Underground space environment monitoring method and system based on Internet of Things

Abstract

The invention relates to the field of environment monitoring, in particular to an underground space environment monitoring method and system based on the Internet of Things, and the method comprises the steps: obtaining the oxygen concentration data of an underground space at each moment, and constructing a data set through the oxygen concentration data at a plurality of moments; and constructing an optimal diameter function of a category in the Fisher optimal solution method, segmenting the data set by using the Fisher optimal solution method to obtain a plurality of segments, and filtering the oxygen concentration data in each segment to obtain denoised oxygen concentration data. According to the invention, the influence of noise data on oxygen concentration data filtering is reduced, and the accuracy of data filtering is improved.

Description

Technical Field

[0001] The present invention relates to the field of environmental monitoring, and in particular to an underground space environment monitoring method and system based on the Internet of Things. Background Art

[0002] Oxygen concentration is a key indicator of underground air quality. It can be used to assess ventilation effectiveness and the impact of human activity on air quality, providing a scientific basis for improving air quality. Monitoring oxygen concentration underground can also help prevent accidents caused by hypoxia and improve the safety of underground workers. Therefore, real-time monitoring of oxygen concentration in underground environments is necessary. However, collected oxygen concentration data often contains noise. To accurately monitor oxygen concentration, this data must be filtered and de-noised.

[0003] Chinese patent publication CN108280816B discloses a Gaussian filtering method and mobile terminal. The method comprises: obtaining a plurality of pixel averages corresponding to a target pixel; and obtaining a Gaussian result corresponding to the target pixel based on the plurality of pixel averages. The method also involves directly obtaining a plurality of pixel averages corresponding to the target pixel; and obtaining a Gaussian result corresponding to the target pixel based on the plurality of pixel averages.

[0004] Gaussian filtering can be used to filter and denoise oxygen concentration data. Existing Gaussian filtering algorithms often require fixed parameters to achieve filtering, and fixed-parameter filtering algorithms are less effective at denoising data with large fluctuations. Therefore, it is necessary to segment the oxygen concentration data and then use different parameters for filtering within each data segment to improve the filtering effect. The Fisher optimal solution is a time series data clustering algorithm that maintains the order of the time series, i.e., data segmentation.

[0005] In the process of segmenting underground space oxygen concentration data, the existing Fisher optimal solution method directly uses the sum of squared deviations of the class to calculate the diameter of the class. The class diameter directly affects the subsequent segmentation results. Due to the presence of noise in the underground space oxygen concentration data, the noise will cause the class diameter in the traditional algorithm to fail to represent the actual data changes, which may lead to the inability to accurately segment the data in subsequent segmentation, resulting in poor data segmentation effect and affecting the denoising effect of the underground space oxygen concentration data. Summary of the Invention

[0006] In order to solve the problem that the denoising effect is affected by directly using the diameter of the category to segment the oxygen concentration data in the Fisher optimal solution method, the present invention provides an underground space environment monitoring method and system based on the Internet of Things.

[0007] In a first aspect, the present invention provides an underground space environment monitoring method based on the Internet of Things, which adopts the following technical solutions: Obtain oxygen concentration data at each moment in the underground space and construct a data set using oxygen concentration data at multiple moments; Constructing the optimal diameter function of the category in the Fisher optimal solution method, using the Fisher optimal solution method to segment the data set into multiple segments, filtering the oxygen concentration data in each segment to obtain denoised oxygen concentration data; in response to the oxygen concentration data in the segment being less than a preset threshold, issuing an early warning prompt; The method for constructing the optimal diameter function is as follows: constructing a data segment with any oxygen concentration data as the center; obtaining the extreme points in the data segment, and constructing an extreme point set using the extreme points; The absolute value of the difference between two adjacent extreme points in the extreme point set is calculated to obtain multiple absolute values ​​of the difference, and the difference set is constructed using the absolute values ​​of the difference. The noise impact index of the corresponding oxygen concentration data is calculated, and the noise impact index is positively correlated with the mean of the data points in the difference set. The optimal diameter function is constructed, and the expression is: Where, represents the optimal diameter of category G during segmentation, Represents the mean of the oxygen concentration data within category G during the segmentation process, is the oxygen concentration data within category G during the segmentation process, Oxygen concentration data Noise impact indicators.

[0008] By calculating the noise impact index of each oxygen concentration data, the optimal diameter of the corresponding category in the segmentation process is further obtained. The optimal diameter improves the segmentation effect and the accuracy of the oxygen concentration data segmentation, making it easier to filter and denoise the oxygen concentration data to obtain accurate oxygen concentration data.

[0009] Preferably, the method further comprises: calculating the time distance between two adjacent extreme value points in the extreme value point set to obtain a plurality of time distances, and constructing a time distance set using the time distances.

[0010] By constructing a time distance set from the time dimension, it is convenient to analyze the characteristics of extreme points in the time dimension and improve the accuracy of calculating noise impact indicators.

[0011] Preferably, the expression of the noise impact index is: ; Where, Represents oxygen concentration data points The noise impact index, represents the variance of the time distance set, represents the variance of the difference set, Represents the mean of the data points in the difference set; tanh represents the hyperbolic tangent function.

[0012] The noise impact index is obtained by comprehensively calculating the variance of the time distance set, the variance of the difference set and the mean of the difference set from multiple dimensions, thereby improving the accuracy of the noise impact index.

[0013] Preferably, the expression of the noise impact index is: ; Where, Represents oxygen concentration data points The noise impact index, represents the mean of the data points in the difference set, It represents the variance of the difference set, and norm represents the normalization function.

[0014] Preferably, the method for filtering the oxygen concentration data within the segment is: Calculate the mean of the noise impact index of the oxygen concentration data in the segment; calculate the optimal filter window in the Gaussian filter, and the optimal filter window is positively correlated with the mean of the noise impact index; and use the Gaussian filter to filter the oxygen concentration data in the segment.

[0015] By segmenting the oxygen concentration data and then using the optimal filtering window of each segment to filter the data in each segment, the accuracy of the filtering result is improved and the filtering effect is improved compared with the traditional filtering method.

[0016] Preferably, the expression of the optimal filter window is: ; Where, represents the optimal filtering window when filtering the i-th segment, represents the reference filtering window, represents the mean value of the noise impact index of the oxygen concentration data in the i-th segment, The symbol for rounding up.

[0017] Preferably, the expression of the optimal filter window is: ; Where, represents the optimal filtering window when filtering the i-th segment, represents the reference filtering window, represents the mean value of the noise impact index of the oxygen concentration data in the i-th segment, exp stands for exponential function with base e.

[0018] The size of the benchmark filtering window is adjusted by using the mean of the noise impact index of the oxygen concentration data in the segment to obtain the optimal filtering window, thereby improving the filtering effect.

[0019] In a second aspect, the present invention provides an underground space environment monitoring system based on the Internet of Things, which adopts the following technical solutions: An underground space environment monitoring system based on the Internet of Things, a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an underground space environment monitoring method based on the Internet of Things is implemented.

[0020] The present invention has the following technical effects: 1. By adjusting the diameter of the categories in the Fisher optimal solution, the oxygen concentration data of the underground space can be accurately segmented, improving the accuracy of the segmentation results. Then, filtering and denoising each segment separately can perform more refined processing on the data characteristics of different concentration ranges and different change trends. It can more accurately identify and remove the noise within each segment, achieve good denoising effect, and thus improve the accuracy of the overall data.

[0021] 2. By adjusting the diameter of the Fisher optimal solution method based on the changing characteristics of the underground space oxygen concentration data, the distribution of the underground space oxygen concentration data sequence can be more accurately identified, and the interference of noise on the oxygen concentration data classification results can be reduced, thereby improving the classification accuracy, and further improving the denoising effect of the underground space oxygen concentration and the accuracy of underground space environmental monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] By reading the detailed description below with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding numbers represent the same or corresponding parts.

[0023] Figure 1 This is a flow chart of an underground space environment monitoring method based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the scope of protection of the present invention.

[0025] It should be understood that when the terms "first," "second," and the like are used in the claims, description, and drawings of the present invention, they are merely used to distinguish between different objects, rather than to describe a specific order. The terms "comprise" and "comprising" used in the description and claims of the present invention indicate the presence of the described features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or combinations thereof.

[0026] The embodiment of the present invention discloses an underground space environment monitoring method based on the Internet of Things, referring to Figure 1 , including the following steps, as follows: S1: Obtain the oxygen concentration data of the underground space at each moment, and construct a data set using the oxygen concentration data at multiple moments.

[0027] Oxygen sensors are used to collect oxygen concentration data in underground spaces. Sampling points should be arranged in places where people frequently move around or where air quality requirements are high. In this embodiment, oxygen sensors are placed in the working area, entrance, and exit of the underground space to collect oxygen concentration data at various locations in the underground space. At the same time, the height of the sensor placement is consistent with the height of the human breathing zone to ensure that the collected oxygen concentration data is representative. For example, the sensor is placed 1.65m above the ground of the underground space.

[0028] The oxygen sensor collects data at a 0.5-minute interval. The sensor is then connected to a monitoring center via the Internet of Things (IoT), for example, via wireless or Bluetooth, to obtain oxygen concentration data at various locations at different times. It should be noted that when processing oxygen concentration data, the data collected by each sensor is processed separately. For each sensor, multiple oxygen concentration data points are collected at various times, and a dataset is constructed using these data points. The oxygen concentration data is arranged in chronological order.

[0029] S2: Calculate the noise impact index of oxygen concentration data.

[0030] There are many gases in the underground space, including some that cross-react with oxygen sensors. As a result, noise exists in the collected oxygen concentration data. Noise can cause the oxygen concentration data to fluctuate irregularly. The data change characteristics caused by noise are used as sensitivity, and the noise impact index of oxygen concentration data is calculated based on sensitivity.

[0031] S21: constructing a data segment with any oxygen concentration data as the center, obtaining extreme points in the data segment, and constructing an extreme point set using the extreme points; Take the dataset corresponding to one of the sensors as an example, is the ith oxygen concentration data in the oxygen concentration data sequence, and the oxygen concentration data As the center, intercept m oxygen concentration data on the left and m oxygen concentration data on the right, and get the oxygen concentration data The data segment with centered on . The extreme points in the data segment are identified by the difference method, and the extreme point set is obtained. The extreme point set is recorded as: ,in Indicates oxygen concentration data The jth extreme point in the data segment centered on is the number of extreme points in the extreme point set.

[0032] S22: Calculate the time distance between two adjacent extreme points in the extreme point set to obtain multiple time distances, and construct a time distance set using the time distances.

[0033] In the extreme point set, each extreme point corresponds to a timestamp, and the difference between the timestamps corresponding to two adjacent extreme points is used as the time distance, thereby obtaining multiple time distances, and using the obtained multiple time distances to construct a time distance set.

[0034] For example, the time distance set for , Indicates oxygen concentration data The time distance set corresponding to the extreme point set of the data segment centered on is, where , 、 Respectively represent oxygen concentration data The extreme point in the data segment centered at and The corresponding timestamp, That is, the adjacent extreme points and The time distance between them.

[0035] By time distance collection The variance can be characterized by the oxygen concentration data points The consistency of the distribution of extreme points in the data segment centered on the time series. Specifically, the larger the variance, the worse the consistency of the extreme point distribution. Conversely, the smaller the variance, the better the consistency of the extreme point distribution.

[0036] S23: Calculate the absolute value of the difference between two adjacent extreme points in the extreme point set to obtain multiple absolute values ​​of the difference, and construct a difference set using the absolute values ​​of the difference.

[0037] Difference Set for ,in, , Represents adjacent extreme points and The absolute value of the difference in oxygen concentration data between the two.

[0038] The variance of the difference set can be used to characterize the oxygen concentration data points. The consistency of the extreme point change range in the data segment centered on is greater. The greater the variance, the worse the consistency of the extreme point change range. On the contrary, the smaller the variance, the better the consistency of the extreme point change range. The mean value can be used to characterize the oxygen concentration data The degree of fluctuation of data within the data segment centered on the center, specifically, the difference set The larger the mean value, the greater the fluctuation of the data in the data segment. On the contrary, the difference set The smaller the mean, the less drastic the fluctuation of data within the data segment.

[0039] S24: Calculate a noise impact index, where the noise impact index is positively correlated with the mean of the data points in the difference set.

[0040] In one embodiment, the expression of the noise impact index is: ; Where, Represents oxygen concentration data points The noise impact index, represents the variance of the time distance set, represents the variance of the difference set, Represents the mean of the data points in the difference set; tanh represents the hyperbolic tangent function, which is used to normalize the data. Characterizing oxygen concentration data It can be understood that the greater the noise impact index, the greater the oxygen concentration data The greater the impact of noise, the smaller the noise impact index is, indicating that the oxygen concentration data The less affected by noise.

[0041] In one embodiment, the expression of the noise impact index is: ; Where, Represents oxygen concentration data points The noise impact index, represents the mean of the data points in the difference set, It represents the variance of the difference set, and norm represents the normalization function.

[0042] S3: Construct the optimal diameter function of the category in the Fisher optimal solution method, and use the Fisher optimal solution method to segment the data set into multiple segments.

[0043] The expression of the optimal diameter function is: Where, represents the optimal diameter of category G during segmentation, Represents the mean of the oxygen concentration data within category G during the segmentation process, is the oxygen concentration data within category G during the segmentation process, Oxygen concentration data When the Fisher optimal solution calculates the diameter during the segmentation process, the larger the noise impact index of the corresponding oxygen concentration data point, the smaller its corresponding weight, thereby reducing the impact of noise on the category diameter, improving the accuracy of the Fisher optimal solution during the segmentation process, and improving the segmentation effect.

[0044] The Fisher optimal solution is used to segment the dataset into multiple segments, where the number of segments is determined using the elbow method. This can also be understood as classifying the oxygen concentration data in the dataset into multiple categories, minimizing the variability of oxygen concentration data within the same category. By classifying the oxygen concentration data in the dataset into multiple categories, filtering can be performed on data of different categories, thereby improving the accuracy of the filtering results.

[0045] S4: Filter the oxygen concentration data in each segment to obtain denoised oxygen concentration data.

[0046] S41: Calculate the optimal filtering window in Gaussian filtering.

[0047] The mean of the noise impact index of the oxygen concentration data in the segment is calculated, and the optimal filter window is positively correlated with the mean of the noise impact index.

[0048] In one embodiment, the expression of the optimal filtering window is: Where, represents the optimal filtering window when filtering the i-th segment, Indicates the benchmark filter window. The size of the benchmark filter window is set manually according to the actual situation. represents the mean value of the noise impact index of the oxygen concentration data in the i-th segment, The symbol for rounding up. The larger the value of , the greater the noise impact on the i-th segment data. In this case, a larger window size is required for filtering to improve the filtering effect.

[0049] In one embodiment, the expression of the optimal filtering window is: ; Where, represents the optimal filtering window when filtering the i-th segment, represents the reference filtering window, represents the mean value of the noise impact index of the oxygen concentration data in the i-th segment, exp stands for exponential function with base e.

[0050] S42: Filter the oxygen concentration data in the segment using a Gaussian filter, and issue an early warning in response to the oxygen concentration data in the segment being less than a preset threshold.

[0051] The oxygen concentration data within each segment is filtered using a Gaussian filter to obtain denoised oxygen concentration data. This denoised oxygen concentration data is then used to monitor the oxygen content within the underground space, facilitating understanding of the changing trends within the underground space. When the oxygen concentration data within a segment falls below a preset threshold, indicating low oxygen levels within the underground space, an early warning is issued. Alternatively, when the oxygen content gradually decreases, an early warning is issued to ensure the safety of underground personnel. The threshold is set manually based on actual conditions.

[0052] For example, the oxygen concentration data within the current hour is segmented into three segments, and the oxygen concentration data in the three segments are denoised. If there is oxygen concentration data below the threshold in a segment, it indicates that there may be a problem of poor ventilation in the underground space, and an early warning is issued in time; or when the oxygen concentration data in the third segment is monitored to gradually decrease, indicating that the oxygen in the underground space is gradually decreasing, an early warning is issued at this time.

[0053] An embodiment of the present invention also discloses an underground space environment monitoring system based on the Internet of Things, including a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, an underground space environment monitoring method based on the Internet of Things according to the present invention is implemented.

[0054] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

[0055] In the present invention, the aforementioned memory can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium can be any suitable magnetic storage medium or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application, module, or both. Any such computer storage medium can be part of, accessible to, or connected to the device.

[0056] While several embodiments of the present invention have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Numerous modifications, variations, and alternatives will occur to those skilled in the art without departing from the concept and spirit of the present invention. It should be understood that various alternatives to the embodiments of the present invention described herein may be employed in practicing the present invention.

[0057] The above are all preferred embodiments of the present invention, and are not intended to limit the scope of protection of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for monitoring underground space environment based on the Internet of Things, characterized in that: Including steps: Obtain oxygen concentration data at each moment in the underground space and construct a data set using oxygen concentration data at multiple moments; Constructing the optimal diameter function of the category in the Fisher optimal solution method, using the Fisher optimal solution method to segment the data set into multiple segments, filtering the oxygen concentration data in each segment to obtain denoised oxygen concentration data; in response to the oxygen concentration data in the segment being less than a preset threshold, issuing an early warning prompt; The method for constructing the optimal diameter function is as follows: constructing a data segment with any oxygen concentration data as the center; obtaining the extreme points in the data segment, and constructing an extreme point set using the extreme points; The absolute value of the difference between two adjacent extreme points in the extreme point set is calculated to obtain multiple absolute values ​​of the difference, and the difference set is constructed using the absolute values ​​of the difference. The noise impact index of the corresponding oxygen concentration data is calculated, and the noise impact index is positively correlated with the mean of the data points in the difference set. The optimal diameter function is constructed, and the expression is: Where, represents the optimal diameter of category G during segmentation, Represents the mean of the oxygen concentration data within category G during the segmentation process, is the oxygen concentration data within category G during the segmentation process, Oxygen concentration data Noise impact indicators.

2. The underground space environment monitoring method based on the Internet of Things according to claim 1, characterized in that: The method further includes: calculating the time distance between two adjacent extreme value points in the extreme value point set to obtain multiple time distances, and constructing a time distance set using the time distances.

3. The underground space environment monitoring method based on the Internet of Things according to claim 2, characterized in that: The expression of noise impact index is: ； Where, Represents oxygen concentration data points The noise impact index, represents the variance of the time distance set, represents the variance of the difference set, Represents the mean of the data points in the difference set; tanh represents the hyperbolic tangent function.

4. The underground space environment monitoring method based on the Internet of Things according to claim 1, characterized in that: The expression of noise impact index is: ； Where, Represents oxygen concentration data points The noise impact index, represents the mean of the data points in the difference set, It represents the variance of the difference set, and norm represents the normalization function.

5. The underground space environment monitoring method based on the Internet of Things according to claim 1 is characterized in that: The method for filtering the oxygen concentration data within a segment is: Calculate the mean of the noise impact index of the oxygen concentration data in the segment; calculate the optimal filter window in the Gaussian filter, and the optimal filter window is positively correlated with the mean of the noise impact index; and use the Gaussian filter to filter the oxygen concentration data in the segment.

6. The underground space environment monitoring method based on the Internet of Things according to claim 5, characterized in that: The expression of the optimal filter window is: ； Where, represents the optimal filtering window when filtering the i-th segment, represents the reference filtering window, represents the mean value of the noise impact index of the oxygen concentration data in the i-th segment, The symbol for rounding up.

7. The underground space environment monitoring method based on the Internet of Things according to claim 5, characterized in that: The expression of the optimal filter window is: ； Where, represents the optimal filtering window when filtering the i-th segment, represents the reference filtering window, represents the mean value of the noise impact index of the oxygen concentration data in the i-th segment, exp stands for exponential function with base e.

8. An underground space environment monitoring system based on the Internet of Things, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an underground space environment monitoring method based on the Internet of Things according to any one of claims 1 to 7 is implemented.

Images