A method for intelligently identifying urban noise sources based on neural networks

Abstract

The present invention discloses a method for intelligently identifying urban noise sources based on a neural network, which relates to the technical field of noise identification. Aiming at the technical problems that the current urban noise source identification method is difficult to achieve real-time detection of noise sources, resulting in a decrease in the accuracy of noise source category identification, making the difficulty of noise source classification relatively high and unable to meet the intelligent identification requirements of noise sources, the method includes the following steps: establishing an urban noise source database, establishing an urban noise basic characteristic parameter database, analyzing based on the urban noise source database to establish a standard data set of noise source characteristic parameters, determining the noise source characteristic parameters, determining the target area, constructing an urban noise monitoring system at the center of the target area, and measuring the characteristic parameter vector of the noise source in the target area. By using the neural network algorithm, the present invention automatically constructs an intelligent noise source identification model to assist in the discrimination of different noise sources, and has a relatively high recognition rate.

Description

Technical Field

[0001] The present invention relates to the technical field of noise recognition, and more specifically, to a method for intelligently identifying urban noise sources based on a neural network. Background Art

[0002] A noise source is the origin of noise generation. Intelligent identification of noise sources is a prerequisite for noise source analysis and the construction of urban sound environment monitoring station networks. However, relevant technical specifications and technological development are significantly lagging behind the speed of urban development. Intelligent identification of noise sources is a prerequisite for noise source monitoring and control, directly affecting the management and service levels of the urban sound environment;

[0003] However, for the existing intelligent noise source identification methods, in the face of complex and variable noise source categories, conventional identification methods are difficult to meet the requirements of intelligent noise source identification. Due to insufficient noise source monitoring equipment, the demand for rapid, comprehensive, and real-time detection cannot be satisfied. Therefore, current noise source identification mainly relies on human ear identification and the identification of sound spectrum characteristics, and the accuracy of human ear identification alone is low. At the same time, the sound spectrum characteristics of noise sources have small differences, and it is difficult to classify noise sources. Conventional detection methods are not easy to achieve the identification and classification of noise sources. In view of this, we propose a method for intelligently identifying urban noise sources based on a neural network. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for intelligently identifying urban noise sources based on a neural network, so as to solve the technical problems that the current urban noise source identification method is difficult to achieve real-time detection of noise sources, resulting in a decrease in the accuracy of noise source category identification, making it difficult to classify noise sources, and unable to meet the requirements of intelligent noise source identification.

[0005] To solve the above technical problems, the present invention provides the following technical solution: A method for intelligently identifying urban noise sources based on a neural network, including the following steps:

[0006] S1: Establish a database of urban noise sources;

[0007] S2: Establish a database of basic characteristic parameters of urban noise;

[0008] S3: Analyze based on the database of urban noise sources to establish a standard data set of noise source characteristic parameters and determine the noise source characteristic parameters;

[0009] S4: Determine the target area, construct an urban noise monitoring system at the center of the target area, and measure the characteristic parameter vector of the noise source in the target area;

[0010] S5: Calculate the radiation value of the noise source in the target area, and its formula is:

[0011] ;

[0012] In the formula, is the sampling time, is the time when the sound source localization sensor detects the maximum noise at position , is the maximum noise detected by the sound source localization sensor at position , is the weight coefficient;

[0013] S6: Calculate the feature vector of the target area , , in the formula, is the geographical coordinate of the sound source localization sensor, is the radiation value of the noise source in the target area, is the type of the noise source in the target area;

[0014] S7: Label the noise source in the target area;

[0015] S8: Establish a neural network based on the labeled noise source parameters in the target area to establish a noise source intelligent recognition model;

[0016] S9: In the target area, input the noise source parameters in the target area into the noise source intelligent recognition model to identify the type of the target noise source.

[0017] Through the analysis and identification of six types of noise sources in the city, the present invention establishes a noise source database, a basic feature parameter database of noise sources, and determines a standard data set of noise source feature parameters. By calculating the radiation value and feature vector of the noise source, a neural network is established, and according to the accuracy rate, the best neural network model is extracted, so as to establish a noise source intelligent recognition model, which can assist in the discrimination of different noise sources, realize the extraction of feature parameters of different noise sources, quantitatively calculate the noise radiation value of different noise sources, and use the neural network algorithm to automatically construct a noise source intelligent recognition model. In actual detection, by calculating the feature vector of the noise source and inputting the feature vector into the noise source intelligent recognition model, the type of the noise source can be intelligently recognized, and a relatively high recognition rate can be obtained.

[0018] Preferably, the step S1 further includes the following steps:

[0019] S101: Collect urban noise source data;

[0020] Among them, the noise source data includes the name of the sound source, the category of the sound source, the attribute of the sound source, the location of the sound source, and the shape of the sound source. According to the category attribute of the sound source, the noise source data is divided into six types: traffic noise source, industrial noise source, construction noise source, sanitation machinery noise source, entertainment noise source, and human voice noise source;

[0021] S102: Classify the sound source data into noise sources and non-noise sources according to the sound source attributes;

[0022] S103: Determine the relative positions of each noise source within the city according to the sound source positions;

[0023] Among them, the sound source position includes the longitude and latitude of the sound source geographical location and the specific position within the city

[0024] S104: Determine the area of the noise source according to the sound source shape.

[0025] Preferably, step S3 further includes the following steps:

[0026] S301: Determine the standard data set of sound source characteristic parameters corresponding to the radiation values of different types of noise sources;

[0027] S302: Determine the distance between the noise source and the sensor, establish the standard data set of the radiation value of the sensor and the noise source to be measured, and obtain the distance range between the noise source and the sensor of the standard data set of the radiation value of the sensor and the noise source to be measured.

[0028] Preferably, the standard data set of the sound source characteristic parameters includes:

[0029] Traffic noise source radiation value: , where is the radiation value of the traffic noise source, representing the sound power level radiated from the source point, represents the sound source power corresponding to the maximum value of the noise source, represents the vehicle speed corresponding to the maximum value of the noise source, represents the temperature and humidity corresponding to the maximum value of the noise source, respectively represent the temperature and humidity constants corresponding to the traffic noise source, represents the noise source in space axis and axis corresponding height;

[0030] Industrial noise source radiation value: , where is the radiation value of the industrial noise source, represents the mechanical power or electric power corresponding to the maximum value of the noise source;

[0031] Construction noise source radiation value: , where is the radiation value of the construction noise source, respectively represent the temperature and humidity constants corresponding to the construction noise source;

[0032] Sanitation machinery noise source radiation value: , where respectively represent the temperature and humidity constants corresponding to the noise sources of sanitation machinery;

[0033] Radiation value of entertainment noise source: , where is the radiation value of the entertainment noise source, represents the number of people corresponding to the maximum value of this type of noise source;

[0034] Radiation value of human voice noise source: , where is the radiation value of the human voice noise source.

[0035] Preferably, the urban noise monitoring system consists of sound source localization sensors to construct a noise monitoring network.

[0036] Preferably, the step S4 further includes the following steps:

[0037] S401: First, determine the target area, use the sound source localization sensors to construct a noise monitoring network, determine the number and position of the sensors, and the characteristic parameters of the noise sources in the target area measured by each sound source localization sensor;

[0038] Among them, the characteristic parameters of the noise sources in the target area include noise frequency and noise sound level;

[0039] S402: Input the obtained characteristic parameters into the noise source basic characteristic parameter database to calculate the characteristic parameter vector of the noise sources in the target area;

[0040] S403: Use the sound source localization sensors to obtain the actual positions of the noise sources in the target area;

[0041] S404: Establish the characteristic vector of the noise sources in the target area according to the characteristic parameter vector of the noise sources in the target area.

[0042] Preferably, the noise sources in the target area are labeled in the following way: input the characteristic vector of the target area into the urban noise source characteristic parameter database, and match the urban noise source parameter that is most similar to the characteristic vector of the target area in the urban noise source characteristic parameter database, mark the corresponding urban noise source parameter, and then the type of the noise sources in the target area can be labeled.

[0043] Preferably, the step S8 further includes the following steps:

[0044] S801: Use the labeled noise source parameters in the target area as the training samples of the neural network;

[0045] S802: Input the sample parameters into the neural network to determine the weights between the neural element nodes in each layer of the neural network AND threshold and use the test sample set to test the neural network to determine the error function of the neural network ;

[0046] S803: Calculate the error function based on the actual value output by the neural network and adjust the threshold and the weight , and its formula is:

[0047] ;

[0048] ;

[0049] In the formula, is the number of iterations, is the training learning rate;

[0050] When , ; When ;

[0051] Among them, when the output error and the predefined error , that is, , the training is completed and the iteration is exited; otherwise, when the output error is less than the preset error, the sample data is input into the neural network for training, and when the output error is greater than the preset error, go to step S802;

[0052] S804: After the training is completed, the intelligent recognition model of the target area noise source is obtained.

[0053] Preferably, step S802 further includes the following steps:

[0054] S802a: Multiply each training sample feature parameter vector by the output weight , and its formula is:

[0055] + ;

[0056] In the formula, is the product of each training sample feature parameter vector and the output weight , is the feature vector of each target area;

[0057] S802b: Obtain the actual value output by the neural network according to ;

[0058] Suppose a function is used as the activation function, then , where represents the natural constant;

[0059] Among them, when the actual value and at time correspond to the predicted value of the th sample, it satisfies ; when the actual value and the predicted value at time satisfy , set the iteration termination condition, otherwise, go to step S803.

[0060] Preferably, when establishing the intelligent identification model of the noise source, an intelligent classification system is established. The intelligent classification system consists of a sensor layer, a collection and processing layer, and an application layer. The intelligent classification system inputs the noise source parameters of the target area into the application layer. The application layer compares the noise source parameters of the target area with the established intelligent identification model of the noise source of the target area to identify the type of the target noise source .

[0061] Compared with the prior art, the beneficial effects of the present invention are:

[0062] 1. By analyzing and identifying six types of noise sources in the city, the present invention establishes a noise source database, a basic characteristic parameter database of noise sources, and determines a standard data set of noise source characteristic parameters. By calculating the radiation value and characteristic vector of the noise source, a neural network is established, and according to the accuracy rate, the best neural network model is extracted, so as to establish an intelligent identification model of the noise source, which can assist in the discrimination of different noise sources, realize the extraction of characteristic parameters of different noise sources, quantitatively calculate the noise radiation value of different noise sources, and use the neural network algorithm to automatically construct an intelligent identification model of the noise source. In actual detection, by calculating the characteristic vector of the noise source and inputting the characteristic vector into the intelligent identification model of the noise source, the type of the noise source can be intelligently identified, and a high recognition rate can be obtained.

[0063] 2. By quantifying the characteristics of different sound sources within the city scope, the present invention extracts the characteristics of urban noise sources, establishes a basic characteristic parameter database of noise sources based on different noise sources, and realizes the identification of noise sources through the establishment of an intelligent identification model of the noise source, reducing the difficulty of noise source identification. This method has practical significance for the identification of urban noise sources.

[0064] 3. Based on the acquisition of sound source data, the present invention constructs a noise source database and a database of basic characteristic parameters of urban noise, performs data processing to obtain datasets of different types of noise sources, analyzes the data of different noise sources, and constructs a neural network. This method solves the problem of difficult discrimination and classification of noise sources in urban noise monitoring and has practical significance for the classified monitoring of urban noise sources. Detailed implementation manner

[0065] A method for intelligently identifying urban noise sources based on a neural network according to the present invention includes the following steps:

[0066] S1: Establish a database of urban noise sources;

[0067] S101: Collect data of urban noise sources;

[0068] In an embodiment of the present invention, the noise source data includes the name of the sound source, the category of the sound source, the attributes of the sound source, the location of the sound source, and the shape of the sound source;

[0069] In an embodiment of the present invention, the noise source data is divided into six types according to the sound source category attributes: traffic noise sources, industrial noise sources, construction noise sources, sanitation machinery noise sources, entertainment noise sources, and human voice noise sources;

[0070] S102: According to the attributes of the sound source, divide the sound source data into noise sources and non-noise sources;

[0071] S103: According to the location of the sound source, determine the relative positions of each noise source within the city;

[0072] In an embodiment of the present invention, the location of the sound source includes the longitude and latitude of the geographical location of the sound source and the specific location within the city;

[0073] S104: According to the shape of the sound source, determine the area of the noise source;

[0074] S2: Establish a database of basic characteristic parameters of urban noise;

[0075] In an embodiment of the present invention, the database of basic characteristic parameters of urban noise includes wind speed, air temperature, temperature and humidity, height of the noise source, vehicle displacement, power of the mechanical noise source, vehicle speed, and population number;

[0076] In an embodiment of the present invention, the height of the noise source refers to the distance between the height of the mechanical noise source and the ground. Taking the construction noise source as an example, it specifically refers to the distance between the height of the mechanical noise source corresponding to the maximum noise level generated by the noise source point and the ground; the temperature and humidity are the temperature and humidity values of the environment around the noise source. Taking the construction noise source as an example, it specifically refers to the temperature and humidity values of the environment corresponding to the maximum noise level generated by the mechanical noise source point; the vehicle speed is obtained through traffic monitoring equipment;

[0077] Based on the acquisition of sound source data, the present invention constructs a noise source database and a database of basic characteristic parameters of urban noise, processes the data to obtain data sets of different types of noise sources, analyzes the data of different noise sources, constructs a neural network, which solves the problem of difficult discrimination and classification of noise sources in urban noise monitoring and has practical significance for the classification monitoring of urban noise sources.

[0078] S3: Establish a standard data set of noise source characteristic parameters;

[0079] Based on the above urban noise source database, analyze the collected urban noise source data to determine the noise source characteristic parameters;

[0080] S301: Determine the standard data set of noise source characteristic parameters corresponding to the radiation values of different types of noise sources:

[0081] Traffic noise source radiation value: , where is the radiation value of the traffic noise source, representing the sound power level radiated from the source point, represents the sound source power corresponding to the maximum value of the noise source, represents the vehicle speed corresponding to the maximum value of the noise source, represents the temperature and humidity corresponding to the maximum value of the noise source, respectively represent the temperature and humidity constants corresponding to the traffic noise source, represents the noise source in space axis and axis corresponding height;

[0082] Industrial noise source radiation value: , where is the radiation value of the industrial noise source, represents the mechanical power or electric power corresponding to the maximum value of the noise source;

[0083] Construction noise source radiation value: , where is the radiation value of the construction noise source, respectively represent the temperature and humidity constants corresponding to the construction noise source;

[0084] Sanitation machinery noise source radiation value: , where respectively represent the temperature and humidity constants corresponding to the sanitation machinery noise source;

[0085] Entertainment noise source radiation value: , where is the radiation value of the entertainment noise source, represents the number of people corresponding to the maximum value of this type of noise source;

[0086] Radiation value of human voice noise source: , where Is the radiation value of the human voice noise source;

[0087] S302: Determine the distance between the noise source and the sensor, establish a standard data set of radiation values ​​between the sensor and the noise source to be measured, and obtain the distance range between the noise source and the sensor in the standard data set of radiation values ​​between the sensor and the noise source to be measured;

[0088] S4: Determine the target area and build an urban noise monitoring system in the center of the target area. A noise monitoring network is constructed by using a sound source localization sensor, and the characteristic parameter vector of the noise source in the target area is measured by the sound source localization sensor;

[0089] S401: First, determine the target area, use sound source positioning sensors to build a noise monitoring network, determine the number and location of sensors, and measure each sound source positioning sensor to obtain characteristic parameters of the noise source in the target area;

[0090] In the embodiment of the present invention, the characteristic parameters of the noise source in the target area include the noise frequency and the noise level. When measuring the noise level, the sampling time needs to be selected. , during which the maximum sound level in the area is monitored and recorded as ;

[0091] S402: Input the obtained characteristic parameters into the noise source basic characteristic parameter database, and calculate and obtain the characteristic parameter vector of the noise source in the target area;

[0092] S403: Obtaining the actual position of the noise source in the target area using a sound source positioning sensor;

[0093] S404: establishing a target area noise source characteristic vector according to the characteristic parameter vector of the target area noise source;

[0094] The present invention quantifies the characteristics of different sound sources in the city, extracts the characteristics of urban noise sources, establishes a noise source basic characteristic parameter database based on different noise sources, and realizes noise source identification by establishing an intelligent noise source identification model, thereby reducing the difficulty of noise source identification. This method has practical significance for urban noise source identification.

[0095] S5: Calculate the radiation value of the noise source in the target area. The formula is:

[0096] ;

[0097] In the formula, is the sampling time, Locate the sensor at the location of the sound source The time when the maximum noise is detected is the maximum noise detected by the sound source localization sensor at the position ; is the weight coefficient;

[0098] S6: Calculate the target area feature vector , , where is the geographical coordinate of the sound source localization sensor, is the radiation value of the noise source in the target area, is the type of the noise source in the target area;

[0099] S7: Label the noise source in the target area;

[0100] Input the target area feature vector into the urban noise source characteristic parameter database, match the urban noise source parameter most similar to the target area feature vector in the urban noise source characteristic parameter database, mark the corresponding urban noise source parameter, and then the type of the noise source in the target area can be labeled;

[0101] S8: Establish a neural network based on the labeled target area noise source parameters to establish a noise source intelligent recognition model;

[0102] S801: Use the labeled target area noise source parameters as the training samples of the neural network; S802: Input the sample parameters into the neural network to determine the weights and threshold values between the neural element nodes in each layer of the neural network, and use the test sample set to test the neural network to determine the error function of the neural network;

[0103] S802a: Multiply each training sample feature parameter vector by the output weight , and its formula is:

[0104] + ;

[0105] where is the product of each training sample feature parameter vector and the output weight , is the feature vector of each target area;

[0106] S802b: According to , obtain the actual value output by the neural network;

[0107] Suppose If the function is used as the activation function, then , where represents the natural constant;

[0108] When the actual value and the predicted value corresponding to the th sample at time satisfy ; when the actual value and the predicted value at time satisfy , set the iteration termination condition, otherwise, go to step S803;

[0109] S803: According to the actual value output by the neural network, calculate the error function , and adjust the threshold and the weights , and its formula is:

[0110] ;

[0111] ;

[0112] where is the number of iterations, is the training learning rate;

[0113] When , ; when ;

[0114] In the embodiment of the present invention, when the output error and the predefined error , that is , the training is completed and the iteration is exited; otherwise, when the output error is less than the preset error, the sample data is input into the neural network for training, and when the output error is greater than the preset error, go to step S802;

[0115] S804: After the training is completed, the intelligent identification model of the target area noise source is obtained;

[0116] S9: In the target area, input the target area noise source parameters into the noise source intelligent identification model;

[0117] In the embodiment of the present invention, when establishing the intelligent identification model of the target area noise source, an intelligent classification system is established, and the establishment of the intelligent classification system consists of a sensor layer, an acquisition and processing layer, and an application layer.

[0118] In an embodiment of the present invention, the intelligent classification system inputs the target area noise source parameters into the application layer, and the application layer compares the target area noise source parameters with the established intelligent recognition model of the target area noise source to identify the type of the target noise source. .

[0119] The embodiments disclosed in the present invention are preferred embodiments, but not limited thereto. Those of ordinary skill in the art can easily understand the spirit of the present invention based on the above embodiments and make different extensions and changes. However, as long as they do not depart from the spirit of the present invention, they are within the protection scope of the present invention.

Claims

1. A method for intelligently identifying urban noise sources based on neural networks, characterized in that: The following steps are involved: S1: Establish urban noise source database; S2: Establish a database of basic characteristic parameters of urban noise; S3: Analyze based on the urban noise source database to establish a standard data set of noise source characteristic parameters and determine the noise source characteristic parameters; S4: Determine the target area, build an urban noise monitoring system in the center of the target area, and measure the characteristic parameter vector of the noise source in the target area; S5: Calculate the radiation value of the noise source in the target area. The formula is: ； In the formula, is the sampling time, Locate the sensor at the location of the sound source The time when the maximum noise is detected, Locate the sensor at the location of the sound source The maximum noise detected at is the weight coefficient; S6: Calculate the target area feature vector , , where The geographical coordinates of the sensor locating the sound source, is the radiation value of the noise source in the target area, is the type of noise source in the target area; S7: Mark the noise sources in the target area; S8: Establish a neural network based on the marked noise source parameters of the target area and establish a noise source intelligent identification model; S9: In the target area, the noise source parameters of the target area are input into the noise source intelligent identification model to identify the type of the target noise source.

2. The method for intelligently identifying urban noise sources based on a neural network according to claim 1, characterized in that: The step S1 also includes the following steps: S101: Collect urban noise source data; The noise source data includes the name of the sound source, the category of the sound source, the attribute of the sound source, the location of the sound source, and the shape of the sound source. According to the attribute of the sound source category, the noise source data is divided into six types: traffic noise source, industrial noise source, construction noise source, sanitation machinery noise source, entertainment noise source, and human voice noise source; S102: Classify the sound source data into noise sources and non-noise sources according to sound source attributes; S103: Determine the relative position of each noise source in the city according to the position of the sound source; The sound source location includes the latitude and longitude of the sound source's geographical location and its specific location in the city. S104: Determine the area of ​​the noise source according to the shape of the sound source.

3. The method for intelligently identifying urban noise sources based on a neural network according to claim 2 is characterized in that: The step S3 also includes the following steps: S301: Determine a standard data set of noise source characteristic parameters corresponding to radiation values ​​of different types of noise sources; S302: Determine the distance between the noise source and the sensor, establish a standard data set of radiation values ​​between the sensor and the noise source to be measured, and obtain the distance range between the noise source and the sensor in the standard data set of radiation values ​​between the sensor and the noise source to be measured.

4. The method for intelligently identifying urban noise sources based on a neural network according to claim 3 is characterized in that: The noise source characteristic parameter standard data set includes: Traffic noise source radiation value: , where is the radiation value of the traffic noise source, indicating the sound power level radiated by the source point. Indicates the sound source power corresponding to the maximum value of the noise source, represents the vehicle speed corresponding to the maximum value of the noise source, Indicates the temperature and humidity corresponding to the maximum value of the noise source, They represent the temperature and humidity constants corresponding to the traffic noise sources, Indicates that the noise source is spatially Axis and The axis corresponds to the height; Radiation values ​​of industrial noise sources: , where is the radiation value of the industrial noise source, Indicates the mechanical power or electrical power corresponding to the maximum value of the noise source; Radiation value of construction noise source: , where is the radiation value of the construction noise source, They represent the temperature and humidity constants corresponding to the construction noise sources respectively; Radiation value of noise source of sanitation machinery: , where They represent the temperature and humidity constants corresponding to the noise sources of sanitation machinery respectively; Entertainment noise source radiation value: , where is the radiation value of the entertainment noise source, Indicates the number of people corresponding to the maximum value of this type of noise source; Radiation value of human voice noise source: , where The radiation value of the human voice noise source.

5. The method for intelligently identifying urban noise sources based on a neural network according to claim 4 is characterized in that: The urban noise monitoring system consists of The noise monitoring network is constructed by using a sound source localization sensor.

6. The method for intelligently identifying urban noise sources based on a neural network according to claim 5, characterized in that: The step S4 also includes the following steps: S401: First, determine the target area, use sound source positioning sensors to build a noise monitoring network, determine the number and location of sensors, and measure each sound source positioning sensor to obtain characteristic parameters of the noise source in the target area; The characteristic parameters of the noise source in the target area include noise frequency and noise level; S402: Input the obtained characteristic parameters into the noise source basic characteristic parameter database, and calculate and obtain the characteristic parameter vector of the noise source in the target area; S403: Obtaining the actual position of the noise source in the target area using a sound source positioning sensor; S404: Establishing a target area noise source characteristic vector according to the characteristic parameter vector of the target area noise source.

7. The method for intelligently identifying urban noise sources based on a neural network according to claim 6, characterized in that: The noise source in the target area is marked in the following way: the feature vector of the target area Input into the urban noise source characteristic parameter database, match the characteristic vector of the target area in the urban noise source characteristic parameter database The most similar urban noise source parameters can be marked by marking the corresponding urban noise source parameters to label the noise source type in the target area.

8. The method for intelligently identifying urban noise sources based on a neural network according to claim 7, characterized in that: The step S8 also includes the following steps: S801: Using the marked noise source parameters of the target area as training samples of the neural network; S802: Input the sample parameters into the neural network to determine the weights between the nodes of each layer of the neural network Threshold , and use the test sample set to test the neural network and determine the error function of the neural network ; S803: Output actual value according to neural network , calculate the error function , and adjust the threshold and weights , the formula is: ； ； In the formula, is the number of iterations, is the training learning rate; when hour, ; hour, ; When the output error is equal to the predefined error ,Right now , the training is completed and the iteration is exited; otherwise, when the output error is less than the preset error, the sample data is input into the neural network for training, and when the output error is greater than the preset error, the process proceeds to step S802; S804: After the training is completed, an intelligent recognition model of noise sources in the target area is obtained.

9. The method for intelligently identifying urban noise sources based on a neural network according to claim 8, characterized in that: The step S802 further includes the following steps: S802a: For each training sample feature parameter vector and output weights The formula for the product is: + ； In the formula, For each training sample feature parameter vector and output weights The product of is the feature vector for each target area; S802b: According to , get the actual value of the neural network output ; If adopted Function as activation function, then , where Expressed as a natural constant; Among them, when the actual value and at the moment Time corresponds to The predicted value of samples satisfy ; Actual value and at the moment The predicted value at satisfy When , set the iteration termination condition, otherwise, go to step S803.

10. The method for intelligently identifying urban noise sources based on neural networks according to claim 9, characterized in that: When establishing the noise source intelligent identification model, an intelligent classification system is established. The intelligent classification system consists of a sensor layer, an acquisition processing layer, and an application layer. The intelligent classification system inputs the target area noise source parameters into the application layer. The application layer compares the target area noise source parameters with the established target area noise source intelligent identification model to identify the target noise source type. .

Images