An underground space environment monitoring method and system based on the Internet of Things

Abstract

The present application relates to the field of environmental monitoring, and more particularly to an underground space environment monitoring method and system based on the Internet of Things, the method comprising: acquiring oxygen concentration data of the underground space at each moment, and constructing a data set using oxygen concentration data at multiple moments; constructing a best diameter function of a category in a Fisher optimal solution method, and segmenting the data set using the Fisher optimal solution method to obtain multiple segments; and filtering oxygen concentration data in each segment to obtain denoised oxygen concentration data. The present application reduces the influence of noise data on oxygen concentration data filtering and improves the accuracy of data filtering.

Description

Technical Field

[0001] This invention relates to the field of environmental monitoring, and in particular to an Internet of Things-based method and system for monitoring the environment of underground space. Background Technology

[0002] Oxygen concentration is a crucial indicator of air quality in underground spaces. It allows for the assessment of ventilation effectiveness and the impact of human activity on air quality, providing a scientific basis for improvement. Furthermore, monitoring oxygen concentration in underground spaces can prevent safety accidents caused by oxygen deficiency, thus enhancing the safety of personnel working in these environments. Therefore, real-time monitoring of oxygen concentration in underground spaces is essential. However, the collected oxygen concentration data often contains noise; to ensure accurate monitoring, the data needs to be filtered and denoised.

[0003] Chinese patent document CN108280816B discloses a Gaussian filtering method and a mobile terminal. The method includes: obtaining the average values ​​of multiple pixels corresponding to a target pixel; and obtaining a Gaussian result corresponding to the target pixel based on the average values ​​of the multiple pixels. This is achieved by directly obtaining the average values ​​of multiple pixels corresponding to the target pixel and then obtaining the Gaussian result corresponding to the target pixel based on the average values ​​of the multiple pixels.

[0004] Gaussian filtering can be used to filter and denoise oxygen concentration data. However, existing Gaussian filtering algorithms often require fixed parameters to achieve filtering, and these fixed-parameter filtering algorithms are ineffective at denoising data with large fluctuations. Therefore, it is necessary to segment the oxygen concentration data and then apply different parameters to different segments to improve the filtering effect. Fisher's optimal solution method is a time-series data clustering algorithm that maintains the time order, i.e., data segmentation.

[0005] The existing Fisher optimal solution method calculates the diameter of a class directly using the sum of squared deviations of the classes when segmenting oxygen concentration data in underground spaces. However, the diameter of a class directly affects the subsequent segmentation results. Since there is noise in the oxygen concentration data in underground spaces, the diameter of the classes in the traditional algorithm cannot represent the true data changes. This may lead to inaccurate data segmentation in subsequent segments, resulting in poor data segmentation and affecting the denoising effect on the oxygen concentration data in underground spaces. Summary of the Invention

[0006] To address the issue that directly segmenting oxygen concentration data using the diameter of the category in Fisher's optimal solution method affects the denoising effect, this invention provides an IoT-based method and system for monitoring underground space environment.

[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 solution:

[0008] Obtain oxygen concentration data for underground space at each moment, and construct a dataset using oxygen concentration data from multiple moments;

[0009] Construct the optimal diameter function for each category in the Fisher optimal solution method, use the Fisher optimal solution method to divide the dataset into multiple segments, filter the oxygen concentration data in each segment to obtain denoised oxygen concentration data, and issue an early warning when the oxygen concentration data in a segment is less than a preset threshold.

[0010] The method for constructing the optimal diameter function is as follows: construct a data segment centered on any oxygen concentration data; obtain the extreme points within the data segment; and construct a set of extreme points using the extreme points.

[0011] Calculate the absolute difference between any two adjacent extreme points within the extreme point set to obtain multiple absolute differences, and construct a difference set using these absolute differences; calculate the noise impact index for the corresponding oxygen concentration data, which is positively correlated with the mean of the data points within the difference set; construct the optimal diameter function, expressed as: In the formula, This represents the optimal diameter for category G during the segmentation process. This represents the mean of oxygen concentration data within category G during the segmentation process. This refers to the oxygen concentration data within category G during the segmentation process. For oxygen concentration data Noise impact index.

[0012] By calculating the noise impact index of each oxygen concentration data point, the optimal diameter for the corresponding category during the segmentation process is obtained. The optimal diameter improves the segmentation effect, enhances the accuracy of oxygen concentration data segmentation, and facilitates filtering and denoising of the oxygen concentration data to obtain accurate oxygen concentration data.

[0013] Preferably, the method further includes: calculating the time distance between two adjacent extreme points within the extreme point set to obtain multiple time distances, and using the time distances to construct a time distance set.

[0014] By constructing a time distance set from the time dimension, it is easier to analyze the characteristics of extreme points in the time dimension, thereby improving the accuracy of calculating the noise impact index.

[0015] Preferably, the expression for the noise impact index is:

[0016] ;

[0017] In the formula, Represents oxygen concentration data points Noise impact index, The variance of the time distance set. The variance of the set of differences. represents the mean of the data points within the difference set; tanh represents the hyperbolic tangent function.

[0018] The noise impact index is obtained by comprehensively calculating multiple dimensions, including the variance of the time distance set, the variance of the difference set, and the mean of the difference set, thus improving the accuracy of the noise impact index.

[0019] Preferably, the expression for the noise impact index is:

[0020] ;

[0021] In the formula, Represents oxygen concentration data points Noise impact index, This represents the mean of the data points within the difference set. denoted by , where represents the variance of the set of differences, and norm represents the normalization function.

[0022] The preferred method for filtering oxygen concentration data within segments is as follows:

[0023] Calculate the mean of the noise impact index of oxygen concentration data within the segment; calculate the optimal filtering window in Gaussian filtering, which is positively correlated with the mean of the noise impact index; and use Gaussian filtering to filter the oxygen concentration data within the segment.

[0024] By segmenting the oxygen concentration data and then using the optimal filtering window for each segment to filter the data within each segment, the accuracy of the filtering results is improved and the filtering effect is enhanced compared to traditional filtering methods.

[0025] The preferred expression for the optimal filtering window is:

[0026] ;

[0027] In the formula, This represents the optimal filtering window when filtering the i-th segment. Indicates the reference filter window, This represents the mean of the noise impact index of the oxygen concentration data within the i-th segment. This is the floor symbol.

[0028] The preferred expression for the optimal filtering window is:

[0029] ;

[0030] In the formula, This represents the optimal filtering window when filtering the i-th segment. Indicates the reference filter window, This represents the mean of the noise impact index of the oxygen concentration data within the i-th segment. The floor sign is exp, which represents an exponential function with base e.

[0031] The optimal filtering window was obtained by adjusting the size of the baseline filtering window using the mean value of the noise impact index of oxygen concentration data within the segment, which improved the filtering effect.

[0032] Secondly, the present invention provides an underground space environment monitoring system based on the Internet of Things, which adopts the following technical solution:

[0033] An Internet of Things (IoT)-based underground space environment monitoring system includes a processor and a memory. The memory stores computer program instructions, which, when executed by the processor, implement the aforementioned IoT-based underground space environment monitoring method.

[0034] The present invention has the following technical effects:

[0035] 1. By adjusting the diameter of the categories in Fisher's optimal solution method, the oxygen concentration data of underground space can be accurately segmented, improving the accuracy of the segmentation results. Then, filtering and denoising are performed on each segment separately, which can perform more refined processing on the data characteristics of different concentration ranges and different trends. It can more accurately identify and remove noise in each segment, with a better denoising effect, thereby improving the accuracy of the overall data.

[0036] 2. By adjusting the diameter of Fisher's optimal solution method based on the changing characteristics of oxygen concentration data in underground spaces, the distribution of oxygen concentration data sequences in underground spaces can be identified more accurately. This reduces the interference of noise on the classification results of oxygen concentration data, thereby improving the accuracy of classification and, consequently, the denoising effect on oxygen concentration in underground spaces, and ultimately improving the accuracy of underground space environmental monitoring. Attached Figure Description

[0037] The above and other objects, features, and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description taken in conjunction with the accompanying drawings. In the drawings, several embodiments of the invention are illustrated by way of example and not limitation, and like or corresponding reference numerals denote like or corresponding parts.

[0038] Figure 1 This is a flowchart of an Internet of Things-based method for monitoring the underground space environment according to the present invention. Detailed Implementation

[0039] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] It should be understood that when the terms "first," "second," etc., are used in the claims, specification, and drawings of this invention, they are only used to distinguish different objects and not to describe a specific order. The terms "comprising" and "including" used in the specification and claims of this invention indicate the presence of the described features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or collections thereof.

[0041] This invention discloses an Internet of Things-based method for monitoring the underground space environment, referring to... Figure 1 The process includes the following steps, as detailed below:

[0042] S1: Obtain oxygen concentration data for each moment in the underground space, and construct a dataset using oxygen concentration data from multiple moments.

[0043] Oxygen sensors are used to collect oxygen concentration data in underground spaces. Sampling points should be located in areas where people frequently move around or where air quality requirements are high. In this embodiment, oxygen sensors are placed at the work area, entrance, and exit of the underground space to collect oxygen concentration data at each location. The height of the sensor placement is consistent with the height of a person's breathing zone to ensure that the collected oxygen concentration data is representative. For example, the sensor placement is 1.65m above the ground of the underground space.

[0044] The oxygen sensors collect data every 0.5 minutes. They are then connected to the monitoring center via the Internet of Things (IoT), for example, through Wi-Fi or Bluetooth, to acquire oxygen concentration data at different locations at different times. It's important to note that each sensor's data is processed individually. For each sensor, multiple oxygen concentration data points are collected at multiple times, and a dataset is constructed using this data, arranged chronologically.

[0045] S2: Noise impact index for calculating oxygen concentration data.

[0046] There are various gases in underground spaces, including some that cross-react with oxygen sensors. This results in noise in the collected oxygen concentration data. The noise causes the oxygen concentration data to fluctuate irregularly. The data change characteristics caused by noise are used as the sensitivity, and the noise impact index of oxygen concentration data is calculated based on the sensitivity.

[0047] S21: Construct a data segment centered on any oxygen concentration data point, obtain the extreme points within the data segment, and construct a set of extreme points using the extreme points;

[0048] Taking the dataset corresponding to one of the sensors as an example, let's say... For the i-th oxygen concentration data in the oxygen concentration data sequence, use the oxygen concentration data... Centered on the data point, extract m oxygen concentration data points from the left and m oxygen concentration data points from the right to obtain the oxygen concentration data. The data segment centered on [the data point]. The extreme points within the data segment are identified using the finite difference method, resulting in a set of extreme points, denoted as: ,in Indicated by oxygen concentration data The j-th extreme point within the data segment centered at the center. This represents the number of extreme points within the set of extreme points.

[0049] S22: Calculate the time distance between two adjacent extreme points within the extreme point set to obtain multiple time distances, and construct a time distance set using the time distances.

[0050] Within the set of extreme points, each extreme point corresponds to a timestamp. The difference between the timestamps of two adjacent extreme points is taken as the time distance, thus obtaining multiple time distances. The multiple time distances are then used to construct a set of time distances.

[0051] For example, time distance sets for , Indicated by oxygen concentration data The set of time distances corresponding to the set of extreme points of the data segment centered on it, where, , , These represent data in terms of oxygen concentration. Extreme points within the central data segment and The corresponding timestamp, That is, adjacent extreme points and The time distance between them.

[0052] By time distance set The variance can characterize the data points of oxygen concentration. The variance is the consistency of the distribution of extreme points in the time series within the data segment centered on the extreme points. Specifically, the larger the variance, the worse the consistency of the distribution of extreme points; conversely, the smaller the variance, the better the consistency of the distribution of extreme points.

[0053] 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 the difference set using the absolute values ​​of the difference.

[0054] Difference set for ,in, , Indicates adjacent extreme points and The absolute value of the difference between the oxygen concentration data.

[0055] The variance of the difference set can be used to characterize oxygen concentration data points. The variance indicates the consistency of the variation range of extreme points within the central data segment. A larger variance indicates poorer consistency, and vice versa. This is achieved through the set of differences. The mean can characterize oxygen concentration data The degree of fluctuation in data within the central data segment, specifically, the set of differences. The larger the mean, the greater the fluctuation in the data within the data segment; conversely, the smaller the mean, the greater the volatility of the difference set. The smaller the mean, the less drastic the fluctuation of the data within the data segment.

[0056] S24: Calculate the noise impact index, which is positively correlated with the mean of the data points in the difference set.

[0057] In one embodiment, the expression for the noise impact index is:

[0058] ;

[0059] In the formula, Represents oxygen concentration data points Noise impact index, The variance of the time distance set. The variance of the set of differences. represents the mean of the data points within the difference set; tanh represents the hyperbolic tangent function, used for data normalization. Wherein, Characterization of oxygen concentration data The sensitivity of the data. This can be understood as: the greater the impact of noise on the oxygen concentration data, the more sensitive the data. The greater the impact of noise, the lower the impact of noise on oxygen concentration data. The less affected by noise.

[0060] In one embodiment, the expression for the noise impact index is:

[0061] ;

[0062] In the formula, Represents oxygen concentration data points Noise impact index, This represents the mean of the data points within the difference set. denoted by , where represents the variance of the set of differences, and norm represents the normalization function.

[0063] S3: Construct the optimal diameter function for each category in Fisher's optimal solution method, and use Fisher's optimal solution method to segment the dataset to obtain multiple segments.

[0064] The expression for the optimal diameter function is: In the formula, This represents the optimal diameter for category G during the segmentation process. This represents the mean of oxygen concentration data within category G during the segmentation process. This refers to the oxygen concentration data within category G during the segmentation process. For oxygen concentration data The noise impact index is considered. When calculating the diameter during segmentation using the Fisher optimal solution method, the higher the noise impact index of the corresponding oxygen concentration data point, the smaller its corresponding weight. This reduces the impact of noise on the class diameter, improves the accuracy of the Fisher optimal solution method during segmentation, and enhances the segmentation effect.

[0065] The dataset is segmented into multiple segments using Fisher's optimal solution method. The elbow method is used to determine the number of segments, which can be understood as classifying the oxygen concentration data within the dataset into multiple categories, minimizing the differences in oxygen concentration data within the same category. Classifying the oxygen concentration data into multiple categories facilitates filtering for different categories, improving the accuracy of the filtering results.

[0066] S4: Filter the oxygen concentration data in each segment to obtain the denoised oxygen concentration data.

[0067] S41: Calculate the optimal filtering window in Gaussian filtering.

[0068] The mean value of the noise impact index of oxygen concentration data within the segment is calculated, and the optimal filtering window is positively correlated with the mean value of the noise impact index.

[0069] In one embodiment, the expression for the optimal filtering window is:

[0070] In the formula, This represents the optimal filtering window when filtering the i-th segment. This represents the reference filter window. The size of the reference filter window is set manually according to the actual situation. This represents the mean of the noise impact index of the oxygen concentration data within the i-th segment. This is the floor symbol. The larger the value, the greater the impact of noise on the i-th segment of data. Therefore, a larger window is needed for filtering to improve the filtering effect.

[0071] In one embodiment, the expression for the optimal filtering window is:

[0072] ;

[0073] In the formula, This represents the optimal filtering window when filtering the i-th segment. Indicates the reference filter window, This represents the mean of the noise impact index of the oxygen concentration data within the i-th segment. The floor sign is exp, which represents an exponential function with base e.

[0074] S42: Use Gaussian filtering to filter the oxygen concentration data within the segment, and issue an early warning when the oxygen concentration data within the segment is less than a preset threshold.

[0075] The oxygen concentration data within each segment is filtered using Gaussian filtering to obtain denoised oxygen concentration data. This denoised data is then used to monitor the oxygen content in the underground space, allowing for the understanding of its changing trends. When the oxygen concentration data within a segment falls below a preset threshold, it indicates low oxygen levels, triggering an early warning. Similarly, an early warning is issued when the oxygen content gradually decreases, ensuring the safety of personnel underground. The threshold is manually set based on actual conditions.

[0076] For example, the oxygen concentration data for the current hour is divided into three segments. The oxygen concentration data in the three segments is then denoised. If there is oxygen concentration data below the threshold in a certain segment, it indicates that there may be a problem with poor ventilation in the underground space, and an early warning is issued in time. Or, if the oxygen concentration data in the third segment is monitored to gradually decrease, it indicates that the oxygen in the underground space is gradually decreasing, and an early warning is issued at this time.

[0077] This invention also discloses an Internet of Things (IoT) based underground space environment monitoring system, including a processor and a memory. The memory stores computer program instructions, which, when executed by the processor, implement an IoT-based underground space environment monitoring method according to the present invention.

[0078] The system also includes other components well known to those skilled in the art, such as communication buses and communication interfaces, the settings and functions of which are known in the art and will not be described in detail here.

[0079] In this invention, the aforementioned memory can be any tangible medium containing or storing 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 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 desired information and can be accessed by an application, module, or both. Any such computer storage medium can be part of a device or accessible to or connected to a device.

[0080] While this specification has shown and described numerous embodiments of the invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many modifications, alterations, and alternatives will occur to those skilled in the art without departing from the spirit and essence of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in the practice of this invention.

[0081] 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, all equivalent changes made in accordance with the structure, shape and principle of the present invention should be covered within the scope of protection of the present invention.

Claims

1. A method for monitoring the underground space environment based on the Internet of Things, characterized in that, Including the following steps: Obtain oxygen concentration data for underground space at each moment, and construct a dataset using oxygen concentration data from multiple moments; Construct the optimal diameter function for each category in the Fisher optimal solution method, use the Fisher optimal solution method to divide the dataset into multiple segments, filter the oxygen concentration data in each segment to obtain denoised oxygen concentration data, and issue an early warning when the oxygen concentration data in a segment is less than a preset threshold. The method for constructing the optimal diameter function is as follows: construct a data segment with any oxygen concentration data as the center; obtain the extreme points within the data segment; construct an extreme point set using the extreme points; calculate the time distance between two adjacent extreme points within the extreme point set to obtain multiple time distances; and construct a time distance set using the time distances. Calculate the absolute difference between any two adjacent extreme points within the extreme point set to obtain multiple absolute differences, and construct a difference set using these absolute differences; calculate the noise impact index of the corresponding oxygen concentration data, including: In the formula, Represents oxygen concentration data points Noise impact index, The variance of the time distance set. The variance of the set of differences. Let represent the mean of the data points within the difference set; tanh represents the hyperbolic tangent function, and the noise impact index is positively correlated with the mean of the data points within the difference set; construct the optimal diameter function, with the expression: In the formula, This represents the optimal diameter for category G during the segmentation process. This represents the mean of oxygen concentration data within category G during the segmentation process. This refers to the oxygen concentration data within category G during the segmentation process.

2. The method for monitoring the underground space environment based on the Internet of Things according to claim 1, characterized in that, The expression for the noise impact index is: ； In the formula, Represents oxygen concentration data points Noise impact index, This represents the mean of the data points within the difference set. denoted by , where represents the variance of the set of differences, and norm represents the normalization function.

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

4. The method for monitoring the underground space environment based on the Internet of Things according to claim 3, characterized in that, The expression for the optimal filtering window is: ； In the formula, This represents the optimal filtering window when filtering the i-th segment. Indicates the reference filter window, This represents the mean of the noise impact index of the oxygen concentration data within the i-th segment. This is the floor symbol.

5. The method for monitoring the underground space environment based on the Internet of Things according to claim 3, characterized in that, The expression for the optimal filtering window is: ； In the formula, This represents the optimal filtering window when filtering the i-th segment. Indicates the reference filter window, This represents the mean of the noise impact index of the oxygen concentration data within the i-th segment. The floor sign is exp, which represents an exponential function with base e.

6. An Internet of Things-based underground space environmental monitoring system, characterized in that, include: A processor and a memory, the memory storing computer program instructions, which, when executed by the processor, implement an Internet of Things-based method for monitoring the underground space environment according to any one of claims 1-5.

Images