A soil gas on-line monitoring method and system for a municipal highway construction site

Abstract

The application relates to the technical field of data monitoring, in particular to a soil gas online monitoring method and system for a municipal highway construction site, which comprises the following steps: acquiring a feature vector by analyzing the correlation between soil gas concentration data and various meteorological data at all collection time points at any depth in each time period, evaluating the similarity of the feature vector between any depth and all other depths, determining a similarity coefficient, and screening out a feature time period; determining a depth feature value by analyzing the time and space distribution characteristics of soil gas concentration, screening out a noisy time point, and correcting soil gas concentration data at the noisy time point. The application corrects soil gas concentration data affected by noise by combining the distribution characteristics of soil gas concentration, thereby improving the accuracy and precision of multi-depth soil gas monitoring of the highway construction site.

Description

Technical Field

[0001] This application relates to the field of environmental monitoring technology, specifically to an online soil gas monitoring method and system for municipal highway construction sites. Background Technology

[0002] Soil gases are gases present in the pores that make up the soil structure. Under normal soil conditions, soil gases typically include common gases such as nitrogen, oxygen, and carbon dioxide. However, in underground environments such as abandoned industrial sites and landfills, buried waste produces volatile organic compounds (VOCs), and these toxic and harmful soil gases can diffuse into the air, affecting human health. During the construction of highway tunnels, deep foundation pits, or expansive soil subgrades, various soil construction activities are required, including earthwork excavation, soil-rock subgrade filling, and soft soil foundation replacement. These activities may disturb underground pollution sources, causing harmful pollutants in the soil to diffuse and threaten the construction site environment and the surrounding ecosystem.

[0003] Existing online soil gas monitoring equipment typically uses sensors to collect data. However, sensors are subject to various interferences during data acquisition and transmission, such as thermal noise and particle noise from the sensor itself, as well as electromagnetic interference during data transmission. This results in noisy data in the collected data, leading to data deviations and reducing the accuracy and precision of soil gas monitoring in highway construction site environments. Summary of the Invention

[0004] To address the aforementioned technical problems, the purpose of this application is to provide a method and system for online monitoring of soil gas at municipal highway construction sites. The specific technical solution adopted is as follows:

[0005] In a first aspect, embodiments of this application provide a method for online monitoring of soil gas at municipal highway construction sites, the method comprising the following steps:

[0006] Acquire soil gas concentration data and various meteorological data at different depths of the highway construction site at various collection times within a preset time period;

[0007] The preset duration is evenly divided into multiple time periods. By analyzing the correlation between soil gas concentration data at any depth and various meteorological data at all collection times within each time period, the feature vector at any depth within each time period is obtained. The similarity between the feature vectors of any depth and all other depths is evaluated, and the similarity coefficient of any depth under each time period is determined so as to select the feature time period of any depth from all time periods within the preset duration.

[0008] Within each characteristic time period at any depth, the dispersion of soil gas concentration data at all sampling times in the neighborhood of each sampling time is analyzed to determine the first characteristic value of each sampling time within each characteristic time period at any depth; the difference in soil concentration data between any depth and its adjacent upper and lower depths at each sampling time within each characteristic time period at any depth is measured to determine the second characteristic value of each sampling time within each characteristic time period at any depth; combined with the first characteristic value, the depth characteristic value of each sampling time within each characteristic time period at any depth is determined to filter out noisy times from all characteristic time periods at any depth.

[0009] Soil gas concentration data at noisy times are corrected based on the depth feature values ​​to monitor soil gas at multiple depths in highway construction sites.

[0010] Preferably, the method for obtaining the feature vector at any depth within each time period is as follows:

[0011] Calculate the Pearson correlation coefficient between soil gas concentration data and various meteorological data at any depth in each time period, and use all Pearson correlation coefficients to form a feature vector at any depth in each time period.

[0012] Preferably, the similarity coefficient of any depth in each time period is the average of the similarity of the feature vectors between any depth and all other depths in each time period.

[0013] Preferably, the screening process for the characteristic time period at any depth is as follows:

[0014] The similarity coefficients of any depth in all time periods within a preset time period are used as input to the threshold segmentation algorithm, and the output is the segmentation threshold of any depth. All time periods with similarity coefficients less than the segmentation threshold are recorded as feature time periods of any depth.

[0015] Preferably, the first characteristic value of each collection moment within each characteristic time period at any depth is the reciprocal of the sum of the standard deviation of the soil gas concentration data at all collection moments in the neighborhood of each collection moment and a preset value.

[0016] Preferably, the method for determining the second feature value at each acquisition time within each characteristic time period at any depth is as follows:

[0017] The first-order forward difference between depth j and its adjacent next-layer depth at acquisition time k within the i-th feature time period of depth j, and the first-order backward difference between depth j and its adjacent previous-layer depth are respectively used as inputs to the sign function. The mean of the output results is used as the second feature value at acquisition time k within the i-th feature time period of depth j.

[0018] Preferably, the depth feature value at each acquisition moment within each feature time period of any depth is the product of the normalized value of the first feature value and the normalized value of the second feature value at each acquisition moment within each feature time period of any depth.

[0019] Preferably, the screening process for the noisy moments is as follows:

[0020] The depth feature values ​​of all acquisition times within all feature time periods at any depth within a preset time period are used as input to the threshold segmentation algorithm, and the segmentation threshold is output and recorded as the depth threshold. Within all acquisition times of all feature time periods at any depth, all acquisition times with depth feature values ​​less than the depth threshold are taken as noisy times at any depth.

[0021] Preferably, the step of correcting the soil gas concentration data at noisy times based on the depth feature values ​​to monitor soil gas at multiple depths at highway construction sites includes:

[0022] Based on the depth feature values, the window length for each noisy time point at any depth is determined as follows:

[0023] Window length at depth m and noisy time n The expression is: ; , These represent the first preset value and the second preset value, respectively. This represents the difference between the numerical value 1 and the depth feature value at the noisy time n at depth m; Q() is a user-defined function that outputs an even number that is not greater than its input value and is closest to the input value.

[0024] The soil gas concentration data at point k at noisy time n at depth m is used as the input to the data smoothing algorithm. The window length at noisy time n at depth m is used as the window length value in the data smoothing algorithm, and the output value is used as the correction data at noisy time n at depth m. The soil gas concentration at multiple depths is monitored based on the correction data.

[0025] Secondly, embodiments of this application also provide an online soil gas monitoring system for municipal highway construction sites, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any of the above-described online soil gas monitoring methods for municipal highway construction sites.

[0026] This application has at least the following beneficial effects:

[0027] This application analyzes the similarity of correlations between soil gas concentration data at different depths in highway construction sites and various meteorological data to identify characteristic time periods, i.e., time periods potentially affected by noise interference. This allows for more detailed analysis and processing within these time periods, improving the accuracy of soil gas concentration monitoring. Furthermore, by analyzing the dispersion of soil gas concentration data within the neighborhood of each collection moment in each characteristic time period, and the differences in soil gas concentration at different depths at each collection moment, depth feature values ​​are constructed. These features can more effectively identify abnormal soil gas concentration data, and the abnormal soil gas concentration data is corrected based on the depth feature values ​​to obtain corrected data that excludes noise interference, thereby improving the accuracy of soil gas concentration monitoring at highway construction sites. This application also analyzes the temporal and spatial distribution characteristics of soil gas concentration at highway construction sites and, combined with a data smoothing algorithm, filters out the impact of noise on the soil gas concentration monitoring process, improving the precision and accuracy of soil gas monitoring at highway construction sites. Attached Figure Description

[0028] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 A flowchart illustrating the steps of an online soil gas monitoring method at a municipal highway construction site, as provided in one embodiment of this application.

[0030] Figure 2 This is a schematic diagram of the noisy moment filtering process provided in an embodiment of this application. Detailed Implementation

[0031] To further illustrate the technical means and effects adopted by this application to achieve the intended purpose of the invention, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of an online soil gas monitoring method and system for municipal highway construction sites proposed in this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0032] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0033] The following description, in conjunction with the accompanying drawings, details the specific scheme of the online soil gas monitoring method and system provided in this application for municipal highway construction sites.

[0034] Please see Figure 1 The diagram illustrates a flowchart of an online soil gas monitoring method for municipal highway construction sites according to an embodiment of this application. The method includes the following steps:

[0035] Step S001: Obtain soil gas concentration data and various meteorological data at different depths of the highway construction site at each collection time within a preset time period.

[0036] Select a piece of land to be monitored at a highway construction site to collect soil gas concentration data at multiple depths. Place meteorological sensors at different depths in the soil to collect soil gas concentration data and all kinds of meteorological data at different depths in real time. Among them, the various meteorological data include at least: temperature, humidity, air pressure and wind speed data.

[0037] In this embodiment, soil gas concentration data and all meteorological data at different depths of the highway construction site are acquired at various collection times within a preset time period. The data acquisition frequency is set to f. In this embodiment, the preset time period is 1 hour and the data acquisition frequency f is 10 Hz. Implementers can also set it according to specific circumstances. This embodiment does not impose any special restrictions.

[0038] It should be noted that in this embodiment, data was collected at five depths: 10cm, 20cm, 30cm, 40cm, and 50cm underground. Implementers may also set their own depths according to specific circumstances. This embodiment does not impose any special restrictions.

[0039] Furthermore, in order to eliminate the influence of data dimensions, the collected data of different depths and types are normalized separately. In this embodiment, the maximum-minimum value normalization method is used to normalize the data. In practical applications, as other implementation methods, implementers may also use other normalization methods such as z-score normalization to normalize the data. This embodiment does not impose any special restrictions on the selection of normalization methods.

[0040] Among them, the maximum-minimum normalization method is a well-known technique, and its specific principles and processes will not be elaborated here.

[0041] Step S002: Divide the preset duration into multiple time periods evenly. By analyzing the correlation between soil gas concentration data at any depth and various meteorological data at all collection times within each time period, obtain the feature vector at any depth within each time period, evaluate the similarity of the feature vector between any depth and all other depths, and determine the similarity coefficient of any depth within each time period, so as to select the feature time period of any depth from all time periods within the preset duration.

[0042] Since soil gas concentration and meteorological data usually have a certain correlation, such as a significant positive correlation between soil gas concentration and temperature, and a significant negative correlation between soil gas concentration and humidity, air pressure and wind speed, and soil at different depths will be under similar meteorological conditions in the same time period, the soil gas concentration data at different depths in the same time period will have a relatively close positive and negative correlation with meteorological data. However, noise data in soil gas concentration data usually destroys this relationship due to its randomness.

[0043] Therefore, based on the above analysis, soil gas concentration data and various meteorological data are obtained at all collection times within the preset time period before the current time, and the preset time period is divided into M equal-length time periods to obtain soil gas concentration data and meteorological data for each time period.

[0044] It should be noted that the value of the number of time periods M is set manually. In this embodiment, the value of M is 9. In actual application, the implementer can also set it according to the specific situation. This embodiment does not impose any special restrictions.

[0045] Furthermore, the Pearson correlation coefficients between soil gas concentration data at any depth and various meteorological data are calculated for each time period. All Pearson correlation coefficients are used to form a feature vector at any depth within each time period, which is used to characterize the positive and negative correlation between soil gas concentration data at any depth within each time period and various meteorological data. The calculation method of the Pearson correlation coefficient is a well-known technique, and its specific calculation steps will not be elaborated here.

[0046] Furthermore, the average similarity between the feature vector of any depth in each time period and the feature vectors of all other depths is used as the similarity coefficient of any depth in each time period. This coefficient is used to assess the similarity of the positive and negative correlation between soil gas concentration and meteorological data between any soil depth and other soil depths in each time period. The greater the similarity, the greater the similarity coefficient, and the more similar the positive and negative correlation between soil gas concentration data and meteorological data at different soil depths in the same time period.

[0047] It should be understood that there are many methods to measure the similarity between vectors. In this embodiment, the cosine similarity between the feature vector of any depth in each time period and the feature vectors of all other depths is taken as the similarity between the feature vector of any depth in each time period and the feature vectors of all other depths. In practical applications, as other implementation methods, the implementer may also use other methods to measure the similarity between vectors, such as the reciprocal of the Euclidean distance. This embodiment does not impose any special restrictions on the selection of methods to measure the similarity between vectors.

[0048] The method for calculating cosine similarity is a well-known technique, and its specific calculation process will not be elaborated here.

[0049] Furthermore, the similarity coefficients at any depth within all time periods within a preset duration are used as input to the threshold segmentation algorithm, and the segmentation threshold at any depth is output. All time periods with similarity coefficients less than the segmentation threshold are recorded as characteristic time periods at any depth, which are used to characterize the time periods when soil gas concentration data may be affected by noise interference.

[0050] It should be noted that this embodiment uses the maximum inter-class variance (MOV) threshold segmentation algorithm. In practical applications, as other implementation methods, other threshold segmentation methods may be used. This embodiment does not impose any special restrictions on the selection of threshold segmentation methods. Furthermore, in this embodiment, the MOV threshold segmentation algorithm is used whenever it is involved.

[0051] Among them, the Otsu's inter-class variance algorithm is a well-known technique, and its specific principles and processes will not be elaborated here.

[0052] Thus, by analyzing the similarity between soil gas concentration data and various meteorological data at different depths, characteristic periods at any depth that may be affected by noise interference were selected from all time periods.

[0053] Step S003: Within each characteristic time period at any depth, analyze the dispersion of soil gas concentration data at all sampling times in the neighborhood of each sampling time, and determine the first characteristic value of each sampling time within each characteristic time period at any depth; measure the difference in soil concentration data between any depth and its adjacent upper and lower depths at each sampling time within each characteristic time period at any depth, and determine the second characteristic value of each sampling time within each characteristic time period at any depth; combine the first characteristic value to determine the depth characteristic value of each sampling time within each characteristic time period at any depth, so as to filter out noisy times from all characteristic time periods at any depth.

[0054] Generally, within a short period, the geological conditions and environmental factors in the soil are relatively stable, resulting in a relatively stable diffusion and emission process of soil gas within the same stratum. This means that the collected soil gas concentration data should exhibit relatively stable fluctuations. Furthermore, soil gas concentration gradually increases with soil depth. This is because gases primarily move from high-concentration areas to low-concentration areas through diffusion. The generation rate of surface soil gases exceeds their diffusion rate, causing volatile organic compounds (VOCs) to accumulate in deeper soil layers. Additionally, the activity of soil microorganisms decreases with increasing soil depth, slowing the rate at which microorganisms decompose organic matter containing VOCs, further contributing to VOC accumulation in deeper soil layers. Soil gas concentration data affected by noise will not exhibit these characteristics due to the randomness of the noise.

[0055] Based on the above analysis, within each characteristic time period at any depth, a neighborhood W is divided with each collection time as the center. The reciprocal of the sum of the standard deviations of the soil gas concentration data at all collection times within the neighborhood of each collection time and a preset value is taken as the first characteristic value for each collection time within each characteristic time period at any depth. This is used to evaluate whether the soil gas concentration data has the characteristic of relatively stable data changes. The smaller the reciprocal of the standard deviation, the larger the first characteristic value, and the more stable the changes in the soil gas concentration data.

[0056] In this embodiment, the radius of the neighborhood W is 5. Implementers can also set it according to specific circumstances. This embodiment does not impose any special restrictions.

[0057] It should be noted that the preset value is used to prevent the denominator from being 0. Its value is set manually. In this embodiment, the preset value is 0.01. Under the premise of ensuring that the denominator is not 0 and does not excessively affect the calculation result, the implementer can also set it according to the specific situation. This embodiment does not impose any special restrictions.

[0058] Furthermore, the first-order forward difference between depth j and its adjacent next-layer depth at collection time k within the i-th characteristic time period of depth j, and the first-order backward difference between depth j and its adjacent previous-layer depth are obtained respectively. These are used to characterize the change in soil gas concentration data at depth j relative to the next-layer depth at each collection time, and the change in soil gas concentration data at depth j relative to the previous depth at each collection time.

[0059] Furthermore, the first-order forward difference between depth j and its adjacent next-layer depth at acquisition time k within the i-th feature time period of depth j, and the first-order backward difference between depth j and its adjacent previous-layer depth are used as inputs to the sign function. The mean of the output results is used as the second feature value at acquisition time k within the i-th feature time period of depth j. By traversing each acquisition time within each feature time period of all depths, the second feature value at each acquisition time within each feature time period of any depth is obtained.

[0060] Specifically, if the current depth is the minimum depth, the result of the first-order forward difference of the current depth is assigned to its first-order backward difference; if the current depth is the maximum depth, the result of the first-order backward difference of the current depth is assigned to its first-order forward difference.

[0061] The methods for obtaining the first-order forward difference and the first-order backward difference are well-known techniques, and their specific acquisition processes will not be elaborated here.

[0062] The first-order forward difference and the first-order backward difference at any depth are used as inputs to the sign function at each collection time within each characteristic time period of any depth. The average of the output results is used as the second feature value at each collection time within each characteristic time period of any depth. This is used to evaluate whether the soil gas concentration data has the characteristic of data change stability. The larger the second feature value, the more obvious the characteristic of soil gas concentration data change stability.

[0063] The symbolic function is a well-known technique, and its specific application process will not be elaborated here.

[0064] Furthermore, the product of the normalized value of the first feature value and the normalized value of the second feature value at each collection time within each characteristic time period at any depth is recorded as the depth feature value at each collection time within each characteristic time period at any depth. This is used to evaluate whether the soil gas concentration data has the characteristics of data change stability and the characteristics of soil gas concentration increasing with increasing soil depth. If the depth feature value is smaller, the soil gas concentration data is less stable in change and less likely to increase with increasing soil depth; conversely, if the depth feature value is larger, the soil gas concentration data is more stable in change and the characteristics of increasing with increasing soil depth are more obvious.

[0065] It should be noted that there are many commonly used normalization methods. In this embodiment, the first and second feature values ​​of all acquisition times within each feature time period are normalized using the maximum-minimum normalization method. The normalized values ​​of the first and second feature values ​​are mapped to the range of [0,1]. In practical applications, as other implementation methods, implementers may also use other normalization methods such as z-score normalization according to specific circumstances. This embodiment does not impose any special restrictions on the selection of normalization methods.

[0066] Among them, the maximum-minimum normalization method is a well-known technique, and the specific process of using it to normalize data will not be elaborated here.

[0067] The depth feature values ​​of all collection times within all characteristic time periods at any depth within a preset time period are used as input to the threshold segmentation algorithm, and the output segmentation threshold is recorded as the depth threshold. Within all collection times of all characteristic time periods at any depth, all collection times with depth feature values ​​less than the depth threshold are used as noisy times at any depth to characterize the collection times when soil gas concentration data are affected by noise.

[0068] Thus, by analyzing the temporal and spatial distribution characteristics of soil gas concentration data, noisy moments were identified.

[0069] Preferably, the schematic diagram of the noisy moment filtering process provided in this embodiment is as follows: Figure 2 As shown.

[0070] Step S004: Correct the soil gas concentration data at noisy times based on the depth feature values ​​to monitor soil gas at multiple depths at highway construction sites.

[0071] This embodiment utilizes a data smoothing algorithm to smooth noise-affected data in the collected soil gas concentration data, thereby correcting the noise-affected data and improving its readability. Existing data smoothing algorithms require a fixed window size during smoothing. However, noise-affected data in the collected soil gas concentration data will exhibit varying degrees of distortion depending on the type of noise. Therefore, to effectively reduce the impact of noise in the collected soil gas concentration data, the following processing is performed.

[0072] Since the greater the noise interference with soil gas concentration data, the greater the data distortion and the less it retains the original data distribution characteristics, the window size of the data smoothing algorithm is adaptively adjusted based on the depth feature value, specifically as follows:

[0073] Window length at depth m and noisy time n The expression is: ; , These represent the first preset value and the second preset value, respectively. This represents the difference between the numerical value 1 and the depth feature value at the noisy time n at depth m, used to achieve negative correlation normalization of the depth feature value; Q() is a user-defined function that outputs an even number that is not greater than its input value and is closest to the input value.

[0074] The soil gas concentration data at point k at noisy time n at depth m is used as the input to the data smoothing algorithm. The window length at noisy time n at depth m is used as the window length value in the data smoothing algorithm, and the output value is used as the correction data at noisy time n at depth m. The soil gas concentration at multiple depths is monitored based on the correction data.

[0075] It should be noted that, , It is used to determine the upper and lower limits of the window size in the data smoothing algorithm. In this embodiment... , The values ​​are 3 and 6 respectively; in this embodiment, a smaller lower limit is set. =3 ensures a certain degree of smoothing even under conditions of large fluctuations, while the upper limit... =6 limits the window size to prevent excessive smoothing from causing the loss of the true trend of data changes. Regarding... , The value of can be set by the implementer, and this embodiment does not impose any special restrictions.

[0076] It should be noted that there are many commonly used data smoothing algorithms. In this embodiment, the moving average algorithm is used to smooth and denoise the data. In practical applications, as other implementation methods, implementers may also use other methods such as exponential smoothing algorithm and Savitzky-Golay filtering algorithm according to specific circumstances. This embodiment does not impose any special restrictions on the selection of data smoothing algorithm.

[0077] The moving average algorithm is a well-known technique, and its specific principles will not be elaborated here.

[0078] Furthermore, the corrected data is transmitted to the display screen of the monitoring equipment for online monitoring of soil gas at multiple depths at the highway construction site.

[0079] Thus, this embodiment adaptively selects an appropriate smoothing window size for the noise-affected soil gas concentration data based on the obtained depth feature values, and uses a data smoothing algorithm to correct the noise-affected data, effectively reducing the impact of noise on the accuracy of soil gas concentration data, thereby improving the readability and accuracy of the online soil gas concentration data displayed during soil gas monitoring.

[0080] Based on the same inventive concept as the above method, this application embodiment also provides an online soil gas monitoring system for municipal highway construction sites, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-described methods for online soil gas monitoring at municipal highway construction sites.

[0081] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments of this specification have been described above. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0082] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0083] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.

Claims

1. A method for online monitoring of soil gas at municipal highway construction sites, characterized in that, The method includes the following steps: Acquire soil gas concentration data and various meteorological data at different depths of the highway construction site at various collection times within a preset time period; The preset duration is evenly divided into multiple time periods. By analyzing the correlation between soil gas concentration data at any depth and various meteorological data at all collection times within each time period, the feature vector at any depth within each time period is obtained. The similarity between the feature vectors of any depth and all other depths is evaluated, and the similarity coefficient of any depth under each time period is determined so as to select the feature time period of any depth from all time periods within the preset duration. Within each characteristic time period at any depth, the dispersion of soil gas concentration data at all sampling times in the neighborhood of each sampling time is analyzed to determine the first characteristic value of each sampling time within each characteristic time period at any depth; the difference in soil concentration data between any depth and its adjacent upper and lower depths at each sampling time within each characteristic time period at any depth is measured to determine the second characteristic value of each sampling time within each characteristic time period at any depth; combined with the first characteristic value, the depth characteristic value of each sampling time within each characteristic time period at any depth is determined to filter out noisy times from all characteristic time periods at any depth. Based on the depth feature value, the soil gas concentration data at noisy times is corrected to monitor soil gas at multiple depths in highway construction sites. The method for obtaining the feature vector at any depth within each time period is as follows: Calculate the Pearson correlation coefficient between soil gas concentration data and various meteorological data at any depth in each time period, and form a feature vector at any depth in each time period using all Pearson correlation coefficients. The process for selecting the characteristic time period at any given depth is as follows: The similarity coefficients of any depth in all time periods within a preset time period are used as the input of the threshold segmentation algorithm, and the output is the segmentation threshold of any depth. All time periods with similarity coefficients less than the segmentation threshold are recorded as the feature time periods of any depth. The depth feature value at each acquisition moment within each feature time period of any depth is the product of the normalized value of the first feature value and the normalized value of the second feature value at each acquisition moment within each feature time period of any depth. The soil gas concentration data at noisy times, corrected based on the depth feature values, is used to monitor soil gas at multiple depths at highway construction sites, including: Based on the depth feature values, the window length for each noisy time point at any depth is determined as follows: Window length at depth m and noisy time n The expression is: ; , These represent the first preset value and the second preset value, respectively. This represents the difference between the numerical value 1 and the depth feature value at the noisy time n at depth m; Q() is a user-defined function that outputs an even number that is not greater than its input value and is closest to the input value. The soil gas concentration data at point k at noisy time n at depth m is used as the input to the data smoothing algorithm. The window length at noisy time n at depth m is used as the window length value in the data smoothing algorithm, and the output value is used as the correction data at noisy time n at depth m. The soil gas concentration at multiple depths is monitored based on the correction data.

2. The method for online monitoring of soil gas at municipal highway construction sites as described in claim 1, characterized in that, The similarity coefficient of any depth in each time period is the average of the similarity of the feature vectors between any depth in each time period and all other depths.

3. The method for online monitoring of soil gas at municipal highway construction sites as described in claim 1, characterized in that, The first characteristic value of each collection moment within each characteristic time period at any depth is the reciprocal of the sum of the standard deviation of the soil gas concentration data at all collection moments in the neighborhood of each collection moment and a preset value.

4. The method for online monitoring of soil gas at municipal highway construction sites as described in claim 1, characterized in that, The method for determining the second feature value at each acquisition time within each characteristic time period at any depth is as follows: The first-order forward difference between depth j and its adjacent next-layer depth at acquisition time k within the i-th feature time period of depth j, and the first-order backward difference between depth j and its adjacent previous-layer depth are respectively used as inputs to the sign function. The mean of the output results is used as the second feature value at acquisition time k within the i-th feature time period of depth j.

5. The method for online monitoring of soil gas at municipal highway construction sites as described in claim 1, characterized in that, The process for filtering the noisy moments is as follows: The depth feature values ​​of all acquisition times within all feature time periods at any depth within a preset time period are used as input to the threshold segmentation algorithm, and the segmentation threshold is output and recorded as the depth threshold. Within all acquisition times of all feature time periods at any depth, all acquisition times with depth feature values ​​less than the depth threshold are taken as noisy times at any depth.

6. An online soil gas monitoring system for municipal highway construction sites, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the online soil gas monitoring method for municipal highway construction sites as described in any one of claims 1-5.

Images