A method for evaluating the reinforcement effect of modified slurry grouting of shield muck based on multi-data fusion
By using a multi-data fusion method, combining on-site monitoring and numerical simulation data, the accuracy of evaluating the grouting reinforcement effect of shield tunnels was solved, improving construction quality and safety, and optimizing resource utilization.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANDONG JIANZHU UNIV
- Filing Date
- 2025-02-05
- Publication Date
- 2026-06-30
AI Technical Summary
Existing methods for evaluating the effectiveness of grouting reinforcement in shield tunnels rely on single data points, making it difficult to comprehensively and accurately reflect the actual construction situation. On-site monitoring data is limited by the layout of monitoring points and measurement errors, while numerical simulation data differs from actual engineering data.
A multi-data fusion method was adopted, combining field monitoring data and numerical simulation data. Field data was acquired through sensors, a three-dimensional numerical model was constructed, simulation was performed, data was preprocessed, a probability distribution model was established, and the posterior probability of the grouting reinforcement effect was calculated using Bayes' theorem.
It enables precise evaluation of the grouting and reinforcement effect of modified soil from shield tunneling, improves the construction quality and safety of shield tunnels, optimizes resource utilization, and provides a scientific basis for engineering decision-making.
Smart Images
Figure CN120068412B_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of shield tunneling grouting, and particularly relates to a method for evaluating the grouting reinforcement effect of shield tunneling slag modified grout based on multi-data fusion. Background Technology
[0002] In shield tunnel construction, grouting reinforcement is a key technology used to fill the voids between the tunnel and the surrounding rock, improve the strength and stability of the surrounding rock, and control ground settlement. However, existing methods for evaluating the effectiveness of grouting reinforcement have many shortcomings. Some evaluation methods rely on only a single type of data, such as field monitoring data or numerical simulation data, which is insufficient to comprehensively and accurately reflect the grouting reinforcement effect. While field monitoring data can reflect the actual construction situation in real time, its representativeness and accuracy are limited by factors such as the layout of monitoring points and measurement errors. Although numerical simulation data can simulate the reinforcement effect under different construction conditions to a certain extent, the model itself contains certain assumptions and simplifications, resulting in differences from actual engineering conditions.
[0003] Therefore, there is an urgent need for a method to evaluate the grouting reinforcement effect that comprehensively considers multiple factors and can effectively integrate on-site monitoring data and numerical simulation data, so as to improve the accuracy and reliability of the evaluation and provide a scientific basis for tunnel engineering construction. Summary of the Invention
[0004] To address the aforementioned technical problems, this invention provides a method for evaluating the reinforcement effect of shield tunneling slag modified grout based on multi-data fusion, comprising:
[0005] Acquire on-site monitoring data based on sensors;
[0006] A three-dimensional numerical model was constructed based on the tunnel structure dimensions and the shield tunneling spoil modified grouting reinforcement scheme. Simulation was performed based on the three-dimensional numerical model to obtain numerical simulation data.
[0007] The on-site monitoring data and the numerical simulation data are preprocessed to obtain preprocessed data;
[0008] Based on existing engineering experience, the prior probability distribution of grouting reinforcement effects at different levels was determined.
[0009] Based on the data indicators of the preprocessed data, a probability distribution model for different grouting reinforcement effect levels is established as the likelihood function.
[0010] The prior probability distribution and the likelihood function are calculated based on Bayes' theorem to obtain the posterior probabilities of the grouting reinforcement effect at different levels. The level with the highest posterior probability is taken as the evaluation result of the grouting reinforcement effect.
[0011] Preferably, the process of acquiring on-site monitoring data based on sensors includes:
[0012] Based on the geological conditions and structural characteristics of the tunnel, monitoring sections were selected around the shield tunnel slag grouting reinforcement area, and soil pressure sensors, displacement sensors and pore water pressure sensors were installed.
[0013] Data from earth pressure sensors are collected at different time points, and the ratio of the difference in earth pressure values at adjacent time points to the time interval is calculated to obtain the rate of change of earth pressure.
[0014] The displacement values of specific monitoring points on the tunnel wall or ground surface are collected at different times based on displacement sensors, and the rate of displacement change is calculated; and the total displacement of the monitoring points from the start of construction to the end of a certain stage is recorded.
[0015] Based on the real-time monitoring of groundwater pressure changes in pores using pore water pressure sensors, the ratio of the difference between the values measured by pore water pressure sensors at different locations to the distance between the sensors is calculated.
[0016] Preferably, the process of obtaining numerical simulation data includes:
[0017] Based on a detailed geological survey report of the tunnel project, combined with the tunnel structural dimensions and the shield tunneling slag modification grouting reinforcement scheme, a three-dimensional numerical model was established using numerical simulation software.
[0018] Based on the aforementioned three-dimensional numerical model, various working conditions during the tunnel boring machine's advancement process and the effects of different grouting reinforcement schemes are simulated.
[0019] Based on the numerical simulation process, the formation deformation data, soil stress state data, and grout diffusion and permeability data are extracted from the numerical simulation.
[0020] Preferably, the process of obtaining preprocessed data includes: for each selected feature parameter, calculating its minimum and maximum values in all preprocessed field monitoring data and numerical simulation data; selecting a linear normalization method to calculate all data based on the distribution characteristics of the feature parameters and the properties of the data, and normalizing the data to the 0-1 interval.
[0021] Preferably, the process of determining the prior probability distribution of grouting reinforcement effect at different levels based on existing engineering experience includes: classifying the grouting reinforcement effect into four levels—excellent, good, qualified, and unqualified—based on existing engineering experience and similar engineering cases, and determining the prior probability distribution of grouting reinforcement effect at different levels.
[0022] Preferably, the expression for calculating the prior probability distribution and the likelihood function based on Bayes' theorem is as follows:
[0023]
[0024] Among them, P(H i |D) represents the posterior probability that the grouting reinforcement effect is at different levels. It is the sum of probabilities of observing monitoring data D under all possible grouting reinforcement effect levels, ΠP(D|H i ) is the product of the likelihood functions of multiple monitoring indicators, where D is the monitoring data, and H is the product of the likelihood functions of multiple monitoring indicators. i This represents the i-th level assumption of the grouting reinforcement effect.
[0025] On the other hand, the present invention also provides an electronic device, including a memory, a processor, and a computing program stored in the memory and executable on the processor, characterized in that the processor implements the method when executing the computer program.
[0026] On the other hand, the present invention also provides a computer-readable storage medium storing a computer program, characterized in that the computer program implements the method when executed by a processor.
[0027] Compared with the prior art, the present invention has the following advantages and technical effects:
[0028] This invention integrates on-site monitoring data and numerical simulation data, and uses a multi-data fusion method to comprehensively and accurately evaluate the grouting reinforcement effect of modified grout for shield tunneling, thereby improving the construction quality and safety of shield tunnels, optimizing the resource utilization strategy of shield tunneling excavated soil, and providing a scientific and reliable basis for engineering decision-making, thus promoting the efficient, safe and sustainable development of shield tunnel engineering. Attached Figure Description
[0029] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:
[0030] Figure 1 This is a schematic diagram of the method flow according to an embodiment of the present invention; Detailed Implementation
[0031] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.
[0032] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.
[0033] Example 1
[0034] like Figure 1 As shown in this embodiment, a method for evaluating the reinforcement effect of shield tunneling slag modified grout based on multi-data fusion is provided, including:
[0035] Acquire on-site monitoring data based on sensors;
[0036] A three-dimensional numerical model was constructed based on the tunnel structure dimensions and the shield tunneling spoil modified grouting reinforcement scheme. Simulation was performed based on the three-dimensional numerical model to obtain numerical simulation data.
[0037] The on-site monitoring data and the numerical simulation data are preprocessed to obtain preprocessed data;
[0038] Based on existing engineering experience, the prior probability distribution of grouting reinforcement effects at different levels was determined.
[0039] Based on the data indicators of the preprocessed data, a probability distribution model for different grouting reinforcement effect levels is established as the likelihood function.
[0040] The prior probability distribution and the likelihood function are calculated based on Bayes' theorem to obtain the posterior probabilities of the grouting reinforcement effect at different levels. The level with the highest posterior probability is taken as the evaluation result of the grouting reinforcement effect.
[0041] Grouting reinforcement implementation based on on-site monitoring:
[0042] Step 1: Based on the tunnel's geological conditions and structural characteristics, scientifically and rationally select monitoring sections around the shield tunneling muck grouting reinforcement area. Install monitoring equipment such as earth pressure sensors, displacement sensors, and pore water pressure sensors on the selected monitoring sections, ensuring that the sensors are firmly installed and accurately positioned to accurately reflect the actual situation of the monitoring area.
[0043] Step Two: During the tunnel boring machine (TBM) excavation and subsequent construction, data from the earth pressure sensor is collected at different time points according to the set data acquisition frequency. Assuming the earth pressure measured at time t1 is P1, and after time Δt, the earth pressure measured at time t2 is P2, then the rate of change of earth pressure is... By calculating the rate of change of earth pressure, the changes in ground stress can be monitored in real time.
[0044] Step 3: Use displacement sensors to collect displacement values at specific monitoring points on the tunnel wall or ground surface at different times. Let the initial displacement of the monitoring point at time t0 be d0, and after a time period T, the displacement changes to d at time t0. Then the rate of displacement change is: Simultaneously, the total displacement L of the monitoring points is continuously recorded from the start of construction to the end of a certain stage. The deformation trend and stability of the tunnel and surrounding strata are assessed based on the displacement change rate and total displacement.
[0045] Step 4: A pore water pressure sensor monitors the pressure changes of groundwater in the pores in real time. The ratio of the difference in the pore water pressure readings at different locations to the distance between the sensors is calculated to obtain the pore water pressure gradient. For example, if the pore water pressure on one side of the tunnel is P1, and the pore water pressure on the other side at a distance L is P2, then the pore water pressure gradient is... By analyzing the dissipation of pore water pressure, we can understand the impact of grouting reinforcement on the groundwater seepage field.
[0046] Grouting reinforcement implementation based on numerical simulation
[0047] Step 1: Based on a detailed geological survey report of the tunnel project, input information such as the tunnel structural dimensions and the grouting reinforcement scheme for modified soil from the shield tunneling machine into numerical simulation software to establish a three-dimensional numerical model. The model should reflect the actual geological conditions and construction process of the project as accurately as possible.
[0048] Step Two: Combining the geological information obtained from the field survey report, indoor test data (such as physical and mechanical tests of soil and rock, grout performance tests, etc.), and engineering experience, determine the various parameters required for the numerical model. The physical and mechanical parameters of the surrounding rock include elastic modulus, Poisson's ratio, unit weight, cohesion, and internal friction angle; the parameters of the modified grout from the shield tunneling excavation soil include grout density, viscosity, and initial setting time; simultaneously, clarify the boundary conditions and load conditions during construction to ensure that the initial state of the model closely approximates the actual engineering conditions, thereby improving the accuracy of the simulation results.
[0049] Step 3: Simulate various possible operating conditions during the tunnel boring machine's (TBM) advancement process, such as different advancement speeds, cutterhead rotation speeds, soil chamber pressures, and the effects of different grouting reinforcement schemes. During the simulation, complex factors such as the interaction between the strata and the structure, and the diffusion patterns of the grout in the soil are fully considered.
[0050] Step 4: After the simulation reaches the predetermined monitoring time, extract the formation deformation data, soil stress state data, and grout diffusion and permeability data from the model output results.
[0051] Formation deformation data are obtained after the numerical simulation reaches the predetermined monitoring time T. m Then, deformation data of the tunnel and surrounding strata are extracted from the model output. This includes tunnel crown settlement S1, tunnel bottom uplift S2, and surface settlement trough distribution S(x). For the surface settlement trough, the Peck formula is used. Perform a fitting analysis, where S maxLet denoted as , where i is the settlement trough width coefficient, and x is the horizontal distance from the tunnel centerline. Analyzing these deformation data provides a clear understanding of the ground stability after grouting reinforcement.
[0052] The soil stress state data consists of stress tensor data collected from the grouting reinforcement area and surrounding soil, including principal stresses σ1, σ2, and σ3. The second invariant of the deviatoric stress tensor J2 and the octahedral shear stress τ are calculated. oct This is used to measure the shear stress level of the soil.
[0053]
[0054] By accurately tracking the diffusion front of the grout in the soil, image processing techniques or the marker cell method are used to determine the grout-filled area at different times, and the grout diffusion radius R is calculated. g The theoretical diffusion radius R calculated based on the theoretical penetration model was obtained. t A comparison was made to evaluate the actual diffusion efficiency of the slurry. The theoretical diffusion radius was derived based on a modified Darcy's law, taking into account the slurry viscosity μ. g Grouting pressure P, formation permeability coefficient k i and grouting time t g Factors such as these are considered, and the formula is as follows: Where R e To account for the equivalent radius of the stratigraphic boundary effect, R i The radius of the grouting pipe is given.
[0055] At the same time, the saturation S of the grout in the grouting area is statistically analyzed. r The ratio of grout volume to total pore volume is used to determine the degree of grout fullness. The formula is: Where V g V is the volume of the slurry. p This represents the pore volume.
[0056] Data fusion and effect evaluation implementation
[0057] Step 1: Standardize the field monitoring data and numerical simulation data using a normalization method. For each selected characteristic parameter (such as the rate of change of earth pressure, the rate of change of displacement, the pore water pressure gradient, the formation deformation, the grout diffusion radius, the grout saturation, etc.), calculate its minimum value x among all preprocessed data. min and maximum value x max The linear normalization method is selected based on the distribution characteristics of the feature parameters and the properties of the data. All data are calculated and normalized to the 0-1 range, so that different types of data have the same dimensions and order of magnitude, which facilitates subsequent fusion analysis.
[0058] Step Two: Based on existing engineering experience and similar project cases, the grouting reinforcement effect is classified into four levels: excellent, good, qualified, and unqualified. The prior probability distribution P(H) of the grouting reinforcement effect at different levels is then determined. i ), where i = 1, 2, 3, 4 correspond to excellent, good, satisfactory, and unsatisfactory, respectively, H i P(H) represents the i-th level assumption of the grouting reinforcement effect. i ) represents the probability that the grouting reinforcement effect is at level i before considering monitoring data.
[0059] Step 3: For each monitoring indicator (including various data indicators from on-site monitoring and numerical simulation), establish its probability distribution model under different grouting reinforcement effect levels, as the likelihood function P(D|H i This function represents the probability of observing monitoring data under the assumption that the grouting reinforcement effect is at the i-th level.
[0060] For example, assuming the displacement rate k d When the grouting reinforcement effect is good, it follows a normal distribution. Then P(k) d |H i It can be based on the normal distribution probability density function. Calculations were performed. Similar methods were used to establish probability distribution models for other monitoring indicators under different grouting reinforcement effect levels and to calculate likelihood functions.
[0061] Step 4: According to Bayes' theorem Calculate the posterior probability P(H) of the grouting reinforcement effect at different levels under monitoring data D. i |D). First, calculate the molecular part ΠP(DH). i )P(H i For each i = 1, 2, 3, 4, ΠP(DH) i The product of the likelihood functions of multiple monitoring indicators is denominator. It is the sum of probabilities of observing monitoring data D under all possible grouting reinforcement effect levels. Finally, P(H) is calculated. i |D) is the posterior probability of the grouting reinforcement effect being excellent, good, qualified, or unqualified based on the monitoring data. This posterior probability represents the probability that the grouting reinforcement effect is at the i-th level after considering the monitoring data D.
[0062] Step 5: Compare the posterior probabilities of different levels. The level with the highest posterior probability is the evaluation result of the grouting reinforcement effect. If P(H1|D)=0.4, P(H2|D)=0.25, P(H3|D)=0.2, and P(H4|D)=0.15, then the grouting reinforcement effect is evaluated as excellent.
[0063] On the other hand, this embodiment also provides an electronic device, including a memory, a processor, and a computing program stored in the memory and executable on the processor, characterized in that the processor implements the method when executing the computer program.
[0064] On the other hand, this embodiment also provides a computer-readable storage medium storing a computer program, characterized in that the computer program implements the method when executed by a processor.
[0065] The above are merely preferred embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
Claims
1. A method for evaluating the effect of shield tunneling slag modification grouting reinforcement based on multi-data fusion, characterized in that, include: Acquire on-site monitoring data based on sensors; A three-dimensional numerical model was constructed based on the tunnel structure dimensions and the shield tunneling spoil modified grouting reinforcement scheme. Simulation was performed based on the three-dimensional numerical model to obtain numerical simulation data. The on-site monitoring data and the numerical simulation data are preprocessed to obtain preprocessed data; Based on existing engineering experience, the prior probability distribution of grouting reinforcement effects at different levels was determined. Based on the data indicators of the preprocessed data, a probability distribution model for different grouting reinforcement effect levels is established as the likelihood function. The prior probability distribution and the likelihood function are calculated based on Bayes' theorem to obtain the posterior probabilities of the grouting reinforcement effect at different levels. The level with the highest posterior probability is taken as the evaluation result of the grouting reinforcement effect. The process of obtaining numerical simulation data includes: Based on a detailed geological survey report of the tunnel project, combined with the tunnel structural dimensions and the shield tunneling slag modification grouting reinforcement scheme, a three-dimensional numerical model was established using numerical simulation software. Based on the aforementioned three-dimensional numerical model, various working conditions during the tunnel boring machine's advancement process and the effects of different grouting reinforcement schemes are simulated. Based on the numerical simulation process, extract the formation deformation data, soil stress state data, and grout diffusion and permeability data from the numerical simulation. The expression for calculating the prior probability distribution and the likelihood function based on Bayes' theorem is as follows: ； in, To represent the posterior probability of grouting reinforcement effects at different levels, It is the sum of probabilities of observing monitoring data D under all possible grouting reinforcement effect levels. It is the product of the likelihood functions of multiple monitoring indicators, where D represents the monitoring data. This represents the i-th level assumption of the grouting reinforcement effect.
2. The method according to claim 1, characterized in that, The process of acquiring on-site monitoring data based on sensors includes: Based on the geological conditions and structural characteristics of the tunnel, monitoring sections were selected around the shield tunnel slag grouting reinforcement area, and soil pressure sensors, displacement sensors and pore water pressure sensors were installed. Data from earth pressure sensors are collected at different time points, and the ratio of the difference in earth pressure values at adjacent time points to the time interval is calculated to obtain the rate of change of earth pressure. The displacement values of specific monitoring points on the tunnel wall or ground surface are collected at different times based on displacement sensors, and the rate of displacement change is calculated; and the total displacement of the monitoring points from the start of construction to the end of a certain stage is recorded. Based on the real-time monitoring of groundwater pressure changes in pores using pore water pressure sensors, the ratio of the difference between the values measured by pore water pressure sensors at different locations to the distance between the sensors is calculated.
3. The method according to claim 1, characterized in that, The process of obtaining preprocessed data includes: for each selected feature parameter, calculating its minimum and maximum values in all preprocessed field monitoring data and numerical simulation data; and selecting a linear normalization method to calculate all data based on the distribution characteristics of the feature parameters and the properties of the data, thereby normalizing the data to the 0-1 interval.
4. The method according to claim 1, characterized in that, The process of determining the prior probability distribution of grouting reinforcement effect at different levels based on existing engineering experience includes: classifying the grouting reinforcement effect into four levels: excellent, good, qualified, and unqualified, based on existing engineering experience and similar engineering cases, and determining the prior probability distribution of grouting reinforcement effect at different levels.
5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method according to any one of claims 1-4.
6. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1-4.