An urban road traffic noise analysis method and system

Abstract

The present invention discloses a method and system for analyzing urban road traffic noise, which relates to the technical field of noise analysis. It includes setting up noise monitoring equipment to continuously collect road traffic noise data; constructing a noise annoyance prediction model to predict the noise annoyance of residents in each area; counting the high annoyance rate of each area, adopting a dynamic time-segmented high annoyance rate calculation method to analyze different time periods respectively, and introducing a time correction term and a regional condition correction term; based on the noise annoyance prediction model and the high annoyance rate calculation results, putting forward suggestions and measures for urban road traffic noise control. The present invention can make precise adjustments according to the noise levels and regional conditions at different times, providing a more valuable reference basis for noise prevention and control decisions.

Description

Technical Field

[0001] The present invention relates to the technical field of noise analysis, and particularly to a method and system for analyzing urban road traffic noise. Background Art

[0002] In recent years, the problem of urban environmental noise pollution has been increasingly concerned by all sectors of society, and noise pollution prevention and control has become an important and indispensable part of ecological civilization construction and environmental protection work. As the main noise source affecting the urban sound environment quality level, road traffic noise has the characteristics of wide coverage, high noise intensity, and high treatment difficulty, seriously affecting the quality of residents' lives and being frequently reported by residents. Road traffic noise prevention and control is the top priority for improving the urban sound environment quality and building a "quiet home".

[0003] In the process of noise analysis, the existing technology lacks an accurate annoyance evaluation mechanism. There are significant differences in residents' perceptions of traffic noise, and the noise impacts on residents in different time periods and regions are also different. Traditional methods are difficult to accurately capture this dynamic change. The vast majority of existing technologies only evaluate the urban noise pollution level through static analysis of noise data, lacking consideration of residents' subjective noise annoyance. There are no personalized and detailed means for noise control, and many control schemes cannot meet the specific needs of residents in actual operation, which severely limits the effectiveness of existing technologies in practical applications. Summary of the Invention

[0004] In view of the existing problems in noise analysis, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is how to evaluate the noise impacts in different time periods and regions.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a method for analyzing urban road traffic noise, which includes setting noise monitoring devices to continuously collect road traffic noise data; constructing a noise annoyance prediction model to predict the noise annoyance of residents in each region; counting the high annoyance rates of each region, using a dynamic time-segmented high annoyance rate calculation method to analyze different time periods respectively, and introducing a time correction term and a regional condition correction term; and proposing suggestions and measures for urban road traffic noise control based on the noise annoyance prediction model and the high annoyance rate calculation results.

[0008] As a preferred embodiment of the urban road traffic noise analysis method of the present invention, wherein: the steps of constructing a noise annoyance prediction model to predict the noise annoyance of residents in each area include: obtaining the noise time series data of the monitoring points and extracting the noise characteristic values in different time periods; collecting the population structure data, dividing the areas according to the population density, and generating the regional population characteristic set. ; combining the noise characteristic values with the population characteristic set, establishing a preliminary correspondence between the noise and the population characteristics according to different time periods t and areas x, and forming an input data matrix: ; using a fuzzy neural network to process the data matrix ; training a noise annoyance prediction model based on the noise levels and population sensitivities in different time periods, wherein the output of the fuzzy neural network is the noise annoyance. ; optimizing the noise annoyance prediction model, calculating the annoyance scores of different resident groups in a specific noise environment, and obtaining the noise annoyance scores of the residents in each area; performing time correction on the noise annoyance of each area according to the noise annoyance scores and the time series changes to obtain the dynamic prediction results of the noise annoyance.

[0009] As a preferred embodiment of the urban road traffic noise analysis method of the present invention, wherein: the extraction of the noise characteristic values in different time periods includes: the formula for the A-weighted sound level is:

[0010] ;

[0011] wherein, is the noise pressure level at time t, and T is the length of the time period; the formula for the day-night equivalent sound level is:

[0012] ;

[0013] wherein, and respectively represent the A-weighted sound levels during the day and at night.

[0014] As a preferred embodiment of the urban road traffic noise analysis method of the present invention, wherein: the calculation process of the annoyance score is as follows:

[0015] ;

[0016] wherein, , , are all regression coefficients; is the time-related correction term; the time correction of the noise annoyance of each area, wherein the dynamic noise annoyance prediction formula is:

[0017] ;

[0018] Wherein, is the time variation, is the time correction factor.

[0019] As a preferred embodiment of the urban road traffic noise analysis method of the present invention, wherein: the dynamic time - segmented high annoyance rate calculation method includes the following steps: divide 24 hours of a day into a night - time rest period, a daytime rest period, and a daytime working period; take the slope of the fitted straight line of the difference between the high annoyance rate of residents in the night - time rest period and the high annoyance rate in the working period as 3, and take the slope of the fitted straight line of the difference between the high annoyance rate in the daytime rest period and the high annoyance rate in the working period as 1, and obtain the time correction term as follows:

[0020] ;

[0021] Wherein, is the high annoyance rate time correction term; is the correction rate.

[0022] As a preferred embodiment of the urban road traffic noise analysis method of the present invention, wherein: the regional condition correction term includes the following: the regional condition correction term is composed of the acoustic function zoning and the age structure of the regional residents; the correction amount of the age structure of the residents is shown in the following formula:

[0023] ;

[0024] Wherein, is the high annoyance rate age structure correction term; m is the sensitive population in the region; the correction amount of the acoustic function zoning is shown in the following formula:

[0025] ;

[0026] ;

[0027] Wherein, is the correction amount of the acoustic function zoning when the area to be predicted is a class 1 acoustic function area; is the correction amount of the acoustic function zoning when the area to be predicted is a class 4a acoustic function area; L is the continuous equivalent A - weighted sound level of the road noise.

[0028] As a preferred embodiment of the urban road traffic noise analysis method of the present invention, wherein: the form of the corrected high annoyance rate model is as follows:

[0029] .

[0030] In a second aspect, an embodiment of the present invention provides an urban road traffic noise analysis system, which includes: a noise monitoring module for setting up noise monitoring devices to continuously collect road traffic noise data; a noise annoyance prediction module for constructing a noise annoyance prediction model to predict the noise annoyance levels of residents in each area; a high annoyance rate statistical analysis module for statistically analyzing the high annoyance rates of each area, using a dynamic time-segmented high annoyance rate calculation method to analyze different time periods respectively, and introducing a time correction term and a regional condition correction term; a noise control suggestion generation module for proposing suggestions and measures for urban road traffic noise control based on the noise annoyance prediction model and the high annoyance rate calculation results, and summarizing the analysis results.

[0031] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and: when the computer program instructions are executed by the processor, the steps of the urban road traffic noise analysis method as described in the first aspect of the present invention are implemented.

[0032] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and: when the computer program instructions are executed by the processor, the steps of the urban road traffic noise analysis method as described in the first aspect of the present invention are implemented.

[0033] The beneficial effects of the present invention are as follows: The present invention not only focuses on the physical intensity of noise, but also introduces a subjective evaluation index - annoyance level, and combines factors such as regional characteristics and time characteristics to dynamically predict the noise annoyance levels of residents in different areas and different time periods. Compared with the existing static noise analysis methods, the prediction model constructed by the present invention can more accurately reflect the actual feelings of residents towards traffic noise. In addition, the dynamic calculation method of the high annoyance rate of the present invention can be accurately adjusted according to the noise levels and regional conditions in different time periods, providing a more valuable reference basis for noise prevention and control decisions. Description of the Drawings

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0035] Figure 1 It is a flowchart of the urban road traffic noise analysis method.

[0036] Figure 2 It is a comparison of high annoyance rate fitting curves (measured data and EU data).

[0037] Figure 3It is the difference in the high annoyance rate between the rest time and the working time.

[0038] Figure 4 It is the difference in the high annoyance rate between different regions.

[0039] Figure 5 It is the prediction of the noise exposure level of residents and the high annoyance rate. Specific implementation manners

[0040] To make the above objects, features and advantages of the present invention more obvious and understandable, the specific implementation manners of the present invention will be described in detail below with reference to the accompanying drawings of the specification.

[0041] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention may be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0042] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure or characteristic that may be included in at least one implementation manner of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that exclude each other with other embodiments.

[0043] Embodiment 1

[0044] Refer to Figures 1 to 4 , which is the first embodiment of the present invention. This embodiment provides a method for analyzing urban road traffic noise. As Figure 1 shown, it includes

[0045] S1: Set noise monitoring devices at multiple monitoring points around urban roads, and continuously collect road traffic noise data, including the continuous equivalent sound level of noise at different time periods, etc.

[0046] First, according to the characteristics of urban roads, select areas with strong noise sources (such as main roads with large traffic flow, intersections, congested sections, etc.) to set noise monitoring points. At the same time, considering the comprehensiveness of monitoring, it is necessary to evenly arrange monitoring points at different positions on both sides of the road, near residential areas, commercial areas, green belts, etc., in order to obtain the noise impact in different regions.

[0047] According to the length of the road, the height and density of surrounding buildings, and the population density, reasonably determine the number and distribution of monitoring points. For example, set a noise monitoring point within a range of every 500 meters to 1 kilometer, and densify the distribution in special areas (such as densely populated residential areas, hospitals, schools, etc.).

[0048] Use noise monitoring instruments that comply with national standards (such as GB 3096, "Ambient Noise Quality Standard"). The equipment should be able to continuously measure A-weighted sound level noise data and record the time series of the noise to analyze the noise changes in different time periods. The dynamic range of the equipment should cover the common sound levels of road traffic noise (50 - 100 dB(A)).

[0049] Among them, the collected noise data includes the continuous equivalent A-weighted sound level of the noise in different time periods and the day-night equivalent sound level .

[0050] S2: According to factors such as the noise data and the regional population structure, construct a noise annoyance prediction model to predict the noise annoyance of residents in each region.

[0051] This noise annoyance prediction model considers multiple influencing factors (such as sound level, time, age of residents, etc.) and uses fuzzy neural networks or regression analysis to calculate the noise annoyance of individual residents.

[0052] S2.1: According to the noise data collected in step S1, obtain the noise time series data of the monitoring points and extract the noise characteristic values in different time periods, including the A-weighted sound level and the day-night equivalent sound level , and the specific formulas are as follows:[[]]

[0053] ;

[0054] Among them, is the noise pressure level at time t, and T is the length of the time period.

[0055] The formula for the day-night equivalent sound level is:[[]]

[0056] ;

[0057] Among them, and represent the A-weighted sound levels during the day and at night respectively.

[0058] S2.2: Collect population structure data, divide the regions according to the population density, and generate a regional population characteristic set , representing the population characteristics of region x.

[0059] S2.3: Combine the noise characteristic values with the population characteristic set, and establish a preliminary correspondence between the noise and the population characteristics according to different time periods t and regions x to form an input data matrix: .

[0060] S2.4: Use a fuzzy neural network for the data matrix Process it and train a noise annoyance prediction model based on the noise levels and population sensitivities in different time periods, including:

[0061] Among them, the fuzzy rule is defined as: If is high and the proportion of sensitive population is high, then the annoyance level is high.

[0062] The output of the fuzzy neural network is the noise annoyance level .

[0063] S2.5: Introduce a regression analysis method to optimize the noise annoyance prediction model, calculate the annoyance scores of different resident groups in a specific noise environment, and obtain the noise annoyance scores of residents in each area.

[0064] Preferably, the calculation process of the annoyance score is as follows:

[0065] ;

[0066] Among them, , , are all regression coefficients; is the time-related correction term, and the noise annoyance score of residents in each area is calculated according to the area x and time t.

[0067] S2.6: According to the noise annoyance score and the time series change, perform time correction on the noise annoyance level of each area to obtain the dynamic prediction result of the noise annoyance level.

[0068] Specifically, according to the noise annoyance score of the residents in the area and the time series change, perform time correction to obtain the dynamic prediction result of the noise annoyance level, where the dynamic noise annoyance prediction formula is:

[0069] ;

[0070] Among them, is the time change amount, is the time correction factor, reflecting the change trend of the noise annoyance level in different time periods.

[0071] S3: Statistically analyze the high annoyance rates of each area. Considering the differences in noise impacts in different time periods, adopt a dynamic sub-period high annoyance rate calculation method to analyze the daytime working period, daytime rest period, and nighttime rest period respectively, and introduce a time correction term and an area condition correction term.

[0072] S3.1: Calculate the high annoyance rates of residents in different areas.

[0073] The high annoyance rate curve of the present invention is fitted according to the logistic function specified in "Acoustics - Assessment and prediction methods of noise annoyance" (GB / T 42473 - 2023), and the formula is as follows:

[0074] ;

[0075] Among them, HA% is the high annoyance rate of the regional residents, and L is the continuous equivalent sound level of road noise.

[0076] By comparing the high annoyance rate curve of residents obtained by fitting the results of the resident annoyance degree survey in this study with the high annoyance rate fitting curve officially announced by the European Commission, similar noise - high annoyance rate dose curves and trends are found. Therefore, this study follows the 10% high annoyance rate threshold. For roads or areas with a high annoyance rate exceeding 10%, they can be regarded as high annoyance areas that need to take treatment measures, as Figure 2 shown.

[0077] S3.2: Divide the time periods, calculate the high annoyance rate for each time period respectively, and adjust according to the noise level in different time periods using the time correction term.

[0078] Among them, since at lower sound levels, the noise annoyance degree of residents in each time period changes little; while after the sound level reaches 64 dB(A) or above, during the rest periods in the early morning, noon, and evening, the annoyance degree of residents gradually increases compared with other time periods, and the greater the sound level, the more significant this difference becomes. Therefore, the time correction term should follow the following principles:

[0079] When the sound level is below 64 dB(A), the correction term should be close to 0;

[0080] When the sound level reaches 64 dB(A) and above, the correction term should increase with the increase of the sound level;

[0081] To simplify the calculation, the 24 - hour day is divided into the evening rest period, the daytime rest period, and the daytime working period. Taking the daytime working period as the reference, the correction term within the daytime working period should be close to 0.

[0082] Draw the annoyance degree difference curve between the rest period and the working period above 63 dB(A) as Figure 3 shown. From Figure 3 it can be seen that as the sound level increases, the influence of time on the high annoyance rate of residents generally shows a linear change. According to the fitting, the slope of the fitting straight line of the difference between the high annoyance rate of residents in the evening rest period and the high annoyance rate in the working period is 3.1674, and the slope of the fitting straight line of the difference between the high annoyance rate in the daytime rest period and the high annoyance rate in the working period is 0.8846. Therefore, according to the principle of approximate convenience, is approximately taken as 3, Approximately take 1 to obtain the following time correction term:

[0083] ;

[0084] Among them, is the high annoyance rate time correction term; is the correction rate, and according to the fitting result, it takes values according to the following formula:

[0085] ;

[0086] Among them, L is the continuous equivalent A-weighted sound level of road noise.

[0087] Night rest period: The period from 22:00 at night to 6:00 in the early morning of the next day;

[0088] Daytime rest periods: Three periods: 6:00 - 8:00, 12:00 - 14:00, 20:00 - 22:00 during the daytime;

[0089] Daytime working periods: Two periods: 8:00 - 12:00, 14:00 - 20:00 during the daytime.

[0090] S3.3: Calculate the regional condition correction term according to the regional conditions, including the acoustic function zoning and the age structure.

[0091] The regional condition correction term is mainly composed of the acoustic function zoning and the age structure of the regional residents. The shapes of the high annoyance curves in regions with the same function zoning but different age compositions are similar, and the differences in high annoyance rates mainly come from the left - right translation of the curves; while the differences in regions with the same age composition but different acoustic function zonings are similar to the differences caused by time.

[0092] Based on this concept, in terms of the age composition of the regional residents, the influence caused by the age structure of the residents is approximately equivalent to the influence of a sound level of 6 dB(A). Thus, the correction amount of the resident age structure is shown in the following formula:

[0093] ;

[0094] Among them, is the high annoyance rate age structure correction term; m is the proportion of sensitive population in the region (residents under 18 years old and over 50 years old).

[0095] Furthermore, in terms of the acoustic function zoning, taking the commonly used Class 2 acoustic function zone as the reference, calculate the difference in high annoyance rates between Class 1 regions, Class 4a regions and Class 2 regions, and draw a curve as Figure 4 shown.

[0096] From Figure 4It can be seen that the difference in the high annoyance rate between different regions increases linearly between 60 and 70 dB(A), reaches its peak at 70 dB(A), and then decreases slowly. Considering that 70 dB(A) is the minimum standard that road noise should meet, only the part below 70 dB(A) is considered according to linear fitting.

[0097] According to the fitting results, the correction amount of the acoustic function zoning can be obtained as shown in the following formula:

[0098] ;

[0099] ;

[0100] where, is the correction amount of the acoustic function zoning when the area to be predicted is a Class 1 acoustic function area; is the correction amount of the acoustic function zoning when the area to be predicted is a Class 4a acoustic function area; L is the continuous equivalent A-weighted sound level of road noise.

[0101] S3.4: Determine the form of the corrected high annoyance rate model as shown in the following formula:

[0102] ;

[0103] S4: Based on the noise annoyance prediction model and the calculation results of the high annoyance rate, put forward suggestions and measures for the control of urban road traffic noise, and summarize the analysis results.

[0104] Specifically, according to the noise annoyance prediction model established in S2 and the high annoyance rate statistically in S3, summarize the noise annoyance degree and high annoyance rate data of each region, generate a regional noise impact analysis report, and highlight the key treatment areas where the high annoyance rate exceeds the threshold (such as 10%).

[0105] Based on the high annoyance rate statistically in S3 and the annoyance degree prediction results in each time period in S2, analyze whether the effects of the current noise control measures (such as speed limit, sound insulation facilities, etc.) meet the expectations. If the high annoyance rate area is still large, it indicates that the existing measures are insufficient and further optimization and adjustment are needed.

[0106] Furthermore, according to the feedback results, optimize the existing noise control strategy. For example, take more targeted treatment measures for high annoyance rate areas, such as adding sound insulation walls, adjusting traffic flow, or implementing noise control at specific areas at night. Implement different noise management policies according to regional characteristics, and focus on treating areas with more noise sources and dense population.

[0107] Furthermore, this embodiment also provides an urban road traffic noise analysis system, including,

[0108] The noise monitoring module is used to set up noise monitoring equipment and continuously collect road traffic noise data. The noise annoyance prediction module is used to construct a noise annoyance prediction model to predict the noise annoyance of residents in each area. The high annoyance rate statistical analysis module is used to statistically analyze the high annoyance rates in each area, adopt a dynamic time-segmented high annoyance rate calculation method, analyze different time periods respectively, and introduce a time correction term and a regional condition correction term. The noise control suggestion generation module is used to propose suggestions and measures for urban road traffic noise control based on the noise annoyance prediction model and the high annoyance rate calculation results, and summarize the analysis results.

[0109] This embodiment also provides a computer device applicable to the situation of the urban road traffic noise analysis method, including a memory and a processor. The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the urban road traffic noise analysis method proposed in the above embodiment.

[0110] This computer device can be a terminal. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of this computer device is used to provide computing and control capabilities. The memory of this computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of this computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of this computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of this computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad set on the outer shell of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0111] This embodiment also provides a storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the urban road traffic noise analysis method proposed in the above embodiment.

[0112] In summary, the present invention not only focuses on the physical intensity of noise, but also introduces a subjective evaluation index - annoyance degree, and combines factors such as regional characteristics and time characteristics to dynamically predict the noise annoyance of residents in different regions and different time periods. Compared with the existing static noise analysis methods, the prediction model constructed by the present invention can more accurately reflect the actual feelings of residents towards traffic noise. In addition, the dynamic calculation method of the high annoyance rate of the present invention can be accurately adjusted according to the noise level and regional conditions in different time periods, providing a more valuable reference basis for noise prevention and control decisions.

[0113] Example 2

[0114] Reference Figure 5 , which is the second embodiment of the present invention. This embodiment provides a method for analyzing urban road traffic noise. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0115] There is a phenomenon of noise disturbing residents in a community near a certain road. In order to understand the impact of the traffic noise generated by this road on the surrounding residents and formulate targeted noise reduction countermeasures, the high annoyance rate of the surrounding residents of this road is now predicted. It is known that the building with complaints is 30m away from the road boundary line, which is classified as a Class 2 sound environment functional area, and there are many noise-sensitive residents such as the elderly and minors.

[0116] The noise generated by this road in one day is monitored. According to the distance between the building and the road, the predicted noise propagation attenuation is about 11 dB(A). Subtracting it gives the noise change curve received by the residents.

[0117] According to the "Ambient Noise Quality Standard", the noise limit value in this area is 60 dB(A) during the day and 50 dB(A) at night. The over-standard periods are from 11:00 during the day to 6:00 the next day. The maximum over-standard amount during the day is 9 dB(A), and the maximum over-standard amount at night is 17 dB(A).

[0118] Use the prediction formula for the high annoyance rate of residents to calculate the high annoyance rate of the residents in this community, and the results are as Figure 5 shown: It can be seen that the over-standard periods are from 10:00 during the day to 3:00 the next day. The maximum high annoyance rate during the day is about 30%, and the maximum high annoyance rate at night is 60%, around 22:00 to 2:00 in the morning. It can be seen from this that the formulation of noise reduction countermeasures should take the night noise at 22:00 as the noise reduction control point, and the noise reduction amount is 11 dB(A). Finally, the maximum value of the noise limit noise reduction amount and the high annoyance rate noise reduction amount is selected as the target noise reduction amount.

[0119] Considering the change of road traffic noise at different heights of buildings, for high-rise buildings, it is recommended to predict the high annoyance rate of noise in different regions according to the noise distribution. In the area from the 6th to the 10th floor, 4 dB(A) can be added to the ground noise intensity for prediction.

[0120] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not restrictive. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A method for analyzing urban road traffic noise, characterized in that: include, Install noise monitoring equipment to continuously collect road traffic noise data; Construct a noise annoyance prediction model to predict the noise annoyance of residents in each area; Statistics on the high annoyance rate in each area, using a dynamic time-division high annoyance rate calculation method, analyzing different time periods separately, and introducing time correction items and regional condition correction items; Based on the noise annoyance prediction model and high annoyance rate calculation results, suggestions and measures for urban road traffic noise control are proposed; The construction of the noise annoyance prediction model to predict the noise annoyance of residents in each area includes the following steps: obtaining the noise time series data of the monitoring points and extracting the noise characteristic values ​​of different time periods; collecting population structure data and dividing the regions according to population density to generate regional population characteristic sets. ; Combine the noise feature value with the population feature set, establish a preliminary correspondence between noise and population characteristics according to different time periods t and regions x, and form an input data matrix: ; Use fuzzy neural network to analyze the data matrix Based on the noise level and crowd sensitivity in different time periods, a noise annoyance prediction model is trained, where the output of the fuzzy neural network is the noise annoyance ; Optimize the noise annoyance prediction model, calculate the annoyance scores of different resident groups in a specific noise environment, and obtain the noise annoyance scores of residents in each area; according to the noise annoyance scores and time series changes, perform time correction on the noise annoyance of each area to obtain the dynamic prediction results of the noise annoyance; The high annoyance rate calculation method using dynamic time periods includes the following steps: divide 24 hours a day into the evening rest period, the daytime rest period and the daytime working period; fit the slope of the straight line of the difference between the high annoyance rate of residents in the evening rest period and the high annoyance rate in the working period Take 3, and fit the slope of the straight line of the difference between the high annoyance rate during the daytime rest period and the work period Take 1 to get the time correction term; the regional condition correction term is composed of the sound function zoning and the age structure of regional residents.

2. The urban road traffic noise analysis method according to claim 1, characterized in that: The extracting of noise characteristic values ​​in different time periods comprises: A-sound level The formula is: ； in, is the noise pressure level at time t, T is the length of the time period; Day and night equivalent sound level The formula is: ； in, and Represents the A sound level during the day and at night respectively.

3. The urban road traffic noise analysis method according to claim 2, characterized in that: The calculation process of the annoyance score is as follows: ； in, , , All are regression coefficients; is the time-related correction term; The noise annoyance level of each area is corrected over time, wherein the dynamic noise annoyance level prediction formula is: ； in, is the time variation, is the time correction factor.

4. The urban road traffic noise analysis method according to claim 3, characterized in that: The time correction items are as follows: ； in, It is the correction item for the high annoyance rate time; is the correction rate.

5. The urban road traffic noise analysis method according to claim 4, characterized in that: The resident age structure correction amount is as follows: ； in, is the correction item for the age structure of high trouble rate; m is the sensitive population in the region; The correction amount of the acoustic function zoning is shown in the following formula: ； ； in, It is the correction value of acoustic function zoning when the area to be predicted is a Class 1 acoustic function zone; It is the correction value of the sound function zoning when the area to be predicted is a Class 4a sound function zone; L is the continuous equivalent A sound level of road noise.

6. The urban road traffic noise analysis method according to claim 5, characterized in that: The corrected high annoyance rate model is as follows: 。 7. An urban road traffic noise analysis system, based on the urban road traffic noise analysis method according to any one of claims 1 to 6, characterized in that: Also includes, Noise monitoring module, used to set up noise monitoring equipment and continuously collect road traffic noise data; A noise annoyance prediction module is used to construct a noise annoyance prediction model to predict the noise annoyance of residents in each area; The high annoyance rate statistical analysis module is used to count the high annoyance rate in each area. It adopts a dynamic time-divided high annoyance rate calculation method to analyze different time periods and introduces time correction items and regional condition correction items. The noise control suggestion generation module is used to put forward suggestions and measures for urban road traffic noise control based on the noise annoyance prediction model and high annoyance rate calculation results, and summarize the analysis results.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the urban road traffic noise analysis method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the urban road traffic noise analysis method according to any one of claims 1 to 6 are implemented.

Images