Method, device and terminal for monitoring and evaluating the effect of microbial mineralization solidification of soil based on self-heating optical fiber

Abstract

The application discloses a method and device for monitoring and evaluating the effect of microbial mineralization and solidification of soil based on a self-heating optical fiber, and a terminal, and belongs to the technical field of data processing. The method comprises the following steps: arranging a self-heating distributed optical fiber in a rock-soil body to be reinforced, obtaining initial thermal response data of the rock-soil body to be reinforced based on the self-heating distributed optical fiber; constructing an initial state benchmark model based on the initial thermal response data; implementing target reinforcement treatment on the rock-soil body to be reinforced, and collecting target thermal response data in the process of the target reinforcement treatment based on the self-heating distributed optical fiber; correcting the target thermal response data based on the initial state benchmark model to extract a target feature vector; and obtaining a reinforcement evaluation result of the rock-soil body to be reinforced based on the target feature vector. The application solves the engineering problem that the reinforcement effect is difficult to accurately monitor in a complex environment, and provides key technical support for reliable application of biotechnology in major projects.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method, apparatus and terminal for monitoring and evaluating the effect of microbial mineralization and solidification of soil based on self-heating optical fiber. Background Technology

[0002] In geotechnical engineering, interfacial defects are one of the key factors affecting the long-term stability of engineering structures. Under the long-term coupled effects of moisture and dynamic loads, fine-grained layers become muddy and rise to the surface, leading to track bed contamination, reduced bearing capacity, and threatening traffic safety.

[0003] In existing technologies, traditional treatment methods such as foundation replacement and setting up sealing layers have problems such as large engineering workload and disruption to operation. Moreover, they are mostly passive remedies and fail to fundamentally improve the soil properties, making the disease prone to recurrence.

[0004] Microbially Induced Calcite Precipitation (MICP) technology can fundamentally improve soil strength and impermeability by generating calcium carbonate cementing particles, providing a new approach to fundamentally treating soil and rock diseases. However, existing technologies lack real-time distributed monitoring of the MIP process, the slurry transport path is unclear, and the treatment effect relies on post-treatment destructive testing, making dynamic control impossible. Due to the uncontrollable process, the amount of calcium carbonate generated and its spatial uniformity are highly uncertain, leading to unstable treatment effects and hindering its widespread application in railway engineering.

[0005] While self-heating distributed optical fibers can sense changes in soil thermal properties, how to intelligently assess the uniformity and effectiveness of MIP processing using its massive spatial data remains a core unresolved issue.

[0006] Therefore, there is an urgent need for a solution that can perceive and intelligently evaluate in real time.

[0007] Therefore, existing technologies still need to be improved and enhanced. Summary of the Invention

[0008] To address the aforementioned deficiencies in existing technologies, this invention provides a method, apparatus, and terminal for monitoring and evaluating the effect of microbial mineralization and solidification soil based on self-heating optical fiber. The aim is to solve the problem of how to isolate environmental factors from interfered monitoring data and accurately extract the reinforcement effect in the complex field environment of MIP treatment.

[0009] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows:

[0010] In a first aspect, the present invention provides a method for monitoring and evaluating the effect of microbial mineralization and soil stabilization based on self-heating optical fiber, the method comprising:

[0011] A self-heating distributed optical fiber is deployed in the rock and soil to be reinforced, and the initial thermal response data of the rock and soil to be reinforced is obtained based on the self-heating distributed optical fiber. The initial thermal response data is the data corresponding to the thermal response changes caused by environmental factors.

[0012] An initial state baseline model is constructed based on the initial thermal response data;

[0013] The target reinforcement treatment is carried out on the rock and soil mass to be reinforced, and the target thermal response data during the target reinforcement treatment process is collected based on the self-heating distributed optical fiber.

[0014] The target thermal response data is corrected based on the initial state benchmark model to extract the target feature vector, which is used to characterize the reinforcement effect of the soil and rock to be reinforced.

[0015] The reinforcement assessment results of the soil and rock mass to be reinforced are obtained based on the target feature vector.

[0016] A second aspect of the present invention provides a monitoring and evaluation device for the effect of microbial mineralization and solidification of soil based on self-heating optical fiber, comprising:

[0017] The first data acquisition module is used to deploy self-heating distributed optical fibers in the rock and soil to be reinforced, and to acquire the initial thermal response data of the rock and soil to be reinforced based on the self-heating distributed optical fibers. The initial thermal response data is the data corresponding to the thermal response changes caused by environmental factors.

[0018] The benchmark construction module is used to construct an initial state benchmark model based on the initial thermal response data;

[0019] The second data acquisition module is used to perform target reinforcement treatment on the rock and soil to be reinforced, and to collect target thermal response data during the target reinforcement treatment process based on the self-heating distributed optical fiber.

[0020] The feature acquisition module is used to correct the target thermal response data based on the initial state benchmark model in order to extract the target feature vector, which is used to characterize the reinforcement effect of the soil and rock to be reinforced.

[0021] The evaluation module is used to obtain the reinforcement evaluation results of the soil and rock mass to be reinforced based on the target feature vector.

[0022] A third aspect of the present invention provides a terminal comprising a processor and a computer-readable storage medium communicatively connected to the processor, the computer-readable storage medium being adapted to store a plurality of instructions, the processor being adapted to invoke the instructions in the computer-readable storage medium to execute the steps of the above-described monitoring and evaluation method for the effect of microbial mineralization and solidification of soil based on self-heating optical fiber.

[0023] Compared with existing technologies, this invention provides a method for monitoring and evaluating the effect of microbial mineralization and soil consolidation based on self-heating optical fibers. The method involves deploying self-heating distributed optical fibers in the soil to be reinforced, acquiring initial thermal response data of the soil to be reinforced based on these fibers (data corresponding to changes in thermal response caused by environmental factors), constructing an initial state benchmark model based on this data, then implementing targeted reinforcement treatment on the soil to be reinforced, and collecting target thermal response data during the reinforcement process using the self-heating distributed optical fibers. Subsequently, the target thermal response data is corrected based on the initial state benchmark model to extract target feature vectors. These target feature vectors characterize the reinforcement effect of the soil to be reinforced. Finally, the reinforcement evaluation result of the soil to be reinforced is obtained based on the target feature vectors. The proposed solution solves the engineering problem of accurately monitoring the reinforcement effect in complex on-site environments by constructing an environmental benchmark-dynamic correction system. It realizes distributed, high-precision, and intelligent evaluation of the reinforcement effect, which essentially ensures the final quality of MIP treatment and provides key technical support for the reliable application of biotechnology in major engineering projects. Attached Figure Description

[0024] Figure 1 A flowchart illustrating an embodiment of the monitoring and evaluation method for the effect of microbial mineralization and solidification of soil based on self-heating optical fiber provided by the present invention;

[0025] Figure 2 A fiber optic distribution diagram for an embodiment of the monitoring and evaluation method for the effect of microbial mineralization and solidification of soil based on self-heating optical fiber provided by the present invention;

[0026] Figure 3 A flowchart illustrating the implementation of an embodiment of the monitoring and evaluation method for the effect of microbial mineralization and solidification of soil based on self-heating optical fiber provided by the present invention.

[0027] Figure 4 A schematic diagram of the structural principle of an embodiment of the monitoring and evaluation device for the effect of microbial mineralization and solidification of soil based on self-heating optical fiber provided by the present invention;

[0028] Figure 5A schematic diagram illustrating the principle of an embodiment of the terminal provided by the present invention. Detailed Implementation

[0029] To make the objectives, technical solutions, and effects of this invention clearer and more explicit, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0030] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0031] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0032] The monitoring and evaluation method for the effect of microbial mineralization and solidification of soil based on self-heating optical fiber provided by this invention can be applied to terminals with computing capabilities. The terminal can execute the monitoring and evaluation method for the effect of microbial mineralization and solidification of soil based on self-heating optical fiber provided by this invention to solve the travel time of seismic waves.

[0033] Example 1

[0034] This embodiment describes a monitoring and evaluation method for the effect of microbial mineralization and soil solidification based on self-heating optical fibers. Specifically, in geotechnical engineering, interfacial layer defects are one of the key factors affecting the long-term stability of engineering structures. Under the long-term coupled action of moisture and dynamic loads, the fine-particle layer softens and becomes muddy, and is squeezed and surged to the track bed as pore water pressure increases, leading to track bed contamination and compaction, a sharp decline in load-bearing capacity, and uneven track conditions, seriously threatening traffic safety and transportation efficiency.

[0035] Currently, the treatment of such soil and rock defects mainly relies on traditional engineering methods, such as foundation replacement, setting up sealing layers, or constructing blind drainage systems. Although these methods are widely used, they have drawbacks such as large engineering workload, high cost, and serious disruption to normal railway operations. More importantly, these methods are mostly passive defenses or remedial measures, failing to fundamentally improve the engineering properties of fine-grained soils. Under long-term loads and hydrological cycles, the defects are prone to recurrence in the original or nearby locations, demonstrating the limitation of treating the symptoms but not the root cause.

[0036] Microbial induced calcium carbonate precipitation (MICP) technology, as an emerging biological soil and rock reinforcement method, injects specific bacterial solutions and reactants into the soil, and utilizes microbial metabolism to induce the generation of calcium carbonate crystals, effectively cementing soil particles, thereby fundamentally improving the strength, stiffness and impermeability of the soil, providing a highly promising new approach for eradicating such soil and rock diseases.

[0037] However, existing technologies lack real-time, distributed monitoring methods for the MIP (Mixed Injection Propagation) process. During grouting, the migration path and distribution range of the grout in the soil are unknown, leading to blind spots and uneven treatment. The evaluation of the treatment effect heavily relies on destructive and delayed detection via core drilling after treatment, making dynamic control and optimization during the process impossible. Due to the uncontrollable process, there is significant uncertainty and randomness regarding whether the final calcium carbonate content meets standards and whether its spatial distribution is uniform, resulting in unstable MIP treatment effects, low material utilization, and difficulty in large-scale application in railway engineering projects with stringent quality requirements.

[0038] Self-heating distributed fiber optic sensing technology can simultaneously serve as a linear heat source and a distributed temperature sensor, providing a revolutionary technical means to perceive the internal state of soil by measuring changes in soil thermophysical parameters. However, how to utilize the massive, continuous spatial data generated by this technology to intelligently and quantitatively evaluate the uniformity and effectiveness of MIP processing, and to form a complete monitoring-evaluation methodology system, remains a core problem that current technologies have not yet solved.

[0039] Therefore, there is an urgent need for a systematic solution that integrates real-time distributed sensing, intelligent evaluation of treatment effects, and dynamic feedback of the treatment process to ensure the reliability, uniformity, and long-term effectiveness of MICP technology.

[0040] In this embodiment, the monitoring and evaluation method for the effect of microbial mineralization and solidification of soil based on self-heating optical fiber is mainly used to solve the problem of how to isolate environmental factors from the interference of monitoring data in complex field environments and accurately extract the real data of reinforcement effect.

[0041] In this embodiment, in addition to the self-heating distributed optical fiber, the system also includes a power supply, a data acquisition unit, a machine learning unit, and a MICP grouting reinforcement unit. The self-heating distributed optical fiber is deployed in a three-dimensional mesh pattern on the surface of the fine-grained layer of the railway subgrade. It is connected to the power supply and also to the data acquisition unit. The data acquisition unit is connected to the machine learning unit and transmits the acquired data to the machine learning unit for analysis. The machine learning unit uses a well-trained random forest model, combined with parameters such as soil inherent properties, environmental hydrology, train load, and the number of MICP treatments as training datasets, to establish a high-precision prediction model for real-time monitoring of the content and uniformity of calcium carbonate generated after MICP treatment. The MICP grouting reinforcement unit performs targeted optimization of the area based on the optimization scheme generated by the machine learning unit's evaluation results.

[0042] Specifically, such as Figure 1 As shown, in one embodiment of the monitoring and evaluation method for the effect of microbial mineralization and solidification of soil based on self-heating optical fiber provided by the present invention, the method includes the following steps: S 100-S500, of which:

[0043] S 100. A self-heating distributed optical fiber is deployed in the rock and soil mass to be reinforced, and the initial thermal response data of the rock and soil mass to be reinforced is obtained based on the self-heating distributed optical fiber. The initial thermal response data is the data corresponding to the thermal response changes caused by environmental factors.

[0044] The method of deploying self-heating distributed optical fibers in the rock and soil mass to be reinforced includes:

[0045] An upper fiber optic network and a lower fiber optic network are constructed based on the self-heating distributed optical fiber, and the network is arranged in a three-dimensional mesh pattern in the fine particle layer.

[0046] The upper fiber optic network is laid on the surface of the fine particle layer and is laid along the longitudinal and transverse directions of the line at a first spacing.

[0047] The lower-layer optical fiber network is deployed at a target distance below the upper-layer optical fiber network, and is laid out along the longitudinal and transverse directions of the line at a second spacing, wherein the first spacing is smaller than the second spacing.

[0048] Reference Figure 2In the process of microbial mineralization and soil consolidation, the first step is to lay self-heating distributed optical fibers within the soil and rock mass to be reinforced. These self-heating distributed optical fibers consist of two 400μm diameter resistance wires and one 250μm diameter temperature-sensing optical fiber, encased in a PVC sheath to form a rectangular cable structure with a cross-sectional dimension of 3mm × 2mm. The resistance wires are used for electrical heating, serving as a linear heat source; the temperature-sensing optical fiber is used to collect real-time temperature distribution data along the fiber.

[0049] Specifically, the self-heating distributed optical fiber is deployed in a three-dimensional mesh form in the fine-grained layer of the railway subgrade.

[0050] Reference Figure 2 The optical fiber is deployed in two layers: the upper optical fiber network is deployed on the surface of the fine-particle layer, and is laid out along the longitudinal and transverse directions of the line at a first spacing. Preferably, the first spacing is set to 0.5m, forming a dense top monitoring layer for high-resolution capture of temperature changes in the surface area;

[0051] The lower-layer fiber optic network is deployed below the upper-layer fiber optic network at a target distance, arranged along the longitudinal and transverse directions of the line at a second spacing. Preferably, the target distance is 20-30cm; in this embodiment, the target distance is 25cm. The second spacing is set to 1.0m, forming the bottom monitoring layer. The first spacing is smaller than the second spacing, meaning the upper-layer monitoring density is higher than the lower-layer density, to balance monitoring accuracy and cabling cost.

[0052] The aforementioned three-dimensional mesh layout enables comprehensive, high spatial resolution temperature field monitoring of the reinforced area, providing a data foundation for subsequent evaluation of the spatial uniformity of the reinforcement effect.

[0053] Furthermore, in this embodiment, before acquiring the initial thermal response data of the soil and rock mass to be reinforced based on the self-heating distributed optical fiber, the following steps are also included:

[0054] The reference thermal conductivity of the rock and soil to be reinforced was measured using a high-precision thermal needle probe.

[0055] The initial thermal conductivity of the soil and rock mass to be reinforced was determined using the self-heating distributed optical fiber.

[0056] The target calibration factor is obtained based on the ratio of the reference thermal conductivity to the initial thermal conductivity;

[0057] The thermal response data measured by the self-heating distributed optical fiber is corrected based on the target calibration factor.

[0058] Specifically, before acquiring initial thermal response data based on the self-heating distributed optical fiber, the temperature data monitored by the self-heating distributed optical fiber needs to be calibrated to eliminate systematic errors caused by the optical fiber's own heat capacity and its contact with the soil.

[0059] The specific calibration steps are as follows:

[0060] First, the reference thermal conductivity of the soil and rock mass to be reinforced is measured using a high-precision thermal needle probe. Preferably, the high-precision thermal needle probe is a TP08 thermal needle probe, which has high measurement accuracy and can be used as a reference.

[0061] Secondly, the initial thermal conductivity of the rock foundation soil to be reinforced at the same location was measured using the self-heating distributed optical fiber.

[0062] Then, the target calibration factor is obtained based on the ratio of the reference thermal conductivity to the initial thermal conductivity. The formula for calculating the target calibration factor is:

[0063] ;

[0064] in, The reference thermal conductivity is the benchmark value of soil thermal conductivity measured by a standard sensor, i.e. The initial thermal conductivity is the initial value of the soil thermal conductivity measured by the self-heating distributed optical fiber.

[0065] Finally, all subsequent thermal response data measured by the self-heating distributed optical fiber are corrected based on the target calibration factor. That is, all subsequent thermal conductivity measurements must be multiplied by this calibration factor. C This is to eliminate systematic errors and ensure the accuracy of measurement data.

[0066] S200. Construct an initial state baseline model based on the initial thermal response data.

[0067] Specifically, in this embodiment, the initial thermal response data includes thermal response data under different hydrological conditions, thermal response data under different load conditions, and thermal response data under different meteorological conditions. The step of constructing an initial state baseline model based on the initial thermal response data includes:

[0068] Based on the initial thermal response data, a mapping relationship between environmental factors and changes in thermal response is established to obtain the initial state baseline model.

[0069] Specifically, after the fiber optic cable is laid and calibrated, and before the target hardening treatment is implemented, background data will be collected to obtain data corresponding to the thermal response changes caused by environmental factors, i.e., the initial thermal response data.

[0070] The initial thermal response data includes thermal response data under different environmental conditions. Specifically, in this embodiment, it includes:

[0071] Thermal response data under different hydrological conditions: including soil foundation thermal conductivity data during periods of no rainfall and rainfall, and under different groundwater level fluctuations. By continuously monitoring the natural hydrological changes, the influence of hydrological factors on thermal response is obtained.

[0072] Thermal response data under different load conditions: including fiber optic temperature rise differences between train-passing and train-free periods. The monitoring data is labeled using train timetables, and the increase in heat convection caused by train vibration is extracted as a characteristic of the influence of load factors on the thermal response.

[0073] Thermal response data under different meteorological conditions: including thermal response data caused by changes in meteorological factors such as temperature and humidity.

[0074] The construction of the initial state baseline model based on the initial thermal response data involves analyzing the variation patterns of thermal response data under different environmental conditions to establish a mapping relationship between environmental factors (hydrological, load, meteorological) and thermal response changes. This mapping relationship constitutes the initial state baseline model. Its core function is that during subsequent reinforcement processing, when target thermal response data is collected, the portion of thermal response changes caused by environmental factors (i.e., non-MICP-induced changes) can be separated based on this baseline model, thereby extracting the net thermal response data that purely characterizes the reinforcement effect.

[0075] In this embodiment, the background data, i.e., the initial thermal response data acquisition period, is 24-48 hours to ensure coverage of a sufficient number of environmental change scenarios, making the benchmark model sufficiently representative and robust. In other embodiments, depending on the time constraints and data accuracy requirements, the initial thermal response data acquisition period can be shorter or longer.

[0076] S300. Target reinforcement treatment is performed on the soil and rock mass to be reinforced, and target thermal response data during the target reinforcement treatment process is collected based on the self-heating distributed optical fiber.

[0077] The targeted reinforcement treatment is a microbial-induced calcium carbonate precipitation reinforcement treatment. The targeted reinforcement treatment of the soil and rock mass to be reinforced includes:

[0078] The self-heating distributed optical fiber is controlled to heat at a target set power, while an equal amount of target mixed solution is injected into the rock and soil to be reinforced in multiple times using a low pH single-phase injection method. The target mixed solution contains urea, calcium chloride and microbial inoculum.

[0079] Specifically, after the initial state baseline model is constructed, targeted reinforcement treatment is applied to the soil and rock mass to be reinforced. In this embodiment, the targeted reinforcement treatment is microbial induced calcium carbonate precipitation (MICP) reinforcement treatment.

[0080] During the reinforcement process, the self-heating distributed optical fiber is controlled to heat at a target power level. In this embodiment, the power is set to 7W / m, and the heating time is 10 minutes. Simultaneously, during heating, an equal volume of the target mixed solution is injected into the monitoring area of ​​the soil to be reinforced using a low-pH single-phase injection method in multiple stages. The low-pH single-phase injection method refers to the MIP grouting process where the pH of the bacterial solution is adjusted to an acidic range (preferably 4.5-5.5) to inhibit urease activity. The bacterial solution and gelling solution are pre-mixed to form a single solution, which is then injected into the soil to be reinforced in a single step. This process inhibits calcium carbonate precipitation in the pipeline through a low-pH environment. After injection into the soil, the pH naturally rises, and the reaction occurs in situ, thereby avoiding pipeline blockage and improving the uniformity of calcium carbonate distribution. In other words, heating and injection are performed simultaneously to ensure real-time capture of thermal response changes caused by the reinforcement process.

[0081] Furthermore, in this embodiment, the target mixed solution used in the MICP treatment is a target mixed solution composed of analytical grade urea, calcium chloride, ammonium chloride, ammonium sulfate, and tris(hydroxymethyl)aminomethane reagent with an initial urease activity of 8 U / mL.

[0082] During the heating and injection process, the target thermal response data is acquired in real time based on the self-heating distributed optical fiber. Because the optical fiber is arranged in a three-dimensional network, high-resolution distributed temperature data covering the entire rock and soil mass to be reinforced can be obtained.

[0083] S400. Based on the initial state benchmark model, the target thermal response data is corrected to extract the target feature vector, which is used to characterize the reinforcement effect of the soil and rock to be reinforced.

[0084] The step of correcting the target thermal response data based on the initial state baseline model to extract the target feature vector includes:

[0085] Based on the initial state baseline model, the portion of thermal response change caused by environmental factors in the target thermal response data is removed to obtain net thermal response data characterizing the effect of microbial-induced calcium carbonate precipitation reinforcement.

[0086] One or more of the following can be extracted from the net thermal response data: thermal conductivity, temperature rise rate, and cumulative temperature rise change, to form the target feature vector.

[0087] Specifically, after collecting the target thermal response data, it is corrected based on the previously constructed initial state benchmark model. The core of the correction is to remove the portion of the thermal response changes caused by environmental factors (hydrology, load, meteorology) from the target thermal response data to obtain the net thermal response data characterizing the effect of microbial-induced calcium carbonate precipitation reinforcement.

[0088] Then, the target feature vector is extracted from the net thermal response data. The target feature vector characterizes the reinforcement effect on the soil and rock to be reinforced, and specifically includes one or more of the following parameters: the relative change in thermal conductivity; the rate of temperature rise during the heating process; and the cumulative change in temperature rise after multiple heating cycles. These feature parameters can sensitively reflect the changes in soil thermophysical properties caused by calcium carbonate formation and are key inputs for subsequent evaluation of the reinforcement effect.

[0089] S500. Obtain the reinforcement evaluation result of the soil and rock mass to be reinforced based on the target feature vector.

[0090] The process of obtaining the reinforcement assessment result of the soil and rock mass to be reinforced based on the target feature vector includes:

[0091] Construct a target training set, which consists of thermal response data and corresponding calcium carbonate content labels of sand column samples with different dry densities and initial saturations after multiple microbial-induced calcium carbonate precipitation and consolidation treatments.

[0092] The initial random forest model is trained based on the target training set to obtain the initial prediction model;

[0093] Using the initial thermal response data as an environmental baseline feature, the baseline thermal conductivity threshold of the initial prediction model is adaptively calibrated to obtain the target prediction model.

[0094] The target feature vector is input into the target prediction model to obtain the reinforcement assessment result, which includes a predicted distribution map of calcium carbonate content and an assessment level of distribution uniformity based on the spatial variability of calcium carbonate content.

[0095] Specifically, refer to Figure 3 After extracting the target feature vector, it is input into a pre-trained machine learning model to obtain the reinforcement assessment results of the soil and rock mass to be reinforced. The reinforcement assessment results include a predicted distribution map of calcium carbonate content and an assessment level of the distribution uniformity based on the spatial variability of calcium carbonate content.

[0096] The construction and application of the machine learning model includes the following steps: constructing a target training set, training the initial random forest model, on-site adaptive calibration, on-site data collection and feature extraction, and outputting model prediction and evaluation results.

[0097] First, the target training set for model training is constructed. The target training set consists of thermal response data and corresponding calcium carbonate content labels for sand column samples with different dry densities and initial saturation after multiple microbial-induced calcium carbonate precipitation and consolidation treatments.

[0098] Specifically, multiple sand column samples were prepared under indoor conditions. Each sample had a different dry density (to simulate different compaction degrees in the field) and a different initial saturation (to simulate different groundwater levels and water content in the field). Self-heating distributed optical fibers were embedded in each sand column sample.

[0099] By simulating different environmental boundary conditions, vibration loads of different frequencies were applied to some sand columns to simulate the disturbance effect of train load on soil thermal diffusion. MIP treatment experiments were conducted under different working conditions to generate samples with calcium carbonate content gradients.

[0100] Specifically, the sand column samples were subjected to microbial-induced calcium carbonate precipitation and consolidation treatments of varying numbers to generate samples with a calcium carbonate content gradient. After each treatment, thermal response data from the treatment process were collected as input features.

[0101] After all processing was completed, the calcium carbonate content of each sand column sample was determined using the acid washing method as the true label. The specific procedure for the acid washing method was as follows: approximately 10g of subsample was taken from the core and edge of each sand column segment, dissolved in excess 1M hydrochloric acid until no bubbles remained, then rinsed with deionized water, and dried at 105℃. The calcium carbonate content was calculated based on the mass difference before and after acid washing, using the following formula:

[0102] ;

[0103] in, The dry weight before pickling. The dry weight after pickling.

[0104] The thermal response data collected under indoor conditions is used as input features, and the calcium carbonate content determined by acid washing is used as the real label to form an "input feature-output label" data pair, thus forming the target training set.

[0105] Then, supervised learning training is performed on the initial random forest model based on the target training set to obtain the initial prediction model, which is the existing basic random forest model. Through training, the model learns and establishes a nonlinear mapping relationship between thermal response features and calcium carbonate content.

[0106] Thus, the complete dataset obtained through the self-heating distributed optical fiber monitoring and acid washing method, containing thermal conductivity, temperature rise rate, cumulative temperature rise change, and corresponding calcium carbonate content, has an important application in providing training data for machine learning units in intelligent monitoring and evaluation methods. Before deploying the field monitoring system, this dataset, obtained from such indoor experiments and possessing a clear "feature-label" correspondence, is used as the initial training set for training the random forest model. This allows the model to learn the complex relationship between soil thermal properties and the effectiveness of MIP treatment, laying the foundation for subsequent non-contact, distributed, and real-time intelligent prediction of the effectiveness of MIP treatment on in-situ subgrade soil.

[0107] Subsequently, the initial thermal response data collected on-site is used as an environmental baseline feature to adaptively calibrate the baseline thermal conductivity threshold of the initial prediction model, thereby obtaining the target prediction model. This calibration step aims to eliminate the differences between on-site environmental factors (such as hydrology, load, and meteorology) and indoor experimental conditions, enabling the target prediction model to adapt to the complex on-site environment.

[0108] Furthermore, in this embodiment, during the on-site reinforcement process, the data acquisition unit will simultaneously perform the following operations: acquire distributed temperature data of the self-heating distributed optical fiber network. The self-heating distributed optical fiber adopts a three-dimensional mesh layout, which can acquire high-resolution temperature field data covering the entire reinforcement area; automatically combine multi-source data such as the inherent property data of the soil and rock to be reinforced, environmental hydrological data, train load data, and the number of MICP processing times.

[0109] Among them, the inherent properties of the soil include particle size distribution and compaction degree; environmental hydrological data include saturation, groundwater level, and rainfall; train load data includes the difference in fiber optic temperature rise between train-passing and train-free periods; and MICP processing count records the number of reinforcement treatments that have been completed so far.

[0110] Then, feature parameters are extracted. These feature parameters include one or more of thermal conductivity, temperature rise rate, and cumulative temperature rise change after multiple heating cycles. Based on the extracted feature parameters, a real-time target feature vector consistent with the input requirements of the machine learning model is constructed.

[0111] Finally, the constructed target feature vector can be input into the target prediction model, which has been trained and adaptively calibrated in the field. The target prediction model analyzes and processes the input feature vector and outputs the hardening assessment result after processing.

[0112] In this embodiment, the reinforcement assessment results include: a predicted distribution map of calcium carbonate content, visually displaying the predicted calcium carbonate content at various locations within the reinforcement area; and a distribution uniformity assessment level based on the spatial variability of calcium carbonate content, used to quantitatively evaluate the uniformity of calcium carbonate distribution throughout the reinforcement area. For example, if the model assessment shows that the average calcium carbonate content predicted for area A (below the center of the roadbed) is 1.8%, indicating good uniformity, while the average content for area B (near the shoulder) is only 0.7%, and the distribution is extremely uneven, it is identified as a "very uneven area".

[0113] This enables real-time, distributed, and intelligent evaluation of the effect of microbial-induced calcium carbonate precipitation and consolidation treatment, providing a basis for decision-making in subsequent optimization treatments.

[0114] In this embodiment, after obtaining the reinforcement evaluation result of the soil and rock mass to be reinforced based on the target feature vector, the method further includes:

[0115] Based on the reinforcement assessment results, areas in the soil and rock mass to be reinforced that do not meet the reinforcement standards are identified as target areas.

[0116] Generate a supplementary reinforcement plan for the target area;

[0117] The target area is subjected to supplementary reinforcement treatment according to the supplementary reinforcement plan.

[0118] After performing supplementary reinforcement treatment on the target area according to the supplementary reinforcement scheme, the method further includes:

[0119] The target area is subjected to supplementary reinforcement treatment according to the aforementioned supplementary reinforcement plan;

[0120] The thermal response data, reinforcement scheme, and corresponding reinforcement evaluation results of each reinforcement process are stored in the database. When the amount of new data accumulated reaches a preset scale or the model performance evaluation index is lower than a preset threshold, the model retraining process is automatically triggered to update the machine learning model.

[0121] Specifically, after obtaining the reinforcement assessment results of the soil and rock mass to be reinforced based on the target feature vector, the areas in the soil and rock mass to be reinforced that do not meet the reinforcement standards are first identified as target areas based on the reinforcement assessment results. Specifically, when the model assessment shows that the average calcium carbonate content of area A is predicted to be 1.8% with good uniformity, while the average content of area B is only 0.7% and the distribution is extremely uneven, and it is identified as a "very uneven area", then area B is determined as the target area. Subsequently, a supplementary reinforcement plan is generated for the target area, such as increasing the number of MICP grouting treatments for area B. Supplementary reinforcement treatment is performed on the target area according to the supplementary reinforcement plan, such as performing a second MICP treatment on area B. After optimization, the new assessment results show that the predicted calcium carbonate content of area B has increased to 1.9%, and the uniformity level has improved to good, proving the effectiveness of the differentiated optimization plan.

[0122] Simultaneously, during the supplementary reinforcement process, the thermal response data, reinforcement scheme, and corresponding reinforcement evaluation results for each reinforcement process are automatically stored in the database. When the accumulated new data reaches a preset scale, or when model performance evaluation indicators (such as the root mean square error (RMSE) and coefficient of determination for predicting calcium carbonate content) are considered, the database will be updated accordingly. When the classification accuracy (for uniformity of distribution) falls below a preset threshold, the system automatically triggers a model retraining process. During retraining, grid search or Bayesian optimization methods are used to automatically optimize the hyperparameters of the random forest model (including the number of decision trees, the maximum tree depth, the minimum number of samples required for internal node splits, and the maximum number of features), thereby updating the machine learning model. For example, after retraining, the model's determination coefficient for predicting calcium carbonate content... The accuracy improved from 0.82 to 0.90, achieving self-evolution of system performance. Through continuous monitoring and iterative model optimization, the system's prediction accuracy has been continuously improved, ultimately achieving accurate evaluation and continuous optimization of the MICP processing effect.

[0123] In one application example, the monitoring and evaluation method for the effect of microbial mineralization and soil consolidation based on self-heating optical fiber provided in this embodiment is used to monitor and evaluate the effect of MIP reinforcement treatment on target railway subgrade soil. The monitoring section is 50m long and approximately one sleeper spacing wide. The specific implementation process is as follows:

[0124] (1) Fiber optic deployment: Self-heating distributed optical fibers are deployed in the soil and rock mass to be reinforced in the railway subgrade of target A. Specifically, a three-dimensional mesh deployment is adopted, with the upper fiber mesh deployed on the surface of the fine-grained layer at a horizontal spacing of 0.5m; the lower fiber mesh is deployed 25cm below the upper fiber mesh at a horizontal spacing of 1.0m and a vertical deployment depth of 25cm.

[0125] (2) Fiber Optic Calibration: Calibration is performed before acquiring initial thermal response data. The reference thermal conductivity of the soil and rock to be reinforced is measured using a TP08 thermal needle probe. The initial thermal conductivity at the same location was measured using a self-heating distributed optical fiber. The target calibration factor is calculated based on the ratio of the two. The thermal response data obtained from subsequent fiber measurements are then corrected based on this calibration factor.

[0126] (3) Initial Thermal Response Data Acquisition and Benchmark Model Construction: Before MICP treatment, i.e., before target reinforcement treatment, initial thermal response data were continuously monitored for 24 hours under different hydrological and load conditions. Specifically, this included recording the soil thermal conductivity under different groundwater level fluctuations and rainfall conditions, as well as the difference in fiber optic temperature rise between train-passing and train-free periods. Based on these initial thermal response data, a mapping relationship between environmental factors and thermal response changes was established to form an initial state benchmark model, which serves as the basis for subsequent environmental disturbance removal.

[0127] (4) Target reinforcement treatment: Microbial-induced calcium carbonate precipitation reinforcement treatment was implemented. The self-heating distributed optical fiber was heated at a power of 7W / m for 10 minutes. At the same time, an equal amount of mixed solution (containing urea, calcium chloride and microbial liquid) was injected into the rock and soil to be reinforced in multiple times using a low pH single-phase injection method as the first treatment.

[0128] (5) Target thermal response data acquisition: During the processing, target thermal response data is synchronously acquired based on self-heating distributed optical fibers. At the same time, environmental hydrological data and train load data are continuously acquired as environmental background references.

[0129] (6) Determination of the true value by acid washing method: Construct a target training set, take samples at the center of the roadbed and the shoulder, and take about 10g of subsamples from the core and edge of each section. Dissolve the samples in excess 1M hydrochloric acid until no bubbles are present, rinse with deionized water, dry at 105℃, and determine the calcium carbonate content using the acid washing method based on the formula. Obtain the true value of calcium carbonate content for subsequent model training.

[0130] (7) Feature extraction: The target thermal response data is corrected based on the initial state baseline model, and the thermal response changes caused by environmental factors are removed to obtain the net thermal response data characterizing the MIP reinforcement effect. Feature parameters such as thermal conductivity, temperature rise rate, and cumulative temperature rise change are extracted from the net thermal response data to form the target feature vector.

[0131] (8) Model pre-training: Before being put into field use, a target training set (containing thermal response data of sand column samples with different dry densities and initial saturation after multiple MIP treatments and their corresponding labels for calcium carbonate content determined by acid washing) has been constructed through indoor experiments. For details, refer to Table 1. Table 1 is the indoor MIP treatment experimental data in this application example. The initial random forest model is trained to obtain the initial prediction model.

[0132] Table 1:

[0133]

[0134] (9) On-site assessment: The initial thermal response data collected on-site was used as the environmental baseline feature. The baseline thermal conductivity threshold of the initial prediction model was adaptively calibrated to obtain the target prediction model. The target feature vector was input into the target prediction model to obtain the reinforcement assessment results of this processing, including the predicted distribution map of calcium carbonate content and the distribution uniformity assessment level. The results show that the average calcium carbonate content predicted for area A (below the center of the roadbed) is 2.1%, and the uniformity level is "good"; the average content for area B (near the shoulder) is only 0.8%, and the uniformity level is "poor". See Table 2 for details.

[0135] Table 2:

[0136]

[0137] (10) Differentiated optimization: Based on the reinforcement assessment results, region B is identified as the target region where the reinforcement effect is not up to standard, and a supplementary reinforcement plan (adding 2 grouting treatments) is generated for this region. The MICP grouting reinforcement unit root performs supplementary reinforcement treatment on region B.

[0138] (11) Model Update: After the reinforcement treatment, the thermal response data, reinforcement scheme, and evaluation results of this treatment are stored in the database. Based on the model update mechanism, when the accumulated new data reaches a preset scale, the model retraining process is automatically triggered to perform incremental learning and hyperparameter optimization on the random forest model. After the update, the determination coefficient R² of the model's prediction of calcium carbonate content increased from 0.85 to 0.92, and the root mean square error decreased from 0.41 to 0.29.

[0139] Through the above closed-loop process, intelligent monitoring, accurate evaluation, and adaptive optimization of the effect of microbial mineralization and soil consolidation are achieved.

[0140] As can be seen, the monitoring and evaluation method for the effect of microbial mineralization and soil stabilization based on self-heating optical fiber described in this embodiment relies on a large amount of historical case data, including laboratory data and limited field data, for model pre-training in the early stages of application. As the number of application projects increases, the thermal response data, stabilization schemes, and corresponding stabilization evaluation results of each stabilization process are automatically stored in the database and used for incremental learning and iterative optimization of the model. Therefore, with the accumulation of projects and the enrichment of data, the model's prediction accuracy will continuously improve, and the system performance will become increasingly accurate with use, achieving continuous optimization and adaptive evolution of the effect of microbial mineralization and soil stabilization.

[0141] Compared with existing technologies, the monitoring and evaluation method for the effect of microbial mineralization and solidification soil based on self-heating optical fiber described in this embodiment firstly includes a self-heating distributed optical fiber that functions as both a linear heat source and a distributed temperature sensor. Through a three-dimensional mesh layout, it achieves comprehensive and real-time monitoring of slurry migration, calcium carbonate content, and their spatial distribution during the MIP (microbial mineralization and solidification) treatment process. Secondly, it utilizes a random forest model to intelligently analyze multi-dimensional fused data, enabling quantitative and locational evaluation of the uniformity and effectiveness of the reinforcement treatment. This replaces traditional methods relying on manual experience and delayed, destructive testing, resulting in more scientific and accurate evaluation conclusions. Thirdly, the evaluation results based on machine learning output drive targeted optimization of the MIP grouting reinforcement unit, significantly improving the utilization efficiency of the treatment material and the reinforcement effect. Ultimately, this constitutes a quality control closed loop of "intelligent monitoring—effect evaluation—precise optimization." By feeding the evaluation results back to the grouting unit in real time and dynamically optimizing construction parameters, it fundamentally ensures the final quality of the MIP treatment, providing key technical support for the reliable application of biotechnology in major engineering projects.

[0142] In summary, this embodiment provides a method for monitoring and evaluating the effect of microbial mineralization and soil consolidation based on self-heating optical fibers. By deploying self-heating distributed optical fibers in the soil to be reinforced, initial thermal response data of the soil to be reinforced is acquired based on these fibers. This initial thermal response data corresponds to changes in thermal response caused by environmental factors. An initial state benchmark model is constructed based on this initial thermal response data. Then, targeted reinforcement treatment is performed on the soil to be reinforced, and target thermal response data is collected during the targeted reinforcement process using the self-heating distributed optical fibers. Subsequently, the target thermal response data is corrected based on the initial state benchmark model to extract target feature vectors. These target feature vectors characterize the reinforcement effect of the soil to be reinforced. Finally, the reinforcement evaluation result of the soil to be reinforced is obtained based on the target feature vectors. The proposed solution in this embodiment solves the engineering problem of accurately monitoring the reinforcement effect in complex on-site environments by constructing an environmental benchmark-dynamic correction system. It realizes distributed, high-precision, and intelligent evaluation of the reinforcement effect, which essentially ensures the final quality of MIP treatment and provides key technical support for the reliable application of biotechnology in major engineering projects.

[0143] It should be understood that although the steps in the flowcharts shown in the accompanying drawings are displayed sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0144] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM). ROM Programmable ROM ( PROM ), electrically programmable ROM ( EPROM Electrically erasable programmable ROM( EEPROM ) or flash memory. Volatile memory may include random access memory (RAM) RAM Alternatively, an external cache memory. This is for illustrative purposes only and not as a limitation. RAM It can be obtained in various forms, such as static RAM ( SRAM ),dynamic RAM ( DRAM ),synchronous DRAM ( SDRAM ), double data rate SDRAM ( DDR SDRAM ), Enhanced SDRAM ( ESDRAM ), Synchronization Link ( Synchlink ), DRAM ( SLDRAM ), memory bus ( Rambus )direct RAM ( RDRAM ), Direct Memory Bus Dynamics RAM ( DRDRAM ), and memory bus dynamics RAM ( RDRAM )wait.

[0145] Example 2

[0146] Based on the above embodiments, the present invention also provides a monitoring and evaluation device for the effect of microbial mineralization and solidification of soil based on self-heating optical fiber, such as... Figure 4 As shown, the monitoring and evaluation device for the effect of microbial mineralization and soil stabilization based on self-heating optical fiber includes:

[0147] The first data acquisition module is used to deploy self-heating distributed optical fibers in the rock and soil to be reinforced, and to acquire the initial thermal response data of the rock and soil to be reinforced based on the self-heating distributed optical fibers. The initial thermal response data is the data corresponding to the thermal response changes caused by environmental factors, as specifically described in Embodiment 1.

[0148] The benchmark construction module is used to construct an initial state benchmark model based on the initial thermal response data, as described in Example 1.

[0149] The second data acquisition module is used to perform target reinforcement treatment on the soil and rock mass to be reinforced, and to collect target thermal response data during the target reinforcement treatment process based on the self-heating distributed optical fiber, as described in Embodiment 1.

[0150] The feature acquisition module is used to correct the target thermal response data based on the initial state benchmark model in order to extract the target feature vector. The target feature vector is used to characterize the reinforcement effect of the soil and rock to be reinforced, as specifically described in Embodiment 1.

[0151] The evaluation module is used to obtain the reinforcement evaluation result of the soil and rock mass to be reinforced based on the target feature vector, as described in Example 1.

[0152] Example 3

[0153] Based on the above embodiments, the present invention also provides a terminal, such as... Figure 5 As shown, the terminal includes a processor 10 and a memory 20. Figure 5 Only some of the terminal components are shown; however, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0154] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as the terminal's hard drive or memory. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard drive or smart memory card equipped on the terminal. SmartMediaCard , SMC ), Secure Digital ( SecureDigital , SD ) card, flash memory card ( FlashCard Furthermore, the memory 20 may include both internal storage units and external storage devices of the terminal. The memory 20 is used to store application software and various types of data installed on the terminal. The memory 20 may also be used to temporarily store data that has been output or will be output. In one embodiment, the memory 20 stores a monitoring and evaluation program 30 for the effect of microbial mineralization and solidification of soil based on self-heating optical fiber. This monitoring and evaluation program 30 for the effect of microbial mineralization and solidification of soil based on self-heating optical fiber can be executed by the processor 10, thereby realizing the monitoring and evaluation method for the effect of microbial mineralization and solidification of soil based on self-heating optical fiber in this application.

[0155] In some embodiments, the processor 10 may be a central processing unit (CPU). Central Processing Unit , CPU (a microprocessor or other chip) is used to run program code or process data stored in the memory 20, such as executing the monitoring and evaluation method for the effect of microbial mineralization and solidification soil based on self-heating optical fiber.

[0156] In one embodiment, when the processor 10 executes the monitoring and evaluation program 30 for the effect of microbial mineralization and solidification of soil based on self-heating optical fiber in the memory 20, the following steps are performed:

[0157] A self-heating distributed optical fiber is deployed in the rock and soil to be reinforced, and the initial thermal response data of the rock and soil to be reinforced is obtained based on the self-heating distributed optical fiber. The initial thermal response data is the data corresponding to the thermal response changes caused by environmental factors.

[0158] An initial state baseline model is constructed based on the initial thermal response data;

[0159] The target reinforcement treatment is carried out on the rock and soil mass to be reinforced, and the target thermal response data during the target reinforcement treatment process is collected based on the self-heating distributed optical fiber.

[0160] The target thermal response data is corrected based on the initial state benchmark model to extract the target feature vector, which is used to characterize the reinforcement effect of the soil and rock to be reinforced.

[0161] The reinforcement assessment results of the soil and rock mass to be reinforced are obtained based on the target feature vector.

[0162] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring and evaluating the effect of microbial mineralization and soil stabilization based on self-heating optical fiber, characterized in that, The monitoring and evaluation method for the effect of microbial mineralization and soil stabilization based on self-heating optical fiber includes: A self-heating distributed optical fiber is deployed in the rock and soil to be reinforced, and the initial thermal response data of the rock and soil to be reinforced is obtained based on the self-heating distributed optical fiber. The initial thermal response data is the data corresponding to the thermal response changes caused by environmental factors. An initial state baseline model is constructed based on the initial thermal response data; The target reinforcement treatment is carried out on the rock and soil mass to be reinforced, and the target thermal response data during the target reinforcement treatment process is collected based on the self-heating distributed optical fiber. The target thermal response data is corrected based on the initial state benchmark model to extract the target feature vector, which is used to characterize the reinforcement effect of the soil and rock to be reinforced. The reinforcement evaluation results of the soil and rock mass to be reinforced are obtained based on the target feature vector. The method of deploying self-heating distributed optical fibers in the rock and soil mass to be reinforced includes: An upper fiber optic network and a lower fiber optic network are constructed based on the self-heating distributed optical fiber, and the network is arranged in a three-dimensional mesh pattern in the fine particle layer. The upper fiber optic network is laid on the surface of the fine particle layer and is laid along the longitudinal and transverse directions of the line at a first spacing. The lower-layer optical fiber network is deployed at a target distance below the upper-layer optical fiber network, and is laid along the longitudinal and transverse directions of the line at a second spacing, wherein the first spacing is smaller than the second spacing. The targeted reinforcement treatment is a microbial-induced calcium carbonate precipitation reinforcement treatment. The targeted reinforcement treatment of the soil and rock mass to be reinforced includes: The self-heating distributed optical fiber is controlled to heat at a target set power, and at the same time, an equal amount of target mixed solution is injected into the rock and soil to be reinforced in multiple times using a low pH single-phase injection method. The target mixed solution contains urea, calcium chloride and microbial liquid. The step of correcting the target thermal response data based on the initial state baseline model to extract the target feature vector includes: Based on the initial state baseline model, the portion of thermal response change caused by environmental factors in the target thermal response data is removed to obtain net thermal response data characterizing the effect of microbial-induced calcium carbonate precipitation reinforcement. One or more of thermal conductivity, temperature rise rate, and cumulative temperature rise change are extracted from the net thermal response data to form the target feature vector; The process of obtaining the reinforcement assessment result of the soil and rock mass to be reinforced based on the target feature vector includes: Construct a target training set, which consists of thermal response data and corresponding calcium carbonate content labels of sand column samples with different dry densities and initial saturations after multiple microbial-induced calcium carbonate precipitation and consolidation treatments. The initial random forest model is trained based on the target training set to obtain the initial prediction model; Using the initial thermal response data as an environmental baseline feature, the baseline thermal conductivity threshold of the initial prediction model is adaptively calibrated to obtain the target prediction model. The target feature vector is input into the target prediction model to obtain the reinforcement assessment result, which includes a predicted distribution map of calcium carbonate content and an assessment level of distribution uniformity based on the spatial variability of calcium carbonate content.

2. The monitoring and evaluation method for the effect of microbial mineralization and soil stabilization based on self-heating optical fiber according to claim 1, characterized in that, Before acquiring the initial thermal response data of the soil and rock mass to be reinforced based on the self-heating distributed optical fiber, the method further includes: The reference thermal conductivity of the rock and soil to be reinforced was measured using a high-precision thermal needle probe. The initial thermal conductivity of the soil and rock mass to be reinforced was determined using the self-heating distributed optical fiber. The target calibration factor is obtained based on the ratio of the reference thermal conductivity to the initial thermal conductivity; The thermal response data measured by the self-heating distributed optical fiber is corrected based on the target calibration factor.

3. The monitoring and evaluation method for the effect of microbial mineralization and soil stabilization based on self-heating optical fiber according to claim 1, characterized in that, The initial thermal response data includes thermal response data under different hydrological conditions, thermal response data under different load conditions, and thermal response data under different meteorological conditions. The construction of an initial state baseline model based on the initial thermal response data includes: Based on the initial thermal response data, a mapping relationship between environmental factors and changes in thermal response is established to obtain the initial state baseline model.

4. The monitoring and evaluation method for the effect of microbial mineralization and soil stabilization based on self-heating optical fiber according to claim 1, characterized in that, After obtaining the reinforcement assessment result of the soil and rock mass to be reinforced based on the target feature vector, the method further includes: Based on the reinforcement assessment results, areas in the soil and rock mass to be reinforced that do not meet the reinforcement standards are identified as target areas. Generate a supplementary reinforcement plan for the target area; The target area is subjected to supplementary reinforcement treatment according to the supplementary reinforcement plan.

5. A monitoring and evaluation device for the effect of microbial mineralization and soil stabilization based on self-heating optical fiber, characterized in that, include: The first data acquisition module is used to deploy self-heating distributed optical fibers in the rock and soil to be reinforced, and to acquire the initial thermal response data of the rock and soil to be reinforced based on the self-heating distributed optical fibers. The initial thermal response data is the data corresponding to the thermal response changes caused by environmental factors. The benchmark construction module is used to construct an initial state benchmark model based on the initial thermal response data; The second data acquisition module is used to perform target reinforcement treatment on the rock and soil to be reinforced, and to collect target thermal response data during the target reinforcement treatment process based on the self-heating distributed optical fiber. The feature acquisition module is used to correct the target thermal response data based on the initial state benchmark model in order to extract the target feature vector, which is used to characterize the reinforcement effect of the soil and rock to be reinforced. The evaluation module is used to obtain the reinforcement evaluation results of the soil and rock mass to be reinforced based on the target feature vector; The method of deploying self-heating distributed optical fibers in the rock and soil mass to be reinforced includes: An upper fiber optic network and a lower fiber optic network are constructed based on the self-heating distributed optical fiber, and the network is arranged in a three-dimensional mesh pattern in the fine particle layer. The upper fiber optic network is laid on the surface of the fine particle layer and is laid along the longitudinal and transverse directions of the line at a first spacing. The lower-layer optical fiber network is deployed at a target distance below the upper-layer optical fiber network, and is laid along the longitudinal and transverse directions of the line at a second spacing, wherein the first spacing is smaller than the second spacing. The targeted reinforcement treatment is a microbial-induced calcium carbonate precipitation reinforcement treatment. The targeted reinforcement treatment of the soil and rock mass to be reinforced includes: The self-heating distributed optical fiber is controlled to heat at a target set power, and at the same time, an equal amount of target mixed solution is injected into the rock and soil to be reinforced in multiple times using a low pH single-phase injection method. The target mixed solution contains urea, calcium chloride and microbial liquid. The step of correcting the target thermal response data based on the initial state baseline model to extract the target feature vector includes: Based on the initial state baseline model, the portion of thermal response change caused by environmental factors in the target thermal response data is removed to obtain net thermal response data characterizing the effect of microbial-induced calcium carbonate precipitation reinforcement. One or more of thermal conductivity, temperature rise rate, and cumulative temperature rise change are extracted from the net thermal response data to form the target feature vector; The process of obtaining the reinforcement assessment result of the soil and rock mass to be reinforced based on the target feature vector includes: Construct a target training set, which consists of thermal response data and corresponding calcium carbonate content labels of sand column samples with different dry densities and initial saturations after multiple microbial-induced calcium carbonate precipitation and consolidation treatments. The initial random forest model is trained based on the target training set to obtain the initial prediction model; Using the initial thermal response data as an environmental baseline feature, the baseline thermal conductivity threshold of the initial prediction model is adaptively calibrated to obtain the target prediction model. The target feature vector is input into the target prediction model to obtain the reinforcement assessment result, which includes a predicted distribution map of calcium carbonate content and an assessment level of distribution uniformity based on the spatial variability of calcium carbonate content.

6. A terminal, characterized in that, The terminal includes: a processor and a computer-readable storage medium communicatively connected to the processor. The computer-readable storage medium is adapted to store multiple instructions, and the processor is adapted to call the instructions in the computer-readable storage medium to execute the steps of the monitoring and evaluation method for the effect of microbial mineralization and solidification soil based on self-heating optical fiber as described in any one of claims 1-4.

Images