CN-121499752-B - Soil gas on-line monitoring method and system for municipal highway construction site

CN121499752BCN 121499752 BCN121499752 BCN 121499752BCN-121499752-B

Abstract

The application relates to the technical field of data monitoring, in particular to a soil gas on-line monitoring method and a system for municipal highway construction sites, wherein the method comprises the steps of obtaining feature vectors by analyzing the correlation between soil gas concentration data and various meteorological data at all acquisition moments at any depth in each time period, evaluating the similarity of the feature vectors between any depth and all other depths, and determining a similarity coefficient so as to screen out feature time periods; and determining depth characteristic values by analyzing time and space distribution characteristics of the soil gas concentration so as to screen out noise-containing time and correct soil gas concentration data at the noise-containing time. According to the application, the soil gas concentration data affected by noise is corrected by combining the distribution characteristics of the soil gas concentration, so that the precision and accuracy of multi-depth soil gas monitoring of a highway construction site are improved.

Inventors

HAN XIAO
LI YULONG
ZHENG WEI
ZHOU YUHUA
WANG YONGSHENG
WANG JUNYAN
XU QIANG
SHI ZHIJIE
NIU TIANTIAN
XING CHENGWEI

Assignees

北京梓淮科技有限公司

Dates

Publication Date: 20260508
Application Date: 20251126

Claims (6)

1. The on-line monitoring method for the soil gas of the municipal road construction site is characterized by comprising the following steps of: Acquiring soil gas concentration data and various meteorological data at different depths of a highway construction site at each acquisition moment within a preset duration; Uniformly dividing the preset time length into a plurality of time periods, acquiring a feature vector at any depth in each time period by analyzing the correlation between the soil gas concentration data and various meteorological data at all the acquisition time points at any depth in each time period, evaluating the similarity of the feature vector between any depth and all other depths, and determining the similarity coefficient of any depth in each time period so as to screen the feature time period of any depth from all the time periods in the preset time length; Analyzing the discrete degree of the soil gas concentration data at all the collecting moments in the neighborhood of each collecting moment in each characteristic period of any depth, determining a first characteristic value of each collecting moment in each characteristic period of any depth, respectively measuring the difference of the soil concentration data between any depth and the adjacent upper and lower layers of depth in each characteristic period of any depth, determining a second characteristic value of each collecting moment in each characteristic period of any depth, combining the first characteristic value, and determining the depth characteristic value of each collecting moment in each characteristic period of any depth so as to screen out the noise-containing moment from all the characteristic periods of any depth; Correcting soil gas concentration data at the noise-containing time based on the depth characteristic value so as to monitor the multi-depth soil gas of the highway construction site; the method for acquiring the feature vector at any depth in each period comprises the following steps: Respectively calculating pearson correlation coefficients between the soil gas concentration data and various meteorological data at any depth of each period, and forming feature vectors at any depth of each period by using all pearson correlation coefficients; The screening process of the characteristic time period of any depth comprises the following steps: taking the similarity coefficient of any depth in all time periods within a preset duration as the input of a threshold segmentation algorithm, outputting a segmentation threshold of any depth, and recording all time periods in which the similarity coefficient is smaller than the segmentation threshold as characteristic time periods of any depth; the depth characteristic value of each acquisition time in each characteristic period of any depth is the product of the normalized value of the first characteristic value and the normalized value of the second characteristic value of each acquisition time in each characteristic period of any depth; The correcting the soil gas concentration data under the noise-containing time based on the depth characteristic value so as to monitor the soil gas of the road construction site at multiple depths comprises the following steps: Based on the depth characteristic value, determining the window length of each noise-containing moment at any depth, specifically: window length at noise-containing time n at depth m The expression of (2) is: ; 、 respectively representing a preset first value and a preset second value; Q () is a self-defined function, and outputs an even number which is not more than the input value and closest to the input value; And taking the soil gas concentration data at k of the noise-containing moment n under the depth m as the input of a data smoothing algorithm, wherein the window length of the noise-containing moment n under the depth m is taken as the value of the window length in the data smoothing algorithm, the output value is taken as the correction data of the noise-containing moment n under the depth m, and the multi-depth soil gas concentration is monitored according to the correction data.
2. The method for on-line monitoring the soil atmosphere in a municipal highway construction site according to claim 1, wherein the similarity coefficient of any depth in each period is a mean value of the similarity of the feature vector between any depth and all other depths in each period.
3. The on-line monitoring method for soil gas in municipal highway construction sites according to claim 1, wherein the first characteristic value of each collection time in each characteristic period of any depth is the result of taking the reciprocal of the sum of the standard deviation of the soil gas concentration data of all collection times in the neighborhood of each collection time and a preset value.
4. The on-line monitoring method for soil gas in municipal highway construction sites according to claim 1, wherein the method for determining the second characteristic value of each acquisition time in each characteristic period of any depth comprises the following steps: And respectively taking a first-order forward difference between the depth j and the depth of the next layer adjacent to the depth j in the ith characteristic period of the depth j and a first-order backward difference between the depth j and the depth of the previous layer adjacent to the depth j as input of a sign function, and taking an average value of output results as a second characteristic value of the depth j in the ith characteristic period of the depth j.
5. The on-line monitoring method for soil gas in municipal road construction sites according to claim 1, wherein the screening process at the noise-containing time is as follows: And taking all the acquisition moments of which the depth characteristic values are smaller than the depth threshold value as noise-containing moments of any depth in all the acquisition moments of all the feature periods of any depth.
6. An on-line monitoring system for soil gas of a municipal road construction site, comprising a memory, a processor and a computer program stored in the memory and running on the processor, characterized in that the processor, when executing the computer program, carries out the steps of a method for on-line monitoring of soil gas of a municipal road construction site according to any one of claims 1-5.

Description

Soil gas on-line monitoring method and system for municipal highway construction site Technical Field The application relates to the technical field of environmental monitoring, in particular to a soil gas on-line monitoring method and system for municipal road construction sites. Background Soil gas is a gas existing in gaps of a space formed by a soil structure, and under a general soil condition, the soil gas generally comprises common gases such as nitrogen, oxygen, carbon dioxide and the like. However, in the underground environment such as the waste industrial carry-over area, the landfill area and the like, volatile organic matters are generated by the underground buried wastes, and soil gas of toxic and harmful substances is diffused into the air to influence the health of human bodies. In the construction process of highway tunnels, deep foundation pits or expansive soil roadbeds, a plurality of soil construction activities such as earth excavation, filling of soil-included stone roadbeds, replacement and filling of soft foundations and the like are required to be carried out on a site. Underground pollution sources can be disturbed in construction activities, so that harmful pollution gases in soil are diffused, and the construction site environment and the surrounding ecological environment are threatened. The existing on-line monitoring equipment for the soil gas generally uses a sensor to collect data, however, the sensor is interfered by various factors during data collection and data transmission, such as thermal noise, shot noise and other electronic noise of the sensor and electromagnetic interference of the data during transmission, so that noise data exist in the collected data to cause deviation of the data, and accuracy and precision of monitoring the soil gas in the road construction site environment are reduced. Disclosure of Invention In order to solve the technical problems, the application aims to provide a soil gas on-line monitoring method and a soil gas on-line monitoring system for municipal highway construction sites, and the adopted technical scheme is as follows: in a first aspect, an embodiment of the present application provides a method for on-line monitoring of soil gas in a municipal highway construction site, the method comprising the steps of: Acquiring soil gas concentration data and various meteorological data at different depths of a highway construction site at each acquisition moment within a preset duration; Uniformly dividing the preset time length into a plurality of time periods, acquiring a feature vector at any depth in each time period by analyzing the correlation between the soil gas concentration data and various meteorological data at all the acquisition time points at any depth in each time period, evaluating the similarity of the feature vector between any depth and all other depths, and determining the similarity coefficient of any depth in each time period so as to screen the feature time period of any depth from all the time periods in the preset time length; Analyzing the discrete degree of the soil gas concentration data at all the collecting moments in the neighborhood of each collecting moment in each characteristic period of any depth, determining a first characteristic value of each collecting moment in each characteristic period of any depth, respectively measuring the difference of the soil concentration data between any depth and the adjacent upper and lower layers of depth in each characteristic period of any depth, determining a second characteristic value of each collecting moment in each characteristic period of any depth, combining the first characteristic value, and determining the depth characteristic value of each collecting moment in each characteristic period of any depth so as to screen out the noise-containing moment from all the characteristic periods of any depth; and correcting the soil gas concentration data at the noise-containing time based on the depth characteristic value so as to monitor the soil gas of the road construction site at multiple depths. Preferably, the method for obtaining the feature vector at any depth in each period comprises the following steps: And respectively calculating pearson correlation coefficients between the soil gas concentration data and various meteorological data at any depth of each period, and forming the feature vector at any depth of each period by using all pearson correlation coefficients. Preferably, the similarity coefficient of any depth in each period is a mean value of the similarity of the feature vector between any depth and all other depths in each period. Preferably, the screening process of the characteristic period of any depth is as follows: And taking the similarity coefficient of any depth in all time periods within a preset time period as input of a threshold segmentation algorithm, outputting a segmentation threshold of any depth, and recording all time periods in wh