GIS-based noise distribution visualization monitoring method and system

Abstract

The present application relates to the field of data processing technology, and specifically to a GIS-based noise distribution visualization monitoring method and system, which specifically includes: collecting noise data by setting different monitoring points in different areas, dynamically analyzing the noise signal change characteristics based on the noise distribution characteristics of the area where each monitoring point is located, and constructing a stage noise correlation characteristic value; comprehensively comparing and analyzing the dynamic change characteristics of different frequency bands of each monitoring point, and constructing the characteristic coefficients of the change differences of different frequency bands of each monitoring point; adjusting the frame rate of each monitoring point based on the characteristic parameters of the two, and determining the update speed of the information of each monitoring point on the GIS visualization display interface; avoiding the problem that the spatiotemporal dynamic change characteristics of noise affect the frame rate setting during the display of the visualization interface, resulting in a lag in the visualization results, and significantly improving the accuracy, fluency and real-time performance of noise distribution visualization monitoring.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a noise distribution visualization monitoring method and system based on GIS. Background Art

[0002] With the acceleration of urbanization, noise pollution is becoming an increasingly prominent problem. Traditional noise monitoring methods are often limited to acquiring and analyzing data from a single monitoring point, making it difficult to intuitively demonstrate the spatial distribution patterns and changing trends of noise. Geographic Information Systems (GIS), as a powerful spatial analysis tool, can combine noise data with geospatial information. Through a visual display interface, it clearly presents the distribution of noise in different urban areas, helping managers quickly locate noise pollution sources and assess the scope and extent of noise pollution, providing intuitive and comprehensive data support for the development of scientific and effective noise control strategies.

[0003] In the process of monitoring the noise distribution visualization display interface based on GIS, the noise distribution characteristics have a key impact on the selection of frame rate. Noise distribution has the characteristics of spatiotemporal dynamics and spatial heterogeneity. In terms of spatiotemporal dynamics, activities such as urban transportation and industrial production cause noise intensity to change continuously over time, and present different distribution patterns in different regions; in terms of spatial heterogeneity, the noise intensity in commercial areas, industrial areas, residential areas and other areas varies significantly. If the frame rate is too low, it is difficult to capture the rapid changes in noise, resulting in a significant delay in the visualization results, and the inability to reflect the real-time status of the noise in a timely manner, reducing the timeliness of monitoring; if the frame rate is too high, it will increase the system computing load, which may cause the system to freeze or even crash, and at the same time cause unnecessary waste of resources. The above-mentioned problem of improper frame rate selection directly affects the accuracy, smoothness and real-time performance of noise distribution visualization monitoring. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of this application is to provide a GIS-based noise distribution visualization monitoring method and system. The technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present application provides a GIS-based noise distribution visualization monitoring method, the method comprising the following steps:

[0006] Deploy multiple monitoring points in each preset area to collect the sound pressure level of noise at each monitoring point in real time; obtain the geographical location information of each monitoring point;

[0007] Construct each historical data sequence of each monitoring point through the noise sound pressure level data transmitted historically at each monitoring point; obtain each neighboring monitoring point of the target monitoring point based on the geographical location of all monitoring points in all areas; construct the correlation feature vector of the target monitoring point and each of its neighboring monitoring points based on the degree of difference between the corresponding historical data sequences of the target monitoring point and each of its neighboring monitoring points; record the correlation feature vector of the target monitoring point and any neighboring monitoring point as the current correlation feature vector, analyze the correlation between the current correlation feature vector and the remaining correlation feature vector of the target monitoring point, as well as the size distribution characteristics of the elements in the remaining correlation feature vector, and construct the stage noise correlation feature value of any neighboring monitoring point of the target monitoring point;

[0008] All neighboring monitoring points of the target monitoring point are screened based on the noise correlation characteristic value of the stage to obtain each comparison monitoring point; each modal component of the time series composed of noise sound pressure level data that is not currently transmitted at each monitoring point is calculated; based on the correlation between the corresponding modal components of the target detection point and its comparison monitoring point, combined with the noise correlation characteristic value of the comparison monitoring point at the stage, the characteristic coefficient of the change difference of the corresponding frequency band of each modal component of the target monitoring point is calculated;

[0009] Constructing a judgment coefficient of dynamic change of noise at the target monitoring point based on the characteristic coefficient of the modal component of the target monitoring point and the degree of disorder of the elements in the modal component;

[0010] Determine the noise distribution visualization interface of the GIS, preset the initial frame rate of each monitoring point and the frame rate variation range of each area, adjust the initial frame rate based on the frame rate variation range and the judgment coefficient, and obtain the adjusted frame rate of each monitoring point; refresh the information of each monitoring point in the visualization interface according to the adjusted frame rate of each monitoring point.

[0011] In one embodiment, the process of acquiring the neighboring monitoring points of the target monitoring point is as follows:

[0012] The geographical locations of all monitoring points are used as inputs to the neighboring point search algorithm to obtain the neighboring monitoring points of the target monitoring point.

[0013] In one embodiment, the process of obtaining each associated feature vector of the target monitoring point is as follows:

[0014] The metric distance between the historical data series of the target monitoring point and each of its neighboring monitoring points transmitted at the same time is calculated, and the vector composed of the metric distances of all transmissions is used as the associated feature vector between the target monitoring point and each of its neighboring monitoring points.

[0015] In one embodiment, the process of obtaining the stage noise correlation characteristic value is as follows:

[0016] For all associated feature vectors corresponding to the target monitoring point, calculate the mean of all elements in each associated feature vector, which is recorded as the first mean; calculate the ratio of the first mean of each associated feature vector to the sum of the first means of all associated feature vectors, which is recorded as the first ratio of each associated feature vector;

[0017] Based on the correlation between the current correlation feature vector and the remaining correlation feature vectors, and the first ratios of the remaining correlation feature vectors, the stage noise correlation feature value of any neighboring monitoring point corresponding to the current correlation feature vector is calculated.

[0018] In one embodiment, the process of obtaining the phase noise correlation eigenvalue of the neighboring monitoring point corresponding to the current correlation eigenvector is as follows:

[0019] Calculate the Pearson correlation coefficient between the current associated eigenvector and the remaining associated eigenvectors, multiply the coefficient by the first ratio, and record the result of the multiplication as the first product; and use the sum of the first products between the current associated eigenvector and the remaining associated eigenvectors as the stage noise correlation eigenvalue of any neighboring monitoring point corresponding to the current associated eigenvector.

[0020] In one embodiment, the process of obtaining the comparison monitoring points of the target monitoring point is as follows:

[0021] The mean of the stage noise correlation characteristic values ​​of all neighboring monitoring points of the target monitoring point is calculated and recorded as the first characteristic mean. The neighboring monitoring points whose stage noise correlation characteristic values ​​are greater than the first characteristic mean are used as comparison monitoring points of the target monitoring point.

[0022] In one embodiment, the expression of the characteristic coefficient of the change difference of each modal component corresponding to the frequency band of the target monitoring point is:

[0023] , where Indicates the target monitoring point The characteristic coefficient of the change difference of each modal component in the corresponding frequency band; Indicates the number of comparison monitoring points for the target monitoring point; Indicates the target monitoring point The modal component and its The first comparison monitoring point Pearson correlation coefficient between the modal components; Indicates the target monitoring point The phase noise correlation characteristic value of the comparison monitoring points; It represents the sum of the noise correlation eigenvalues ​​of all comparison monitoring points at the target monitoring point.

[0024] In one embodiment, the process of obtaining the judgment coefficient of the dynamic change of noise at the target monitoring point is as follows:

[0025] Calculate the normalized value of the characteristic coefficient of each modal component and calculate the standard deviation of all data in each modal component; calculate the sum of the products of the normalized values ​​and the standard deviation of all modal components of the target monitoring point as the judgment coefficient of the dynamic change of noise at the target monitoring point.

[0026] In one embodiment, the process of obtaining the adjusted frame rate of each monitoring point is as follows:

[0027] Calculate the product of the normalized value of the judgment coefficient corresponding to the current monitoring point and the frame rate variation range in the area, which is recorded as the second product; and use the sum of the initial frame rate of the current monitoring point and the second product as the adjusted frame rate of the current monitoring point.

[0028] In a second aspect, an embodiment of the present application also provides a GIS-based noise distribution visualization monitoring system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above-mentioned methods when executing the computer program.

[0029] The embodiments of the present application have at least the following beneficial effects:

[0030] This application collects noise data by setting up different monitoring points in different areas, dynamically analyzes the noise signal change characteristics based on the noise distribution characteristics of the area where each monitoring point is located, constructs the stage noise correlation characteristic value, and fully considers the noise source characteristics and the differences in the propagation paths in the area; conducts a comprehensive comparative analysis of the dynamic change characteristics of different frequency bands of each monitoring point, and constructs the characteristic coefficients of the change differences of different frequency bands of each monitoring point; adjusts the frame rate of each monitoring point based on the characteristic parameters of the two, and accurately determines the update speed of the information of each monitoring point in the GIS visualization display interface, thereby realizing the optimized design of noise distribution visualization display monitoring; its beneficial effect lies in the deep integration of the spatiotemporal dynamic characteristics of noise distribution, accurately analyzing the noise change characteristics of each area, and thus efficiently and accurately presenting the noise distribution information in the visualization interface, avoiding the spatiotemporal dynamic change characteristics of noise affecting the frame rate setting during the visualization interface display process, making it difficult to capture the dynamic evolution of noise in real time and the problem of lagging visualization results, and significantly improving the accuracy, fluency and real-time performance of noise distribution visualization monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0032] Figure 1 A flowchart of the steps of a GIS-based noise distribution visualization monitoring method provided in one embodiment of the present application;

[0033] Figure 2 Schematic diagram of the process of obtaining the stage noise correlation eigenvalue. DETAILED DESCRIPTION

[0034] To further illustrate the technical means and effectiveness of this application's objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effectiveness of the GIS-based noise distribution visualization monitoring method and system proposed in this application. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0035] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0036] The specific scheme of the noise distribution visualization monitoring method and system based on GIS provided by this application is described in detail below with reference to the accompanying drawings.

[0037] See also Figure 1 , which shows a flowchart of the steps of a noise distribution visualization monitoring method based on GIS provided by an embodiment of the present application, the method includes the following steps:

[0038] Step S1: deploy multiple monitoring points in each preset area, collect the sound pressure level of the noise at each monitoring point in real time, and obtain the geographical location information of each monitoring point.

[0039] The noise distribution visualization interface display of GIS mainly includes the following processes: (1) Data collection: obtaining raw noise data through sensors deployed in different areas; (2) Data processing: performing feature analysis on the collected raw noise data; (3) GIS analysis: integrating noise data with geographic spatial information; (4) Visual rendering: designing the visualization interface based on a determined frame rate; (5) Interactive application: providing users with an operation portal.

[0040] The scientific arrangement of monitoring points during the data collection process is the basis for obtaining accurate noise data. First, according to the functional zoning of the city, monitoring points are reasonably set in typical areas such as commercial areas, industrial areas, traffic arteries, and residential areas. Specifically, in commercial areas, considering the noise generated by pedestrian flow and business activities, monitoring points are densely arranged in locations such as busy streets and around large shopping malls, and monitoring points are set at intervals of 10 to 50 meters. In one embodiment of the present application, the interval between monitoring points in commercial areas is set to 10 meters; in industrial areas, monitoring points are set at equal intervals of 50 to 100 meters around noise sources such as factories and workshops. In one embodiment of the present application, the interval between monitoring points in industrial areas is set to 50 meters; monitoring points are set every 200 to 300 meters on traffic arteries. In one embodiment of the present application, the interval between monitoring points on traffic arteries is set to 200 meters; in residential areas, monitoring points are set between different buildings and at the entrances and exits of the community.

[0041] Each monitoring point is equipped with a high-precision noise sensor, which collects noise sound pressure level and frequency data in real time. At the same time, it is equipped with a GPS positioning module to accurately record the geographical location information of the monitoring point. In addition, to ensure the continuity and stability of data collection, the equipment is equipped with a solar power supply system and a data storage module, which can achieve long-term uninterrupted operation and temporarily store the collected data.

[0042] The collected noise data needs to be transmitted to the monitoring center in a timely manner. Specifically, the equipment at each monitoring point sends the noise data containing noise sound pressure level data, frequency, geographic location and other information to the monitoring center server through the 4G / 5G communication network. In order to ensure the accuracy and integrity of data transmission, the CRC check algorithm is used to check the transmitted data during the data transmission process. If a data error is found, it is immediately retransmitted. At the same time, a data transmission priority system is established to give priority to the transmission of sudden high-intensity noise data to ensure that the monitoring center can obtain important information in the first time and take timely response measures. In addition, in order to prevent loss during data transmission, a multi-point backup transmission strategy is adopted to send data to multiple backup servers at the same time to further improve the reliability of data transmission. For example, in an urban environment, sudden high-intensity noise refers to noise with an instantaneous sound pressure level exceeding 85 decibels and with sudden and short-term characteristics, which may cause instantaneous interference to residents' lives. For example, there are the harsh noises of more than 110 decibels caused by equipment failures in industrial production, such as wear of compressor parts, or the instantaneous impulse noise of 130 decibels during blasting operations; the 105 decibel noise caused by vehicle tire blowouts in transportation, and the high-intensity noise of 115 decibels near the runway when an airplane takes off; the 120-decibel screams caused by overloaded audio equipment at celebrations in commercial plazas in social life, and the 115-decibel noise caused by hydraulic breakers operating at construction sites; there are also the 100-decibel impact noises caused by fallen trees due to typhoons in natural and accidental scenes, and the 130-decibel instantaneous noise when a gas pipeline explodes.

[0043] Step S2, constructing each historical data sequence of each monitoring point through the noise sound pressure level data transmitted historically by each monitoring point; obtaining each neighboring monitoring point of the target monitoring point based on the geographical location of all monitoring points in all areas; constructing the correlation feature vector of the target monitoring point and each of its neighboring monitoring points based on the degree of difference between the corresponding historical data sequences of the target monitoring point and each of its neighboring monitoring points; recording the correlation feature vector between the target monitoring point and any neighboring monitoring point as the current correlation feature vector, analyzing the correlation between the current correlation feature vector and the remaining correlation feature vectors of the target monitoring point, as well as the element size distribution characteristics in the remaining correlation feature vectors, and constructing the stage noise correlation feature value of any neighboring monitoring point of the target monitoring point.

[0044] When processing data, considering the large differences in interference sources and propagation paths in different areas during noise distribution visualization monitoring, the monitoring data collected by different monitoring points have significant dynamic change differences in different frequency bands, which in turn affects the accuracy of visualization monitoring. Therefore, based on the correlation change characteristics of monitoring data caused by the distribution of interference sources and propagation paths of monitoring points in different areas, the dynamic change differences of different monitoring points in the actual monitoring process are accurately analyzed. The specific analysis and processing process is as follows:

[0045] First, for each monitoring point, all noise sound pressure level data are arranged in ascending order of time, and the resulting sequence is recorded as the time series of monitoring data transmitted each time by each monitoring point; the history of each monitoring point closest to the current moment is obtained. The monitoring data time series sequence transmitted is used as the historical data sequence of each monitoring point; preferably, in the embodiment of the present application, The value of is set to 50. As other embodiments of this application, the implementer can set it according to the actual situation. The value of .

[0046] Then, each monitoring point is used as a target monitoring point. For the target monitoring point, in order to accurately analyze the stage differences of noise changes at the target monitoring point, each historical data series of the noise sound pressure level data of the target monitoring point is obtained;

[0047] Since the collection time of all monitoring points is the same, in order to accurately analyze the dynamic change characteristics of the target monitoring point where the data is collected, the K nearest neighbor monitoring points of the target monitoring point are obtained. Specifically, the geographical locations of all monitoring points in all areas are used as inputs of the K nearest neighbor search algorithm to obtain the K nearest neighbor monitoring points of the target monitoring point. In this embodiment of the present application, the value of K is set to 10; in other embodiments of the present application, the implementer can set the value of K according to actual conditions.

[0048] Therefore, for the noise sound pressure level data of the target monitoring point, the DTW distance between the historical data sequence of the target monitoring point and each of its neighboring monitoring points transmitted at the same time is calculated. The larger the DTW distance, the smaller the correlation between the data collected between the target monitoring point and its neighboring monitoring points in the corresponding time period; the vector composed of all the DTW distances between the target monitoring point and each of its neighboring monitoring points in the corresponding time sequence is used as the correlation feature vector between the target monitoring point and each of its neighboring monitoring points, and the correlation feature vector reflects the phased correlation change characteristics between different monitoring points. Among them, the correlation feature vector between the target monitoring point and its xth neighboring monitoring point is used as the xth correlation feature vector of the target monitoring point. Among them, the K nearest neighbor search algorithm and the DTW distance are both well-known technologies, and the specific process will not be repeated.

[0049] It should be noted that for the distance measurement between historical data sequences and the acquisition of neighboring monitoring points of the target monitoring points, this application only provides a distance measurement method and a neighboring point search method. There are many existing distance measurement methods and neighboring point search methods. Implementers can also use other distance measurement formulas and neighboring point search algorithms to respectively measure the distance between historical data sequences and obtain the neighboring monitoring points of the target monitoring points. This application does not make specific restrictions.

[0050] Next, the absolute value of the Pearson correlation coefficient between any two associated feature vectors of the target monitoring point is calculated. The larger the absolute value, the greater the correlation between the corresponding two neighboring monitoring points and the target monitoring point at different stages of the association change. In other words, the two neighboring monitoring points currently have similar stage-by-stage change characteristics with respect to the data collected by the target monitoring point. The Pearson correlation coefficient is well known in the art, and the specific process will not be repeated here.

[0051] It should be noted that for the correlation calculation between associated feature vectors, this application only provides a correlation calculation method. There are many existing correlation calculation methods, and implementers can also use other correlation algorithms to calculate the correlation between associated feature vectors. This application does not make specific restrictions.

[0052] Furthermore, based on the correlation change characteristics of different monitoring points compared with the target monitoring point at different stages, the stage noise correlation characteristic value is calculated, and the expression is:

[0053]

[0054] Where, Represents the stage noise correlation eigenvalue of the xth neighboring monitoring point of the target monitoring point; represents the Pearson correlation coefficient between the xth and ith associated feature vectors of the target monitoring point; and are the means of all elements in the j-th and i-th associated feature vectors of the target monitoring point, respectively, recorded as the first mean; K represents the number of associated feature vectors of the target monitoring point, that is, the number of neighboring monitoring points of the target monitoring point. is the first ratio. is the first product.

[0055] The larger the calculated stage noise correlation characteristic value is, the more significant the correlation between the monitoring data of different monitoring points at different locations and the monitoring data of the target monitoring point at different time periods is. The greater the correlation between the neighboring monitoring points and the dynamic change comparison analysis of the noise of the target monitoring point, the greater the correlation between the neighboring monitoring points and the dynamic change of the noise of the target monitoring point.

[0056] Step S3: Based on the stage noise correlation characteristic value, all neighboring monitoring points of the target monitoring point are screened to obtain each comparison monitoring point; each modal component of the time series composed of the noise sound pressure level data not currently transmitted by each monitoring point is calculated; based on the correlation between the corresponding modal components of the target detection point and its comparison monitoring point, combined with the stage noise correlation characteristic value of the comparison monitoring point, the characteristic coefficient of the change difference of the corresponding frequency band of each modal component of the target monitoring point is calculated.

[0057] Based on the phased correlation analysis characteristics of other neighboring monitoring points determined above compared to the target monitoring point, the dynamic change characteristics of the data collected by the target monitoring point are analyzed, that is, by comparing the monitoring points with correlation characteristics at different time periods with the target monitoring point, a comparative analysis of the degree of difference in dynamic changes is performed. If the comparison difference is large, it means that the noise distribution in the current area, the interference source and the data dynamic change characteristics caused by the difference in propagation path are significant. Specifically:

[0058] First, the mean of the phase-by-phase noise correlation characteristic values ​​of all neighboring monitoring points of the target monitoring point is calculated, recorded as the first characteristic mean. Among all the neighboring monitoring points of the target monitoring point, the neighboring monitoring points with phase-by-phase noise correlation characteristic values ​​greater than the first characteristic mean are selected as comparison monitoring points of the target monitoring point. The purpose of obtaining comparison monitoring points is to consider the phase-by-phase correlation change characteristics of data collected by different monitoring points in the neighboring area. Then, based on the regional noise distribution characteristics, the neighboring monitoring points with the most significant correlation changes are selected to analyze the dynamic change characteristics of the collected data.

[0059] Furthermore, a time series of currently collected, but untransmitted, noise sound pressure level data at each monitoring point is obtained as the current data sequence at each monitoring point. An empirical mode decomposition algorithm is used to obtain each modal component of the current data sequence at each monitoring point. In the embodiment of the present application, the number of modal components is 5. The empirical mode decomposition algorithm is a well-known technique, and the specific process is not described in detail here.

[0060] It should be noted that for the modal decomposition of time series, this application only provides a modal decomposition method. There are many existing modal decomposition methods, and implementers can also use other modal decomposition algorithms to perform modal decomposition on time series. This application does not make specific restrictions.

[0061] Furthermore, due to differences in the distribution of interference sources and propagation paths between different regions, there are dynamic changes in different frequency bands between the data collected by the monitoring point and the data collected by the associated comparison monitoring point. Therefore, the Pearson correlation coefficient between the corresponding modal components of the target monitoring point and each of its neighboring monitoring points is calculated to evaluate the correlation between the corresponding modal components of the two monitoring points.

[0062] Based on the correlation between the modal components, the dynamic change difference characteristics of the target monitoring point in different frequency bands are analyzed, and the characteristic coefficient of the change difference corresponding to each modal component of the target monitoring point is constructed. The expression is:

[0063]

[0064] Where, Indicates the target monitoring point The characteristic coefficient of the change difference of each modal component in the corresponding frequency band; Indicates the number of comparison monitoring points for the target monitoring point; Indicates the target monitoring point The modal component and its The first comparison monitoring point Pearson correlation coefficient between the modal components; Indicates the target monitoring point The phase noise correlation characteristic value of the comparison monitoring points; It represents the sum of the noise correlation eigenvalues ​​of all comparison monitoring points at the target monitoring point.

[0065] The larger the characteristic coefficient of the calculated change difference, the more significant the dynamic change characteristics of the regional noise distribution in the corresponding frequency band are. A higher frame rate needs to be set during the corresponding rendering process to more accurately reflect the dynamic change characteristics of the noise in the local area.

[0066] Step S4: constructing a judgment coefficient of the dynamic change of noise at the target monitoring point based on the characteristic coefficient of the modal component of the target monitoring point and the degree of disorder of the elements in the modal component.

[0067] Based on the results of the above analysis and calculations, a correlation analysis of data across different frequency bands is performed for monitoring points with phase correlation. If the phase correlation is strong, but the dynamic changes in the current monitoring data of the target monitoring point across different frequency bands vary significantly, this indicates that the location of the target monitoring point is affected by the distribution of interference sources and propagation paths in the area, resulting in significant differences in the dynamic changes in noise monitoring. Therefore, based on the characteristic coefficients of the changes in different frequency bands corresponding to the target monitoring point, the frame rate of the visualization interface display during the monitoring process is optimized and adjusted for the different monitoring points.

[0068] Specifically, the characteristic coefficients of the change differences of all modal components of the target monitoring point corresponding to the frequency band are used as input, and the normalization algorithm is used to process them to obtain the normalized results of the characteristic coefficients of the change differences in different frequency bands; based on the normalized results, the judgment coefficient of the dynamic change of the noise at the target monitoring point is determined. The specific calculation relationship is:

[0069]

[0070] Where, The judgment coefficient indicating the dynamic change of noise at the target monitoring point; is the number of modal components of the target monitoring point. In the embodiment of the present application, t=5; Indicates the target monitoring point Normalized result of characteristic coefficient of change difference of each modal component corresponding to the frequency band; Indicates the target monitoring point The standard deviation of all data in a modal component.

[0071] The larger the calculated judgment coefficient is, the more significant the difference in dynamic noise changes is due to the influence of interference sources and propagation paths on the location of the target monitoring point through the analysis of the dynamic changes of frequency bands in the local area where the target monitoring point is located. A larger frame rate is set for rendering accordingly, thereby accurately characterizing the noise distribution characteristics at the location.

[0072] Step S5, determine the noise distribution visualization interface of GIS, preset the initial frame rate of each monitoring point and the frame rate variation range of each area, adjust the initial frame rate based on the frame rate variation range and the judgment coefficient, and obtain the adjusted frame rate of each monitoring point; refresh the information of each monitoring point in the visualization interface through the adjusted frame rate of each monitoring point.

[0073] First, considering the hardware performance and resource load, by simulating the operating status of the noise distribution visualization interface of GIS at different frame rates, testing its response time, CPU occupancy, memory usage and other indicators, and selecting a frame rate with lower system resource consumption while ensuring the smooth effect of the visualization display interface; specifically, in this application, the frame rate range for setting monitoring points in residential areas is 15~30FPS, 30~40FPS in commercial areas, 40~60FPS in main traffic roads, and 30~60FPS in industrial locations; based on the above range, the initial frame rate of each monitoring point in the corresponding area is determined to be the corresponding minimum frame rate.

[0074] Furthermore, considering the differences in interference sources and propagation paths in different areas during the actual monitoring process, the frame rate of the monitoring points in the area is dynamically adjusted based on the judgment coefficients of the dynamic changes in noise corresponding to the different monitoring points determined above as target monitoring points. Specifically:

[0075] The normalization algorithm is used to normalize the judgment coefficients corresponding to all monitoring points. The frame rate variation range of each monitoring point in the area is calculated. For example, the frame rate variation range of the monitoring points in the residential area is 15. The frame rate corresponding to each monitoring point is dynamically adjusted based on the judgment coefficient of the dynamic change of noise in the area where each monitoring point is located. The expression is:

[0076] ,in Indicates the adjusted frame rate of the current monitoring point; Indicates the initial frame rate of the current monitoring point; Indicates the normalized result of the judgment coefficient corresponding to the current monitoring point; Indicates the frame rate variation range within the area where the current monitoring point is located. is the second product.

[0077] Finally, the visual monitoring results are output, specifically:

[0078] In the process of displaying the noise distribution visualization interface of the GIS described in step S1, after obtaining the frame rate that needs to be adjusted for each monitoring point, the noise data of each monitoring point is first integrated with the geographic spatial information during the GIS analysis process, and the visual display method of the noise data is designed in the visualization rendering layer based on the adjusted frame rate of each monitoring point:

[0079] For noise sound pressure levels, a color mapping table is used to map the numerical range to different colors. For example, the noise sound pressure level is divided into multiple intervals: below 30 decibels is represented by light green, 30-50 decibels is represented by yellow, 50-70 decibels is represented by orange, and above 70 decibels is represented by red. During the dynamic display process, the color of each monitoring point icon in the visualization interface is updated according to the real-time noise data as the corresponding adjusted frame rate progresses, intuitively presenting the dynamic changes in noise intensity. The spatial distribution differences of noise are displayed using a three-dimensional bar chart, and the height of the bar chart is proportional to the noise sound pressure level. Within each visualization time interval (i.e., each frame), the height of the bar chart is updated according to the collected data, and a smooth transition animation is set to make the rise and fall of the bar chart natural and smooth, avoiding the jumpy feeling caused by frame rate changes. The specific visualization rendering process is a technology well known to technicians in the field and will not be described in detail.

[0080] At the same time, a timeline is set on the visualization interface, and users can drag the timeline to view changes in noise distribution at different times, achieving a dynamic visualization of noise distribution. In addition, to facilitate users' in-depth analysis of noise data, interactive functions are added to the visualization results. For example, clicking on a monitoring point will pop up detailed noise data information, including sound pressure level, frequency, acquisition time, etc.; it supports user-defined query areas, and the system automatically calculates statistical information such as the average, maximum, and minimum noise values ​​in the area and displays them in the form of charts. Ultimately, the visualization monitoring results are output through various terminals such as web pages and mobile applications, obtaining real-time noise distribution information and providing accurate monitoring data for noise pollution prevention and control and urban planning.

[0081] The schematic diagram of the process of obtaining the stage noise correlation characteristic value is as follows: Figure 2 shown.

[0082] Based on the same inventive concept as the above method, an embodiment of the present application also provides a GIS-based noise distribution visualization monitoring system, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned GIS-based noise distribution visualization monitoring methods are implemented.

[0083] In summary, the embodiment of the present application provides a GIS-based noise distribution visualization monitoring method, which collects noise data by setting different monitoring points in different areas, dynamically analyzes the noise signal change characteristics based on the noise distribution characteristics of the area where each monitoring point is located, constructs a stage noise correlation characteristic value, and fully considers the noise source characteristics and propagation path differences in the area; comprehensively compares and analyzes the dynamic change characteristics of different frequency bands of each monitoring point, and constructs the characteristic coefficients of the change differences of different frequency bands of each monitoring point; adjusts the frame rate of each monitoring point based on the characteristic parameters of the two, and accurately determines the update speed of the information of each monitoring point in the GIS visualization display interface, thereby realizing the optimized design of noise distribution visualization display monitoring; its beneficial effect is to deeply integrate the spatiotemporal dynamic characteristics of noise distribution, accurately analyze the noise change characteristics of each area, and thus efficiently and accurately present the noise distribution information in the visualization interface, avoiding the spatiotemporal dynamic change characteristics of noise affecting the frame rate setting during the visualization interface display process, making it difficult to capture the dynamic evolution of noise in real time and the problem of lagging visualization results, and significantly improving the accuracy, fluency and real-time performance of noise distribution visualization monitoring.

[0084] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the above descriptions are of specific embodiments of the present application. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0085] The various embodiments in this application are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0086] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A GIS-based noise distribution visualization monitoring method is characterized by: The method comprises the following steps: Deploy multiple monitoring points in each preset area to collect the sound pressure level of noise at each monitoring point in real time; obtain the geographical location information of each monitoring point; Construct each historical data sequence of each monitoring point through the noise sound pressure level data transmitted historically at each monitoring point; obtain each neighboring monitoring point of the target monitoring point based on the geographical location of all monitoring points in all areas; construct the correlation feature vector of the target monitoring point and each of its neighboring monitoring points based on the degree of difference between the corresponding historical data sequences of the target monitoring point and each of its neighboring monitoring points; record the correlation feature vector of the target monitoring point and any neighboring monitoring point as the current correlation feature vector, analyze the correlation between the current correlation feature vector and the remaining correlation feature vector of the target monitoring point, as well as the size distribution characteristics of the elements in the remaining correlation feature vector, and construct the stage noise correlation feature value of any neighboring monitoring point of the target monitoring point; All neighboring monitoring points of the target monitoring point are screened based on the noise correlation characteristic value of the stage to obtain each comparison monitoring point; each modal component of the time series composed of noise sound pressure level data that is not currently transmitted at each monitoring point is calculated; based on the correlation between the corresponding modal components of the target detection point and its comparison monitoring point, combined with the noise correlation characteristic value of the comparison monitoring point at the stage, the characteristic coefficient of the change difference of the corresponding frequency band of each modal component of the target monitoring point is calculated; Constructing a judgment coefficient of dynamic change of noise at the target monitoring point based on the characteristic coefficient of the modal component of the target monitoring point and the degree of disorder of the elements in the modal component; Determine the noise distribution visualization interface of the GIS, preset the initial frame rate of each monitoring point and the frame rate variation range of each area, adjust the initial frame rate based on the frame rate variation range and the judgment coefficient, and obtain the adjusted frame rate of each monitoring point; refresh the information of each monitoring point in the visualization interface according to the adjusted frame rate of each monitoring point.

2. The GIS-based noise distribution visualization monitoring method according to claim 1, characterized in that: The process of obtaining the neighboring monitoring points of the target monitoring point is as follows: The geographical locations of all monitoring points are used as inputs to the neighboring point search algorithm to obtain the neighboring monitoring points of the target monitoring point.

3. The GIS-based noise distribution visualization monitoring method according to claim 1, characterized in that: The acquisition process of each associated feature vector of the target monitoring point is: The metric distance between the historical data series of the target monitoring point and each of its neighboring monitoring points transmitted at the same time is calculated, and the vector composed of the metric distances of all transmissions is used as the associated feature vector between the target monitoring point and each of its neighboring monitoring points.

4. The GIS-based noise distribution visualization monitoring method according to claim 1, characterized in that: The process of obtaining the noise correlation eigenvalue in the above stage is as follows: For all associated feature vectors corresponding to the target monitoring point, calculate the mean of all elements in each associated feature vector, which is recorded as the first mean; calculate the ratio of the first mean of each associated feature vector to the sum of the first means of all associated feature vectors, which is recorded as the first ratio of each associated feature vector; Based on the correlation between the current correlation feature vector and the remaining correlation feature vectors, and the first ratios of the remaining correlation feature vectors, the stage noise correlation feature value of any neighboring monitoring point corresponding to the current correlation feature vector is calculated.

5. The GIS-based noise distribution visualization monitoring method according to claim 4, characterized in that: The process of obtaining the phase noise correlation eigenvalue of the neighboring monitoring point corresponding to the current correlation eigenvector is as follows: Calculate the Pearson correlation coefficient between the current associated eigenvector and the remaining associated eigenvectors, multiply the coefficient by the first ratio, and record the result of the multiplication as the first product; and use the sum of the first products between the current associated eigenvector and the remaining associated eigenvectors as the stage noise correlation eigenvalue of any neighboring monitoring point corresponding to the current associated eigenvector.

6. The GIS-based noise distribution visualization monitoring method according to claim 1, characterized in that: The acquisition process of each comparison monitoring point of the target monitoring point is as follows: The mean of the stage noise correlation characteristic values ​​of all neighboring monitoring points of the target monitoring point is calculated and recorded as the first characteristic mean. The neighboring monitoring points whose stage noise correlation characteristic values ​​are greater than the first characteristic mean are used as comparison monitoring points of the target monitoring point.

7. The GIS-based noise distribution visualization monitoring method according to claim 1, characterized in that: The expression of the characteristic coefficient of the change difference of each modal component corresponding to the frequency band of the target monitoring point is: , where Indicates the target monitoring point The characteristic coefficient of the change difference of each modal component in the corresponding frequency band; Indicates the number of comparison monitoring points for the target monitoring point; Indicates the target monitoring point The modal component and its The first comparison monitoring point Pearson correlation coefficient between the modal components; Indicates the target monitoring point The phase noise correlation characteristic value of the comparison monitoring points; It represents the sum of the noise correlation eigenvalues ​​of all comparison monitoring points at the target monitoring point.

8. The GIS-based noise distribution visualization monitoring method according to claim 1, characterized in that: The process of obtaining the judgment coefficient of the dynamic change of noise at the target monitoring point is as follows: Calculate the normalized value of the characteristic coefficient of each modal component and calculate the standard deviation of all data in each modal component; calculate the sum of the products of the normalized values ​​and the standard deviation of all modal components of the target monitoring point as the judgment coefficient of the dynamic change of noise at the target monitoring point.

9. The GIS-based noise distribution visualization monitoring method according to claim 1, characterized in that: The process of obtaining the adjusted frame rate of each monitoring point is as follows: Calculate the product of the normalized value of the judgment coefficient corresponding to the current monitoring point and the frame rate variation range in the area, which is recorded as the second product; and use the sum of the initial frame rate of the current monitoring point and the second product as the adjusted frame rate of the current monitoring point.

10. A noise distribution visualization monitoring system based on GIS, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

Images