Factory boundary noise on-line monitoring and tracing system and method

Abstract

The invention provides a factory boundary noise online monitoring traceability system and method, and belongs to the technical field of noise monitoring. The system comprises a data acquisition module; the data processing module is used for judging whether factory boundary noise processing is carried out or not; when the boundary noise processing is determined to be carried out, determining a direction corresponding to the directional microphone with the maximum sound level as a noise source direction; based on the noise source direction, a data acquisition instruction is generated and sent to the data acquisition module, and audio frequency information and video information, collected in real time and fed back by the data acquisition module, in the noise source direction are recycled; and taking the audio frequency information and the video information in the noise source direction as input parameters, and based on a pre-established abnormal sound source positioning model and a pre-established sound feature recognition model, obtaining a noise source visual sound field cloud picture and a noise classification recognition result. The purposes of noise comprehensive response, noise orientation definition and noise accurate traceability are achieved, evidence is provided for factory boundary noise source definition, and disputes are effectively avoided.

Description

Technical Field

[0001] The present invention relates to the field of noise monitoring technology, and in particular to a factory boundary noise online monitoring and tracing system, a factory boundary noise online monitoring and tracing method, a machine-readable storage medium and an electronic device. Background Art

[0002] Currently, clear control requirements for industrial noise have been established, and cities with the necessary conditions are encouraged to strengthen precision noise pollution prevention and control through information-based tools such as noise mapping and noise source tracing. While businesses can currently monitor noise by deploying online noise monitoring points, this approach only provides comprehensive noise measurements at factory boundaries and cannot trace the noise source, leading to unclear definitions of factory boundary noise pollution. Exceeding factory boundary noise standards can also pollute sensitive areas such as residential areas, potentially leading to complaints from residents and potentially causing noise pollution disputes with surrounding businesses.

[0003] Therefore, how to achieve targeted tracing of excessive noise at factory boundaries and provide evidence for the definition of noise sources at factory boundaries to avoid disputes is an issue that needs to be addressed urgently. Summary of the Invention

[0004] The purpose of the embodiments of the present invention is to provide an online monitoring and tracing system and method for factory boundary noise, so as to at least solve the above-mentioned problem of how to achieve directional tracing of excessive noise at the factory boundary, provide evidence for the definition of the factory boundary noise source, and avoid disputes.

[0005] In order to achieve the above object, the present invention provides a first aspect of an online monitoring and tracing system for factory boundary noise, comprising: a data acquisition module and a data processing module, wherein the data acquisition module is communicatively connected to the data processing module;

[0006] The data acquisition module is used to collect factory boundary sound source information, which includes at least the factory boundary comprehensive noise value, real-time meteorological condition information and the equivalent sound level of directional microphones in different directions;

[0007] The data processing module includes:

[0008] A factory boundary noise judgment and processing unit is used to determine whether to process the factory boundary noise based on the comprehensive factory boundary noise value and real-time meteorological condition information;

[0009] A noise source direction determination unit is used to determine, when determining to process factory boundary noise, the direction corresponding to the directional microphone with the maximum sound level as the noise source direction based on the equivalent sound levels of directional microphones in different directions;

[0010] A collection direction control unit is used to generate a data collection instruction based on the noise source direction and send it to the data collection module, and to recover the audio and video information of the noise source direction collected in real time fed back by the data collection module;

[0011] The noise identification and positioning unit is configured to input audio information and video information of a noise source direction as input parameters, and obtain a noise source visualized sound field cloud map and a noise classification and identification result based on a pre-established abnormal sound source positioning model and a pre-established sound feature identification model.

[0012] Optionally, the sound feature identification model comprises a preprocessing sub-model and a neural network sub-model.

[0013] The processing rule of the sound feature identification model comprises:

[0014] The audio information of the noise source direction is input into the preprocessing sub-model, and frame division, windowing, fast Fourier transform and Mel transform processing are sequentially performed to obtain corresponding Mel spectrum features.

[0015] Based on the corresponding Mel spectrum features, audible frequency band spectrum features and ultrasonic frequency band spectrum features of the audio information of the noise source direction are extracted.

[0016] The noise source visualized sound field cloud map, the audible frequency band spectrum features and the ultrasonic frequency band spectrum features of the audio information of the noise source direction are input into the neural network sub-model to obtain the noise classification and identification result.

[0017] Optionally, the neural network sub-model is built-in a noise identification database, and the noise identification database comprises a plurality of noise categories.

[0018] The noise source visualized sound field cloud map, the audible frequency band spectrum features and the ultrasonic frequency band spectrum features corresponding to each noise category.

[0019] Optionally, the data acquisition module comprises an omnidirectional noise monitor, a directional microphone array, an acoustic imaging device and a meteorological instrument, and the omnidirectional noise monitor, the directional microphone array, the acoustic imaging device and the meteorological instrument are in communication connection with the data processing module.

[0020] The omnidirectional noise monitor is configured to monitor a plant boundary comprehensive noise value, wherein the plant boundary comprehensive noise value represents a real-time collected equivalent sound level of a corresponding sound environment functional area.

[0021] The directional microphone array is configured to obtain directional microphone equivalent sound levels in different directions.

[0022] The acoustic imaging device is configured to collect audio information and video information of a noise source direction.

[0023] The meteorological instrument is configured to monitor real-time meteorological condition information, and the real-time meteorological condition information at least comprises wind speed and direction parameters, temperature and humidity parameters, rainfall parameters and atmospheric pressure parameters.

[0024] Optionally, the acoustic imaging device comprises a two-dimensional microphone array and a visible light camera, which are in communication connection with the data processing module;

[0025] The two-dimensional microphone array is used to collect acoustic information of the noise source direction;

[0026] The visible light camera is used to collect video information of the noise source direction.

[0027] Optionally, the acoustic information of the noise source direction comprises sound signals collected by each microphone in the two-dimensional microphone array;

[0028] The processing rule of the abnormal sound source positioning model comprises:

[0029] Based on the beamforming algorithm, the sound signals collected by each microphone in the two-dimensional microphone array are filtered and weighted and superimposed to obtain a sound field distribution cloud map and the position of the noise source in the sound field distribution cloud map;

[0030] The sound field distribution cloud map is superimposed with the corresponding visible light picture in the video information of the noise source direction to obtain a noise source visualized sound field cloud map.

[0031] Optionally, the arrangement mode of the two-dimensional microphone array comprises at least a cross shape, a circular shape, a random distribution, a spiral shape and / or a nested shape.

[0032] Optionally, the directional microphone array comprises a plurality of directional microphones, which are in communication connection with the data processing module, and the plant boundary noise online monitoring and tracing system further comprises a fixed vertical rod, the directional microphones, the omnidirectional noise monitor, the acoustic imaging device and the weather meter are arranged on the fixed vertical rod, and a rotating holder is arranged between the fixed vertical rod and the acoustic imaging device, which is in communication connection with the data processing module;

[0033] The rotating holder is used to receive and rotate according to the data collection instruction, so as to make the acoustic imaging device collect the acoustic information and the video information of the noise source direction.

[0034] Optionally, the plant boundary noise judgment processing unit comprises:

[0035] A noise value comparison subunit is configured to compare the plant boundary comprehensive noise value with a corresponding preset noise threshold based on the collection time period and the corresponding sound environment functional area of the plant boundary comprehensive noise value;

[0036] A noise exceeding determination subunit is configured to determine that the plant boundary noise exceeds the standard if the plant boundary comprehensive noise value exceeds the corresponding preset noise threshold.

[0037] The meteorological condition comparison subunit is configured to compare real-time meteorological condition information with preset effective meteorological conditions when the plant boundary noise exceeds the standard, and determine whether to process the plant boundary noise based on the comparison result.

[0038] Optionally, the plant boundary noise online monitoring and tracing system further comprises an alarm module, which is in communication connection with the data processing module.

[0039] The alarm module is configured to send an alarm information based on the noise source visualized sound field cloud map and the noise classification and identification result.

[0040] Optionally, the plant boundary noise online monitoring and tracing system further comprises a communication module, and the data acquisition module and the data processing module are in communication connection through the communication module.

[0041] The second aspect of the present application provides a plant boundary noise online monitoring and tracing method, which is executed by a data processing module, and the data processing module is in communication connection with a data acquisition module.

[0042] The method comprises the following steps:

[0043] Based on the plant boundary comprehensive noise value and the real-time meteorological condition information, it is determined whether to process the plant boundary noise.

[0044] When it is determined to process the plant boundary noise, the direction corresponding to the directional microphone with the maximum sound level in different directions is determined as the noise source direction based on the equivalent sound level of the directional microphone in different directions.

[0045] Based on the noise source direction, a data acquisition instruction is generated and sent to the data acquisition module, and real-time collected sound frequency information and video information of the noise source direction fed back by the data acquisition module are recovered.

[0046] The sound frequency information and the video information of the noise source direction are taken as input parameters, and based on a pre-established abnormal sound source positioning model and a pre-established sound feature identification model, a noise source visualized sound field cloud map and a noise classification and identification result are obtained, respectively.

[0047] Optionally, the determination of whether to process the plant boundary noise based on the plant boundary comprehensive noise value and the real-time meteorological condition information comprises the following steps:

[0048] The plant boundary comprehensive noise value is compared with a corresponding preset noise threshold value based on the acquisition time period corresponding to the plant boundary comprehensive noise value and the sound environment functional area to which the plant boundary comprehensive noise value belongs.

[0049] If the plant boundary comprehensive noise value exceeds the corresponding preset noise threshold value, it is determined that the plant boundary noise exceeds the standard.

[0050] When the plant boundary noise exceeds the standard, real-time meteorological condition information is compared with preset effective meteorological conditions, and whether to process the plant boundary noise is determined based on the comparison result of the meteorological conditions.

[0051] Optionally, the data acquisition module comprises a two-dimensional microphone array, and the audio information of the noise source direction comprises sound signals collected by each microphone in the two-dimensional microphone array.

[0052] The processing rule of the abnormal sound source positioning model comprises:

[0053] Based on the beamforming algorithm, the sound signals collected by each microphone in the two-dimensional microphone array are filtered and weighted and superimposed to obtain a sound field distribution cloud picture and a noise source position in the sound field distribution cloud picture.

[0054] The sound field distribution cloud picture is superimposed on the corresponding visible light picture in the video information of the noise source direction to obtain a noise source visualized sound field cloud picture.

[0055] Optionally, the sound feature recognition model comprises a pre-processing sub-model and a neural network sub-model.

[0056] The processing rule of the sound feature recognition model comprises:

[0057] The audio information of the noise source direction is input into the pre-processing sub-model, and frame division, windowing, fast Fourier transform and Mel transform processing are sequentially performed to obtain corresponding Mel spectrum features.

[0058] Based on the corresponding Mel spectrum features, audible frequency band spectrum features and ultrasonic frequency band spectrum features of the audio information of the noise source direction are extracted, respectively.

[0059] The noise source visualized sound field cloud picture, the audible frequency band spectrum features and the ultrasonic frequency band spectrum features of the audio information of the noise source direction are input into the neural network sub-model to obtain a noise classification recognition result.

[0060] In a third aspect of the present application, a machine-readable storage medium is provided, the machine-readable storage medium stores instructions, and the instructions, when executed by a processor, cause the processor to be configured to perform the plant boundary noise online monitoring and tracing method described above.

[0061] In a fourth aspect of the present application, an electronic device is provided, the electronic device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the plant boundary noise online monitoring and tracing method described above when executing the computer program.

[0062] Through the technical scheme, a plant boundary noise online monitoring and tracing system and method are provided, which collects plant boundary sound source information such as plant boundary comprehensive noise value, real-time meteorological condition information and equivalent sound level of directional microphones in different directions through a data collection module. The data processing module determines whether to process the plant boundary noise according to the plant boundary comprehensive noise value and the real-time meteorological condition information. In the case of determining to process the plant boundary noise, the equivalent sound levels of directional microphones in different directions are analyzed and compared in real time to obtain directional position information corresponding to the directional microphone with the maximum sound level, and the direction corresponding to the directional microphone with the maximum sound level is taken as the noise source direction. Therefore, according to the noise source direction, the data collection module is controlled to collect sound frequency information and video information of the noise source direction in real time. The sound frequency information and the video information of the noise source direction are processed by using a pre-established abnormal sound source positioning model to obtain a noise source visualized sound field cloud map in the form of a visible light cloud map, which shows the noise position. The sound frequency information of the noise source direction is analyzed and processed by using a pre-established sound feature recognition model to output a noise classification and recognition result. The system and method integrate directional microphones and acoustic imaging equipment on the basis of an omnidirectional noise monitor to form a complete monitoring technology and equipment integrating omnidirectional point type, directional point type and imaging surface type, achieve the purposes of noise comprehensive response, noise position definition and noise accurate tracing, and thus achieve the purposes of plant boundary noise directional tracing and clarifying the responsibility subject, provide evidence for plant boundary noise source definition, and effectively avoid disputes.

[0063] Other features and advantages of the present application will be described in detail in the following detailed description. BRIEF DESCRIPTION OF DRAWINGS

[0064] The accompanying drawings are included to provide a further understanding of the present application and are incorporated in and constitute a part of this specification, illustrate embodiments of the present application and serve to explain the principles of the present application, but do not limit the present application. In the drawings:

[0065] Figure 1 is a block diagram of a plant boundary noise online monitoring and tracing system provided by an embodiment of the present application;

[0066] Figure 2 is a structural schematic diagram of another plant boundary noise online monitoring and tracing system provided by an embodiment of the present application;

[0067] Figure 3 is a flowchart of model processing data provided by an embodiment of the present application;

[0068] Figure 4 is a structural schematic diagram of still another plant boundary noise online monitoring and tracing system provided by an embodiment of the present application;

[0069] Figure 5This is a flow chart of noise identification and positioning provided by one embodiment of the present invention;

[0070] Figure 6 This is a flow chart of a method for online monitoring and tracing the source of factory boundary noise provided by one embodiment of the present invention;

[0071] Figure 7 It is a schematic diagram of the structure of an electronic device provided by a preferred embodiment of the present invention.

[0072] Description of Reference Numerals

[0073] 1- omnidirectional noise monitor, 2- directional microphone array, 3- acoustic imaging device, 4- rotating pan / tilt head, 5- meteorological instrument, 6- power supply, 7- fixed pole, 10- electronic device, 100- processor, 101- memory, 102- computer program. DETAILED DESCRIPTION

[0074] The following describes the specific embodiments of the present invention in detail with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present invention and are not intended to limit the present invention.

[0075] Example 1

[0076] Figure 1 This is a block diagram of an online monitoring and tracing system for factory boundary noise provided by one embodiment of the present invention. Figure 2 This is a schematic diagram of another factory boundary noise online monitoring and tracing system provided by one embodiment of the present invention. Figure 1 and Figure 2 As shown, an embodiment of the present invention provides an online monitoring and tracing system for factory boundary noise, comprising: a data acquisition module and a data processing module, wherein the data acquisition module is communicatively connected with the data processing module;

[0077] The data acquisition module is used to collect factory boundary sound source information, which includes at least the factory boundary comprehensive noise value, real-time meteorological condition information and the equivalent sound level of directional microphones in different directions;

[0078] In detail, the above-mentioned data acquisition module includes an omnidirectional noise monitor 1, a directional microphone array 2, an acoustic imaging device 3 and a meteorological instrument 5. The omnidirectional noise monitor 1, the directional microphone array 2, the acoustic imaging device 3 and the meteorological instrument 5 are respectively communicated with the data processing module.

[0079] The omnidirectional noise monitor 1 is used to monitor the integrated noise level at the factory boundary. This represents the real-time equivalent sound level of the corresponding acoustic environment functional zone. The omnidirectional noise monitor 1 refers to a sound level meter. The sound level meter is used to monitor the integrated noise level at the factory boundary. The monitoring point for the sound level meter can be set 1m outside the factory boundary of the industrial enterprise, at a height of at least 1.2m, and at least 1m away from any reflecting surface. If the factory boundary is surrounded by a wall and is surrounded by noise-sensitive buildings, the sound level meter should be set 1m outside the factory boundary and at least 0.5m above the wall.

[0080] Directional microphone array 2 is used to obtain the equivalent sound levels of directional microphones in different directions. Directional microphone array 2 consists of a set of directional microphones with a directional accuracy of no more than 180°. The directional microphones are evenly arranged on both sides of the factory boundary and are used to determine the direction of excessive noise within the factory boundary. Specifically, it can consist of two directional microphones with a directional accuracy of 180°, one on each side of the factory boundary, aimed at the inside and outside of the factory boundary. Alternatively, it can consist of four directional microphones with a positioning accuracy of 90°, located at four azimuths of the factory boundary, and aimed at four directions for monitoring.

[0081] The acoustic imaging device 3 is used to collect audio information and video information from the direction of the noise source.

[0082] The meteorological instrument 5 is used to monitor real-time meteorological conditions, which include at least wind speed and direction parameters, temperature and humidity parameters, rainfall parameters, and atmospheric pressure parameters. The monitored real-time meteorological conditions are considered valid when the measurement environment is free of rain, snow, and thunderstorms, and the wind speed is below 5 m / s.

[0083] The data processing module includes:

[0084] A factory boundary noise judgment and processing unit is used to determine whether to process the factory boundary noise based on the comprehensive factory boundary noise value and real-time meteorological condition information;

[0085] Furthermore, the above-mentioned factory boundary noise judgment and processing unit includes: a noise value comparison subunit, which is used to compare the factory boundary comprehensive noise value with the corresponding preset noise threshold based on the collection time period and the sound environment functional zone corresponding to the factory boundary comprehensive noise value; a noise exceeding standard determination subunit, which is used to determine that the factory boundary noise exceeds the standard if the factory boundary comprehensive noise value exceeds the corresponding preset noise threshold; a meteorological condition comparison subunit, which is used to compare the real-time meteorological condition information with the preset effective meteorological condition when the factory boundary noise exceeds the standard, and determine whether to process the factory boundary noise based on the meteorological condition comparison result.

[0086] Specifically, the plant boundary noise judgment processing unit obtains the monitoring plant boundary comprehensive noise value collected by the omnidirectional noise monitor 1 in real time, the noise value comparison subunit compares the plant boundary comprehensive noise value with the corresponding preset noise threshold according to the collection time period corresponding to the plant boundary comprehensive noise value and the sound environment functional area to which the plant boundary comprehensive noise value belongs, and if the plant boundary comprehensive noise value exceeds the corresponding preset noise threshold, the meteorological condition comparison subunit is triggered to work, the meteorological condition comparison subunit obtains the real-time meteorological condition information collected by the meteorological instrument 5, and compares the real-time meteorological condition information with the preset effective meteorological condition (for example, when the measurement environment is in a weather without rain and snow, without thunder and lightning, and the wind speed is below 5 m / s, the real-time meteorological condition information monitored is considered to be effective), and when the real-time meteorological condition information is effective, it is determined to process the plant boundary noise.

[0087] The noise source direction determination unit is configured to, when it is determined to process the plant boundary noise, determine the direction corresponding to the directional microphone with the maximum sound level as the noise source direction based on the sound levels in equivalent of the directional microphones in different directions.

[0088] Specifically, when it is determined to process the plant boundary noise, the sound levels in equivalent of the directional microphones in different directions (i.e., the response values of the directional microphones) are analyzed and compared in real time, the direction position information corresponding to the directional microphone with the maximum sound level is obtained, and the direction position corresponding to the directional microphone with the maximum sound level is taken as the noise source direction (i.e., the direction indicated by the directional microphone with the maximum response value is taken as the noise source direction).

[0089] The collection direction control unit is configured to generate a data collection instruction based on the noise source direction and send the data collection instruction to the data collection module, and recover the audio information and video information of the noise source direction collected in real time fed back by the data collection module.

[0090] In some embodiments of the present embodiment, the directional microphone array 2 described above includes a plurality of directional microphones, the plurality of directional microphones are in communication connection with the data processing module, and the plant boundary noise online monitoring and tracing system further includes a fixed vertical rod 7, the plurality of directional microphones, the omnidirectional noise monitor 1, the acoustic imaging device 3, and the meteorological instrument 5 are arranged on the fixed vertical rod 7, a rotating holder 4 is arranged between the fixed vertical rod 7 and the acoustic imaging device 3, and the rotating holder 4 is in communication connection with the data processing module; the rotating holder 4 is configured to receive and rotate according to the data collection instruction, so that the acoustic imaging device 3 collects the audio information and video information of the noise source direction.

[0091] Figure 4 is a structural schematic diagram of another plant boundary noise online monitoring and tracing system provided by an embodiment of the present application. As Figure 4As shown, the directional microphone, the omnidirectional noise monitor 1, the acoustic imaging device 3 and the meteorograph 5 are all installed on the fixed vertical pole 7. The fixed vertical pole 7 is connected with the acoustic imaging device 3 through the rotating holder 4. When the directional microphone array 2 confirms the noise source direction of the factory boundary noise exceeding the standard, the rotating holder 4 is controlled to rotate to the monitoring angle of the directional microphone corresponding to the direction of the maximum sound level, and the acoustic imaging device 3 is controlled to collect the audio information and the video information of the noise source direction in real time.

[0092] Further, the acoustic imaging device 3 is integrated by a two-dimensional microphone array and a visible light camera, and the two-dimensional microphone array and the visible light camera are respectively in communication connection with the data processing module; the two-dimensional microphone array is used to collect the audio information of the noise source direction; and the visible light camera is used to collect the video information of the noise source direction.

[0093] In some embodiments of the present embodiment, the arrangement mode of the two-dimensional microphone array includes at least cross shape, circular shape, random distribution, spiral type and / or nested type.

[0094] The noise identification and positioning unit is used to take the audio information and the video information of the noise source direction as input parameters, and based on the pre-established abnormal sound source positioning model and the pre-established sound feature recognition model, to obtain the noise source visualized sound field cloud map and the noise classification recognition result respectively.

[0095] Specifically, the system collects the factory boundary sound source information such as the factory boundary comprehensive noise value, the real-time meteorological condition information and the equivalent sound level of the directional microphone in different directions through the data acquisition module. The data processing module judges whether to process the factory boundary noise according to the factory boundary comprehensive noise value and the real-time meteorological condition information. In the case of determining to process the factory boundary noise, the equivalent sound levels of the directional microphones in different directions are analyzed and compared in real time to obtain the direction position information corresponding to the directional microphone of the maximum sound level, and the direction position corresponding to the directional microphone of the maximum sound level is taken as the noise source direction. Therefore, according to the noise source direction, the data acquisition module is controlled to collect the audio information and the video information of the noise source direction in real time. The pre-established abnormal sound source positioning model is used to process the audio information and the video information of the noise source direction, and the noise source visualized sound field cloud map in the form of a visible light cloud map is obtained to show the noise position. The pre-established sound feature recognition model is used to analyze and process the audio information of the noise source direction to output the noise classification recognition result. The system integrates the directional microphone, the acoustic imaging device 3 on the basis of the omnidirectional noise monitor 1 to form a complete monitoring technology and equipment integrating omnidirectional point type, directional point type and imaging surface type, realizes the purposes of noise comprehensive response, noise position definition and noise accurate tracing, and further achieves the purposes of directional tracing of the factory boundary noise exceeding the standard and clarifying the responsibility subject, provides evidence for the definition of the factory boundary noise source, and effectively avoids disputes.

[0096] It should be noted that when the noise recognition positioning unit is executed, the system automatically starts the data real-time recording and storage function.

[0097] In some embodiments of the present embodiment, the audio information of the noise source direction includes sound signals collected by each microphone in the two-dimensional microphone array; and the processing rule of the abnormal sound source positioning model includes: based on a beamforming algorithm, filtering and weighted superposition processing are performed on the sound signals collected by each microphone in the two-dimensional microphone array to obtain a sound field distribution cloud picture and a noise source position in the sound field distribution cloud picture; and the sound field distribution cloud picture is superimposed on a corresponding visible light picture in the video information of the noise source direction to obtain a noise source visualized sound field cloud picture.

[0098] Specifically, the abnormal sound source positioning model identifies the noise source through a beamforming algorithm, filters and weighted superimposes sound signals collected by each microphone in the two-dimensional microphone array arranged on the surface of the acoustic imaging device 3 to form a beam, and identifies the noise source to obtain a sound field distribution cloud picture and a noise source position in the sound field distribution cloud picture. The sound field distribution cloud picture is superimposed on a monitoring scene in the video information of the noise source direction collected by the visible light camera of the acoustic imaging device 3 to form a noise source visualized sound field cloud picture, so as to real-time locate the abnormal sound source.

[0099] In some embodiments of the present embodiment, the sound feature recognition model includes a pre-processing sub-model and a neural network sub-model; and the processing rule of the sound feature recognition model includes: inputting the audio information of the noise source direction into the pre-processing sub-model, and sequentially performing frame division, windowing, fast Fourier transform and Mel transform processing to obtain corresponding Mel spectrum features; based on the corresponding Mel spectrum features, audible frequency band spectrum features and ultrasonic frequency band spectrum features of the audio information of the noise source direction are extracted respectively; the noise source visualized sound field cloud picture, the audible frequency band spectrum features and the ultrasonic frequency band spectrum features of the audio information of the noise source direction are input into the neural network sub-model to obtain a noise classification recognition result.

[0100] Please refer to Figure 3 , Figure 3is a flow chart of a model processing data provided by an embodiment of the present application. Specifically, the acoustic frequency information of the noise source direction collected by the acoustic imaging device 3 is input into the pre-processing sub-model. The pre-processing sub-model includes the steps of framing, windowing, fast Fourier transform, and Mel transform. The acoustic frequency information of the noise source direction is processed by the pre-processing sub-model to obtain the Mel spectrum features. The frequency range of the noise audio collected by the acoustic imaging device 3 covers the audible frequency band and the ultrasonic frequency band, and the audible frequency band spectrum features and the ultrasonic frequency band spectrum features of the acoustic frequency information of the noise source direction are extracted respectively. The three-dimensional information of the noise source visualized sound field cloud map, the audible frequency band spectrum features and the ultrasonic frequency band spectrum features of the acoustic frequency information of the noise source direction are input into the neural network sub-model for noise type identification.

[0101] In some embodiments of the present application, the neural network sub-model described above is built-in with a noise identification database, and the noise identification database contains a plurality of noise types, and the noise source visualized sound field cloud map, the audible frequency band spectrum features and the ultrasonic frequency band spectrum features corresponding to each noise type.

[0102] For example, the noise identification database contains common plant boundary noises such as vehicle transportation, animal calls, music horns and production devices.

[0103] In some embodiments of the present application, the plant boundary noise online monitoring and tracing system further comprises an alarm module, which is in communication connection with the data processing module; the alarm module is used to issue an alarm information based on the noise source visualized sound field cloud map and the noise classification and identification result.

[0104] Specifically, the alarm module realizes the alarm and reminder of the noise exceeding the standard, the system automatically outputs the sound source type (i.e. the noise classification and identification result) and displays the point where the noise source is located in the form of a visualized sound field cloud map, and the personnel in the monitoring center further disposes according to the noise source visualized sound field cloud map and the noise classification and identification result.

[0105] In some embodiments of the present application, the plant boundary noise online monitoring and tracing system further comprises a communication module, and the data acquisition module and the data processing module are in communication connection through the communication module. The communication module can be a 4G module, a 5G module and a WIFI module.

[0106] In some embodiments of the present application, the system is further provided with a power supply 6, which is used to supply power to the omnidirectional noise monitor 1, the directional microphone array 2, the acoustic imaging device 3, the rotating holder 4 and the weather instrument 5.

[0107] Embodiment 2

[0108] Please refer to Figure 4 , Figure 4is a structure diagram of another plant boundary noise online monitoring and tracing system provided by an embodiment of the present application. The directional microphone array 2 of the plant boundary noise online monitoring and tracing system is composed of two directional microphones with a directional accuracy of 180°. The two directional microphones are fixed on a vertical rod and respectively point to the inside and outside of the plant boundary. The two-dimensional microphone array of the acoustic imaging device 3 is randomly arranged.

[0109] In this embodiment, the sound environment functional area outside the plant boundary is 2 areas. The equivalent continuous A sound level monitored by the omnidirectional noise monitor 1 at 10:00 in the daytime is 58dB(A), which does not exceed the threshold value of 60dB(A) in the daytime (6:00-22:00), and the system continues to monitor.

[0110] Embodiment 3

[0111] Please refer to Figure 4 , Figure 4 is a structure diagram of another plant boundary noise online monitoring and tracing system provided by an embodiment of the present application. The directional microphone array 2 of the plant boundary noise online monitoring and tracing system is composed of two directional microphones with a directional accuracy of 180°. The two directional microphones are fixed on a vertical rod and respectively point to the inside and outside of the plant boundary. The two-dimensional microphone array of the acoustic imaging device 3 is randomly arranged.

[0112] In this embodiment, the sound environment functional area outside the plant boundary is 2 areas. The equivalent continuous A sound level monitored by the omnidirectional noise monitor 1 at 2:00 in the early morning is 58dB(A), which exceeds the threshold value of 50dB(A) in the night (22:00-6:00 of the next day), the system obtains real-time meteorological information as a weather without rain and snow, without thunder and lightning, and a wind speed of 10m / s, which exceeds the effective wind speed of 5m / s, the system automatically judges that the effective meteorological condition is not met, and the system continues to monitor.

[0113] Embodiment 4

[0114] Please refer to Figure 4 , Figure 4 is a structure diagram of another plant boundary noise online monitoring and tracing system provided by an embodiment of the present application. The directional microphone array 2 of the plant boundary noise online monitoring and tracing system is composed of two directional microphones with a directional accuracy of 180°. The two directional microphones are fixed on a vertical rod and respectively point to the inside and outside of the plant boundary. The two-dimensional microphone array of the acoustic imaging device 3 is randomly arranged.

[0115] In this embodiment, the functional area of the external sound environment of the plant boundary is area 1, and the equivalent continuous A sound level monitored by the omnidirectional noise monitor 1 at 10:00 in the daytime is 58 dB(A), which exceeds the threshold value of 55 dB(A) during the day (6:00-22:00). The system obtains real-time weather information as no rain and snow, no thunder and lightning weather, and a wind speed of 2 m / s, and the system judges that it is valid weather information for the next step of directional microphone value processing. According to the monitoring value results of the two directional microphones, the microphone monitoring result towards the plant boundary is 60 dB(A), and the microphone monitoring result towards the plant boundary is 50 dB(A). The initial position of the sound imaging equipment is oriented in the same direction as the plant boundary, and the system controls the pan-tilt to rotate 90° after judgment, turns to the outside of the plant boundary, and collects audio and video information and transmits it to the background for judgment. After analysis and judgment, it is caused by a truck passing and continuously honking. The system automatically records and stores the results for monitoring personnel to view and handle.

[0116] Embodiment 5

[0117] Figure 5 is a flowchart of a noise identification and positioning method provided by an embodiment of the present application, Figure 6 is a flowchart of a plant boundary noise online monitoring and tracing method provided by an embodiment of the present application. As shown in Figure 5 and Figure 6 shown, the plant boundary noise online monitoring and tracing method provided by the embodiment of the present application is executed by a data processing module, the data processing module is in communication connection with a data acquisition module, the data acquisition module is used to acquire plant boundary sound source information, and the plant boundary sound source information at least includes plant boundary comprehensive noise value, real-time weather condition information and equivalent sound level of directional microphone in different directions;

[0118] The method comprises:

[0119] Based on the plant boundary comprehensive noise value and the real-time weather condition information, it is determined whether to process the plant boundary noise;

[0120] When it is determined to process the plant boundary noise, based on the equivalent sound level of the directional microphone in different directions, the direction corresponding to the directional microphone with the maximum sound level is determined as the noise source direction;

[0121] Based on the noise source direction, a data acquisition instruction is generated and sent to the data acquisition module, and the real-time acquired sound frequency information and video information of the noise source direction fed back by the data acquisition module are recovered;

[0122] The sound frequency information and video information of the noise source direction are taken as input parameters, and based on the pre-established abnormal sound source positioning model and the pre-established sound feature recognition model, a noise source visual sound field cloud map and a noise classification recognition result are obtained, respectively.

[0123] Specifically, the method collects the plant boundary comprehensive noise value, real-time meteorological condition information, and plant boundary sound source information such as the equivalent sound level of the directional microphone in different directions through the data acquisition module. The data processing module determines whether to process the plant boundary noise according to the plant boundary comprehensive noise value and the real-time meteorological condition information. In the case of determining to process the plant boundary noise, the equivalent sound levels of the directional microphones in different directions are analyzed and compared in real time to obtain the directional position information corresponding to the directional microphone with the maximum sound level, and the direction corresponding to the directional microphone with the maximum sound level is taken as the noise source direction. Therefore, according to the noise source direction, the data acquisition module is controlled to collect the audio information and video information of the noise source direction in real time. The pre-established abnormal sound source positioning model is used to process the audio information and video information of the noise source direction, and a noise source visualized sound field cloud map showing the noise position in the form of a visible light cloud map is obtained. The pre-established sound feature recognition model is used to analyze and process the audio information of the noise source direction to output a noise classification and recognition result. Based on the omnidirectional noise monitor 1, the directional microphone and the acoustic imaging device 3 are integrated to form a complete monitoring technology and equipment integrating omnidirectional point type, directional point type and imaging surface type, achieving the purposes of noise comprehensive response, noise direction definition and noise accurate tracing, and further achieving the purposes of plant boundary noise directional tracing and clarifying the responsibility subject, providing evidence for plant boundary noise source definition, and effectively avoiding disputes.

[0124] In some embodiments of the present embodiment, the determination of whether to process the plant boundary noise based on the plant boundary comprehensive noise value and the real-time meteorological condition information includes: comparing the plant boundary comprehensive noise value with a corresponding preset noise threshold based on the acquisition time period and the corresponding sound environment functional area of the plant boundary comprehensive noise value; if the plant boundary comprehensive noise value exceeds the corresponding preset noise threshold, it is determined that the plant boundary noise is over-standard; and when the plant boundary noise is over-standard, the real-time meteorological condition information is compared with the preset effective meteorological condition, and whether to process the plant boundary noise is determined based on the meteorological condition comparison result.

[0125] Specifically, the monitoring plant boundary comprehensive noise value collected by the omnidirectional noise monitor 1 is obtained in real time, the plant boundary comprehensive noise value is compared with a corresponding preset noise threshold based on the acquisition time period and the corresponding sound environment functional area of the plant boundary comprehensive noise value, if it exceeds the corresponding preset noise threshold, the real-time meteorological condition information is compared with the preset effective meteorological condition (for example, when the measurement environment is in a weather without rain and snow, without thunder and lightning, and the wind speed is below 5 m / s, the real-time meteorological condition information monitored is considered effective), and when the real-time meteorological condition information is effective, it is determined to process the plant boundary noise.

[0126] In some embodiments of the present embodiment, the data acquisition module comprises a two-dimensional microphone array, and the sound frequency information of the noise source direction comprises sound signals collected by each microphone in the two-dimensional microphone array; and the processing rule of the abnormal sound source positioning model comprises: filtering and weighted superposition processing the sound signals collected by each microphone in the two-dimensional microphone array based on a beamforming algorithm to obtain a sound field distribution cloud picture and a noise source position in the sound field distribution cloud picture; and superimposing the sound field distribution cloud picture and a corresponding visible light picture in the video information of the noise source direction to obtain a noise source visualized sound field cloud picture.

[0127] Specifically, the abnormal sound source positioning model identifies the noise source position in the sound field distribution cloud picture by filtering and weighted superposition processing the sound signals collected by each microphone in the two-dimensional microphone array arranged on the surface of the acoustic imaging device 3 through a beamforming algorithm to form a beam, and identifies the noise source position in the sound field distribution cloud picture.

[0128] In some embodiments of the present embodiment, the sound feature recognition model comprises a pre-processing sub-model and a neural network sub-model; and the processing rule of the sound feature recognition model comprises: inputting the sound frequency information of the noise source direction into the pre-processing sub-model to sequentially perform frame division, windowing, fast Fourier transform and Mel transform processing to obtain corresponding Mel spectrum features; based on the corresponding Mel spectrum features, extracting audible sound frequency band spectrum features and ultrasonic frequency band spectrum features of the sound frequency information of the noise source direction respectively; and inputting the noise source visualized sound field cloud picture, the audible sound frequency band spectrum features and the ultrasonic frequency band spectrum features of the sound frequency information of the noise source direction into the neural network sub-model to obtain a noise classification recognition result.

[0129] Please refer to Figure 3 , Figure 3 is a flowchart of a model processing data provided by an embodiment of the present application. Specifically, the sound frequency information of the noise source direction collected by the acoustic imaging device 3 is input into the pre-processing sub-model. The pre-processing sub-model includes frame division, windowing, fast Fourier transform, and Mel transform steps. The sound frequency information of the noise source direction is processed by the pre-processing sub-model to obtain Mel spectrum features. The noise sound frequency range collected by the acoustic imaging device 3 covers an audible sound frequency band and an ultrasonic frequency band. The audible sound frequency band spectrum features and the ultrasonic frequency band spectrum features of the sound frequency information of the noise source direction are extracted respectively. The noise source visualized sound field cloud picture, the audible sound frequency band spectrum features and the ultrasonic frequency band spectrum features of the sound frequency information of the noise source direction are input into the neural network sub-model for noise type recognition.

[0130] Embodiment 6

[0131] An embodiment of the present invention further provides a machine-readable storage medium having instructions stored thereon. When the instructions are executed by the processor 100, the processor 100 is configured to execute the above-mentioned data processing module.

[0132] Machine-readable storage media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0133] An embodiment of the present invention further provides an electronic device 10, which includes a memory 101, a processor 100, and a computer program 102 stored in the memory 101 and executable on the processor 100. When the processor 100 executes the computer program 102, the above-mentioned data processing module is implemented.

[0134] like Figure 7 FIG. 1 is a schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 7 As shown, the electronic device 10 of this embodiment includes: a processor 100, a memory 101, and a computer program 102 stored in the memory 101 and executable on the processor 100. When the processor 100 executes the computer program 102, the steps of the above-described method embodiment are implemented. Alternatively, when the processor 100 executes the computer program 102, the functions of the modules / units in the above-described device embodiment are implemented.

[0135] For example, the computer program 102 can be divided into one or more modules / units, one or more modules / units are stored in the memory 101 and executed by the processor 100 to complete the present application. One or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program 102 in the electronic device 10. For example, the computer program 102 can be divided into factory boundary noise judgment processing unit, noise source direction determination unit, acquisition direction control unit and noise identification positioning unit.

[0136] The electronic device 10 can be a desktop computer, a notebook computer, a palm computer, a cloud server and the like. The electronic device 10 can include, but is not limited to, the processor 100 and the memory 101. Those skilled in the art can understand that the electronic device 10 can include more or less components, or combine some components, or different components, for example, the electronic device can also include an input / output device, a network access device, a bus and the like. Figure 7 The electronic device 10 is only an example and does not constitute a limitation on the electronic device 10, and can include more or less components than the diagram, or combine some components, or different components, for example, the electronic device can also include an input / output device, a network access device, a bus and the like.

[0137] The processor 100 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0138] The memory 101 can be an internal storage unit of the electronic device 10, such as a hard disk or a memory of the electronic device 10. The memory 101 can also be an external storage device of the electronic device 10, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card and the like equipped on the electronic device 10. Further, the memory 101 can include both the internal storage unit and the external storage device of the electronic device 10. The memory 101 is used to store the computer program and other programs and data required by the electronic device 10. The memory 101 can also be used to temporarily store data that has been output or will be output.

[0139] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is taken as an example, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction, and do not limit the protection scope of the application. The specific working process of the units and modules in the system can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0140] Those skilled in the art will appreciate that embodiments of the application can be provided as methods, systems, or computer program 102 products. Therefore, the application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the application can take the form of a computer program 102 product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0141] The application is described with reference to flowcharts and / or block diagrams according to the method, device (system), and computer program 102 product of the embodiments of the application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram can be realized by computer program 102 instructions. These computer program 102 instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device that implements the functions specified in the flowchart and / or block diagram. Figure 1 one flow or multiple flows and / or blocks Figure 1 an apparatus that performs the functions specified in one block or multiple blocks.

[0142] These computer program 102 instructions can also be stored in a computer-readable storage 101 that can guide the computer or other programmable data processing devices to work in a specific way, so that the instructions stored in the computer-readable storage 101 produce a manufactured product including instruction devices that implement the functions specified in the flowchart and / or block diagram. Figure 1 one flow or multiple flows and / or blocks Figure 1 an apparatus that performs the functions specified in one block or multiple blocks.

[0143] These computer program instructions 102 can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 Figure 1

[0144] It is also important to note that the terms "comprises" and / or "comprising", or "includes" and / or "including" when used in this specification, specify the presence of stated features, integers, steps, operations, elements, or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or groups thereof.

[0145] The embodiments of method, device, and system of the present application can take many different forms. The present application should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided for illustrative purposes. Although the present application has been described in some detail, those skilled in the art should appreciate that many modifications are possible that will come within the scope of the present application as defined by the appended claims. Accordingly, the terms of such claims should not be construed as limiting the present application to the precise steps or other such tightly-defined formulations.​​

Claims

1. A factory boundary noise online monitoring and tracing system, characterized by: include: A data acquisition module and a data processing module, wherein the data acquisition module is in communication with the data processing module; The data acquisition module is used to collect factory boundary sound source information, and the factory boundary sound source information at least includes the factory boundary comprehensive noise value, real-time meteorological condition information and the equivalent sound level of directional microphones in different directions; The data processing module includes: a plant boundary noise determination and processing unit, configured to determine whether to perform plant boundary noise processing based on the plant boundary comprehensive noise value and the real-time meteorological condition information; A noise source direction determination unit is used to determine, when determining to process factory boundary noise, the direction corresponding to the directional microphone with the maximum sound level as the noise source direction based on the equivalent sound levels of directional microphones in different directions; A collection direction control unit, configured to generate a data collection instruction based on the noise source direction and send the instruction to the data collection module, and to retrieve the audio and video information of the noise source direction collected in real time and fed back by the data collection module; The noise identification and positioning unit is used to take the audio information and video information of the noise source direction as input parameters, and obtain the noise source visualization sound field cloud map and noise classification and identification results respectively based on the pre-established abnormal sound source positioning model and the pre-established sound feature recognition model.

2. The factory boundary noise online monitoring and tracing system according to claim 1 is characterized in that: The sound feature recognition model includes a pre-processing sub-model and a neural network sub-model; The processing rules of the sound feature recognition model include: Input the audio frequency information of the noise source direction into the pre-processing sub-model, perform framing, windowing, fast Fourier transform and Mel transform processing in sequence, and obtain the corresponding Mel spectrum features; extracting the audible sound band spectrum features and the ultrasonic frequency band spectrum features of the audio information in the direction of the noise source based on the corresponding Mel spectrum features; The visualized sound field cloud image of the noise source, the audible frequency band spectrum characteristics and the ultrasonic frequency band spectrum characteristics of the audio information in the direction of the noise source are input into the neural network sub-model to obtain the noise classification and recognition results.

3. The factory boundary noise online monitoring and tracing system according to claim 2 is characterized in that: The neural network sub-model has a built-in noise recognition database, and the noise recognition database contains multiple noise types; and Visualized sound field cloud map of noise sources corresponding to each noise type, audible sound frequency band spectrum characteristics of audio information, and ultrasonic frequency band spectrum characteristics.

4. The factory boundary noise online monitoring and tracing system according to claim 1 is characterized in that: The data acquisition module includes an omnidirectional noise monitor, a directional microphone array, an acoustic imaging device and a meteorological instrument, and the omnidirectional noise monitor, the directional microphone array, the acoustic imaging device and the meteorological instrument are respectively communicatively connected to the data processing module; The omnidirectional noise monitor is used to monitor the comprehensive noise value at the factory boundary, wherein the comprehensive noise value at the factory boundary represents the real-time acquisition equivalent sound level of the corresponding sound environment functional area; The directional microphone array is used to obtain the equivalent sound levels of directional microphones in different directions; The acoustic imaging device is used to collect audio information and video information from the direction of the noise source; The meteorological instrument is used to monitor real-time meteorological condition information, which at least includes wind speed and direction parameters, temperature and humidity parameters, rainfall parameters and atmospheric pressure parameters.

5. The factory boundary noise online monitoring and tracing system according to claim 4 is characterized in that: The acoustic imaging device includes a two-dimensional microphone array and a visible light camera, and the two-dimensional microphone array and the visible light camera are respectively communicatively connected to the data processing module; The two-dimensional microphone array is used to collect audio information from the direction of the noise source; The visible light camera is used to collect video information in the direction of the noise source.

6. The factory boundary noise online monitoring and tracing system according to claim 5 is characterized in that: The audio information in the direction of the noise source includes the sound signals collected by each microphone in the two-dimensional microphone array; The processing rules of the abnormal sound source localization model include: Based on the beamforming algorithm, the sound signals collected by each microphone in the two-dimensional microphone array are filtered and weighted superpositioned to obtain the sound field distribution cloud map and the location of the noise source in the sound field distribution cloud map; The sound field distribution cloud map is superimposed with the corresponding visible light image in the video information of the noise source direction to obtain a visualized sound field cloud map of the noise source.

7. The factory boundary noise online monitoring and tracing system according to claim 5 is characterized in that: The arrangement of the two-dimensional microphone array includes at least a cross, a circle, a random distribution, a spiral and / or a nested arrangement.

8. The factory boundary noise online monitoring and tracing system according to claim 4 is characterized in that: The directional microphone array includes a plurality of directional microphones, and the plurality of directional microphones are communicatively connected to the data processing module. The factory boundary noise online monitoring and tracing system also includes a fixed pole, and the plurality of directional microphones, the omnidirectional noise monitor, the acoustic imaging device, and the meteorological instrument are respectively arranged on the fixed pole. A rotating pan-tilt platform is provided between the fixed pole and the acoustic imaging device, and the rotating pan-tilt platform is communicatively connected to the data processing module. The rotating pan-tilt platform is used to receive and rotate according to a data acquisition instruction, so that the acoustic imaging device can collect audio information and video information in the direction of the noise source.

9. The factory boundary noise online monitoring and tracing system according to claim 1 is characterized in that: The factory boundary noise judgment processing unit includes: A noise value comparison subunit is configured to compare the factory boundary comprehensive noise value with a corresponding preset noise threshold based on a collection time period and an acoustic environment functional zone corresponding to the factory boundary comprehensive noise value; a noise exceeding standard determination subunit, configured to determine that the factory boundary noise exceeds the standard if the factory boundary comprehensive noise value exceeds the corresponding preset noise threshold; The meteorological condition comparison subunit is used to compare the real-time meteorological condition information with the preset effective meteorological conditions when the factory boundary noise exceeds the standard, and based on the meteorological condition comparison results, determine whether to process the factory boundary noise.

10. The factory boundary noise online monitoring and tracing system according to claim 1 is characterized in that: It also includes an alarm module, which is in communication with the data processing module; The alarm module is used to issue an alarm message based on the noise source visual sound field cloud map and the noise classification and identification result.

11. The factory boundary noise online monitoring and tracing system according to claim 1 is characterized in that: It also includes a communication module, and the data acquisition module and the data processing module are communicatively connected through the communication module.

12. A method for online monitoring and tracing of factory boundary noise, characterized in that: The data processing module is executed, the data processing module is communicatively connected to the data acquisition module, the data acquisition module is used to collect factory boundary sound source information, the factory boundary sound source information at least includes the factory boundary comprehensive noise value, real-time meteorological condition information and the equivalent sound level of directional microphones in different directions; The method comprises: Determining whether to process the factory boundary noise based on the factory boundary comprehensive noise value and the real-time meteorological condition information; When determining to process factory boundary noise, based on the equivalent sound levels of directional microphones in different directions, determine the direction corresponding to the directional microphone with the maximum sound level as the noise source direction; Based on the direction of the noise source, a data acquisition instruction is generated and sent to the data acquisition module, and the audio and video information of the direction of the noise source collected in real time and fed back by the data acquisition module is recovered; The audio information and video information of the noise source direction are used as input parameters, and based on a pre-established abnormal sound source localization model and a pre-established sound feature recognition model, a noise source visualization sound field cloud map and a noise classification recognition result are obtained respectively.

13. The method for online monitoring and tracing the source of factory boundary noise according to claim 12, characterized in that: The determining whether to process the factory boundary noise based on the factory boundary comprehensive noise value and the real-time meteorological condition information includes: Based on the collection time period and the acoustic environment functional zone corresponding to the factory boundary comprehensive noise value, the factory boundary comprehensive noise value is compared with the corresponding preset noise threshold; If the comprehensive noise value at the factory boundary exceeds the corresponding preset noise threshold, it is determined that the factory boundary noise exceeds the standard; When the factory boundary noise exceeds the standard, the real-time meteorological condition information is compared with the preset effective meteorological conditions, and based on the meteorological condition comparison results, it is determined whether the factory boundary noise should be processed.

14. The method for online monitoring and tracing the source of factory boundary noise according to claim 12, characterized in that: The data acquisition module includes a two-dimensional microphone array, and the audio information in the direction of the noise source includes the sound signals collected by each microphone in the two-dimensional microphone array; The processing rules of the abnormal sound source localization model include: Based on the beamforming algorithm, the sound signals collected by each microphone in the two-dimensional microphone array are filtered and weighted superpositioned to obtain the sound field distribution cloud map and the location of the noise source in the sound field distribution cloud map; The sound field distribution cloud map is superimposed with the corresponding visible light image in the video information of the noise source direction to obtain a visualized sound field cloud map of the noise source.

15. The method for online monitoring and tracing the source of factory boundary noise according to claim 12, characterized in that: The sound feature recognition model includes a pre-processing sub-model and a neural network sub-model; The processing rules of the sound feature recognition model include: Input the audio frequency information of the noise source direction into the pre-processing sub-model, perform framing, windowing, fast Fourier transform and Mel transform processing in sequence, and obtain the corresponding Mel spectrum features; extracting the audible sound band spectrum features and the ultrasonic frequency band spectrum features of the audio information in the direction of the noise source based on the corresponding Mel spectrum features; The visualized sound field cloud image of the noise source, the audible frequency band spectrum characteristics and the ultrasonic frequency band spectrum characteristics of the audio information in the direction of the noise source are input into the neural network sub-model to obtain the noise classification and recognition results.

16. A machine-readable storage medium having instructions stored thereon, characterized in that: When executed by a processor, the instruction causes the processor to be configured to execute the method for online monitoring and tracing source of factory boundary noise as described in any one of claims 12 to 15.

17. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for online monitoring and tracing the source of factory boundary noise as described in any one of claims 12 to 15 is implemented.

Images