An intelligent soil environment monitoring method, device and system

Abstract

The application relates to the technical field of soil environment monitoring, in particular to an intelligent soil environment monitoring method, device and system, which comprises the following steps: acquiring the temperature at each depth in the soil in real time by using a tubular sensor, collecting the volume water content at the deep depth in real time; presetting a monitoring period of the filling medium state, obtaining the water fluctuation value of each period; extracting the wave peak feature set at each depth in each period respectively; obtaining the standard transmission delay duration of heat conduction in each period; constructing a time deviation matrix in each period, solving the minimum deviation path, and then obtaining the heat conduction deviation degree in each period; monitoring the state of the filling medium in the drill hole where the tubular sensor is located, and obtaining effective data for soil environment monitoring. The application aims to accurately distinguish various states of the soil filling medium, and improve the reliability and availability of the soil environment monitoring data under all-weather conditions.

Description

Technical Field

[0001] This application relates to the field of soil environmental monitoring technology, specifically to an intelligent soil environmental monitoring method, device, and system. Background Technology

[0002] Soil profile monitoring is the data foundation for precision agriculture irrigation decisions and geological disaster early warning. The industry widely uses tubular sensors for multi-layer synchronous monitoring. Tubular sensors are usually installed using a borehole grouting process, which involves injecting mud, such as cement grout or bentonite grout, between the tube wall and the borehole to fill the gap.

[0003] Existing tubular sensors are installed using borehole grouting, and the state of the filling medium directly affects the confidence level of the monitoring data. Whether in the initial slurry solidification stage or the long-term operation stage where desiccation leads to voids (contact failure), there is a lack of effective quantitative methods for determination. In particular, current technology mainly relies on fixed heat conduction models for state assessment, ignoring the physical characteristics of soil thermal diffusivity dynamically changing with moisture content. This leads to a high risk of misinterpreting normal physical changes as voids under conditions where rainfall infiltration causes soil wetting and accelerated heat conduction, making it impossible to accurately distinguish between the solidification, voiding, and rainfall infiltration states of the filling medium. This severely impacts the reliability and usability of all-weather monitoring data. Summary of the Invention

[0004] In view of the above, it is necessary to provide an intelligent soil environmental monitoring method, device, and system that, compared with traditional intelligent soil environmental monitoring methods, improves the reliability and usability of soil environmental monitoring data under all-weather conditions by accurately distinguishing various states of the soil filling medium.

[0005] In a first aspect, embodiments of this application provide an intelligent soil environment monitoring method, which includes the following steps:

[0006] The temperature at various depths in the soil is acquired in real time using a tubular sensor, which includes shallow and deep depths. The volumetric water content at the deep depth is also collected in real time. The monitoring period for the filling medium is preset, and the water content fluctuation value for each period is obtained by observing the fluctuation of volumetric water content within each period. The peak feature set at each depth within each period is extracted based on the temperature within each period.

[0007] Based on the preset reference thermal diffusivity of the soil, the basic delay time of heat conduction is obtained, and the basic delay time is corrected by the average level of volumetric water content in each cycle to obtain the standard transmission delay time of heat conduction in each cycle. By comparing the time difference between different peak combinations among the peak feature sets at all depths with the deviation of the standard transmission delay time, a time deviation matrix in each cycle is constructed, and the minimum deviation path is solved by the time deviation matrix to obtain the degree of heat conduction deviation in each cycle.

[0008] The delay deviation judgment threshold and fluctuation amplitude judgment threshold are generated for each period based on the standard transmission delay duration and volumetric water content, respectively. These thresholds are then compared with the thermal conduction deviation and the moisture fluctuation value to monitor the state of the filling medium in the borehole where the tubular sensor is located, thereby obtaining effective data for soil environmental monitoring.

[0009] In one embodiment, the process of obtaining the moisture fluctuation value is as follows:

[0010] Linear fitting was performed on the volumetric water content over time for each period;

[0011] The moisture fluctuation value is the difference between the volumetric moisture content and its fitted value for each period.

[0012] In one embodiment, the extraction process of the peak feature set is as follows:

[0013] The temperature peaks at each depth within each period are obtained in time sequence. Each peak and its timestamp are combined into a tuple. All the tuples corresponding to each depth within each period are combined into a peak feature set at each depth within each period.

[0014] In one embodiment, the process of obtaining the standard transmission delay duration is as follows:

[0015] The difference between the average volumetric moisture content of all cycles and the preset reference volumetric moisture content is recorded as the moisture content difference; the product of the moisture content difference and the preset moisture content correction coefficient is calculated, and the difference between 1 and the product is recorded as the correction difference.

[0016] The standard transmission delay duration is the product of the base delay duration and the correction difference.

[0017] In one embodiment, the process of obtaining the time deviation matrix is ​​as follows:

[0018] The row index of the time deviation matrix represents the peak at shallow depth, and the column index represents the peak at deep depth.

[0019] The calculation method for each element in the time deviation matrix is ​​as follows: calculate the time difference between the peak of the column where each element is located and the peak of the row where it is located, and take the time difference and the time interval between the standard transmission delay as each element.

[0020] In one embodiment, the process of obtaining the thermal conductivity deviation is as follows:

[0021] Calculate the sum of all elements on the path with the minimum deviation;

[0022] Find the maximum value among the number of rows and columns of the time deviation matrix;

[0023] The thermal conductivity deviation is the ratio of the sum to the maximum value.

[0024] In one embodiment, the method for generating the delay deviation decision threshold and the fluctuation amplitude decision threshold is as follows:

[0025] The delay deviation decision threshold is the product of the standard transmission delay duration and a preset positive number less than 1;

[0026] The fluctuation amplitude judgment threshold is the product of the average volumetric water content of all cycles and a preset ratio.

[0027] In one embodiment, the state of the filling medium in the borehole where the monitoring tubular sensor is located includes:

[0028] The initial state of the filling medium is set to unsteady. If the moisture fluctuation value in each cycle is greater than or equal to the fluctuation amplitude judgment threshold in the unsteady state, the filling medium in the current cycle is directly determined to be in a rainfall infiltration state, and the filling medium is maintained in an unsteady state. If the moisture fluctuation value in each cycle is less than the fluctuation amplitude judgment threshold, the filling medium in each cycle is determined to be in a non-rainfall infiltration state. At the same time, if the heat conduction deviation in each cycle is less than the delay deviation judgment threshold, the filling medium in each cycle is determined to meet the stabilization condition. If the filling medium in the previous consecutive preset number of cycles meets the stabilization condition, the filling medium in the current cycle is updated to a solidification confirmation state.

[0029] The product of the delay deviation decision threshold and the preset value is recorded as the empty threshold.

[0030] If, under the confirmed curing state, the filling medium is in a non-rainfall infiltration state in the current cycle, and the thermal conduction deviation is greater than the voiding threshold for a number of consecutive preset cycles prior to the current cycle, the filling medium in the current cycle will be updated to a voiding state.

[0031] If, under the curing confirmation state, the filling medium is in a non-rainfall infiltration state during the current cycle, and the thermal conduction deviation has been between the delay deviation judgment threshold and the voiding threshold for a number of consecutive preset cycles prior to the current cycle, the filling medium will maintain the curing confirmation judgment during the current cycle.

[0032] Secondly, embodiments of this application also provide an intelligent soil environment monitoring device, the device comprising:

[0033] The data preprocessing module uses tubular sensors to acquire the temperature at various depths in the soil in real time, including shallow and deep depths, and collects the volumetric water content at the deep depth in real time; it presets the monitoring cycle of the filling medium state, and obtains the water fluctuation value of each cycle by observing the fluctuation of volumetric water content within each cycle; it extracts the peak feature set at each depth within each cycle based on the temperature within each cycle.

[0034] The heat conduction deviation analysis module is used to obtain the basic delay time of heat conduction based on the preset reference thermal diffusivity of the soil, and to correct the basic delay time using the average level of volumetric water content in each cycle to obtain the standard transmission delay time of heat conduction in each cycle. By comparing the time difference between different peak combinations among the peak feature sets at all depths with the deviation of the standard transmission delay time, a time deviation matrix is ​​constructed for each cycle, and the minimum deviation path is solved by the time deviation matrix to obtain the degree of heat conduction deviation in each cycle.

[0035] The effective data acquisition module is used to generate delay deviation judgment thresholds and fluctuation amplitude judgment thresholds for each period based on the standard transmission delay duration and volumetric water content, and then compare them with the thermal conduction deviation and the moisture fluctuation value, respectively, to monitor the state of the filling medium in the borehole where the tubular sensor is located, thereby acquiring effective data for soil environmental monitoring.

[0036] Thirdly, embodiments of this application also provide an intelligent soil environment monitoring system, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of any of the above-described intelligent soil environment monitoring methods.

[0037] This application has at least the following beneficial effects:

[0038] This application calculates moisture fluctuation values ​​to reflect the steady-state state of the microstructure of the filling medium within each cycle, which helps to distinguish between the uncured filling medium itself and the increase in moisture caused by external rainfall. By extracting the temperature peaks and their timestamps within each cycle, the heat conduction characteristics within each cycle can be captured, which helps to calculate the time difference required for shallow peaks to travel to deeper layers, providing a basis for quantifying heat conduction delay. By correcting the basic delay time of heat conduction through volumetric water content, the corrected standard transmission delay time can adaptively change with environmental changes, better conforming to actual physical conditions, helping to avoid misjudgment of rainfall infiltration, and thus distinguishing this normal physical change from anomalies caused by medium voiding. By constructing a time deviation matrix, the time relationship between shallow and deep peaks is quantified, thereby obtaining the heat conduction deviation degree. By optimizing the algorithm to accurately match shallow and deep peaks, a quantitative index that comprehensively reflects the integrity of heat conduction is obtained. Furthermore, a decision threshold is dynamically generated, enabling the decision logic to adapt to different soil conditions, thereby accurately distinguishing various states of the soil filling medium and improving the reliability and usability of soil environmental monitoring data under all-weather conditions. Attached Figure Description

[0039] 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.

[0040] Figure 1 A flowchart illustrating the steps of an intelligent soil environment monitoring method provided in one embodiment of this application;

[0041] Figure 2 This is a schematic diagram of the monitoring process for the state of the filling medium. Detailed Implementation

[0042] In the description of the embodiments in this application, the words "exemplary," "or," and "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary," "or," and "for example" is intended to present the relevant concepts in a specific manner.

[0043] 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 belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. It should be understood that, unless otherwise stated, " / " in this application means "or".

[0044] It should also be noted that the terms "first" and "second" in this application are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0045] The following description, in conjunction with the accompanying drawings, details the specific scheme of the intelligent soil environment monitoring method, device, and system provided in this application.

[0046] Please see Figure 1 The diagram illustrates a flowchart of a smart soil environment monitoring method according to an embodiment of this application. The method includes the following steps:

[0047] Step 1: Use a tubular sensor to acquire the temperature at various depths in the soil in real time, including shallow depth and deep depth, and collect the volumetric water content at the deep depth in real time; preset the monitoring period of the filling medium state, and obtain the water fluctuation value of each period by observing the fluctuation of volumetric water content in each period; extract the peak feature set at each depth in each period by using the temperature in each period.

[0048] Step 1.1: Use a tubular sensor to obtain the temperature at various depths in the soil in real time, where depth includes shallow depth and deep depth, and collect the volumetric water content at the deep depth in real time.

[0049] The geometric parameters in the tubular sensor hardware configuration are read, specifically the vertical distance between the shallow and deep nodes, in meters (m). The shallow and deep nodes refer to two monitoring points at a specific depth on the tubular sensor. The temperature at the shallow depth of the soil is acquired in real time through the shallow node, and the temperature at the deep depth of the soil is acquired in real time through the deep node. The volumetric water content at the deep depth of the soil is also collected in real time. The volumetric water content is expressed as a decimal, i.e., 100% = 1.0.

[0050] In this embodiment, the shallow depth is 20cm below the surface and the deep depth is 80cm below the surface. The reason is that within the depth range [20cm, 80cm], the surface temperature fluctuation still has detectable amplitude characteristics and is relatively less affected by external environmental interference.

[0051] In this embodiment, the time interval for collecting volumetric moisture content and temperature is 15 minutes. The time interval is preset by the user and can be set by the user according to the actual situation.

[0052] Step 1.2: Preset the monitoring cycle of the filling medium state, and obtain the moisture fluctuation value of each cycle by observing the fluctuation of the volumetric moisture content within each cycle.

[0053] The monitoring cycle for the filling medium status is preset. To fully cover the lag window of temperature conduction, the data segment from 00:00 to 06:00 the next day is taken as a cycle.

[0054] During the initial stages of grouting solidification and settlement, the moisture probe readings often exhibit unstable drift or increased dispersion due to water exudation, microstructural reorganization, and non-uniform settlement within the filling medium. Conversely, in the stable soil after solidification, moisture changes are primarily driven by evapotranspiration, exhibiting a smooth linear or quasi-linear trend. Therefore, quantifying the fluctuations in moisture data can effectively assess the microscopic stability of the filling medium.

[0055] Based on the above analysis, the water content fluctuation value for each period is obtained by observing the fluctuation of volumetric water content within each period. The specific process is as follows:

[0056] To eliminate the background trend influence of natural soil drying or wetting, the volumetric moisture content in each period was linearly fitted over time to obtain a trend line reflecting the overall dry and wet trend in each period. Then, the difference between all volumetric moisture contents in each period and their fitted values ​​was taken as the moisture fluctuation value of each period.

[0057] In this embodiment, the least squares method is used to perform linear fitting of the volumetric moisture content over time. The least squares method is a well-known technique and will not be described in detail here. As other implementation methods, based on the ability to perform linear fitting of the volumetric moisture content over time, implementers may use other existing feasible techniques, and this application does not impose any special restrictions.

[0058] In this embodiment, the difference between all volumetric moisture content and its fitted value in each period is the root mean square error. The root mean square error is a well-known technique and will not be described in detail here. As other implementation methods, based on the ability to measure the difference between volumetric moisture content and its fitted value, the implementer may use other existing techniques, such as mean absolute error, etc. This application does not impose any special restrictions.

[0059] It should be noted that: the larger the calculated moisture fluctuation value, the more violent the volumetric moisture content fluctuates around the trend line, and there may be uncured flow or unstable interference at the contact surface inside the filling medium; the smaller the calculated moisture fluctuation value, the smoother the volumetric moisture content, and the more stable the microstructure of the filling medium tends to be.

[0060] Step 1.3: Extract the peak feature set at each depth within each cycle based on the temperature within each cycle.

[0061] A significant characteristic of soil heat conduction is the specific time lag that occurs when temperature fluctuations are transmitted from shallow to deep layers. To quantify this time lag, it is necessary to extract the peaks of temperature over time.

[0062] Based on the above analysis, the peak feature sets at each depth within each cycle are extracted using the temperature within each cycle, specifically as follows:

[0063] The temperature peaks at each depth within each period are obtained in time sequence. Each peak and its timestamp are combined into a tuple. All the tuples corresponding to each depth within each period are combined into a peak feature set at each depth within each period.

[0064] It should be noted that the method for obtaining the peak is as follows: taking the a-th temperature at the shallow depth in the k-th cycle as an example, construct a window centered on the a-th temperature at the shallow depth in the k-th cycle. If the a-th temperature at the shallow depth in the k-th cycle is greater than all other temperatures within the window centered on it, then the a-th temperature at the shallow depth in the k-th cycle is determined as the peak.

[0065] Step 2: Based on the preset reference thermal diffusivity of the soil, obtain the basic delay time of heat conduction, and correct the basic delay time using the average level of volumetric water content in each cycle to obtain the standard transmission delay time of heat conduction in each cycle; construct the time deviation matrix in each cycle by comparing the time difference of different peak combinations between the peak feature sets at all depths with the deviation of the standard transmission delay time, and solve the minimum deviation path through the time deviation matrix to obtain the degree of heat conduction deviation in each cycle.

[0066] Step 2.1: Based on the preset reference thermal diffusivity of the soil, obtain the basic delay time of heat conduction, and use the average level of volumetric water content in each cycle to correct the basic delay time, so as to obtain the standard transmission delay time of heat conduction in each cycle.

[0067] Traditional soil monitoring techniques typically calculate theoretical heat transfer delays based on fixed soil thermophysical parameters. However, in reality, soil thermal diffusion performance is significantly affected by volumetric water content: when rainfall infiltration causes soil wetting, the water film between soil particles enhances heat transfer efficiency, leading to faster actual heat diffusion and shorter lag times. If a fixed baseline is still used, this normal physical change may be misinterpreted as contact failure, resulting in monitoring failure.

[0068] Based on the above analysis, and using the preset reference thermal diffusivity of the soil, the basic delay time of heat conduction is obtained. This basic delay time is then corrected using the average volumetric water content within each cycle to obtain the standard transmission delay time of heat conduction within each cycle. The specific process is as follows:

[0069] Based on the vertical distance between shallow and deep nodes and a preset reference thermal diffusivity, the fundamental delay time of heat conduction under the reference state is calculated using the periodic solution formula of the one-dimensional heat conduction equation. The expression is as follows:

[0070] In the formula, This represents the fundamental delay time of heat conduction under reference conditions; This represents the vertical distance between shallow nodes and deep nodes; This represents the total number of seconds in a single day, which is 86400s. Represents pi; Indicates the preset reference thermal diffusivity;

[0071] The expression for the standard transport delay time of heat conduction within each cycle is:

[0072] In the formula, This represents the standard transmission delay time of heat conduction within the k-th cycle; This represents the fundamental delay time of heat conduction under reference conditions; This indicates the preset moisture content correction factor; This represents the average volumetric water content within the k-th period; This indicates the preset reference volumetric moisture content. Recorded as the moisture content difference; This is denoted as the correction difference.

[0073] In this embodiment, the preset reference thermal diffusivity, preset moisture content correction coefficient, and preset reference volumetric moisture content are respectively... The preset reference thermal diffusivity, preset moisture content correction coefficient, and preset reference volumetric moisture content are all preset by humans. Implementers can set them according to actual conditions. This application does not impose any special restrictions.

[0074] It should be noted that: when the actual soil moisture content is Higher than the reference value For example, when rainfall occurs, the correction item If positive, it will lead to The standard transmission delay time is less than 1. The decrease in temperature is entirely consistent with the physical law that "as the soil becomes wetter and hotter, heat conduction becomes faster and the delay shortens." Through this reverse correction, the heat conduction delay can be adaptively adjusted according to environmental changes.

[0075] Step 2.2: Construct a time deviation matrix for each period by comparing the time difference between different peak combinations among the peak feature sets at all depths with the deviation of the standard transmission delay duration.

[0076] Due to factors such as deep signal attenuation, noise interference, or inter-diurnal truncation, the measured number of shallow wave peaks is often not equal to the number of deep wave peaks. This "non-equivalent" data characteristic makes simple one-to-one correspondence comparisons unable to accurately reflect the true inter-layer conduction relationships. To find the correspondence that best conforms to physical logic, it is necessary to traverse all possible pairing combinations and construct a fully connected cost matrix.

[0077] Based on the above analysis, a time deviation matrix is ​​constructed for each period by comparing the time difference between different peak combinations among the peak feature sets at all depths with the deviation of the standard transmission delay duration. The specific process is as follows:

[0078] The row index of the time deviation matrix represents the peak at shallow depths, and the column index represents the peak at deep depths.

[0079] For a single period, the time difference between the peak of the column and the peak of the row of each element in the time deviation matrix is ​​calculated, and the time interval between the time difference and the standard transmission delay duration is used as each element in the time deviation matrix.

[0080] It should be noted that: the element in the i-th row and j-th column of the time deviation matrix... For example, This reflects the deviation between the actual heat conduction lag time and the standard transmission delay time when a conduction relationship is assumed between the i-th wave peak at shallow depth and the j-th wave peak at deep depth.

[0081] It should be added that: with For example, if the timestamp of the j-th wave peak at a deep depth is less than or equal to the timestamp of the i-th wave peak at a shallow depth, it is determined that this is physically impossible. The value is assigned to Infinity, a computer-representable infinite value, so that it can be automatically eliminated during the subsequent process of solving for the minimum deviation path. The path.

[0082] Furthermore, in order to use the optimization algorithm to solve for the minimum deviation path, the time deviation matrix needs to be completed into a square matrix. The specific process is as follows:

[0083] If the number of rows in the time deviation matrix is ​​greater than the number of columns, meaning there are more wave peaks at shallow depths than at deeper depths, then add [a certain number of columns] to the time deviation matrix. The list represents virtual deep wave peaks, where M represents the number of wave peaks at shallow depths and N represents the number of wave peaks at deep depths.

[0084] If the number of rows in the time deviation matrix is ​​less than the number of columns, meaning there are fewer wave peaks at shallow depths than at deeper depths, then add [a certain number of columns] to the time deviation matrix. Linear shallow wave peaks;

[0085] After completion, the time deviation matrix has the following dimensions: .

[0086] For all elements in the time deviation matrix that involve virtual peaks, their values ​​are uniformly assigned as the deficit matching compensation value. When a wave peak cannot be found at another depth, a "signal loss" event is considered to have occurred. This represents a quantitative penalty for "signal loss" events. Specifically, when the number of peaks at shallow and deep depths is inconsistent, the extra peaks must be matched with virtual peaks. To reflect the integrity loss caused by missing peaks in the final structural evaluation, i.e., calculating the thermal conductivity deviation, elements involving virtual peaks are assigned a large fixed cost, thus forcing the optimization algorithm to prioritize real matches when a real correspondence exists, and only accept the penalty of virtual matching when a reasonable correspondence cannot be found. In this embodiment, taking the k-th cycle as an example, Set as with Equal values.

[0087] Step 2.3: Solve for the minimum deviation path using the time deviation matrix, and then obtain the heat conduction deviation degree in each cycle.

[0088] In this embodiment, the Hungarian algorithm is used to solve the time deviation matrix within each cycle to obtain the minimum deviation path within each cycle. Then, the heat conduction deviation within each cycle is obtained through the minimum deviation path within each cycle.

[0089] It should be added that, taking the k-th cycle as an example, before solving, the number of wave peaks is checked. If the number of wave peaks at shallow depth and the number of wave peaks at deep depth are both 0 in the k-th cycle, for example due to extreme constant temperature weather or complete sensor failure, there is no basis for calculation. In this case, the k-th cycle cannot be calculated, the thermal conduction deviation in the k-th cycle is marked as invalid value NULL, and the subsequent steps are skipped.

[0090] If the peak data is valid, the completed time deviation matrix is ​​input into the Hungarian algorithm to solve for the global optimum, i.e., the minimum deviation path. The specific process is as follows:

[0091] (1) Subtract the minimum value of each row of the time deviation matrix so that each row has at least one zero element, and subtract the minimum value of each column of the time deviation matrix so that each column has at least one zero element, thereby transforming the problem of finding the minimum deviation into the problem of finding the combination of zero elements.

[0092] (2) Try to find a set of independent zero elements in the time deviation matrix, that is, select only one zero element in the same row or column; if the number of independent zero elements is equal to the matrix dimension, then the combination is the optimal solution; otherwise, use the fewest straight lines to cover all zero elements.

[0093] (3) Based on the minimum value among the elements not covered by the coverage line, adjust the values ​​of the elements in the time deviation matrix to generate new zero elements, and repeat steps (2) and (3) until the optimal solution is found.

[0094] Ultimately, the Hungarian algorithm outputs a set of optimal matching index pairs. The path formed by the elements involved in the optimal matching index pair set is the path with the minimum deviation. The optimal matching index pair set represents the correspondence between shallow and deep wave peaks with the minimum total deviation in a statistical sense, that is, the most reasonable combination of interlayer heat conduction paths.

[0095] The expression for the thermal conduction deviation within each cycle is:

[0096] In the formula, This indicates the thermal conduction deviation within the k-th cycle; max() represents the maximum value operation; This represents the number of wave peaks at shallow depths within the k-th period; This represents the number of wave peaks at a deep depth within the k-th cycle; represents the set of optimal matching index pairs in the k-th period; i represents the row number in the time deviation matrix; j represents the column number in the time deviation matrix.

[0097] It should be noted that: It reflects the total deviation under the minimum deviation path, which includes the time deviation between the actual peak pairings and the compensation value for the missing match introduced by signal loss; through The total deviation was processed to eliminate the influence of the number of wave peaks on the magnitude of the index, making the indexes comparable under different weather conditions. The smaller the calculated thermal conduction deviation, the closer the time difference between the measured wave peaks conforms to the standard transmission delay, and the less signal loss there is, indicating that the filling medium is more likely to be in a tight solid-state contact state. Conversely, the larger the calculated thermal conduction deviation, the further the time difference between the measured wave peaks deviates from the standard transmission delay, or the more signal loss there is, indicating that the filling medium is more likely to be in an unsteady state such as mud flow or a contact failure state such as air blockage.

[0098] Step 3: Based on the standard transmission delay duration and volumetric moisture content, generate delay deviation decision thresholds and fluctuation amplitude decision thresholds for each period, and then compare them with the thermal conduction deviation and the moisture fluctuation value, respectively, to monitor the state of the filling medium in the borehole where the tubular sensor is located, thereby obtaining effective data for soil environmental monitoring.

[0099] To ensure the universality of the judgment logic across different soil types and installation depths, this application does not use a fixed decision threshold. Instead, it generates delay deviation and fluctuation amplitude decision thresholds for each cycle based on the standard transmission delay duration and volumetric moisture content within each cycle. Specifically:

[0100] The product of the standard heat conduction delay time in each cycle and a preset positive number less than 1 is used as the delay deviation judgment threshold in each cycle.

[0101] The product of the average volumetric moisture content of all cycles and the preset ratio is used as the threshold for judging the fluctuation amplitude in each cycle.

[0102] In this embodiment, the preset value of a positive number less than 1 is 0.3, and the preset ratio is 1%. The preset values ​​of the positive number less than 1 and the preset ratio are both derived from experimental data.

[0103] It should be noted that the delay deviation decision threshold is dynamically adjusted according to the volumetric moisture content in the environment. When the soil becomes wet, causing the standard transmission delay time to shorten, the allowable deviation range is also narrowed accordingly, thereby maintaining the physical consistency of the decision scale.

[0104] Furthermore, by comparing the thermal conduction deviation and delay deviation decision thresholds within each cycle, and comparing the moisture fluctuation value and fluctuation amplitude decision thresholds within each cycle, the state of the filling medium in the borehole where the tubular sensor is located is monitored. The specific process is as follows:

[0105] The initial state of the filling medium is set to unsteady. If the moisture fluctuation value in the k-th cycle is greater than or equal to the fluctuation amplitude judgment threshold in the unsteady state, the filling medium in the k-th cycle is directly determined to be in a rainfall infiltration state, and the filling medium is maintained in an unsteady state. If the moisture fluctuation value in the k-th cycle is less than the fluctuation amplitude judgment threshold, the filling medium in the k-th cycle is determined to be in a non-rainfall infiltration state. At the same time, if the heat conduction deviation in the k-th cycle is less than the delay deviation judgment threshold, the filling medium in the k-th cycle is determined to meet the stability condition. If the filling medium in the previous consecutive preset number of cycles meets the stability condition, the filling medium in the current cycle is updated to the solidification confirmation state.

[0106] The product of the delay deviation decision threshold and the preset value is recorded as the empty threshold.

[0107] If, under the confirmed curing state, the filling medium is in a non-rain infiltration state in the current cycle, and if the thermal conduction deviation is greater than the void threshold for a number of consecutive preset cycles before the current cycle, it indicates that the interlayer thermal conduction path has been blocked by the air layer and the contact has failed. In this case, the filling medium in the current cycle will be updated to a void state.

[0108] If, under the solidification confirmation state, the filling medium is in a non-rainfall infiltration state during the current cycle, and if the thermal conduction deviation has been between the delay deviation judgment threshold and the voiding threshold for a consecutive preset number of cycles prior to the current cycle, then the current cycle is determined to be a transition observation period, and the filling medium maintains the solidification confirmation judgment during the current cycle.

[0109] The above operations effectively distinguish between "natural rainfall causing data fluctuations" and "contact failure causing data fluctuations." A schematic diagram of the monitoring process for the filling medium's condition is shown below. Figure 2 As shown.

[0110] In this embodiment, the preset quantity, preset number, and preset value are 3, 5, and 3, respectively, and the preset quantity, preset number, and preset value are all calculated from experimental data.

[0111] Furthermore, based on the state of the filling medium, effective data for soil environmental monitoring is output, specifically:

[0112] Taking the k-th cycle as an example, if the filling medium is in a solidified confirmed state during the k-th cycle, including cases where it is determined to be rainwater infiltration, all temperature and volumetric moisture content data obtained during the k-th cycle are determined to be valid data. This data is then transmitted to a cloud database or user terminal via wireless transmission technology. Subsequently, the valid data is used for soil environmental monitoring, ensuring the quality and availability of soil environmental monitoring data from the source.

[0113] If the filling medium is in an unsteady state or a voided state during the k-th cycle, all temperatures and all volumetric moisture contents during the k-th cycle are determined to be invalid data and cannot reflect the real soil environment. An abnormal status code is added to the data message, such as Error_Code:0x01 indicating unsteady state and 0x02 indicating voided state.

[0114] Based on the same inventive concept as the above method, this application also provides an intelligent soil environment monitoring device, comprising:

[0115] The data preprocessing module uses tubular sensors to acquire the temperature at various depths in the soil in real time, including shallow and deep depths, and collects the volumetric water content at the deep depth in real time; it presets the monitoring cycle of the filling medium state, and obtains the water fluctuation value of each cycle by observing the fluctuation of volumetric water content within each cycle; it extracts the peak feature set at each depth within each cycle based on the temperature within each cycle.

[0116] The heat conduction deviation analysis module is used to obtain the basic delay time of heat conduction based on the preset reference thermal diffusivity of the soil, and to correct the basic delay time using the average level of volumetric water content in each cycle to obtain the standard transmission delay time of heat conduction in each cycle. By comparing the time difference between different peak combinations among the peak feature sets at all depths with the deviation of the standard transmission delay time, a time deviation matrix is ​​constructed for each cycle, and the minimum deviation path is solved by the time deviation matrix to obtain the degree of heat conduction deviation in each cycle.

[0117] The effective data acquisition module is used to generate delay deviation judgment thresholds and fluctuation amplitude judgment thresholds for each period based on the standard transmission delay duration and volumetric water content, and then compare them with the thermal conduction deviation and the moisture fluctuation value, respectively, to monitor the state of the filling medium in the borehole where the tubular sensor is located, thereby acquiring effective data for soil environmental monitoring.

[0118] Based on the same inventive concept as the above method, this application embodiment also provides an intelligent soil environment monitoring system, 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 intelligent soil environment monitoring methods.

[0119] In summary, this application calculates moisture fluctuation values ​​to reflect the steady-state of the microstructure of the filling medium within each cycle, which helps to distinguish between the uncured filling medium itself and the increase in moisture caused by external rainfall. By extracting temperature peaks and their timestamps within each cycle, the heat conduction characteristics within each cycle can be captured, which helps to calculate the time difference required for shallow peaks to travel to deeper layers, providing a basis for quantifying heat conduction delay. By correcting the basic delay time of heat conduction through volumetric water content, the corrected standard transmission delay time can adaptively adapt to environmental changes, better conforming to actual physical conditions, helping to avoid misjudgment of rainfall infiltration, thus distinguishing this normal physical change from anomalies caused by medium voiding. By constructing a time deviation matrix, the time relationship between shallow and deep peaks is quantified, thereby obtaining the heat conduction deviation degree. By optimizing the algorithm to accurately match shallow and deep peaks, a quantitative index that comprehensively reflects the integrity of heat conduction is obtained. Furthermore, a decision threshold is dynamically generated, enabling the decision logic to adapt to different soil conditions, thereby accurately distinguishing various states of the soil filling medium and improving the reliability and usability of soil environmental monitoring data under all-weather conditions.

[0120] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0121] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from its essential characteristics. Therefore, the embodiments described above should be considered exemplary and non-limiting in all respects.

Claims

1. A method for intelligent soil environmental monitoring, characterized in that, The method includes the following steps: The temperature at various depths in the soil is acquired in real time using a tubular sensor, which includes shallow and deep depths. The volumetric water content at the deep depth is also collected in real time. The monitoring period for the filling medium is preset, and the water content fluctuation value for each period is obtained by observing the fluctuation of volumetric water content within each period. The peak feature set at each depth within each period is extracted based on the temperature within each period. Based on the preset reference thermal diffusivity of the soil, the basic delay time of heat conduction is obtained, and the basic delay time is corrected by the average level of volumetric water content in each cycle to obtain the standard transmission delay time of heat conduction in each cycle. By comparing the time difference between different peak combinations among the peak feature sets at all depths with the deviation of the standard transmission delay time, a time deviation matrix in each cycle is constructed, and the minimum deviation path is solved by the time deviation matrix to obtain the degree of heat conduction deviation in each cycle. The delay deviation judgment threshold and fluctuation amplitude judgment threshold are generated for each period based on the standard transmission delay duration and volumetric water content, respectively. These thresholds are then compared with the thermal conduction deviation and the moisture fluctuation value to monitor the state of the filling medium in the borehole where the tubular sensor is located, thereby obtaining effective data for soil environmental monitoring.

2. The intelligent soil environment monitoring method as described in claim 1, characterized in that, The process for obtaining the moisture fluctuation value is as follows: Linear fitting was performed on the volumetric water content over time for each period; The moisture fluctuation value is the difference between the volumetric moisture content and its fitted value for each period.

3. The intelligent soil environment monitoring method as described in claim 1, characterized in that, The extraction process of the peak feature set is as follows: The temperature peaks at each depth within each period are obtained in time sequence. Each peak and its timestamp are combined into a tuple. All the tuples corresponding to each depth within each period are combined into a peak feature set at each depth within each period.

4. The intelligent soil environment monitoring method as described in claim 1, characterized in that, The process for obtaining the standard transmission delay duration is as follows: The difference between the average volumetric moisture content of all cycles and the preset reference volumetric moisture content is recorded as the moisture content difference; the product of the moisture content difference and the preset moisture content correction coefficient is calculated, and the difference between 1 and the product is recorded as the correction difference. The standard transmission delay duration is the product of the base delay duration and the correction difference.

5. The intelligent soil environment monitoring method as described in claim 3, characterized in that, The process of obtaining the time deviation matrix is ​​as follows: The row index of the time deviation matrix represents the peak at shallow depth, and the column index represents the peak at deep depth. The calculation method for each element in the time deviation matrix is ​​as follows: calculate the time difference between the peak of the column where each element is located and the peak of the row where it is located, and take the time difference and the time interval between the standard transmission delay as each element.

6. The intelligent soil environment monitoring method as described in claim 1, characterized in that, The process for obtaining the thermal conductivity deviation is as follows: Calculate the sum of all elements on the path with the minimum deviation; Find the maximum value among the number of rows and columns of the time deviation matrix; The thermal conductivity deviation is the ratio of the sum to the maximum value.

7. The intelligent soil environment monitoring method as described in claim 1, characterized in that, The methods for generating the delay deviation decision threshold and the fluctuation amplitude decision threshold are as follows: The delay deviation decision threshold is the product of the standard transmission delay duration and a preset positive number less than 1; The fluctuation amplitude judgment threshold is the product of the average volumetric water content of all cycles and a preset ratio.

8. The intelligent soil environment monitoring method as described in claim 1, characterized in that, The state of the medium filling the borehole where the monitoring tubular sensor is located includes: The initial state of the filling medium is set to unsteady. If the moisture fluctuation value in each cycle is greater than or equal to the fluctuation amplitude judgment threshold in the unsteady state, the filling medium in the current cycle is directly determined to be in a rainfall infiltration state, and the filling medium is maintained in an unsteady state. If the moisture fluctuation value in each cycle is less than the fluctuation amplitude judgment threshold, the filling medium in each cycle is determined to be in a non-rainfall infiltration state. At the same time, if the heat conduction deviation in each cycle is less than the delay deviation judgment threshold, the filling medium in each cycle is determined to meet the stabilization condition. If the filling medium in the previous consecutive preset number of cycles meets the stabilization condition, the filling medium in the current cycle is updated to a solidification confirmation state. The product of the delay deviation decision threshold and the preset value is recorded as the empty threshold. If, under the confirmed curing state, the filling medium is in a non-rainfall infiltration state in the current cycle, and the thermal conduction deviation is greater than the voiding threshold for a number of consecutive preset cycles prior to the current cycle, the filling medium in the current cycle will be updated to a voiding state. If, under the curing confirmation state, the filling medium is in a non-rainfall infiltration state during the current cycle, and the thermal conduction deviation has been between the delay deviation judgment threshold and the voiding threshold for a number of consecutive preset cycles prior to the current cycle, the filling medium will maintain the curing confirmation judgment during the current cycle.

9. An intelligent soil environment monitoring device, employing the intelligent soil environment monitoring method as described in claim 1, characterized in that, The device includes: The data preprocessing module uses tubular sensors to acquire the temperature at various depths in the soil in real time, including shallow and deep depths, and collects the volumetric water content at the deep depth in real time; it presets the monitoring cycle of the filling medium state, and obtains the water fluctuation value of each cycle by observing the fluctuation of volumetric water content within each cycle; it extracts the peak feature set at each depth within each cycle based on the temperature within each cycle. The heat conduction deviation analysis module is used to obtain the basic delay time of heat conduction based on the preset reference thermal diffusivity of the soil, and to correct the basic delay time using the average level of volumetric water content in each cycle to obtain the standard transmission delay time of heat conduction in each cycle. By comparing the time difference between different peak combinations among the peak feature sets at all depths with the deviation of the standard transmission delay time, a time deviation matrix is ​​constructed for each cycle, and the minimum deviation path is solved by the time deviation matrix to obtain the degree of heat conduction deviation in each cycle. The effective data acquisition module is used to generate delay deviation judgment thresholds and fluctuation amplitude judgment thresholds for each period based on the standard transmission delay duration and volumetric water content, and then compare them with the thermal conduction deviation and the moisture fluctuation value, respectively, to monitor the state of the filling medium in the borehole where the tubular sensor is located, thereby acquiring effective data for soil environmental monitoring.

10. An intelligent soil environment monitoring system, 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 intelligent soil environment monitoring method as described in any one of claims 1-8.

Images