocess the collected data, and obtain the total low-altitude flight noise value; S2. Calculate the total noise limit of the monitoring area dynamically based on the surrounding environmental information. If the total noise value of low-altitude flight exceeds the total noise limit of the monitoring area, determine the number of low-altitude aircraft in the monitoring area. If there are multiple low-altitude aircraft, perform multi-target separation on the low-altitude flight noise signal, extract the noise characteristic parameters and measured flight noise values ​​corresponding to each low-altitude aircraft. If there is only one low-altitude aircraft, determine the noise level according to the preset grading strategy and output the corresponding handling action. S3. Obtain the flight parameter information of each low-altitude aircraft, and perform similarity matching between the noise characteristic parameters corresponding to each low-altitude aircraft and the data in the pre-built aircraft model voiceprint feature library to obtain the aircraft model corresponding to each low-altitude aircraft. S4. Input the noise characteristic parameters, surrounding environment information, flight parameter information and aircraft model of each low-altitude aircraft into the pre-trained noise limit prediction model. The model outputs the noise prediction limit corresponding to each low-altitude aircraft. S5 compares the measured flight noise value of each low-altitude aircraft with the noise prediction limit. If the measured flight noise value of any low-altitude aircraft exceeds the corresponding noise prediction limit, the noise level of the corresponding aircraft is determined according to the preset classification strategy, and the corresponding handling action is output. If none of them exceed the corresponding noise prediction limit, a coordinated alarm command is output. S6 binds the current noise processing results with the aircraft's flight parameters, surrounding environment information, and aircraft model, and stores them in the historical flight monitoring database for updating the noise limit prediction model.

2. The method for monitoring noise of low-altitude aircraft as described in claim 1, characterized in that, Step S1 includes the following sub-steps: S11, continuously collect low-altitude flight noise signals through a distributed acoustic sensor array, and simultaneously obtain surrounding environmental information of the monitoring area through temperature and humidity sensors, wind speed sensors and air pressure sensors. The surrounding environmental information includes ambient background noise, wind speed, wind direction, temperature, humidity and atmospheric pressure. S12 performs DC rejection, anti-aliasing filtering, wind noise suppression, A-weighting calibration and meteorological sound propagation compensation preprocessing on the low-altitude flight noise signal to obtain the standard flight noise signal. S13, calculate the A-weighted equivalent continuous sound level based on the standard flight noise signal, and use the A-weighted equivalent continuous sound level as the total noise value for low-altitude flight.

3. The method for monitoring noise of low-altitude aircraft as described in claim 2, characterized in that, Step S2 includes the following sub-steps: S21. Determine the basic limit based on the area type and time period of the monitoring area, and calculate the meteorological propagation correction value and background noise correction value based on the surrounding environmental information. Add the meteorological propagation correction value and background noise correction value to the basic limit to obtain the dynamic total noise limit. S22, compare the total noise value of low-altitude flight with the dynamic total noise limit. If the total noise value of low-altitude flight does not exceed the dynamic total noise limit, the judgment ends. If it exceeds the limit, proceed to step S23; S23, perform frequency domain analysis on the preprocessed low-altitude flight noise signal, extract significant peaks in the spectrum, count the number of significant peaks, and determine the number of low-altitude aircraft in the current monitoring area based on the number of significant peaks; If the number of significant peaks is equal to 1, then the number of low-altitude aircraft is determined to be 1, and the total noise value of low-altitude flight is taken as the measured flight noise value. The noise level is determined according to the preset classification strategy and the corresponding handling action is output. If the number of significant peaks is greater than 1, it is determined that there are multiple low-altitude aircraft, and the process proceeds to step S24. If the number of significant peaks is 0, it is determined to be a no-flying event, and the current determination ends; S24 performs multi-target separation on the low-altitude flight noise signal, decomposes it into multiple independent signals, and extracts the noise characteristic parameters and measured flight noise values ​​of each independent signal.

4. The method for monitoring noise of low-altitude aircraft as described in claim 3, characterized in that, Step S24, which describes multi-target separation of the low-altitude flight noise signal into multiple independent signals, includes the following sub-steps: Microphone array beamforming technology is used to perform spatial filtering on sound sources arriving at different azimuth angles to obtain spatially decoupled direction signals of multiple sound sources. The blind source separation and independent component analysis techniques are used to decompose the signals from each sound source direction into multiple statistically independent acoustic signals, each of which corresponds to the noise emitted by an aircraft. Spectral analysis was performed on each of the decomposed independent acoustic signals to extract the blade passage frequency fundamental frequency component in the spectrum. Multiple distinct blade fundamental frequency components were identified using multi-peak detection and clustering algorithms to verify whether the number of separated independent acoustic signals was consistent with the number of significant peaks. If they match, the blade fundamental frequency component of each independent acoustic signal is associated with the corresponding spatial orientation, and a unique identifier is assigned to each independent acoustic signal to complete the separation of aliased noise signals; if they do not match, the process returns to the step of using microphone array beamforming technology to re-execute the separation.

5. The method for monitoring noise of low-altitude aircraft as described in claim 4, characterized in that, The noise characteristic parameters include: A-weighted equivalent continuous sound level, maximum sound level, noise duration, 1 / 3 octave band spectrum with a frequency range of 20Hz to 20kHz, blade passing frequency, background noise, signal-to-noise ratio, and time-domain rise and fall slopes; the measured flight noise value is obtained by subtracting the corresponding background noise from the A-weighted equivalent continuous sound level.

6. The method for monitoring noise of low-altitude aircraft as described in claim 5, characterized in that, Step S3 includes the following sub-steps: S31, Obtain flight parameter information for each low-altitude aircraft, including the flight altitude, area type, time period, flight speed, and heading of the low-altitude aircraft; S32, construct a voiceprint feature library for low-altitude aircraft. The voiceprint feature library stores standard voiceprint templates for various aircraft models. The standard voiceprint template for each aircraft model includes the blade passing frequency fundamental frequency and harmonic frequency of the corresponding aircraft model under normal flight conditions, 1 / 3 octave band standard spectrum, time domain envelope and modulation features. S33, calculate the similarity between the blade passing frequency, 1 / 3 octave band spectrum and time domain envelope features corresponding to each signal and the corresponding features of the standard voiceprint templates of each model in the voiceprint feature library. S34. Select the model template with the highest similarity that exceeds the preset candidate threshold as the matching result and output the corresponding model number; if all similarities are lower than the preset threshold, output the unknown model identifier and store the noise feature parameters corresponding to the current acoustic signal as new template candidates in the pending review queue of the voiceprint feature library.

7. The method for monitoring noise of low-altitude aircraft as described in claim 6, characterized in that, The training process of the noise determination model in step S4 includes the following sub-steps: Flight event information is extracted from the historical flight status database. Each flight event information includes noise characteristic parameters, surrounding environment information, aircraft model, flight parameter information, measured flight noise value, and reasonable noise limit label. The noise feature parameters, flight parameter information, surrounding environment information and aircraft model in each flight event information are combined into an input feature vector, and the corresponding reasonable noise limit label is used as the output target to form a training sample set. An initial noise determination model is constructed based on a neural network structure. The training sample set is divided into a training set and a validation set. The input feature vector is used as the model input, and the mean square error between the noise prediction limit and the reasonable noise limit label is used as the loss function. The gradient descent algorithm is used to iteratively update the model parameters until the preset maximum number of iterations is reached and training stops. The performance of the trained model is evaluated on the validation set, and the mean absolute error is calculated. If the model performance meets the preset performance threshold, the current model parameters are saved as the final noise judgment model.

8. The method for monitoring noise of low-altitude aircraft as described in claim 7, characterized in that, The preset classification strategy determines the noise level of the corresponding aircraft and outputs the corresponding handling action, including: When the measured flight noise value is lower than the noise prediction limit, it is determined to be silent flight, the noise level is 0 and no alarm action is executed. When the measured flight noise value exceeds the noise prediction limit by a margin within the first threshold range, it is judged as a slight exceedance, the noise level is 1, and local recording is executed. When the measured flight noise value exceeds the noise prediction limit by a margin within the second threshold range, it is judged as a general exceedance, the noise level is 2, and an early warning is pushed to the monitoring platform. If the measured flight noise value exceeds the noise prediction limit by a margin within the third threshold range, it is judged as a serious exceedance, with a noise level of 3, and a strong alarm and evidence capture are triggered. If the measured flight noise value exceeds the noise prediction limit by more than the upper limit of the third threshold, or if the maximum sound level exceeds the fourth threshold, it is judged as extremely disturbing the peace, with a noise level of 4, and a mandatory alarm and enforcement work order are triggered.

9. A low-altitude aircraft noise monitoring system, implemented using the low-altitude aircraft noise monitoring method as described in any one of claims 1-8, characterized in that, include: The data acquisition module is used to collect low-altitude flight noise signals and surrounding environmental information of the monitoring area, preprocess the collected data, and obtain the total low-altitude flight noise value. The primary determination and separation module is used to dynamically calculate the total noise limit of the monitoring area based on the surrounding environmental information. If the total noise value of low-altitude flight exceeds the total noise limit of the monitoring area, the number of low-altitude aircraft in the monitoring area is determined. If there are multiple low-altitude flight noise signals, multi-target separation is performed on the low-altitude flight noise signal to extract the noise characteristic parameters and measured flight noise values ​​corresponding to each low-altitude aircraft. If the number is 1, the noise level is determined according to the preset classification strategy, and the corresponding handling action is output. The aircraft identification module is used to obtain the flight parameter information of each low-altitude aircraft, and to perform similarity matching between the noise characteristic parameters corresponding to each low-altitude aircraft and the data in the pre-built aircraft model voiceprint feature library to obtain the aircraft model corresponding to each low-altitude aircraft. The noise limit prediction module is used to input the noise characteristic parameters, surrounding environment information, flight parameter information and aircraft model of each low-altitude aircraft into the pre-trained noise limit prediction model. The model outputs the noise prediction limit corresponding to each low-altitude aircraft. The noise level determination module is used to compare the measured flight noise value of each low-altitude aircraft with the noise prediction limit. If the measured flight noise value of any low-altitude aircraft exceeds the corresponding noise prediction limit, the noise level of the corresponding aircraft is determined according to the preset classification strategy, and the corresponding handling action is output. If none of them exceed the corresponding noise prediction limit, a coordinated alarm command is output. The data binding and storage module is used to bind the current noise processing results with the aircraft's flight parameters, surrounding environment information, and aircraft model, and store them in the historical flight monitoring database for updating the noise limit prediction model.

10. A computer-readable storage medium, characterized in that, The storage medium stores a low-altitude aircraft noise monitoring method program, which, when executed, implements the low-altitude aircraft noise monitoring method as described in any one of claims 1-8.

Images