Intelligent air quality detection method and system and air quality detector

Abstract

The invention relates to the technical field of air quality detection, in particular to an intelligent air quality detection method and system and an air quality detector.The method comprises the steps that multi-dimensional gas data of different positions in a detection area are obtained, and a detector space structure diagram is constructed by means of the space distance between air quality sensors; and aiming at the air quality sensors with a connection relation in the detector space structure diagram, optimizing and adjusting the detector space structure diagram in combination with diffusion relation characteristics expressed among the multi-dimensional gas data, thereby utilizing a topological structure relation among the air quality sensors in the optimized detector space structure diagram to determine the air quality in the detector space structure diagram. And a concentration distribution model of gas particles in the detection area is established in combination with the multi-dimensional gas data, so that the air quality of the detection area is evaluated and alarmed. According to the invention, overall air quality evaluation is carried out on the detection area, and the air quality evaluation effect in the detection area is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of air quality detection, and particularly relates to an intelligent air quality detection method, system and air quality detector. Background Art

[0002] In the indoor environment, air quality also affects people's physical health. Therefore, it is essential to detect the air quality in the indoor environment. At the same time, with the rapid development of technologies such as the Internet of Things, big data, and artificial intelligence, air quality monitors based on intelligent technologies have emerged. They can monitor harmful substances in the air in real time and timely warn of potential air quality problems. Intelligent air quality detection methods usually include sensor technology, data transmission technology, data analysis and processing technology, etc. Concentration data of various pollutants in the air (such as PM2.5, PM10, CO, NO2, SO2, etc.) are collected through high-precision sensors, and then data processing and analysis are carried out through a cloud platform, and finally intuitive air quality monitoring results are provided to users.

[0003] However, in the indoor environment, even though the air flow rate is relatively small compared to the outdoors, the gas particles in the air are not evenly distributed in space but have the characteristic of gradient propagation. Then, in the conventional air quality detection process, even if there are multiple air quality detectors in an area, due to their independent operation, it is impossible to have an overall detection of the composition of the air in this area, resulting in low reliability of the detection results. Summary of the Invention

[0004] The present invention provides an intelligent air quality detection method, system and air quality detector to solve the existing problems.

[0005] The intelligent air quality detection method, system and air quality detector of the present invention adopt the following technical solutions: An embodiment of the present invention provides an intelligent air quality detection method, which includes the following steps: Obtain multi-dimensional gas data at several positions in the detection area through several air quality sensors; Utilize the spatial positions of the air quality sensors in the detection area and combine the spatial distances between the air quality sensors to construct a sensor spatial structure diagram; For the air quality sensors with connection relationships in the detector spatial structure diagram, in combination with the diffusion relationship characteristics shown between the multi-dimensional gas data, optimize and adjust the detector spatial structure diagram, utilize the topological structure relationship between the air quality sensors in the optimized detector spatial structure diagram, and establish a concentration distribution model of gas particles in the detection area in combination with the multi-dimensional gas data; Evaluate and alarm the air quality of the detection area using the concentration distribution model of the gas particles.

[0006] Further, the method for constructing the sensor spatial structure diagram by using the spatial positions of the air quality sensors in the detection area and combining the spatial distances between the air quality sensors specifically includes: Take any air quality sensor as a spatial node. Starting from any spatial node, use the depth-first search algorithm to traverse all spatial nodes, obtain the spatial node closest to the starting point, and connect them. During the traversal process, iterate through the traversal according to the minimum distance until all spatial nodes are traversed. The obtained connection result is used as the initial structure corresponding to the spatial starting point of the starting point. Merge the initial structures after iteratively traversing with all spatial nodes as starting points respectively, count the number of edges corresponding to the same connected spatial nodes at both ends as the edge weights of the edges, and use the merged graph structure as the detector spatial structure diagram. The detector spatial structure diagram contains several air quality sensors as spatial nodes, the connection edges between spatial nodes, and the edge weights corresponding to the edges.

[0007] Further, for the air quality sensors with connection relationships in the detector spatial structure diagram, combine the diffusion relationship characteristics shown between multi-dimensional gas data to optimize and adjust the detector spatial structure diagram. The specific method includes: Perform gas diffusion analysis by combining any gas data collected by the connected air quality sensors in the detector spatial structure diagram to obtain the diffusion relationship degree between the two air quality sensors corresponding to any edge in the detector spatial structure diagram. Then, use the diffusion relationship degree to feedback and optimize the detector spatial structure diagram to obtain the optimized detector spatial structure diagram.

[0008] Further, the specific method for obtaining the diffusion relationship degree is: For the two air quality sensors corresponding to the same connection edge in the detector spatial structure diagram, based on the change correlation degree between the gas data collected by the two air quality sensors, obtain all the diffusion correlation factors between the two air quality sensors. According to the spatial distance between the two air quality sensors in the detection area and the diffusion correlation factors, calculate the diffusion relationship degree of any gas data between the two air quality sensors. The diffusion relationship degree is negatively correlated with the spatial distance and positively correlated with the diffusion correlation factors.

[0009] Further, the specific method for obtaining the diffusion correlation factor is: Obtain the cumulative distance matrix, the sub-diagonal of the cumulative distance matrix, and the shortest path in the cumulative distance matrix between the gas data collected by any two air quality sensors corresponding to an edge in the spatial structure diagram of the detector through the DTW algorithm. According to the relative relationship between the sub-diagonal and the shortest path in the cumulative distance matrix between the gas data, obtain the diffusion gradient parameter between the two air quality sensors, and combine the DTW distance between the gas data and the distance distribution of the shortest path and the elements on the sub-diagonal in the corresponding cumulative distance matrix between the gas data to calculate the diffusion correlation factor between the gas data.

[0010] Further, the specific method for obtaining the diffusion gradient parameter between the two air quality sensors according to the relative relationship between the sub-diagonal and the shortest path in the cumulative distance matrix between the gas data includes: For any edge in the spatial structure diagram of the detector, obtain the number of the absolute values of the minimum differences between the corresponding data points in the two gas data corresponding to the shortest path of the cumulative distance matrix between the gas data collected by the two air quality sensors corresponding to the edge in the spatial structure diagram of the detector, and the number of elements included in the shortest path of the cumulative distance matrix between the gas data collected by the th edge in the spatial structure diagram of the detector. Combine the ratio of the number of the absolute values of the minimum differences to the number of elements included in the shortest path of the cumulative distance matrix, and the absolute value of the minimum difference to calculate the diffusion gradient parameter between the two air quality sensors corresponding to the edge in the spatial structure diagram of the detector. Both the ratio and the absolute value of the minimum difference are positively correlated with the diffusion gradient parameter.

[0011] Further, the specific method for establishing the concentration distribution model of gas particles in the detection area by using the topological structure relationship between air quality sensors in the optimized spatial structure diagram of the detector and combining multi-dimensional gas data includes: Establish a three-dimensional rectangular coordinate system , and use the spatial distances between all air quality sensors to obtain the positions of the air quality sensors in space , so as to use the positions of the air quality sensors as the part of the three-dimensional rectangular coordinate system, and use the gas concentration values corresponding to the data points in the gas data as the axis; Take the gas concentration collected by each air quality sensor as the node attribute of the corresponding spatial node. Based on the edge weights of the optimized spatial structure diagram of the detector, use the weighted Kriging interpolation method to obtain the gas particle concentration values at each position in the three-dimensional rectangular coordinate system, generate a continuous concentration distribution, and thus obtain the concentration distribution model of the corresponding gas particles.

[0012] Further, the method for evaluating and alarming the air quality of the detection area by using the concentration distribution model of the gas particles includes the following specific steps: For any gas, obtain several peaks in the corresponding concentration distribution model; Preset the concentration threshold corresponding to the gas , and regard the peaks with numerical levels exceeding the concentration threshold as high-concentration peaks; Obtain the cross-sectional area of all high-concentration peaks on the XOY plane at a certain time as the high-concentration area, and take the ratio of the cumulative value of all high-concentration areas to the area of the detection area as the air quality coefficient; When the air quality coefficient is greater than or equal to the preset quality threshold, all air quality detectors in the detection area will alarm through the buzzer; when the air quality coefficient is less than the quality threshold, obtain the air quality sensor closest to the high-concentration peak in the corresponding concentration distribution model, and alarm through the air quality detector to which the air quality sensor belongs.

[0013] An intelligent air quality detection system includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of any one of the intelligent air quality detection methods described above.

[0014] An air quality detector adopts any one of the intelligent air quality detection methods described above, and includes the following modules: Data acquisition module: used to obtain multi-dimensional gas data at several positions in the detection area through several air quality sensors; Spatial structure module: used to utilize the spatial positions of air quality sensors in the detection area and combine the spatial distances between air quality sensors to construct a sensor spatial structure diagram; Model construction module: used to optimize and adjust the detector spatial structure diagram for the air quality sensors with connection relationships in the detector spatial structure diagram, combine the diffusion relationship characteristics shown between multi-dimensional gas data, utilize the topological structure relationship between air quality sensors in the optimized detector spatial structure diagram, and establish a concentration distribution model of gas particles in the detection area in combination with multi-dimensional gas data; Quality evaluation module: used to evaluate and alarm the air quality of the detection area by using the concentration distribution model of the gas particles.

[0015] The beneficial effects of the technical solution of the present invention are as follows: By constructing a topological map and a feedback optimization mechanism for air quality sensors, and spatially integrating the physical distribution of air quality sensors with the gradient characteristics of gas diffusion, that is, using the depth-first search algorithm to generate an initial space structure diagram of the detector, and dynamically pruning invalid edges in combination with the diffusion relationship degree, the topological structure is made more conform to the actual gas propagation path, so that the distribution of gas concentration in the detection area can be effectively determined in the subsequent process, so as to conduct an overall air quality assessment of the detection area and improve the air quality assessment effect of the detection area. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0017] Figure 1 It is a flowchart of the steps of an intelligent air quality detection method of the present invention; Figure 2 It is a module structure diagram of an air quality detector of the present invention; Figure 3 It is a schematic diagram of the traversal path when starting from the air quality detector 1 provided by an embodiment of the present invention; Figure 4 It is a schematic diagram of the traversal path when starting from the air quality detector 2 provided by an embodiment of the present invention; Figure 5 It is a schematic diagram of the cumulative distance matrix provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following will, in combination with the drawings and preferred embodiments, elaborate in detail on a method, system and air quality detector for intelligent air quality detection proposed according to the present invention, its specific implementation manner, structure, features and effects. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field of the present invention.

[0020] The following specifically describes the specific solutions of an intelligent air quality detection method, system, and air quality detector provided by the present invention in conjunction with the accompanying drawings.

[0021] Please refer to Figure 1 , which shows a step flowchart of an intelligent air quality detection method provided by an embodiment of the present invention. The method includes the following steps: Step S001: Obtain multi-dimensional gas data at several positions in the detection area through several air quality sensors.

[0022] It should be noted that since usually, gas particles in the air will change in concentration due to air flow and diffusion effects, the concentration of gas particles in the air is not evenly distributed in an area. Therefore, in an area where air quality needs to be detected, in order to more accurately and reliably detect the air quality of the area as a whole, several air quality sensors need to be deployed in the detection area, and the air quality sensors are used to detect the concentration of gas particles at different positions in the detection area.

[0023] Specifically, in order to implement the intelligent air quality detection method proposed in this embodiment, it is first necessary to collect multi-dimensional gas data at different positions in the detection area. The specific process is as follows: First, determine the detection area, deploy air quality sensors at different positions in the detection area, use the air quality sensors to collect the content data of each gas component in the current environment in real time to obtain multi-dimensional gas data, record and store the collected multi-dimensional gas data, and transmit it to the cloud platform through Internet of Things technology.

[0024] Then, use Gaussian filtering to filter and denoise all gas data, and further perform standardization processing on the filtered and denoised gas data.

[0025] So far, multi-dimensional gas data at several positions in the detection area is obtained through the above method.

[0026] Step S002: Use the spatial positions of the air quality sensors in the detection area and combine the spatial distances between the air quality sensors to construct a sensor spatial structure diagram.

[0027] It should be noted that during the propagation process of gas particles in the air, there is a certain correlation between the concentration of gas particles in space and time. Due to the spatial distribution and the diffusion rate of gas particles, the gas particles show a gradient distribution characteristic in the space corresponding to the detection area. Therefore, when detecting and evaluating the air quality of the detection area, it is necessary to consider the distribution characteristics shown in space by the data collected by different air quality sensors in the detection area. In addition, when gas particles propagate in the air, there must be a sequence at different positions and a certain propagation path. In order to accurately reflect the propagation characteristics of gas particles in space, in the embodiments of the present invention, the air quality sensors used to collect gas concentration data are selected as spatial nodes in space, and a connected graph is constructed using them to facilitate the subsequent description of the possible paths of gas particles in the space propagation process in the detection area.

[0028] Specifically, as an optional embodiment, the specific method for obtaining the spatial structure diagram of the detector includes: First, take any air quality sensor as a spatial node. Starting from any spatial node, use the depth-first search algorithm to traverse all spatial nodes, obtain the spatial node closest to the starting point, and connect them. During the traversal process, iterate and traverse according to the minimum distance until all spatial nodes are traversed. The obtained connection result is used as the initial structure corresponding to the spatial starting point of the starting point.

[0029] Then, merge the initial structures after iteratively traversing all spatial nodes as starting points respectively, count the number of edges corresponding to the same connected spatial nodes at both ends as the edge weight of the edge, and use the merged graph structure as the spatial structure diagram of the detector. The spatial structure diagram of the detector includes several air quality sensors as spatial nodes, the connection edges between spatial nodes, and the edge weights corresponding to the edges.

[0030] It should be noted that in the embodiments of the present invention, the merging process is equivalent to obtaining the union of all initial structures, so that all initial structures form a graph structure and retain the connection relationship between the air quality sensors in each original initial structure in the graph structure.

[0031] It should be noted that since gas particles spread and diffuse to varying degrees at various positions in space, and the air quality sensor can most directly reflect the concentration information of gas particles, in the embodiments of the present invention, the air quality sensor is selected as the spatial node, and each air quality sensor serving as the spatial node is used as the starting point, and based on the process of gradual diffusion of gas particles in space, traversal is performed according to the distance size, so that the air quality sensors distributedly deployed in the detection area are used to model the spatial structure to a certain extent, thereby improving the characterization effect of the diffusion of gas particles in space in the detection area. As Figure 3 , 4 shown are respectively the schematic diagram of the traversal path starting from the air quality sensor 1 and the schematic diagram of the traversal path starting from the air quality sensor 2. It can be seen that when different air quality sensors are used as the starting point, the traversal paths obtained according to the above search method are not exactly the same. This is because it is affected by the distance between the air quality sensors in the detection area, and at the same time, the change in the concentration of gas particles in the air during the propagation and diffusion in space is detected by the air quality sensor, so the propagation and diffusion characteristics of gas particles are reflected in the spatial structure diagram of the detector.

[0032] So far, the spatial structure diagram of the detector is obtained through the above method.

[0033] Step S003: For the air quality sensors with connection relationships in the spatial structure diagram of the detector, combined with the diffusion relationship characteristics shown among multi-dimensional gas data, optimize and adjust the spatial structure diagram of the detector, utilize the topological structure relationship between the air quality sensors in the optimized spatial structure diagram of the detector, and establish a concentration distribution model of gas particles in the detection area in combination with multi-dimensional gas data.

[0034] It should be noted that for any kind of gas particles, during the diffusion process in the detection area, it has certain spatial gradient distribution characteristics. And the spatial structure diagram of the detector established by using multiple air quality sensors in step S002 can be analyzed in terms of spatial structure with the gas data obtained by the corresponding air quality sensors, so as to realize a fitting analysis similar to from discrete to continuous, and understand the specific situation of the spatial gradient distribution of gas particles in the detection area.

[0035] Specifically, in step S301, perform gas diffusion analysis by combining any gas data collected by the connected air quality sensors in the spatial structure diagram of the detector, obtain the diffusion relationship degree between the two air quality sensors corresponding to any edge in the spatial structure diagram of the detector, and thus use the diffusion relationship degree to perform feedback optimization on the spatial structure diagram of the detector to obtain an optimized spatial structure diagram of the detector.

[0036] It should be noted that when constructing the spatial structure diagram of the detector by obtaining the path through iterative search and traversal, it is only achieved by using the distance between the air quality sensors. In this way, the space of the current detection area cannot be effectively reflected. Therefore, some connection relationships do not conform to the diffusion characteristics of gases in space. Therefore, in the embodiments of the present invention, the mechanical energy feedback of the spatial structure diagram of the detector is selected for optimization, so as to facilitate subsequent air quality detection in combination with the diffusion characteristics of gases.

[0037] As a preferred embodiment, the specific process of optimizing the spatial structure diagram of the detector to obtain the optimized spatial structure diagram of the detector is as follows: First, for two air quality sensors corresponding to the same connection edge in the spatial structure diagram of the detector, based on the degree of change correlation between the gas data collected by the two air quality sensors, obtain all the diffusion-related factors between the two air quality sensors. According to the spatial distance between the two air quality sensors in the detection area and the diffusion-related factors, calculate the diffusion relationship degree of any gas data between the two air quality sensors. The diffusion relationship degree is negatively correlated with the spatial distance and positively correlated with the diffusion-related factors.

[0038] As an alternative embodiment, the specific calculation method of the diffusion relationship degree is as follows: Among them, represents the diffusion relationship degree between two air quality sensors corresponding to the th edge in the spatial structure diagram of the detector; represents the spatial distance between two air quality sensors corresponding to the th edge in the detection area in the spatial structure diagram of the detector; represents the diffusion-related factor between two air quality sensors corresponding to the th edge in the spatial structure diagram of the detector; represents the linear normalization function.

[0039] The diffusion relationship degree is used to describe the degree of conformity of the actual situation of the diffusion relationship shown by the distance and gas data between two air quality sensors corresponding in the spatial structure diagram of the detector in the detection area. The greater the diffusion relationship degree (the closer the spatial distance between the two air quality sensors in the detection area and the higher the diffusion-related factor), the more obvious the diffusion correlation characteristics of gas particles between the two air quality sensors in the detection area, and a corresponding concentration gradient distribution characteristic can be formed in space.

[0040] As an alternative embodiment, the specific method for obtaining the diffusion-related factor is as follows: The cumulative distance matrix, the sub-diagonal of the cumulative distance matrix, and the shortest path among the gas data collected by any two air quality sensors corresponding to an edge in the detector spatial structure diagram are obtained through the DTW algorithm. According to the relative relationship between the sub-diagonal and the shortest path in the cumulative distance matrix of the gas data, the diffusion gradient parameter between the two air quality sensors is obtained, and in combination with the DTW distance between the gas data and the distance distribution of the elements on the shortest path and the sub-diagonal in the corresponding cumulative distance matrix of the gas data, the diffusion-related factor between the gas data is calculated.

[0041] As an alternative embodiment, the specific calculation method for the diffusion-related factor is as follows: Wherein, represents the diffusion-related factor between two air quality sensors corresponding to the -th edge in the detector spatial structure diagram; represents the diffusion gradient parameter between two air quality sensors corresponding to the -th edge in the detector spatial structure diagram; represents the DTW distance between the gas data collected by two air quality sensors corresponding to the -th edge in the detector spatial structure diagram; represents the average value of the distances in the -th direction between the elements in the shortest path and the elements on the sub-diagonal of the cumulative distance matrix between the gas data collected by two air quality sensors corresponding to the -th edge in the detector spatial structure diagram; represents the standard deviation of the distances in the -th direction between the elements in the shortest path and the elements on the sub-diagonal of the cumulative distance matrix between the gas data collected by two air quality sensors corresponding to the -th edge in the detector spatial structure diagram.

[0042] Where the cumulative distance matrix is a two-dimensional matrix. When in the -th direction, it represents the direction corresponding to each row in the cumulative distance matrix, i.e., horizontal; when in the -th direction, it represents the direction corresponding to each column in the cumulative distance matrix, i.e., vertical.

[0043] For example: the average value of the distances in the -th direction between the elements in the shortest path and the elements on the sub-diagonal of the cumulative distance matrix, when When it is, specifically expressed as: in the cumulative distance matrix, obtain the average value of the horizontal distance between the elements corresponding to the shortest path in all rows and the sub-diagonal of the cumulative distance matrix.

[0044] The diffusion correlation factor is used to describe the degree of association between the gas data collected by the corresponding two air quality sensors in terms of the change in gas particle concentration. The larger the diffusion correlation factor, the greater the gradient relationship in concentration between the gas data collected by the two air quality sensors, and there is a certain time delay, and this time delay exhibits the time lag characteristics of gas particles during the diffusion process; among them represents the correlation between two gas data; represents the time delay during the diffusion process of two gas data. In the cumulative clustering matrix, the greater the horizontal and vertical distances and the more concentrated the values between the shortest path and the elements in the sub-diagonal, the higher the time delay during the diffusion process, and then the higher the possibility of the existence of a diffusion relationship, and the larger the value of the diffusion correlation factor. As Figure 5 shown in the schematic diagram of the cumulative distance matrix, where the gray part is the shortest path.

[0045] As a preferred embodiment, the method for obtaining the diffusion gradient parameter between the two air quality sensors according to the relative relationship between the sub-diagonal and the shortest path in the cumulative distance matrix of the gas data includes the following specific method: For any edge in the detector space structure diagram, obtain the absolute value of the minimum difference between the corresponding data points in the two gas data corresponding to the shortest path of the cumulative distance matrix of the gas data collected by the two air quality sensors corresponding to the edge in the detector space structure diagram, and the number of elements included in the shortest path of the cumulative distance matrix of the gas data collected by the two air quality sensors corresponding to the th edge in the detector space structure diagram. Combine the ratio of the number of the absolute values of the minimum differences to the number of elements included in the shortest path of the cumulative distance matrix, and the absolute value of the minimum difference, and calculate the diffusion gradient parameter between the two air quality sensors corresponding to the edge in the detector space structure diagram. Both the ratio and the absolute value of the minimum difference are positively correlated with the diffusion gradient parameter.

[0046] As an alternative embodiment, the specific calculation method of the diffusion gradient parameter is: Among them, represents the diffusion gradient parameter between the two air quality sensors corresponding to the th edge in the detector space structure diagram; represents the The absolute value of the minimum difference between corresponding data points in two gas data corresponding to the shortest path of the cumulative distance matrix between the gas data collected by two air quality sensors for each side; Denotes the Number of the absolute values of the minimum differences between corresponding data points in two gas data corresponding to the shortest path of the cumulative distance matrix between the gas data collected by two air quality sensors for each side; Denotes the Number of elements included in the shortest path of the cumulative distance matrix between the gas data collected by two air quality sensors for each side; Denotes the logarithmic function with the natural constant as the base.

[0047] The diffusion gradient parameter is used to describe the degree to which the gas particle concentrations between two air quality sensors conform to a gradient distribution. The larger the diffusion gradient parameter, the higher the degree to which the gas particle concentrations between two air quality sensors conform to a gradient distribution; Reflects the minimum difference between data points where there is a matching relationship between gas data, Reflects the proportionality of the number of minimum differences. The larger the minimum difference and the larger the proportionality of the number of minimum differences, the higher the degree to which the gas particle concentrations between two air quality sensors show a gradient distribution; Additionally, the introduction of the logarithmic function achieves Nonlinear scaling of, avoiding the excessive influence of large numerical differences on parameter calculation, and at the same time the logarithmic transformation simulates the attenuation characteristics of the concentration gradient during the gas diffusion process.

[0048] Then, the edges and edge weights in the detector spatial structure diagram are adjusted using the diffusion relationship degree to obtain an optimized detector spatial structure diagram.

[0049] As an optional embodiment, the specific process is as follows: During the traversal by depth - first search, obtain the sequence formed by the spatial distances between the m - th air quality sensor and other air quality sensors in ascending order. At a distance when the diffusion relationship degree is less than or equal to a preset diffusion relationship degree threshold (the diffusion relationship degree threshold is preset to 0.3 according to experience), disconnect or do not connect the corresponding edges in the detector spatial structure diagram, and obtain the diffusion relationship degree between the th air quality sensor and the corresponding air quality sensors at a distance

[0050] Step S302: Use the topological structure relationship formed by the air quality sensors in the optimized detector space structure diagram, and combine the gas data collected by different air quality sensors to establish a concentration distribution model for any gas particles in the detection area.

[0051] As a preferred embodiment, the specific method for obtaining the concentration distribution model of the gas particles is as follows: First, establish a three-dimensional rectangular coordinate system , and use the spatial distances between all air quality sensors to obtain the positions of the air quality sensors in space , so as to take the positions of the air quality sensors as the part of the three-dimensional rectangular coordinate system, and take the gas concentration values corresponding to the data points in the gas data as the axis.

[0052] Then, take the gas concentration collected by each air quality sensor as the node attribute of the corresponding spatial node, and based on the edge weights of the optimized detector space structure diagram, use the weighted Kriging interpolation method to obtain the gas particle concentration values at each position in the three-dimensional rectangular coordinate system, generate a continuous concentration distribution, and thus obtain the concentration distribution model corresponding to the gas particles.

[0053] The gas data distribution model is based on the topological structure formed by the air quality sensors at different positions in the detection area, and combines the corresponding gas particle concentrations (i.e., gas data) at each position. It fits the data collected by the air quality sensors as discrete spatial nodes to obtain the overall gas concentration distribution in the detection area, which can provide model support for the subsequent overall air quality assessment of the detection area.

[0054] So far, the concentration distribution model of the gas particles is obtained through the above method.

[0055] Step S004: Use the concentration distribution model of the gas particles to evaluate and alarm the air quality of the detection area.

[0056] Specifically, first, for any gas, obtain several peaks in the corresponding concentration distribution model.

[0057] Then, preset the concentration threshold corresponding to the gas , and take the peaks with numerical levels exceeding the concentration threshold as high-concentration peaks; obtain the cross-sectional area of all high-concentration peaks on the XOY plane at as the high-concentration area, and take the ratio of the cumulative value of all high-concentration areas to the area of the detection area as the air quality coefficient.

[0058] It should be noted that the concentration threshold corresponding to the gas It can be set according to the ambient air quality standard. For example, under normal circumstances, the concentration of sulfur dioxide in the air does not exceed , and the concentration of carbon monoxide does not exceed . Therefore, in the embodiments of the present invention, the concentration threshold of the gas is not specifically limited.

[0059] Finally, when the air quality coefficient is greater than or equal to the preset quality threshold, all the air quality detectors in the detection area alarm through the buzzer; when the air quality coefficient is less than the quality threshold, the air quality sensor closest to the high-concentration peak in the corresponding concentration distribution model is obtained, and the air quality detector to which the air quality sensor belongs alarms.

[0060] It should be noted that in the embodiments of the present invention, the quality threshold is preset to 0.6 according to experience and can be adjusted according to the actual situation, and is not specifically limited in the embodiments of the present invention.

[0061] Through the above steps, the air quality detection of the current environment is completed.

[0062] In the embodiments of the present invention, an air quality intelligent detection system is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the contents of steps S001 to S004 of the air quality intelligent detection method are implemented.

[0063] Furthermore, in an optional embodiment, the above-mentioned memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. The memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0064] The above-mentioned processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor supporting the advanced reduced instruction set machine (ARM) architecture.

[0065] In addition, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc.

[0066] Please refer to Figure 2 , which shows an air quality detector provided by an embodiment of the present invention. Using the above-described intelligent air quality detection method, it includes the following modules: Data acquisition module: used to obtain multi-dimensional gas data at several positions in the detection area through several air quality sensors; Spatial structure module: used to utilize the spatial positions of the air quality sensors in the detection area and combine the spatial distances between the air quality sensors to construct a sensor spatial structure diagram; Model construction module: used to optimize and adjust the detector spatial structure diagram for the air quality sensors with connection relationships in the detector spatial structure diagram, combine the diffusion relationship characteristics shown between the multi-dimensional gas data, utilize the topological structure relationship between the air quality sensors in the optimized detector spatial structure diagram, and establish a concentration distribution model of gas particles in the detection area in combination with the multi-dimensional gas data; Quality assessment module: used to evaluate and alarm the air quality of the detection area by using the concentration distribution model of the gas particles.

[0067] In this embodiment, by constructing a topological graph and a feedback optimization mechanism of the air quality sensors, and spatially integrating the physical distribution of the air quality sensors and the gradient characteristics of gas diffusion, that is, using the depth-first search algorithm to generate an initial detector spatial structure diagram, dynamically pruning invalid edges in combination with the diffusion relationship degree, making the topological structure more conform to the actual gas propagation path, so that the distribution of gas concentration in the detection area can be effectively determined in the subsequent process, in order to conduct an overall air quality assessment of the detection area, and improving the air quality assessment effect of the detection area.

[0068] It should be noted that the model used in this embodiment is only used to represent the negative correlation relationship and restrict the result of the model output to be within the interval. In specific implementation, it can be replaced with other models with the same purpose. This embodiment only takes the model as an example for description, and does not make specific limitations on it, where refers to the input of the model.

[0069] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent air quality detection method, characterized in that, The method includes the following steps: Obtain multi-dimensional gas data at several positions in the detection area through several air quality sensors; Utilize the spatial positions of the air quality sensors in the detection area and combine with the spatial distances between the air quality sensors to construct a sensor spatial structure diagram; For the air quality sensors with connection relationships in the detector spatial structure diagram, combine with the diffusion relationship characteristics shown between the multi-dimensional gas data, optimize and adjust the detector spatial structure diagram, utilize the topological structure relationship between the air quality sensors in the optimized detector spatial structure diagram, and establish a concentration distribution model of gas particles in the detection area in combination with the multi-dimensional gas data; Utilize the concentration distribution model of the gas particles to evaluate and alarm the air quality of the detection area.

2. The air quality intelligent detection method according to claim 1, characterized in that The specific method included in "utilize the spatial positions of the air quality sensors in the detection area and combine with the spatial distances between the air quality sensors to construct a sensor spatial structure diagram" is as follows: Take any air quality sensor as a spatial node, take any spatial node as the starting point, use the depth-first search algorithm to traverse all spatial nodes, obtain the spatial node closest to the starting point, and connect them. During the traversal process, iterate through the traversal according to the minimum distance until all spatial nodes are traversed, and use the obtained connection result as the initial structure corresponding to the spatial starting point of the starting point; Merge the initial structures after iteratively traversing with all spatial nodes as the starting points respectively, count the number of corresponding edges when the spatial nodes connected at both ends are the same as the edge weight of the edge, and use the merged graph structure as the detector spatial structure diagram. The detector spatial structure diagram includes several air quality sensors as spatial nodes, the connection edges between the spatial nodes, and the edge weights corresponding to the edges.

3. The intelligent air quality detection method according to claim 1, characterized in that The specific method included in "for the air quality sensors with connection relationships in the detector spatial structure diagram, combine with the diffusion relationship characteristics shown between the multi-dimensional gas data, optimize and adjust the detector spatial structure diagram" is as follows: Combine the gas diffusion analysis of any gas data collected by the connected air quality sensors in the detector spatial structure diagram to obtain the diffusion relationship degree between the two air quality sensors corresponding to any edge in the detector spatial structure diagram, so as to use the diffusion relationship degree to perform feedback optimization on the detector spatial structure diagram and obtain the optimized detector spatial structure diagram.

4. The intelligent air quality detection method according to claim 3, characterized in that, The specific method for obtaining the diffusion relationship degree is as follows: For two air quality sensors corresponding to the same connection edge in the detector spatial structure diagram, based on the change correlation degree between the gas data collected by the two air quality sensors, obtain all diffusion correlation factors between the two air quality sensors, and calculate the diffusion relationship degree of any gas data between the two air quality sensors according to the spatial distance between the two air quality sensors in the detection area and the diffusion correlation factors. The diffusion relationship degree is negatively correlated with the spatial distance and positively correlated with the diffusion correlation factor.

5. The intelligent air quality detection method according to claim 4, characterized in that, The specific method for obtaining the diffusion correlation factor is as follows: Obtain the cumulative distance matrix, the sub-diagonal of the cumulative distance matrix, and the shortest path in the cumulative distance matrix between the gas data collected by any two air quality sensors corresponding to an edge in the spatial structure diagram of the detector through the DTW algorithm. According to the relative relationship between the sub-diagonal and the shortest path in the cumulative distance matrix between the gas data, obtain the diffusion gradient parameter between the two air quality sensors, and combine the DTW distance between the gas data and the distance distribution of the shortest path and the elements on the sub-diagonal in the corresponding cumulative distance matrix between the gas data to calculate the diffusion correlation factor between the gas data.

6. The intelligent air quality detection method according to claim 5, characterized in that, The specific method for obtaining the diffusion gradient parameter between the two air quality sensors according to the relative relationship between the sub-diagonal and the shortest path in the cumulative distance matrix between the gas data includes: For any edge in the spatial structure diagram of the detector, in the shortest path of the cumulative distance matrix between the gas data collected by the two air quality sensors corresponding to the edge in the spatial structure diagram of the detector, the number of the absolute values of the minimum differences between the corresponding data points in the two corresponding gas data, and the number of elements included in the shortest path of the cumulative distance matrix between the gas data collected by the two air quality sensors corresponding to the th edge in the spatial structure diagram of the detector. Combining the ratio of the number of the absolute values of the minimum differences to the number of elements included in the shortest path of the cumulative distance matrix, and the absolute value of the minimum difference, calculate the diffusion gradient parameter between the two air quality sensors corresponding to the edge in the spatial structure diagram of the detector. Both the ratio and the absolute value of the minimum difference are positively correlated with the diffusion gradient parameter.

7. The air quality intelligent detection method according to claim 2, wherein The specific method for using the topological structure relationship between the air quality sensors in the optimized spatial structure diagram of the detector and combining multi-dimensional gas data to establish a concentration distribution model of gas particles in the detection area includes: Establish a three-dimensional rectangular coordinate system , and obtain the positions of air quality sensors in space by using the spatial distances between all air quality sensors , so as to use the positions of the air quality sensors as the part of the three-dimensional rectangular coordinate system, and use the gas concentration values corresponding to the data points in the gas data as the axis; Take the gas concentration collected by each air quality sensor as the node attribute of the corresponding spatial node. Based on the edge weights of the optimized spatial structure diagram of the detector, use the weighted Kriging interpolation method to obtain the gas particle concentration value at each position in the three-dimensional rectangular coordinate system, generate a continuous concentration distribution, and thus obtain the concentration distribution model of the corresponding gas particles.

8. The intelligent air quality detection method according to claim 7, wherein The specific method for using the concentration distribution model of the gas particles to evaluate and alarm the air quality of the detection area includes: For any gas, obtain several peaks in the corresponding concentration distribution model; Preset the concentration threshold corresponding to the gas , and take the peak with a numerical level exceeding the concentration threshold as a high-concentration peak; obtain the cross-sectional area of all high-concentration peaks on the XOY plane at as the high-concentration area, and take the ratio of the cumulative value of all high-concentration areas to the area of the detection region as the air quality coefficient; When the air quality coefficient is greater than or equal to the preset quality threshold, all air quality detectors in the detection area alarm through the buzzer; When the air quality coefficient is less than the quality threshold, obtain the air quality sensor closest to the high-concentration peak in the corresponding concentration distribution model, and alarm through the air quality detector to which the air quality sensor belongs.

9. An intelligent air quality detection system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of an intelligent air quality detection method according to any one of claims 1 to 8.

10. An air quality detector, which adopts an intelligent air quality detection method as described in any one of claims 1-8, characterized in that, It includes the following modules: Data acquisition module: used to obtain multi-dimensional gas data at several positions in the detection area through several air quality sensors; Spatial structure module: used to utilize the spatial positions of the air quality sensors in the detection area and combine the spatial distances between the air quality sensors to construct a sensor spatial structure diagram; Model construction module: used to optimize and adjust the spatial structure diagram of the detector for the air quality sensors with connection relationships in the spatial structure diagram of the detector, combine the diffusion relationship characteristics shown between the multi-dimensional gas data, use the topological structure relationship between the air quality sensors in the optimized spatial structure diagram of the detector, and combine the multi-dimensional gas data to establish a concentration distribution model of gas particles in the detection area; Quality evaluation module: used to evaluate and alarm the air quality of the detection area by using the concentration distribution model of the gas particles.

Images