Dynamic visual noise monitoring method and system

Abstract

The invention discloses a dynamic visual noise monitoring method and system, and relates to the technical field of noise monitoring, and the method comprises the steps: obtaining the position coordinates of noise monitoring points in a to-be-monitored region, and collecting the noise intensity sequence of each noise monitoring point in real time; based on the noise intensity sequence, obtaining position coordinates and noise intensity of the estimated noise source; dividing a to-be-monitored area into a plurality of sub-areas, and obtaining a target area of a to-be-interpolated position; calculating interpolation weights of each noise monitoring point and each estimated noise source in the target area based on the position coordinates of the noise monitoring points and the estimated noise sources; performing bimodal interpolation on the to-be-interpolated position to obtain the noise intensity of the to-be-interpolated position; mapping the noise intensity and color of each position to be interpolated to obtain a noise intensity thermodynamic diagram of the area to be monitored; according to the invention, accurate interpolation can be carried out on the noise intensity of an unknown position, the accuracy of noise monitoring is enhanced, and a dynamic visualization effect of noise monitoring is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of noise monitoring, and in particular to a dynamic visualization monitoring method and system for noise. Background Art

[0002] With the acceleration of urbanization and the increase in human activity in areas such as traffic planning and industrial regulation, noise pollution has become an increasingly serious environmental problem. Long-term exposure to noise not only causes irritability, poor sleep quality, and dizziness, but can also lead to heart disease, learning disabilities, and tinnitus. Therefore, monitoring and controlling urban noise pollution is necessary and of practical significance. Noise monitoring is the monitoring of sounds and their sources that interfere with people's learning, work, and life. This includes noise monitoring in various functional areas of a city, road traffic noise monitoring, regional environmental noise monitoring, and noise source monitoring. Noise monitoring results are generally expressed in weighted sound levels, using sound level meters and spectrum analyzers as the primary instruments. Noise monitoring results are used to analyze the current status and changing trends of noise pollution, and also provide basic data for planning, management, and comprehensive remediation of noise pollution.

[0003] Traditional noise monitoring methods typically rely on a limited number of fixed monitoring points, failing to provide real-time feedback on noise changes across various areas. Furthermore, because noise sensors are typically distributed across diverse locations, existing technologies fuse and interpolate these scattered monitoring data to infer the noise distribution across the entire area. However, most traditional noise monitoring methods employ IDW (Inverse-Distance-Weighting) for spatial interpolation, relying solely on the distance between the interpolated location and the noise sensor. This method ignores the influence of noise source distribution within the monitoring area and differences in sensor density. As a result, the interpolated result fails to exceed the maximum noise intensity measured by the sensor, and the noise intensity in areas near the noise source is underestimated. This makes traditional noise monitoring methods prone to significant deviations in noise intensity distribution, resulting in poor noise monitoring accuracy. Furthermore, traditional noise monitoring methods lack direct observation of noise intensity, making them less intuitive. Summary of the Invention

[0004] In order to accurately interpolate the noise intensity at an unknown location, enhance the accuracy of noise monitoring, achieve dynamic visualization of noise monitoring, and address the drawback of traditional noise monitoring methods that often result in large deviations in noise intensity distribution when performing spatial interpolation, the present invention provides a method and system for dynamic visualization of noise monitoring. The technical solution is as follows: In a first aspect, the present invention provides a dynamic visualization monitoring method for noise, the steps of which include: obtaining the position coordinates of noise monitoring points in a to-be-monitored area, and collecting the noise intensity sequence of each noise monitoring point in real time; clustering the noise intensity sequence to obtain a number of clusters, setting an equal number of particles according to the number of clusters, and iteratively updating the parameters of the particles to obtain the position coordinates and noise intensities of a number of estimated noise sources; dividing the to-be-monitored area into a number of sub-areas, and obtaining a target area for the position to be interpolated; based on the position coordinates of the noise monitoring points and the estimated noise sources, calculating the interpolation weights of each noise monitoring point and the estimated noise source in the target area; performing bimodal interpolation on the position to be interpolated based on the interpolation weights of the noise monitoring points and the estimated noise sources to obtain the noise intensity of the position to be interpolated; mapping the noise intensity of each position to be interpolated with a color to obtain a noise intensity heat map of the to-be-monitored area at the current moment; Among them, based on the position coordinates of the noise monitoring points and estimated noise sources in the target area, the density interpolation weights and distance interpolation weights of all noise monitoring points and estimated noise sources in the target area are calculated; the product of the density interpolation weight and the distance interpolation weight of each noise monitoring point is used as the interpolation weight of the corresponding noise monitoring point, and the interpolation weight of each estimated noise source is obtained similarly.

[0005] Preferably, according to the actual scenario, multiple positions are randomly selected or equidistantly selected in the same horizontal plane of the area to be monitored as noise monitoring points, a noise sensor is placed at each noise monitoring point, a two-dimensional plane coordinate system is established based on the area to be measured, the position coordinates of each noise monitoring point are recorded, the noise intensity of the noise monitoring point is collected in real time by the noise sensor, and the noise intensity data within the preset time period is used as the noise intensity sequence of the corresponding noise monitoring point at the current moment.

[0006] Preferably, all noise intensity sequences are differentially processed to obtain a differential sequence corresponding to each noise monitoring point, and the differential sequence is clustered using the DBSCAN algorithm to obtain a number of clusters. According to the number of clusters, a number of position points in the monitored area are randomly selected as particles, the number of particles is the same as the number of clusters, and each particle corresponds to an estimated noise source; the initial parameters of the particles are obtained and set, including the initial position coordinates and the initial noise intensity, and the set initial noise intensity is greater than or equal to the maximum value of all noise intensity sequences.

[0007] Preferably, based on the distance between the noise monitoring point and the particle, the ideal attenuated noise intensity of all particles at each noise monitoring point position is calculated through the point sound source noise attenuation formula, and based on the multi-noise decibel superposition principle, the ideal superimposed noise intensity of each noise monitoring point position is calculated. Based on the noise intensity sequence and the ideal superimposed noise intensity collected in real time at the noise monitoring point, the objective function of the particle swarm optimization is constructed, the particle swarm optimization algorithm is used to optimize the initial parameters of the particles, and the initial parameters of the particles are iteratively updated to obtain the optimized parameters of all particles, and then the position coordinates and noise intensity of all estimated noise sources are obtained.

[0008] Preferably, the area to be monitored is divided into multiple sub-areas of equal size. For a certain position to be interpolated, the sub-area where the position to be interpolated is located and all its adjacent sub-areas are merged, which is called the target area of ​​the position to be interpolated. The target area of ​​each position to be interpolated contains at least one noise monitoring point and one estimated noise source.

[0009] Preferably, the position coordinates of all noise monitoring points and estimated noise sources in the target area are obtained, the average value of the Euclidean distances between the position of a noise monitoring point in the target area and the positions of the remaining noise monitoring points is used as the average distribution distance of the noise monitoring point, the average value of the Euclidean distances between the position of the noise monitoring point and the positions of all estimated noise sources in the target area is used as the average monitoring distance of the noise monitoring point, and the ratio between the average distribution distance and the average monitoring distance is used as the density interpolation weight of the noise monitoring point; similarly, the average value of the Euclidean distances between the position of a certain estimated noise source in the target area and the positions of the remaining estimated noise sources is used as the average distribution distance of the estimated noise source, the average value of the Euclidean distances between the position of the estimated noise source and the positions of all noise monitoring points in the target area is used as the average emission distance of the estimated noise source, and the ratio between the average distribution distance and the average emission distance is used as the density interpolation weight of the estimated noise source; calculations are performed on each noise monitoring point and estimated noise source in turn to obtain the density interpolation weights of all noise monitoring points and estimated noise sources in the target area.

[0010] Preferably, the Euclidean distance between the position of each noise monitoring point in the target area and the position to be interpolated is calculated, and one-half the square of the Euclidean distance corresponding to each noise monitoring point is used as the distance interpolation weight of the corresponding noise monitoring point; similarly, the Euclidean distance between the position of each estimated noise source in the target area and the position to be interpolated is calculated, and one-half the square of the Euclidean distance corresponding to each estimated noise source is used as the distance interpolation weight of the corresponding estimated noise source; the density interpolation weights and distance interpolation weights of the noise monitoring points and the estimated noise sources are combined to obtain the interpolation weights of each noise monitoring point and the estimated noise source in the target area.

[0011] Preferably, the ratio of the interpolation weight of each noise monitoring point in the target area to the sum of the interpolation weights of all noise monitoring points in the target area is used as the normalized interpolation weight of the corresponding noise monitoring point. Similarly, the ratio of the interpolation weight of each estimated noise source in the target area to the sum of the interpolation weights of all estimated noise sources in the target area is used as the normalized interpolation weight of the corresponding estimated noise source; the product of the normalized interpolation weight of each noise monitoring point in the target area and the average value of the corresponding noise intensity sequence is used as the weight component of each noise monitoring point, and the weight components of all noise monitoring points in the target area are accumulated to serve as the noise monitoring point interpolation of the corresponding position to be interpolated; similarly, the product of the normalized interpolation weight of each estimated noise source in the target area and the noise intensity of the corresponding estimated noise source is used as the weight component of each estimated noise source, and the weight components of all estimated noise sources in the target area are accumulated to serve as the estimated noise source interpolation of the corresponding position to be interpolated; the weights of the noise monitoring point interpolation and the estimated noise source interpolation are set, and the sum of the products of the noise monitoring point interpolation and the estimated noise source interpolation with the corresponding weights is used as the noise intensity of the corresponding position to be interpolated.

[0012] Preferably, according to the restriction requirements on noise intensity in actual scenarios, the value range of noise intensity is divided into several levels, and different levels of noise intensity are mapped to different colors respectively. The noise intensity within the same level range corresponds to one color, and the noise intensity of all interpolation positions in the area to be monitored at the current moment is mapped to the color of the corresponding level respectively, so as to obtain the noise intensity heat map of the area to be monitored at the current moment, and update the noise intensity heat map of the area to be monitored in real time to realize dynamic visual monitoring of noise intensity.

[0013] In a second aspect, the present invention provides a dynamic visualization monitoring system for noise, which is used to implement the above-mentioned dynamic visualization monitoring method for noise, and includes: a processor, a memory, a communication interface, a display screen and a noise sensor. The processor stores computer program instructions for implementing the above-mentioned dynamic visualization monitoring method for noise. The noise sensors are provided in plurality and installed on the same horizontal plane. The communication interface is communicatively connected to the display screen and the noise sensor.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The present invention obtains the location information and noise intensity of each noise monitoring point and estimated noise source, calculates the density interpolation weight and distance interpolation weight corresponding to the noise monitoring point and estimated noise source in the target area at each position to be interpolated, and then obtains the noise monitoring point interpolation and estimated noise source interpolation of each position to be interpolated. Finally, the interpolation weights of the noise monitoring point and the estimated noise source are combined to perform bimodal interpolation on the position to be interpolated to obtain the noise intensity of each position to be interpolated. By accurately interpolating the noise intensity of unknown positions through bimodal interpolation, the accuracy of noise monitoring can be effectively enhanced. Compared with the traditional noise monitoring method that only uses the IDW interpolation method for interpolation, the present invention solves the defect that the existing IDW interpolation method relies only on distance division weights, which makes the interpolation unable to exceed the maximum noise intensity measured by the noise sensor, resulting in local optimality of the interpolated data and large global deviation. It also solves the problem that the traditional noise monitoring method easily leads to a large deviation between the noise intensity distribution of the monitoring results and the actual noise intensity distribution; at the same time, by mapping the noise intensity of each to-be-interpolated position with color and displaying it in the form of a heat map, the noise intensity heat map of the to-be-monitored area is updated in real time, thereby achieving a dynamic visualization effect of noise monitoring and making the noise intensity monitoring results more intuitive. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flowchart of an implementation method of a dynamic visual monitoring method of noise according to an embodiment of the present application; Figure 2 This is a structural block diagram of a dynamic visualization monitoring system for noise according to an embodiment of the present application. DETAILED DESCRIPTION

[0016] The technical features of the present invention are further described in detail below with reference to the accompanying drawings so that those skilled in the relevant art can understand them.

[0017] A dynamic visual monitoring method for noise, the implementation process is as follows Figure 1 The specific implementation steps are as follows: Step S1: Obtain the position coordinates of the noise monitoring points in the area to be monitored, and collect the noise intensity sequence of each noise monitoring point in real time; Specifically, according to the actual scenario, multiple locations are randomly selected or equidistantly selected in the same horizontal plane of the area to be monitored as noise monitoring points, a noise sensor is placed at each noise monitoring point, and each noise sensor corresponds to a noise monitoring point. A two-dimensional plane coordinate system is established based on the area to be measured, and the position coordinates of each noise monitoring point are recorded. The noise intensity of the noise monitoring point is collected in real time by the noise sensor, and the noise intensity data within a preset time period is used as the noise intensity sequence of the corresponding noise monitoring point at the current moment; Among them, the noise intensity sequence specifically refers to the noise intensity data within a window including the current moment and the previous moments. The preset period, that is, the collection duration of the noise intensity, can be set to 10 seconds to 10 minutes according to the real-time requirements of noise monitoring in actual application scenarios. The noise is monitored in real time by collecting the noise intensity sequence instead of the noise intensity value at the current moment. The reason is that the time delay of noise propagation needs to be considered to avoid accidental errors caused by environmental factors.

[0018] Step S2: clustering the noise intensity sequence to obtain a number of clusters, setting an equal number of particles according to the number of clusters, iteratively updating the parameters of the particles, and obtaining a number of estimated noise source position coordinates and noise intensities; Since there may be multiple noise sources in the noise monitoring area, each noise monitoring point is at a different distance from the noise source and is affected inconsistently by different noise sources, resulting in complex and diverse noise distribution in the area. The existing technology uses the IDW interpolation method to interpolate unknown positions in the monitoring area, but the IDW interpolation method only relies on distance to calculate weights. The closer the noise monitoring point is, the greater the influence on the interpolation position. When multiple noise monitoring points are close to the position to be interpolated, the close monitoring points dominate the interpolation size, resulting in the interpolation influence of the slightly farther monitoring points being over-smoothed, resulting in the phenomenon that the noise intensity deviates from the true distribution. Therefore, it is necessary to obtain the estimated position coordinates and noise intensity of the noise source based on the particle swarm optimization algorithm, so as to more accurately calculate the noise intensity of the position to be interpolated in subsequent steps.

[0019] Specifically, all noise intensity sequences are differentially processed to obtain a differential sequence corresponding to each noise monitoring point. The DBSCAN algorithm is a density-based spatial clustering algorithm. The DBSCAN (Density-Based-Spatial-Clustering-of-Applications-with-Noise) algorithm is used to cluster the differential sequences to obtain several clusters. According to the number of clusters, several position points in the monitored area are randomly selected as particles. The number of particles is the same as the number of clusters, and each particle corresponds to an estimated noise source. The initial parameters of the particles are obtained and set, including the initial position coordinates and the initial noise intensity. Each particle contains three parameters: the x-axis coordinate, the y-axis coordinate, and the noise intensity. The set initial noise intensity is greater than or equal to the maximum value of all noise intensity sequences. In addition, based on the distance between the noise monitoring point and the particle, the ideal attenuated noise intensity of all particles at each noise monitoring point is calculated using the point sound source noise attenuation formula. Based on the principle of multi-noise decibel superposition, the ideal superimposed noise intensity at each noise monitoring point is calculated. Point sound source noise attenuation and multi-noise decibel superposition are both existing technologies. Based on the noise intensity sequence and the ideal superimposed noise intensity collected in real time by the noise monitoring point, the objective function of the particle swarm optimization is constructed. The process is as follows: the difference between the ideal superimposed noise intensity and the average value of the noise intensity sequence of each noise monitoring point in the monitored area is calculated, and the square of the difference corresponding to each noise monitoring point is accumulated as the objective function of the particle swarm optimization. The initial parameters of the particles are optimized using the particle swarm optimization algorithm. The process is as follows: based on the requirements of the actual application scenario for real-time noise monitoring, the number of iterations is preset, and the particle position parameter update step size and noise intensity parameter update step size are set. Then, based on the particle swarm optimization algorithm and the objective function, the initial parameters of the particles are iteratively updated until the preset number of iterations is reached, and the optimized parameters of all particles are obtained, and then the position coordinates and noise intensity of all estimated noise sources are obtained. Among them, the objective function formula of particle swarm optimization is as follows: Where, represents the objective function of particle swarm optimization, represents the number of noise monitoring points, Indicates the The ideal superimposed noise intensity of each noise monitoring point is Indicates the The average value of the noise intensity sequence corresponding to the noise monitoring points; The particle swarm optimization algorithm is used to update the parameters of the particles. The update step size of the position parameter can be set to 1, and the update step size of the noise intensity parameter can be set to no less than the average value of the noise intensity sequence of the nearest noise monitoring point. The particle parameters are continuously updated iteratively, and the ideal attenuated noise intensity of all particles at each noise monitoring point and the ideal superimposed noise intensity at each noise monitoring point are repeatedly calculated to obtain the corresponding objective function value. The iteration is stopped until a preset number of iterations is reached. An exemplary preset number of iterations is 50. The particle parameters corresponding to the minimum objective function value during the iteration process are selected as the position coordinates and noise intensity data of the estimated noise source. Each particle corresponds to an estimated noise source.

[0020] Step S3: Divide the area to be monitored into several sub-areas and obtain the target area of ​​the position to be interpolated; Specifically, the area to be monitored is divided into multiple sub-areas of equal size. For a certain position to be interpolated, the sub-area where the position to be interpolated is located and all its adjacent sub-areas are merged to form the target area of ​​the position to be interpolated. The target area of ​​each position to be interpolated contains at least one noise monitoring point and one estimated noise source. There are three cases for the target area: when the position to be interpolated is in the corner area, the number of its adjacent sub-areas is 3; when the position to be interpolated is in the edge area, the number of its adjacent sub-areas is 5; and when the position to be interpolated is in the middle area, the number of its adjacent sub-areas is 8.

[0021] Step S4: Based on the position coordinates of the noise monitoring points and the estimated noise sources, the interpolation weights of each noise monitoring point and the estimated noise source in the target area are calculated; Specifically, the position coordinates of all noise monitoring points and estimated noise sources in the target area are obtained, the average value of the Euclidean distances between the position of a noise monitoring point and the positions of the remaining noise monitoring points in the target area is used as the average distribution distance of the noise monitoring point, the average value of the Euclidean distances between the position of the noise monitoring point and the positions of all estimated noise sources in the target area is used as the average monitoring distance of the noise monitoring point, and the ratio between the average distribution distance and the average monitoring distance is used as the density interpolation weight of the noise monitoring point; similarly, the average value of the Euclidean distances between the position of an estimated noise source in the target area and the positions of the remaining estimated noise sources is used as the average distribution distance of the estimated noise source, the average value of the Euclidean distances between the position of the estimated noise source and the positions of all noise monitoring points in the target area is used as the average emission distance of the estimated noise source, and the ratio between the average distribution distance and the average emission distance is used as the density interpolation weight of the estimated noise source; calculations are performed on each noise monitoring point and estimated noise source in turn to obtain the density interpolation weights of all noise monitoring points and estimated noise sources in the target area; The calculation logic of the density interpolation weight is as follows: for a noise monitoring point, the smaller the Euclidean distance between it and the other noise monitoring points in the target area, the greater the density of the monitoring point. Over-reliance on this monitoring point will cause the interpolation to fall into a local optimum, so the density interpolation weight should be proportional to the Euclidean distance between the monitoring points. At the same time, for a noise monitoring point, the greater the Euclidean distance between it and the estimated noise source in the target area, the greater the impact of the environment on the noise intensity measured at the monitoring point, and the more likely it is to cause measurement distortion. Over-reliance on this monitoring point will cause the interpolation to deviate from the true distribution. Therefore, the density interpolation weight should be inversely proportional to the Euclidean distance between the monitoring point and the estimated noise source. The density interpolation weight of noise monitoring points in the target area is calculated as follows: Where, Indicates the target area The density interpolation weight of noise monitoring points, Indicates the The average value of the Euclidean distance between the location of the noise monitoring point and the locations of the other noise monitoring points in the target area, Indicates the The average value of the Euclidean distances between the locations of the noise monitoring points and all estimated noise source locations within the target area; Similarly, the density interpolation weight of the estimated noise source in the target area is calculated as follows: Where, Indicates the target area density interpolation weights for estimating noise sources, Indicates the The average value of the Euclidean distances between the estimated noise source location and the other estimated noise source locations in the target area, Indicates the The average value of the Euclidean distances between the estimated noise source location and all noise monitoring points in the target area.

[0022] In addition, the Euclidean distance between the position of each noise monitoring point in the target area and the position to be interpolated is calculated, and one-half of the square of the Euclidean distance corresponding to each noise monitoring point is used as the distance interpolation weight of the corresponding noise monitoring point; similarly, the Euclidean distance between the position of each estimated noise source in the target area and the position to be interpolated is calculated, and one-half of the square of the Euclidean distance corresponding to each estimated noise source is used as the distance interpolation weight of the corresponding estimated noise source; the density interpolation weights and distance interpolation weights of the noise monitoring points and the estimated noise sources are combined, and the product of the density interpolation weight and the distance interpolation weight of each noise monitoring point is used as the interpolation weight of the corresponding noise monitoring point. Similarly, the product of the density interpolation weight and the distance interpolation weight of each estimated noise source is used as the interpolation weight of the corresponding estimated noise source, thereby obtaining the interpolation weight of each noise monitoring point and the estimated noise source in the target area; The interpolation weight of the noise monitoring points in the target area is calculated as follows: Where, Indicates the target area The interpolation weight of the noise monitoring point, Indicates the The Euclidean distance between the noise monitoring point and the position to be interpolated, Indicates the The distance interpolation weight of each noise monitoring point, Indicates the Density interpolation weight of noise monitoring points; Similarly, the interpolation weight of the estimated noise source in the target area is calculated as follows: Where, Indicates the target area The interpolation weights for estimating noise sources, Indicates the The Euclidean distance between the estimated noise source position and the position to be interpolated, Indicates the The distance interpolation weights of the estimated noise sources, Indicates the density interpolation weights for estimating noise sources; The weights of monitoring points are measured using the dual dimensions of density and distance. In dense areas, since too many monitoring points easily dominate the interpolation direction, their weights should be appropriately reduced. In sparse areas, although the monitoring points are farther away, the measured noise intensity distribution range is larger, so their weights should be appropriately increased to avoid local interpolation optimality.

[0023] Step S5: performing bimodal interpolation on the position to be interpolated based on the interpolation weights of the noise monitoring point and the estimated noise source to obtain the noise intensity at the position to be interpolated; Specifically, the ratio of the interpolation weight of each noise monitoring point in the target area to the sum of the interpolation weights of all noise monitoring points in the target area is used as the normalized interpolation weight of the corresponding noise monitoring point. Similarly, the ratio of the interpolation weight of each estimated noise source in the target area to the sum of the interpolation weights of all estimated noise sources in the target area is used as the normalized interpolation weight of the corresponding estimated noise source. Among them, The normalized interpolation weight of the noise monitoring point is , the normalization formula is as follows: n represents the number of noise monitoring points in the target area. Similarly, The normalized interpolation weight of each estimated noise source is ; In addition, the product of the normalized interpolation weight of each noise monitoring point in the target area and the average value of the corresponding noise intensity series is used as the weight component of each noise monitoring point, and the weight components of all noise monitoring points in the target area are accumulated to serve as the noise monitoring point interpolation of the corresponding position to be interpolated; similarly, the product of the normalized interpolation weight of each estimated noise source in the target area and the noise intensity of the corresponding estimated noise source is used as the weight component of each estimated noise source, and the weight components of all estimated noise sources in the target area are accumulated to serve as the estimated noise source interpolation of the corresponding position to be interpolated; the weights of the noise monitoring point interpolation and the estimated noise source interpolation are set, and the sum of the products of the noise monitoring point interpolation and the estimated noise source interpolation with the corresponding weights is used as the noise intensity of the corresponding position to be interpolated; The calculation formula for the noise intensity at the position to be interpolated is as follows: Where, Indicates the noise intensity at a certain position to be interpolated, Indicates the number of noise monitoring points in the target area, Indicates the The normalized interpolation weight of the noise monitoring points, Indicates the The average value of the noise intensity sequence of noise monitoring points, represents the number of estimated noise sources in the target area, Indicates the The interpolation weights after normalization of the estimated noise sources, Indicates the An estimated noise source's noise intensity, represents the interpolation of noise monitoring points, represents the estimated noise source interpolation, represents the weight of the noise monitoring point interpolation, Represents the weight of the estimated noise source interpolation. The weight of the noise monitoring point interpolation and the estimated noise source interpolation is usually set to 0.5; Since the noise source in the monitored area is unknown, the selected noise monitoring point is not necessarily the location of the noise source, resulting in the noise intensity collected by the noise monitoring point being usually lower than the noise intensity of the noise source; the existing technology obtains the noise intensity of the unknown location through the noise intensity of the known noise monitoring point and IDW interpolation, and the IDW interpolation depends on the distance between the noise monitoring point and the unknown location for weighted fusion interpolation, resulting in the interpolation result not exceeding the noise intensity of the noise monitoring point at most, masking the noise intensity distribution near the noise source in the area, resulting in the phenomenon of underestimated noise intensity and untimely warning; therefore, the present invention obtains the noise monitoring point interpolation through the normalized interpolation weight of the noise monitoring point, obtains the estimated noise source interpolation through the normalized interpolation weight of the estimated noise source, performs weighted fusion on the noise monitoring point interpolation and the estimated noise source interpolation, and obtains the noise intensity of the location to be interpolated through bimodal interpolation; by performing bimodal interpolation on the estimated noise source and the noise monitoring point, it is possible to analyze the noise intensity under the influence of the superposition of multiple estimated noise sources, obtain a more accurate noise intensity distribution, and adapt to the dynamic visual monitoring of mobile noise sources, avoiding the phenomenon that the interpolation cannot exceed the known monitoring point.

[0024] Step S6: Mapping the noise intensity and color of each position to be interpolated to obtain a noise intensity heat map of the area to be monitored at the current moment; Specifically, according to the restriction requirements on noise intensity in actual scenarios, the value range of noise intensity is divided into several levels, and different levels of noise intensity are mapped to different colors. The noise intensity within the same level range corresponds to one color, and the noise intensity of all interpolation positions in the monitored area at the current moment is mapped to the color of the corresponding level to obtain the noise intensity heat map of the monitored area at the current moment. The noise intensity heat map of the monitored area is updated in real time to realize dynamic visual monitoring of noise intensity. In addition, the noise intensity threshold can be set, and the positions where the noise intensity exceeds the threshold in the monitored area are marked and a flashing notification warning is issued.

[0025] The present invention also discloses a dynamic visualization monitoring system for noise, which is used to implement the dynamic visualization monitoring method for noise. The system structure is as follows: Figure 2 As shown, it includes: a processor, a memory, a communication interface, a display screen and a noise sensor. The processor stores computer program instructions for implementing the above-mentioned dynamic visualization monitoring method for noise. The noise sensors are provided in plurality and installed on the same horizontal plane. The communication interface is communicatively connected with the display screen and the noise sensor.

[0026] The embodiments included in the present invention are merely descriptions of preferred implementation methods of the present invention and are not limited to the precise structures described above and shown in the accompanying drawings. Various modifications and changes can be made without departing from the scope of protection of the present invention. Without departing from the design concept of the present invention, various modifications and improvements made to the technical solution of the present invention by engineers and technicians in this field should fall within the scope of protection of the present invention.

Claims

1. A dynamic visual monitoring method for noise, characterized by: Obtain the position coordinates of the noise monitoring points in the area to be monitored, and collect the noise intensity sequence of each noise monitoring point in real time; cluster the noise intensity sequence to obtain several clusters, set an equal number of particles according to the number of clusters, iteratively update the parameters of the particles, and obtain the position coordinates and noise intensity of several estimated noise sources; divide the area to be monitored into several sub-areas, and obtain the target area of ​​the position to be interpolated; based on the position coordinates of the noise monitoring points and the estimated noise sources, calculate the interpolation weights of each noise monitoring point and estimated noise source in the target area; combine the interpolation weights of the noise monitoring points and the estimated noise sources to perform bimodal interpolation on the position to be interpolated to obtain the noise intensity of the position to be interpolated; map the noise intensity of each position to be interpolated to color to obtain a noise intensity heat map of the area to be monitored at the current moment; Among them, based on the position coordinates of the noise monitoring points and estimated noise sources in the target area, the density interpolation weights and distance interpolation weights of all noise monitoring points and estimated noise sources in the target area are calculated; the product of the density interpolation weight and the distance interpolation weight of each noise monitoring point is used as the interpolation weight of the corresponding noise monitoring point, and the interpolation weight of each estimated noise source is obtained similarly.

2. The dynamic visualization monitoring method for noise according to claim 1, characterized in that: The method of obtaining the position coordinates of the noise monitoring points in the area to be monitored and collecting the noise intensity sequence of each noise monitoring point in real time includes: randomly selecting or equidistantly selecting multiple positions as noise monitoring points in the same horizontal plane of the area to be monitored according to the actual scenario, placing a noise sensor at each noise monitoring point, establishing a two-dimensional plane coordinate system based on the area to be measured, recording the position coordinates of each noise monitoring point, collecting the noise intensity of the noise monitoring point in real time through the noise sensor, and using the noise intensity data within a preset time period as the noise intensity sequence of the corresponding noise monitoring point at the current moment.

3. The dynamic visualization monitoring method for noise according to claim 1, characterized in that: The noise intensity sequence is clustered to obtain a plurality of clusters, and an equal number of particles are set according to the number of clusters, including: performing differential processing on all noise intensity sequences to obtain a differential sequence corresponding to each noise monitoring point, clustering the differential sequence using the DBSCAN algorithm to obtain a plurality of clusters, and randomly selecting a plurality of position points in the area to be monitored as particles according to the number of clusters, wherein the number of particles is the same as the number of clusters, and each particle corresponds to an estimated noise source; and obtaining and setting initial parameters of the particles, including initial position coordinates and initial noise intensity, wherein the set initial noise intensity is greater than or equal to the maximum value of all noise intensity sequences.

4. The dynamic visualization monitoring method for noise according to claim 3, characterized in that: The parameters of the particles are iteratively updated to obtain the position coordinates and noise intensities of several estimated noise sources, including: calculating the ideal attenuated noise intensity of all particles at each noise monitoring point position based on the distance between the noise monitoring point and the particle using a point sound source noise attenuation formula; calculating the ideal superimposed noise intensity at each noise monitoring point position based on the multi-noise decibel superposition principle; constructing a particle swarm optimization objective function based on the noise intensity sequence and the ideal superimposed noise intensity collected in real time at the noise monitoring point; optimizing the initial parameters of the particles using a particle swarm optimization algorithm; iteratively updating the initial parameters of the particles to obtain the optimized parameters of all particles, and then obtaining the position coordinates and noise intensities of all estimated noise sources.

5. The dynamic visualization monitoring method for noise according to claim 1, characterized in that: The method of dividing the area to be monitored into a plurality of sub-areas and obtaining a target area for the position to be interpolated includes: dividing the area to be monitored into a plurality of sub-areas of equal size; for a certain position to be interpolated, merging the sub-area where the position to be interpolated is located with all its adjacent sub-areas, which is referred to as the target area for the position to be interpolated; and each target area for the position to be interpolated contains at least one noise monitoring point and one estimated noise source.

6. The dynamic visual monitoring method for noise according to claim 1, characterized in that: The method of calculating the interpolation weight of each noise monitoring point and estimated noise source in the target area based on the position coordinates of the noise monitoring point and the estimated noise source includes: obtaining the position coordinates of all noise monitoring points and estimated noise sources in the target area, taking the average of the Euclidean distances between the position of a noise monitoring point and the positions of other noise monitoring points in the target area as the average distribution distance of the noise monitoring point, taking the average of the Euclidean distances between the position of the noise monitoring point and the positions of all estimated noise sources in the target area as the average monitoring distance of the noise monitoring point, and taking the ratio between the average distribution distance and the average monitoring distance as the density interpolation weight of the noise monitoring point; similarly, taking the average of the Euclidean distances between the position of an estimated noise source in the target area and the positions of other estimated noise sources as the average distribution distance of the estimated noise source, taking the average of the Euclidean distances between the position of the estimated noise source and the positions of all noise monitoring points in the target area as the average emission distance of the estimated noise source, and taking the ratio between the average distribution distance and the average emission distance as the density interpolation weight of the estimated noise source; and performing calculations on each noise monitoring point and estimated noise source in turn to obtain the density interpolation weights of all noise monitoring points and estimated noise sources in the target area.

7. The dynamic visual monitoring method for noise according to claim 6, characterized in that: The method of calculating the interpolation weight of each noise monitoring point and estimated noise source in the target area based on the position coordinates of the noise monitoring point and the estimated noise source also includes: calculating the Euclidean distance between the position of each noise monitoring point in the target area and the position to be interpolated, and using one-half the square of the Euclidean distance corresponding to each noise monitoring point as the distance interpolation weight of the corresponding noise monitoring point; similarly, calculating the Euclidean distance between the position of each estimated noise source in the target area and the position to be interpolated, and using one-half the square of the Euclidean distance corresponding to each estimated noise source as the distance interpolation weight of the corresponding estimated noise source; and comprehensively combining the density interpolation weights and distance interpolation weights of the noise monitoring points and the estimated noise sources to obtain the interpolation weight of each noise monitoring point and the estimated noise source in the target area.

8. The dynamic visualization monitoring method for noise according to any one of claims 1 to 7, characterized in that: The method combines the interpolation weights of the noise monitoring points and the estimated noise sources to perform bimodal interpolation on the position to be interpolated to obtain the noise intensity of the position to be interpolated, including: taking the ratio of the interpolation weight of each noise monitoring point in the target area to the sum of the interpolation weights of all noise monitoring points in the target area as the normalized interpolation weight of the corresponding noise monitoring point; similarly, taking the ratio of the interpolation weight of each estimated noise source in the target area to the sum of the interpolation weights of all estimated noise sources in the target area as the normalized interpolation weight of the corresponding estimated noise source; taking the product of the normalized interpolation weight of each noise monitoring point in the target area and the average value of the corresponding noise intensity sequence as The weight component of each noise monitoring point is accumulated by adding the weight components of all noise monitoring points in the target area as the noise monitoring point interpolation of the corresponding position to be interpolated; similarly, the product of the normalized interpolation weight of each estimated noise source in the target area and the noise intensity of the corresponding estimated noise source is used as the weight component of each estimated noise source, and the weight components of all estimated noise sources in the target area are accumulated as the estimated noise source interpolation of the corresponding position to be interpolated; the weights of the noise monitoring point interpolation and the estimated noise source interpolation are set, and the sum of the products of the noise monitoring point interpolation and the estimated noise source interpolation with the corresponding weights is used as the noise intensity of the corresponding position to be interpolated.

9. The dynamic visualization monitoring method for noise according to claim 1, characterized in that: The noise intensity of each to-be-interpolated position is mapped with color to obtain a noise intensity heat map of the area to be monitored at the current moment, including: dividing the value range of noise intensity into several levels according to the restriction requirements on noise intensity in actual scenarios, mapping different levels of noise intensity with different colors, and the noise intensity within the same level range corresponds to one color, mapping the noise intensity of all to-be-interpolated positions in the area to be monitored at the current moment with the color of the corresponding level, obtaining a noise intensity heat map of the area to be monitored at the current moment, updating the noise intensity heat map of the area to be monitored in real time, and realizing dynamic visual monitoring of noise intensity.

10. A dynamic visual noise monitoring system, characterized by: The device comprises a processor, a memory, a communication interface, a display screen and a noise sensor, wherein the processor stores computer program instructions for implementing the dynamic visual monitoring method for noise according to any one of claims 1 to 9, a plurality of noise sensors are provided and installed on the same horizontal plane, and the communication interface is communicatively connected to the display screen and the noise sensor.

Images