A diaphragm wall trench hole mud protection wall stability analysis method

Abstract

The present application relates to the field of intelligent civil engineering, and more particularly to a method for analyzing the stability of a diaphragm wall slot hole mud wall. The method comprises the following steps: obtaining slot hole geological data and mud property data, and performing pressure simulation according to the slot hole geological data and the mud property data to obtain slot hole pressure data; performing mud pressure analysis according to the slot hole pressure data to obtain mud pressure data, and performing slot hole wall surface stress calculation according to the mud pressure data to obtain slot hole wall surface stress data; performing instability region processing according to the slot hole wall surface stress data to obtain slot hole wall surface instability region data; and performing slot hole stability analysis according to the slot hole wall surface instability region data and the slot hole wall surface stress data to obtain slot hole stability data. The present application not only identifies high-risk areas in the slot hole, but also provides dynamic monitoring of instability, which facilitates construction personnel to take preventive reinforcement measures during construction to ensure construction safety.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent civil engineering, and in particular to a method for analyzing the stability of a diaphragm wall slot hole mud wall. BACKGROUND

[0002] In the construction process of a diaphragm wall slot hole, mud is usually used as a wall protection material to maintain the stability of the slot hole and prevent collapse. However, due to the complexity of factors such as stratum conditions, slot hole depth, and mud characteristics, the pressure and stress distribution on the slot hole wall surface at different depths and regions is often uneven, which can easily lead to stress concentration and further instability or even collapse. If unstable regions appear on the slot hole wall surface during construction, it will seriously affect construction safety and engineering quality, leading to construction accidents, delays in construction, and increased engineering costs. Therefore, how to timely detect the stability of the diaphragm wall slot hole mud wall has become a problem. SUMMARY

[0003] To solve the above technical problems, the present application provides a method for analyzing the stability of a diaphragm wall slot hole mud wall to solve at least one of the above technical problems.

[0004] The present application provides a method for analyzing the stability of a diaphragm wall slot hole mud wall, which comprises:

[0005] S1, obtaining slot hole geological data and mud characteristic data, and performing pressure simulation according to the slot hole geological data and the mud characteristic data to obtain slot hole pressure data;

[0006] S2, performing mud pressure analysis according to the slot hole pressure data to obtain mud pressure data, and performing slot hole wall surface stress calculation according to the mud pressure data to obtain slot hole wall surface stress data;

[0007] S3, performing instability region processing according to the slot hole wall surface stress data to obtain slot hole wall surface instability region data;

[0008] S4, performing slot hole stability analysis according to the slot hole wall surface instability region data and the slot hole wall surface stress data to obtain slot hole stability data.

[0009] The present application can dynamically process the slot hole geology and mud data, through real-time pressure simulation and stress analysis, and is suitable for the changing geological environment in the construction process. By obtaining accurate slot hole geological data and mud characteristic data, and performing pressure simulation on the same, the obtained slot hole pressure data is more in line with the actual working condition. Through mud pressure analysis and slot hole wall stress calculation based on the pressure data, the pressure and stress distribution inside and around the slot hole accurately reflect the actual situation. The instability region processing step can identify possible instability regions through the stress distribution and concentration of the slot hole wall surface, thereby realizing early warning. Based on the instability region data and slot hole wall surface stress data, stability analysis can be performed to provide the overall safety factor and stability evaluation of the slot hole, facilitating construction decision-making.

[0010] Optionally, S1 comprises:

[0011] S11, obtaining slot hole geological data and mud characteristic data through a geological engineering database or a geological engineering input interface;

[0012] S12, performing mud characteristic modeling according to the mud characteristic data to obtain a mud characteristic clustering model;

[0013] S13, performing geological dynamic feature conversion according to the slot hole geological data to obtain geological dynamic feature sequence data;

[0014] S14, performing virtual reality stratum modeling according to the mud characteristic clustering model and the geological dynamic feature sequence data to obtain a three-dimensional stratum feature model;

[0015] S15, performing mud characteristic distribution depth calculation according to the three-dimensional stratum feature model to obtain mud characteristic distribution depth data;

[0016] S16, performing slot hole dynamic pressure simulation on the mud characteristic distribution depth data to obtain slot hole pressure data.

[0017] In the present application, multi-source slot hole geological data and mud property data are obtained through a geological engineering database or a data input interface, so that the initial data source is rich and accurate. The mud property modeling step generates a mud property clustering model, which provides a classification basis for the similarity and difference of different mud property data in depth and distribution, and adopts appropriate simulation strategies for different property distributions, thereby improving the accuracy of pressure and stress analysis. The geological dynamic feature conversion step generates dynamic feature sequence data, so that the time-varying nature of slot hole geological properties can be quantified, and the real geological condition changes can be reflected in the simulation process, which helps to improve the adaptability of the model to geological changes, thereby supporting more accurate construction plan formulation. The three-dimensional stratigraphic feature model generated by the virtual reality stratigraphic modeling provides intuitive three-dimensional visualization for the property distribution of mud and slot holes, so that engineering personnel can more clearly understand the slot hole surrounding geological structure and mud distribution. Through mud property distribution depth calculation, the distribution of mud physical properties at different depths of the slot hole is analyzed to ensure that the pressure data in the subsequent simulation steps are more accurate. The slot hole dynamic pressure simulation generates slot hole pressure data, which more realistically reflects the effect of mud at different depths on the slot hole wall through dynamic simulation of real-time pressure changes.

[0018] Optionally, wherein the mud property modeling comprises:

[0019] According to the mud property data, mud property feature extraction is performed to obtain mud property feature data;

[0020] According to the mud property feature data, feature coding is performed to obtain mud property coding data;

[0021] The mud feature coding data is preliminarily clustered to obtain mud property clustering data;

[0022] According to the mud property clustering data, clustering scale adjustment and clustering boundary multi-scaling are performed to obtain mud property multi-scale clustering data;

[0023] According to the mud property multi-scale clustering data, the mud property data is labeled and associated to obtain mud property clustering label association data;

[0024] According to the mud property clustering label association data, a model is constructed to obtain a mud property clustering model.

[0025] The key features are extracted from the mud property data in the application, which provides refined and important data input for subsequent encoding and clustering, effectively reduces redundant information, and increases data processing efficiency. Feature encoding quantitatively processes the mud properties, so that the information of the data in the high-dimensional feature space is more regular and standardized. Through preliminary clustering, the encoded data is grouped according to the similarity of properties, and mud property clustering data is obtained. Preliminary clustering effectively reduces the data dimension, provides simplified basic data for subsequent clustering scale adjustment, and helps to improve the analysis efficiency. Through adaptive adjustment of the clustering scale and multi-scale processing of the boundary, the clustering analysis can adapt to the different density distribution of the mud data. Multi-scale clustering can refine the clustering boundary of the dense area, reduce the boundary ambiguity and error, and thus provide more scientific results for clustering of different mud properties. The label association step forms mud property clustering label association data by assigning labels to the clustering data. Label association enhances the interpretability of the model, so that construction personnel can understand the use and effect of different mud properties according to the label, and provide clear classification guidance for the construction process. The model construction step according to the clustering label association data forms the mud property clustering model, which provides a complete data model containing mud multi-dimensional properties, clustering labels and association relationships.

[0026] Optionally, the feature encoding comprises:

[0027] According to the mud property feature data, local linear embedding processing is performed to obtain mud property feature mapping data;

[0028] According to the mud property feature mapping data, property abstraction layering is performed to obtain mud abstract property tensor data;

[0029] The mud abstract property tensor data is subjected to encoding preprocessing to obtain mud compressed feature data;

[0030] The mud compressed feature data is subjected to recursive encoding to obtain mud property encoding data.

[0031] In the present application, the mud characteristic data is mapped from a high-dimensional space to a low-dimensional feature space by local linear embedding, the local geometric structure of the characteristic data is preserved, the calculation complexity is reduced, and the inherent characteristic relationship of the data is ensured, which provides more refined input data for subsequent characteristic abstraction and layering. The characteristic abstraction and layering extracts the core information of the mud characteristics through layer-by-layer abstraction, so that the data has higher representativeness. Each abstraction process gradually retains the elements closely related to the mud characteristics, so that the characteristic data can more completely represent the multi-dimensional characteristics of the mud. The pre-processing of coding compresses the mud abstract characteristic tensor, removes redundant and noise information, generates mud compressed feature data, significantly improves the purity and compactness of the data, ensures that the recursive coding process only needs to process the core features, improves the coding efficiency and reduces the calculation overhead. The recursive coding converts the mud compressed feature data into a structured mud characteristic code, forming an efficient data representation that can be used for further analysis. The process of recursive coding can identify and capture the deep relationship of the characteristic data, and the generated coding data has uniqueness and high discrimination, which is suitable for subsequent mud clustering and analysis.

[0032] Optionally, wherein the clustering scale adjustment and the clustering boundary multi-scaling include:

[0033] According to the mud characteristic clustering data, the clustering scale is initialized to obtain mud characteristic initial scale data;

[0034] According to the mud characteristic initial scale data, the density center is identified to obtain mud characteristic clustering center data;

[0035] The mud characteristic clustering center data is processed by scale step-by-step expansion to obtain mud characteristic expansion scale data;

[0036] According to the mud characteristic expansion scale data, the clustering center change rate is calculated and the clustering change characteristics are extracted to obtain mud characteristic clustering center change rate data and mud characteristic clustering change feature data;

[0037] According to the mud characteristic clustering center change rate data and the mud characteristic clustering change feature data, the mud characteristic expansion scale data is adjusted to obtain clustering characteristic multi-scale adjustment data;

[0038] According to the clustering characteristic multi-scale adjustment data, the dense area is refined to obtain mud characteristic multi-scale clustering data.

[0039] By dynamically adjusting the clustering scale and boundary in the application, the method can more accurately identify the dense area and difference of mud characteristic data, effectively reduce the error, avoid the over-clustering or under-clustering problem generated by the traditional clustering method, and make the clustering model have higher adaptability and accuracy in diversified mud characteristic data. The multi-scale clustering technology supports differential processing of different density areas, thereby adapting to the complex distribution of mud data, can form refined clustering in dense areas, while maintaining reasonable scale and boundary in sparse areas, and enhances the universality and adaptability of clustering. Through layer-by-layer expansion and boundary adjustment, multi-level analysis from macro to micro is supported, which is helpful to observe the change and rule of mud characteristic distribution at different scales, and the multi-level characteristics provide more comprehensive understanding of mud characteristics for engineering construction, facilitating optimization decision. The clustering center change rate and clustering change characteristic data enhance the physical interpretability of the clustering result, so that the engineering personnel can understand the law of mud characteristic clustering according to the change rate of characteristics and the adjustment of clustering boundary, support more reasonable mud distribution control and management.

[0040] Optionally, S2 comprises:

[0041] S21, performing pressure multi-dimensional deconstruction diagram processing according to the slot hole pressure data to obtain mud multi-dimensional pressure deconstruction diagram data;

[0042] S22, performing slot hole depth pressure correlation analysis according to the mud multi-dimensional pressure deconstruction diagram data to obtain mud pressure data;

[0043] S23, performing pressure sensitive point identification according to the mud pressure data to obtain mud pressure sensitive point data;

[0044] S24, performing stress conduction mapping on the mud pressure sensitive point data to obtain mud stress conduction mapping data;

[0045] S25, performing slot hole stress response simulation according to the mud stress conduction mapping data to obtain slot hole stress response data;

[0046] S26, performing stress concentration area screening according to the slot hole stress response data to obtain slot hole wall surface stress data.

[0047] The mud multi-dimensional pressure deconstruction diagram data is generated by multi-dimensional deconstruction of the slot hole pressure data in the present application, which shows the distribution of pressure in different dimensions and different positions, decomposes complex pressure data, highlights key features, and helps to identify the distribution pattern of pressure. By analyzing the correlation of pressure data at different depths, the change rule of pressure with depth is identified. This analysis helps to understand the difference of mud pressure at different depths, so that the construction party can monitor the abnormal points of pressure at a certain depth to prevent instability risk caused by abnormal pressure. Identifying sensitive points in mud pressure data can quickly locate the area where pressure is concentrated, effectively indicating potential weak links and instability areas in the slot hole, providing accurate data source for stress transmission and concentration area calculation, and improving the safety of the model. Through stress transmission mapping of pressure sensitive points, the pressure transmission path and range of mud in the slot hole are simulated. Stress transmission mapping can accurately show the transmission of pressure from sensitive points to surrounding areas, providing real data basis for slot hole stress response simulation, which helps to evaluate the effect of mud wall protection. Based on stress transmission mapping, stress response simulation of slot hole wall surface is carried out. This step simulates the effect of mud pressure on different areas of slot hole wall surface, helps to identify high stress areas and stress concentration positions, and provides key guidance for mud configuration and pressure control for construction party. The stress concentration area screening step screens the stress concentration area of slot hole wall surface by analyzing stress response data, generates slot hole wall surface stress data, and provides accurate pressure distribution area, which is convenient for construction party to take additional stabilizing measures in these high stress areas to ensure the stability of the structure.

[0048] Optionally, wherein the stress transmission mapping comprises:

[0049] According to the mud pressure sensitive point data, sensitive point mechanical property analysis is carried out to obtain sensitive point mechanical property matrix data;

[0050] According to the sensitive point mechanical property matrix data, stress field initialization is carried out to obtain initial stress field distribution diagram data;

[0051] The initial stress field distribution diagram data is subjected to adjacent pressure transmission simulation to obtain pressure transmission sequence data;

[0052] According to the pressure transmission sequence data, transmission path optimization is carried out to obtain optimized transmission sequence data;

[0053] According to the optimized transmission sequence data, geological stress attenuation simulation is carried out to obtain stress attenuation distribution matrix data;

[0054] According to the stress attenuation distribution matrix data, the initial stress field distribution diagram data is subjected to stress transmission boundary adjustment to obtain stress transmission boundary data;

[0055] According to the mapping reconstruction of the optimized conduction sequence data, the stress attenuation distribution matrix data and the stress conduction boundary data, mud stress conduction mapping data is obtained.

[0056] In the present application, through sensitive point mechanical property analysis, stress field initialization and conduction path optimization, real pressure conduction and stress distribution are simulated under different depths and environments, so that the generated stress mapping is more accurate and detailed, and fully reflects the actual working condition stress conduction. Through fine processing, including stress attenuation simulation and boundary adjustment, the present application can dynamically adjust to stress changes in different regions, and detailed stress control provides a deep understanding of the stress distribution of the slot hole wall, which helps to discover potential instability risks and prevent them. By analyzing the mechanical properties of sensitive points, the generated stress conduction mapping data has physical meaning, which is convenient for interpreting the transmission and change of pressure in different regions. At the same time, the present application can adapt to various geological conditions and mud characteristics data, making the model more universal. Conduction path optimization and stress attenuation simulation enable the method to quickly identify areas with high stress concentration, thereby providing key data for instability analysis and construction decision-making. Timely identification of high stress areas can help construction parties take preventive measures to ensure construction safety. Optimization and reconstruction of conduction data provide dynamic response capability for mud wall protection during construction, so that the stress conduction model during construction can adapt to changes in working conditions in real time, improving the practicality of the model and helping to manage and adjust stress during construction.

[0057] Optionally, S3 comprises:

[0058] S31, stress distribution anomaly detection is performed according to the slot hole wall stress data to obtain stress anomaly point data;

[0059] S32, instability region analysis is performed according to the stress anomaly point data to obtain slot hole wall instability region data;

[0060] S33, instability trend analysis is performed according to the slot hole wall instability region data to obtain slot hole wall instability trend data;

[0061] S34, instability region depth identification is performed on the slot hole wall instability trend data to obtain instability region identification data;

[0062] S35, instability region dynamic mapping is performed according to the instability region identification data to obtain slot hole wall instability region data.

[0063] The application can identify high-risk areas before the instability trend appears, provide early warning and prompt construction personnel to take preventive measures, early identification helps to reduce the risk of instability, avoid accidents and improve construction safety. Through instability trend analysis and dynamic mapping, the instability of the slot hole wall surface can be monitored and predicted in real time, so that the change of instability trend can be tracked in time, and dynamic analysis supports engineering personnel to quickly adjust the construction strategy when the instability trend changes, ensuring engineering safety. The application can accurately identify the instability region position and depth on the slot hole wall surface, accurate positioning helps the construction party to take targeted reinforcement measures, thereby reducing the instability influence range and optimizing the construction scheme. The application can adapt to complex construction environment and provide support for multi-level instability analysis. No matter how the pressure and stress distribution of the slot hole wall surface changes, the evolution and expansion of the instability region can be effectively identified. The instability region mapping data generated by the dynamic mapping step provides key data for dynamic instability control. Through real-time monitoring of the change of the instability region, engineering personnel can continuously monitor and adjust to reduce the probability of instability and improve the overall safety of the slurry wall.

[0064] Optionally, S4 comprises:

[0065] S41, stability feature extraction is performed according to the slot hole wall surface instability region data and the slot hole wall surface stress data, to obtain stability feature data;

[0066] S42, stability index calculation is performed according to the stability feature data, to obtain slot hole region stability index data;

[0067] S43, multi-factor cross analysis is performed according to the slot hole wall surface instability region data and the slot hole wall surface stress data, to obtain multi-factor cross analysis matrix data;

[0068] S44, stress instability risk assessment is performed according to the slot hole region stability index data and the multi-factor cross analysis matrix data, to obtain instability risk assessment matrix data;

[0069] S45, slot hole safety coefficient calculation is performed according to the instability risk assessment matrix data, to obtain slot hole stability data.

[0070] The application generates stability characteristic data by extracting the instability region of the groove hole wall surface and the stability characteristics of the stress data, providing core characteristic indexes for stability analysis. According to the stability characteristic data, the stability index of the groove hole region is calculated, so that the stability evaluation result can be quantitatively presented. The stability index provides an intuitive numerical reference for engineering personnel, enabling them to quickly judge the safety state of different regions and facilitate the implementation of targeted protection measures. Through multi-factor cross analysis of the instability region data and stress data of the groove hole wall surface, a cross analysis matrix is generated, integrating multiple influencing factors to help identify the mutual relationship between different factors and their comprehensive influence on the stability of the groove hole, which is helpful for more comprehensive evaluation of the safety of the groove hole wall surface. Based on the stability index and the cross analysis matrix, stress instability risk assessment is carried out, effectively quantifying the instability risk of the groove hole wall surface. The instability risk assessment matrix can provide detailed high-risk areas and potential instability factors for the construction party, guiding them to take additional protection and monitoring measures in dangerous areas. The groove hole safety factor is calculated using the instability risk assessment matrix, and the generated groove hole stability data can comprehensively reflect the stability of the groove hole wall surface under the current construction conditions.

[0071] The purpose of the application is to combine the groove hole geology and mud characteristic data for pressure simulation, so that the initial pressure data has a real engineering background, ensuring the physicality and rationality of the pressure calculation. Through multi-dimensional pressure analysis and groove hole wall surface stress calculation, the pressure and stress distribution of the groove hole is gradually refined, not only identifying high stress areas of the groove hole wall surface, but also effectively capturing stress concentration phenomena existing in the mud wall protection system, which helps to identify potential instability risks early. Abnormal detection is carried out using the groove hole wall surface stress data, which can quickly capture pressure concentration areas and evaluate the instability risk of these areas. Through dynamic trend analysis of the instability region, the evolution characteristics of the instability region at different depths and time nodes can be captured, providing instability expansion direction and rate information for the construction party. On the basis of instability region identification, further depth identification is carried out to accurately locate the range and depth of the instability region, providing a clear target area for the implementation of protection measures. By extracting the stability characteristics of the instability region and stress data, the stability index is calculated, generating a stability index for different groove hole regions. Through the multi-factor cross analysis matrix, the groove hole wall surface instability region data, stress data and stability index are integrated into the same framework, systematically analyzing the mutual influence between factors. Based on the instability risk assessment matrix, the groove hole safety factor is calculated, obtaining the overall stability data of the groove hole. BRIEF DESCRIPTION OF DRAWINGS

[0072] Other features, objects, and advantages of the application will become more apparent from the following detailed description of non-limiting embodiments made with reference to the drawings:

[0073] Figure 1 A step flow chart of a diaphragm wall trench hole slurry protection wall stability analysis method is shown in an embodiment;

[0074] Figure 2 A step flow chart of a trench hole pressure simulation method is shown in an embodiment;

[0075] Figure 3 A step flow chart of a trench hole wall surface stress calculation method is shown in an embodiment;

[0076] Figure 4 A step flow chart of a trench hole wall surface instability region processing method is shown in an embodiment;

[0077] Figure 5 A step flow chart of a trench hole stability analysis method is shown in an embodiment;

[0078] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0079] The technical method of the present application will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0080] In addition, the accompanying drawings are only schematic illustrations of the present application, and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus repeated descriptions thereof will be omitted. Some block diagrams shown in the drawings are functional entities, and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0081] It should be understood that although the terms "first", "second" and the like can be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of the example embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the associated associated items.

[0082] The construction party first obtains the formation depth, density, and physical properties of the mud from geological surveys and laboratory data. Based on the above data, pressure simulation is performed through finite element analysis. The simulation results obtain the pressure distribution of the slot hole at different depths. For example: depth 0-10 meters: pressure 0.6 MPa, depth 10-20 meters: pressure 0.9 MPa, depth 20-30 meters: pressure 1.2 MPa, depth 30-50 meters: pressure 1.5 MPa.

[0083] The slot hole pressure data is multi-dimensionally deconstructed to form a multi-dimensional pressure deconstruction diagram of the mud. For example, the 0-10 meter depth area is divided into several grid nodes, and the pressure distribution of each node generates a multi-dimensional deconstruction diagram. Correlation analysis is performed on the pressure data at different depths to identify the pressure change relationship at each depth. For example, the pressure in the 10-20 meter depth area increases significantly, forming a high pressure correlation area. By analyzing the positions of significant pressure changes in the deconstruction diagram, mud pressure sensitive points are identified. For example, the pressure at 20 meters and 30 meters increases significantly and is marked as a pressure sensitive point. According to the pressure sensitive point data, stress conduction mapping is performed. By analyzing the conduction path of the mud at these sensitive points, a pressure conduction sequence is formed. For example, the pressure at the 20 meter sensitive point is conducted to the 30 meter depth, and an attenuation model is generated, indicating that the attenuation coefficient of the pressure from 20 meters to 30 meters is 0.85. The stress conduction mapping is applied to the entire slot hole wall surface to simulate the wall surface stress response distribution. For example, the stress generated at 20 meters is distributed on the wall surface as 1.1 MPa, while at 30 meters it is distributed as 0.9 MPa. Based on the stress response data, high stress areas on the wall surface are selected to obtain the stress data on the slot hole wall surface. For example, the 20-30 meter depth is a stress concentration area with a stress value close to 1.2 MPa.

[0084] The slot hole wall surface stress data is detected to identify abnormal high stress points. For example, the stress value at 30 meters depth reaches 1.2 MPa, exceeding the safety threshold, and is determined as an instability abnormal point. Taking the abnormal point as the center point, its influence range is analyzed to determine the instability region, and the 28-35 meter depth is determined as the instability region. The time variation trend of the instability region is analyzed to obtain the instability trend. The analysis shows that the instability region has an upward expansion trend with an expansion speed of 0.5 meters / day. Based on the instability trend data, the depth range of the instability region is further determined to obtain the identification data: the 28-35 meter region is the main instability depth, and the expansion trend reaches a depth of 40 meters. The dynamic changes of the instability region are mapped to show the expansion of the instability region at different depths and time points.

[0085] The key features affecting the stability of the slot hole wall surface are extracted from the instability region and stress data, including depth range, stress concentration degree, etc. The stability features obtained include stress concentration coefficient, expansion rate, etc. Based on the stability feature data, the stability index of the slot hole region is calculated. The stability index at a depth of 30 meters is 0.65 (lower than the safety threshold of 0.75), indicating that there is a risk of instability. Cross analysis of the instability region data, stress data and stability index shows that stress concentration degree and formation density are the key influencing factors, and the cross analysis matrix generated reflects the comprehensive relationship between the factors. Through the instability risk assessment matrix, the instability risk of the slot hole is assessed, and the assessment shows that the instability risk at a depth of 30 meters is high, with a risk coefficient of 0.8. According to the risk assessment data, the overall safety factor of the slot hole is calculated, and the calculated safety factor is 1.2 (lower than the standard value of 1.5), indicating that reinforcement measures need to be taken.

[0086] Please refer to Figures 1 to 5 The present application provides a method for analyzing the stability of a diaphragm wall slot hole mud protection wall, which comprises:

[0087] S1, obtaining slot hole geological data and mud characteristic data, and performing pressure simulation according to the slot hole geological data and mud characteristic data to obtain slot hole pressure data;

[0088] In an embodiment, first, slot hole geological data needs to be obtained through field geological survey, laboratory testing and the like, including slot hole depth, soil layer structure, underground water level and the like. In addition, experimental analysis data of the mud used for protection wall needs to be collected to obtain the physical and chemical characteristics of the mud, such as density, viscosity, rheological property and the like. The fluidity and permeability of the mud affect the pressure distribution of the mud in the slot hole. Next, pressure simulation is performed using the slot hole geological data and mud characteristic data. The pressure simulation can be performed in a layered and segmented manner to analyze the pressure exerted by the mud on the slot hole wall surface layer by layer. In the calculation process, the mud density is associated with the slot hole depth by controlling the variable to simulate the slot hole pressure data at different depths. In the pressure simulation process, the support of the soil layer around the slot hole and the simulation of the hydrostatic pressure effect of the mud are also taken into account.

[0089] The slot hole geological data are as follows: slot hole depth: 20 meters, soil layer structure: clay layer at 0-10 meters, sand layer at 10-20 meters, underground water level: 8 meters, mud characteristic data: mud density: 1.2 g / cm 3 , mud viscosity: 20 mPa x s. According to the slot hole geological data and mud characteristic data, the pressure in the slot hole is simulated. It can be assumed that the pressure distribution of the slot hole is a hydrostatic pressure calculation model. In the case where the mud density is known, the mud pressure at different depths of the slot hole is calculated using the following formula:

[0090] P = p x g x h;

[0091] Where: P is the trench mud pressure (Pa), ρ is the mud density (1.2 g / cm³). 3 =1200kg / m 3 ), g is the acceleration due to gravity (9.81 m / s²). 2 ), where h is the mud depth. For example, to calculate the mud pressure in a trench with a depth of 10 meters: P = 1200 × 9.81 × 10 = 117,720 Pa.

[0092] S2. Perform mud pressure analysis based on the slot pressure data to obtain mud pressure data, and calculate the slot wall stress based on the mud pressure data to obtain slot wall stress data.

[0093] In one embodiment, mud pressure analysis needs to consider the variation of mud pressure with depth and the influence of the trench structure on pressure transmission. A hierarchical analysis method is used to finely decompose the mud pressure data, ensuring the accuracy of the data at different depths. Next, the stress distribution on the trench wall is calculated based on the mud pressure data. The calculation is performed by accumulating stress layer by layer using stress formulas to simulate the stress conditions on the trench wall at different locations. The stress calculation involves the frictional force between the mud pressure and the trench wall, as well as the lateral pressure exerted by the mud on the trench wall at different depths. Through this layer-by-layer decomposition and accumulation method, complete stress data of the trench wall is obtained, providing a basis for instability region analysis.

[0094] A detailed analysis of mud pressure at different depths in the trench is performed. Considering the influence of soil structure at different depths on mud pressure, the mud pressure can be adjusted with depth. The total stress borne by the trench wall is calculated, and the effective wall stress of the trench (considering soil resistance) is given by the formula: σ w =P―σ t , where σ w Where σ is the wall stress, P is the mud pressure, and σ is the wall stress. t The resistance stress provided by the soil layer. In clay layers, the soil resistance stress is 20,000 Pa, and in sand layers it is 10,000 Pa. In clay layers at a depth of 10 meters: σ w =117,720 - 20,000 = 97,720 Pa. In the sand layer at a depth of 15 meters: P = 1200 × 9.81 × 15 = 176,580 Pa, σ w =176,580-10,000=166,580 Pa. The stress distribution on the slot wall surface was obtained through calculation.

[0095] S3. Based on the stress data of the slot wall, perform instability region processing to obtain the instability region data of the slot wall;

[0096] In an embodiment, the slot hole wall surface stress data obtained in step S2 is used to analyze and identify potential instability regions of the slot hole wall surface. First, a stress threshold for the stability of the slot hole wall surface needs to be set, which is set according to the bearing capacity of the soil layer and the supporting capacity of the mud. When the stress value of the slot hole wall surface exceeds the threshold, instability will occur. By marking the regions exceeding the stability threshold in the slot hole wall surface stress data, the instability regions can be identified. In the specific operation process, the slot hole wall surface stress data is layered by depth, and the stress value is compared with the stability threshold layer by layer to determine the instability regions of each layer, forming slot hole wall surface instability region data, which includes the depth, range, and stress value exceeding the threshold of the instability region. The wall surface stress data is compared with the instability threshold of the slot hole. For example, the instability threshold is 150,000 Pa, and when the slot hole wall surface stress exceeds this value, it is considered to have instability risk. At a depth of 10 meters, the wall surface stress is 97,720 Pa, which is lower than the instability threshold and has no instability risk. At a depth of 15 meters, the wall surface stress is 166,580 Pa, which exceeds the instability threshold and has instability risk. Therefore, the sand layer region at a depth of 15 meters is marked as an instability region.

[0097] S4, performing slot hole stability analysis according to the slot hole wall surface instability region data and the slot hole wall surface stress data to obtain slot hole stability data.

[0098] In an embodiment, the overall stability of the slot hole is evaluated using the obtained instability region data and wall surface stress data. First, according to the range and depth of the instability region, the overall stability of the slot hole wall surface is calculated. The stress of the instability region can be compared with the stress of the surrounding stable region using a regional weighting analysis method to calculate the comprehensive stability index of the slot hole wall surface at different depths. Then, by comprehensively analyzing the stability index of each layer, the stability condition of the entire slot hole is judged. If it is found that the stability index of some regions is low, corresponding support or reinforcement measures need to be taken during construction to ensure the safety of the slot hole. The formed slot hole stability data contains the overall stability index of the slot hole and the instability possibility of each depth level, providing a scientific basis for risk control during construction.

[0099] According to the instability region data and the overall wall surface stress distribution, the overall stability of the slot hole is evaluated. The instability region is weighted to calculate the overall stability index. The stability formula of the slot hole as a whole is:

[0100]

[0101] where S is the stability index, with a value range of 0 to 1, and the closer to 1, the more stable, σ max is the instability threshold 150,000 Pa, and σ wFor each layer of the actual stress value, n is the total number of layers. Substituting the data, at a depth of 10 meters: S 10 = (150,000-97,720) / 150,000≈0.347. At a depth of 15 meters: S 15 = (150,000-166,580) / 150,000≈-0.110 (indicating instability), calculate the overall stability index: S total = (0.347+(-0.110)) / 2≈0.118. The result indicates that the slot hole has a risk of instability and needs to be reinforced or additional support measures.

[0102] Optionally, S1 comprises:

[0103] S11, obtaining slot hole geological data and mud property data through a geological engineering database or a geological engineering input interface;

[0104] In an embodiment, the geological data and mud property data of the slot hole are obtained through an existing geological engineering database interface or engineering input interface. The slot hole geological data includes information such as soil layer structure, groundwater level, pore pressure, etc. The data is stored in a standardized format in the database and extracted through SQL query or API call. In addition, the mud property data mainly covers the density, viscosity, rheology, etc. of the mud, which can be determined by experiment or retrieved from the database. The required data is loaded into the modeling platform through the interface.

[0105] S12, mud property modeling according to the mud property data to obtain a mud property clustering model;

[0106] In an embodiment, the modeling process of the mud property data aims to cluster and classify the mud properties at different depths to determine the behavior patterns of the mud at different depths. First, the mud data is standardized to normalize the density, viscosity, etc. parameters to improve accuracy in the multivariate clustering process. Next, the mud properties are classified through an iterative method, and mud with similar properties is assigned to the same category. After clustering, the system generates a mud property clustering model to display the property distribution of the mud at different depths.

[0107] S13, geological dynamic feature conversion according to the slot hole geological data to obtain geological dynamic feature sequence data;

[0108] In an embodiment, the borehole geological data needs to be converted into dynamic feature sequence data suitable for calculation. First, the geological data is preprocessed, such as filtering abnormal data, removing noise, and filling in missing data by interpolation. Then, the geological data is segmented according to the changes in soil layer structure and the increments of borehole depth. Then, the segmented geological feature data is generated according to the depth. For example, the transition point of clay layer and sand layer will be marked, and a set of sequence data according to the depth increment will be generated, showing the soil layer type and corresponding characteristics at each depth, providing necessary geological dynamic feature information for three-dimensional stratum modeling.

[0109] In an embodiment, the borehole geological data is converted into dynamic feature sequence to represent the depth and property changes of different geological layers. The borehole is divided into several layers according to the borehole depth, and the soil layer type and depth range of each layer are marked. For example, 0-10 meters is divided into clay layer, 10-20 meters is divided into transition layer, and 20-30 meters is divided into sand layer. The geological layer information and groundwater level at each depth are integrated into a set of dynamic sequence data, including soil layer type, groundwater level influence, pore pressure, etc. The obtained dynamic feature sequence data is as follows: depth 0-10 meters: soil layer type "clay layer", groundwater level influence small, pore pressure high. Depth 10-20 meters: transition layer, groundwater level influence moderate, pore pressure moderate. Depth 20-30 meters: sand layer, groundwater level influence large, pore pressure low.

[0110] S14, virtual reality stratum modeling according to the mud property clustering model and the dynamic feature sequence data, to obtain a three-dimensional stratum feature model;

[0111] In an embodiment, the mud property clustering model and the dynamic feature sequence data are combined to construct a three-dimensional stratum model. First, the borehole depth is divided into multiple virtual layers, and the depth of each layer is determined according to the mud property distribution and the change of geological features. Then, the mud property clustering model data is input into the modeling platform to assign values to the mud property of each layer; at the same time, the dynamic feature sequence data is imported into the model, so that each layer contains soil layer information and corresponding mud property. The three-dimensional model is processed by gridding to decompose the borehole into multiple three-dimensional cells, each cell having independent mud and soil layer properties. After visualization of the model, the system outputs a three-dimensional stratum feature model, realizing virtual reproduction of the real environment of the borehole.

[0112] S15, mud property distribution depth calculation according to the three-dimensional stratum feature model, to obtain mud property distribution depth data;

[0113] In an embodiment, the mud property distribution depth calculation is performed based on the three-dimensional formation model to obtain mud property data at different depths. First, each cell in the three-dimensional model is scanned layer by layer to extract the corresponding mud property value and depth information. Then, the data is sorted by depth to generate a mud property distribution depth table. For example, if the mud density fluctuates at different depths, the model automatically marks these changes and saves the density values at each depth as mud property distribution depth data. This data directly reflects the distribution of mud in the slot hole and provides a reliable basis for slot hole dynamic pressure simulation.

[0114] S16, performing slot hole dynamic pressure simulation on the mud property distribution depth data to obtain slot hole pressure data.

[0115] In an embodiment, the pressure data of the slot hole is obtained by simulating the pressure distribution of the mud in the slot hole. Based on the mud property distribution depth data, the hydrostatic pressure of the mud at each depth is first calculated. For example, the hydrostatic pressure formula is used to calculate the mud pressure of each cell, taking into account the variation of gravitational acceleration and mud density. Then, the cells at different depths in the slot hole model are iteratively calculated to obtain the overall pressure distribution. The calculation results are integrated to generate slot hole pressure data, forming a depth-pressure relationship curve, which lays a foundation for mud wall stability analysis.

[0116] Optionally, wherein the mud property modeling comprises:

[0117] extracting mud property feature data from the mud property data;

[0118] In an embodiment, the feature data for describing the behavior of the mud is extracted by analyzing the key variables in the mud property data. The mud property data includes information such as the density, viscosity, rheological parameters (such as yield stress, plastic viscosity) and permeability of the mud. The main variables reflecting the properties of the mud are selected from the mud data, including density, viscosity, yield stress, plastic viscosity and permeability, etc., to ensure that each variable can effectively represent the properties of the mud. The average, maximum, minimum and standard deviation of the selected variables are calculated, and these features are arranged into a structured data table, with each row representing the features of the mud at different depths and each column representing a specific mud property.

[0119] encoding the mud property feature data to obtain mud property encoding data;

[0120] In an embodiment, each variable in the feature data is normalized so that the data is in the same dimension range. For non-numeric variables (such as soil layer type), one-hot encoding is used to convert the categorical variables into numeric variables to adapt to the clustering algorithm. The encoded data is integrated into a new table to form a standardized feature encoding data table. At this time, each data point is represented in a numerical manner, facilitating subsequent calculations.

[0121] The mud feature encoding data is preliminarily clustered to obtain mud property clustering data;

[0122] In an embodiment, the encoded mud property data is preliminarily clustered to identify mud data points with similar properties. By calculating the similarity between data points, a distance matrix of mud property data is constructed. Similarity can be calculated using Euclidean distance, and the distance between each pair of data points represents the degree of similarity between the two. According to the distance matrix, data points with high similarity are assigned to the same cluster. This preliminary clustering process can use an iterative assignment method to gradually assign all data points to different classes. The preliminary cluster number to which each data point belongs is recorded to form mud property clustering data.

[0123] According to the mud property clustering data, the clustering scale is adjusted and the clustering boundary is multi-scaled to obtain multi-scale mud property clustering data;

[0124] In an embodiment, by adjusting the scale parameter and boundary multi-scaling of the cluster, the clustering effect is further optimized, and the boundary between each cluster group is more clear. Analyzing the preliminary clustering results, adjacent cluster groups that are close in distance but not classified into the same class are merged. The scale is adjusted to a larger range to ensure that data points of the same class are classified into the same cluster. The boundary data points of the cluster are processed to make the boundary of each cluster multi-level. For example, the area close to the core cluster point is set as a high confidence boundary, the slightly distant area is set as a medium confidence boundary, and the outermost boundary is set as a low confidence boundary. The boundary and core area of each cluster are recorded, and the boundary confidence of each level is marked to form multi-scale mud property multi-scale clustering data.

[0125] Mud property multi-scale clustering data table 1 is as follows:

[0126] Depth (m) Initial clustering Core boundary Near boundary Far boundary 1-5 Class 1 1-3 m 4-5 m 10-15 m 5-10 Class 2 5-8 m 9-10 m

[0127] According to the mud property multi-scale clustering data, the mud property data is associated with a label to obtain mud property clustering label association data;

[0128] In an embodiment, the multi-scale clustering data is labeled associated with the mud property data, so as to give clear labels to different clustering groups. Based on the clustering multi-scale distribution results, a label is given to each cluster. For example, a cluster with high density and high viscosity is labeled as "high density-high viscosity mud". The cluster number of each data point is converted into its corresponding cluster label. For example, if the cluster number "1" represents "high density-high viscosity mud", the cluster number "1" is converted into the corresponding literal label. The features of each data point are integrated with the cluster label to form a mud property clustering label association data table, which contains the label information of each mud property data point.

[0129] According to the mud property clustering label association data, a mud property clustering model is constructed.

[0130] In an embodiment, a mud property clustering model is established based on the label association data for predicting and classifying new data. Based on the existing label association data, a clustering model is trained to enable it to identify mud property patterns of different labels. During the training process, the model learns the feature distribution of each cluster group so that it can make correct classification when encountering new data. The trained model is verified, a part of the data is used as a test set, and the classification accuracy and robustness of the model are calculated. Through parameter adjustment, it is ensured that the model can effectively distinguish between mud property categories. The trained and verified model is saved as a mud property clustering model, which can input new mud property data to automatically cluster and label classify.

[0131] Optionally, the feature encoding includes:

[0132] According to the mud property feature data, local linear embedding processing is performed to obtain mud property feature mapping data;

[0133] In an embodiment, the mud property feature data is standardized, including density, viscosity, permeability and other properties, each of which is converted into standardized data to eliminate the influence of different feature dimensions. A number of neighboring points k (for example, 5) is selected, the nearest neighbors of each data point are calculated, and each data point is connected with its neighbors to form a local neighborhood. For each data point, it is reconstructed in the neighborhood, and the influence degree of other data points in the neighborhood on it in the local geometric structure is calculated. Specifically, the reconstruction weight of each point in the neighborhood is found by minimizing the reconstruction error. The reconstruction weight matrix is input into a low-dimensional space to maintain the same local structure relationship as in the high-dimensional space, thereby obtaining low-dimensional mud property feature mapping data. The mapping data can effectively preserve the key structural information in the original mud property, facilitating further property abstraction.

[0134] According to the mud property feature mapping data, property abstraction and layering are performed to obtain mud abstract property tensor data;

[0135] In an embodiment, the dimension-reduced mud property mapping data is further hierarchically abstracted to form a multi-level abstracted property tensor of the mud. Based on the new dimension feature values in the feature mapping data, it is divided into multiple levels, each corresponding to a different level of abstraction. For example, if the dimension-reduced property mapping data has two main feature dimensions, they can be divided into low, medium, and high property levels according to their value ranges. The data in different hierarchical layers is integrated into a multi-dimensional tensor structure. Each tensor layer represents the change of mud properties at different levels of abstraction, for example, the density property can be in the first dimension of the tensor, and the viscosity property can be in the second dimension, to construct a multi-dimensional abstracted property tensor of the mud. The corresponding property values at different levels are filled into the tensor structure. The data points at different levels of abstraction, such as depth, density, and viscosity, are filled into the corresponding tensor levels to obtain the abstracted property tensor data of the mud.

[0136] In an embodiment, the values of feature 1 and feature 2 are divided into multiple abstraction levels according to the feature value range. For example, set feature values 0 to 0.5 as "low-level properties" and 0.5 to 1 as "high-level properties". These hierarchical properties are organized into a tensor structure. For example, if feature 1 and feature 2 represent the density and permeability properties of the mud, a 2x3 tensor (2-dimensional features x 3 levels) is constructed: level 1: low density-low permeability, level 2: high density-low permeability, level 3: high density-high permeability. Each data point is mapped to the corresponding tensor level according to its feature value range to obtain the following abstracted property tensor data of the mud:

[0137] The abstracted property tensor data of the mud is shown in Table 2:

[0138] Tensor level Feature 1 density Feature 2 permeability Level 1 0.3 0.7 Level 2 0.8 0.4 Level 3 0.5 0.9

[0139] The abstracted property tensor data of the mud is processed before encoding to obtain compressed feature data of the mud;

[0140] In an embodiment, the abstracted property tensor data of the mud is pre-processed before encoding to compress the features and reduce data redundancy, obtaining the simplified compressed feature data of the mud. The mud property tensor data is dimension-reduced to remove redundant information. Principal Component Analysis (PCA) or other dimension-reduction methods are used to compress the dimensions with less variation in the tensor data to reduce the complexity of the properties. In the dimension-reduced tensor data, the main features are selected according to their importance. The variance of each feature at different levels can be calculated to retain the features with larger variation and remove unimportant features. The dimension-reduced and selected features are reconstructed into a compressed feature matrix of the mud. This matrix has fewer property dimensions, but retains the most important information of the mud properties.

[0141] In an embodiment, the property tensor is reduced in dimensionality, and dimensions with large changes are retained. For example, the variance of each tensor level is calculated, and the dimension with the largest variance is retained to reduce the feature dimension complexity. Features with large variance in the tensor are selected for combination. For example, feature 1 has large changes, and feature 2 has small changes, and feature 1 is mainly retained. The reduced tensor data is reorganized into a matrix to obtain mud compression feature data

[0142] The mud compression feature data is recursively encoded to obtain mud property encoding data.

[0143] In an embodiment, the compression feature data is recursively encoded to generate mud property encoding data. The recursive encoder is initialized, and the number of recursive layers and the input dimension are set. For example, the number of encoding layers is set to 3 layers to gradually extract high-level features in the data. In each layer, the input mud compression feature data is further encoded, and the high-dimensional feature space is mapped to a low-dimensional space layer by layer. The output of each layer is used as the input of the next layer, so that the high-level features in the data gradually appear. The recursive encoding captures the complex patterns hidden in the mud properties through nonlinear transformation. The final encoding result, i.e., the mud property encoding data, is output at the last layer of the recursive encoding. The data contains mud property data that has been abstracted and compressed multiple times, and can effectively express the core property patterns of the mud.

[0144] Optionally, wherein the clustering scale adjustment and the clustering boundary multi-scaling include:

[0145] According to the mud property clustering data, the initial scale of the mud property is initialized to obtain mud property initial scale data;

[0146] In an embodiment, the initial scale of the mud property is set using the mud property clustering data to determine the distribution range and density of the initial cluster. Based on the distance distribution of the data points in the cluster to the cluster center, the average distance is calculated as the initial scale radius of each cluster. The radius is set as the average distance of all data points to the center point, for example, if the average distance of the points in a cluster to the center point is 3 meters, the initial scale radius is 3 meters. The density of data points per unit area in each cluster is calculated to provide a basis for subsequent density center identification. The density distribution is obtained by counting the number of points in each initial scale. The mud property initial scale data is obtained, and the initial scale range of each cluster is set to lay a foundation for the next step of density center identification.

[0147] According to the mud property initial scale data, the density center is identified to obtain mud property clustering center data;

[0148] In an embodiment, high-density center points within the cluster are identified, which will serve as the core for further expansion and boundary adjustment. From each initial cluster center, the point density variation at different distances is calculated step by step by expanding outward. For example, the point density is calculated at multiple levels with a radius of 2 meters, 3 meters, 4 meters, etc. from the cluster center. When the density at a certain distance reaches a peak, the distance is marked as a high-density center point, which serves as the basis for expansion. If the density at a radius of 3 meters in a certain cluster is the highest, then the density center radius is set to 3 meters. The position of the density peak of each cluster is marked as the cluster center, which serves as the core point for the next step of scale expansion.

[0149] The scale step-by-step expansion processing is performed on the cluster center data of the mud property to obtain mud property expansion scale data;

[0150] In an embodiment, the scale of each cluster is expanded step by step to capture potential boundary features and the distribution of adjacent clusters. Starting from the cluster center, the radius is gradually expanded, and the expansion distance is increased to include more data points. For example, the number of new data points within the expanded radius is calculated by increasing the radius by 1 meter each time. The density of the new area is calculated after each expansion, and the density distribution after each expansion is recorded. If the density decreases significantly after expansion, the expansion stops; otherwise, the expansion continues until the density stabilizes gradually. The expansion radius and its density are recorded at each expansion to form expansion scale data. If the density stabilizes when the expansion radius reaches 6 meters, for example, then 6 meters is recorded as the expansion radius. The obtained mud property expansion scale data includes the density variation of each cluster from the center to the boundary.

[0151] According to the mud property expansion scale data, the cluster center change rate calculation and the cluster change feature extraction are performed to obtain mud property cluster center change rate data and mud property cluster change feature data;

[0152] In an embodiment, the expansion change of each cluster is analyzed, and the core features of the cluster property change are extracted. At each expansion scale, the density change rate of each layer is calculated. The change rate formula can be set as the ratio of the density difference between adjacent layers to the expansion radius. By observing the increasing and decreasing trend of the change rate, the boundary with significant density change is identified. The point with the most significant density change during the expansion process is recorded as the change feature of the cluster. For example, if the change rate reaches the highest peak when the expansion radius is 3 meters, then 3 meters is marked as the change feature. The change features of each cluster are sorted into a table to form the cluster center change rate data and the cluster change feature data.

[0153] According to the mud property cluster center change rate data and the mud property cluster change feature data, the boundary adjustment is performed on the mud property expansion scale data to obtain multi-scale adjustment data of the cluster property;

[0154] In one embodiment, the cluster boundary is adjusted according to the rate of change and the change profile, to ensure that the boundary reflects the true distribution of the cluster. The boundary of each cluster is identified according to the rate of change data. The location where the rate of change significantly decreases is taken as the boundary stop point. For example, when the rate of change decreases to below 10% at 4 meters, 4 meters is marked as the boundary. In the vicinity of the boundary, the boundary is modified according to the distribution profile in the change profile data, so that the boundary can cover the region where the density decreases slowly. Through hierarchical boundary adjustment, boundary ranges of different radii are formed, such as "core boundary", "near boundary", and "far boundary", representing the multi-scale distribution of multi-level boundaries.

[0155] In one embodiment, the cluster boundary is adjusted according to the rate of change and the change profile, to ensure that the boundary reflects the true distribution of the cluster. The boundary of each cluster is identified according to the rate of change data. The location where the rate of change significantly decreases is taken as the boundary stop point. For example, when the rate of change decreases to below 10% at 4 meters, 4 meters is marked as the boundary. In the vicinity of the boundary, the boundary is modified according to the distribution profile in the change profile data, so that the boundary can cover the region where the density decreases slowly. Through hierarchical boundary adjustment, boundary ranges of different radii are formed, such as "core boundary", "near boundary", and "far boundary", representing the multi-scale distribution of multi-level boundaries.

[0156] According to the multi-scale adjustment data of the cluster characteristics, the dense region is refined to obtain multi-scale clustering data of mud characteristics.

[0157] In one embodiment, the dense region is refined according to the multi-scale adjustment data, and the dense subgroups in the cluster are identified to obtain more accurate multi-scale clustering data. Within the multi-scale boundary, the density values of each sub-region are calculated, and the region with a density higher than a certain threshold is identified as a dense region. For example, the region with a density greater than 0.8 within a radius of 3 meters is taken as the core dense region. The dense region is further divided into several subgroups. Similar dense data points are grouped into a group to refine the internal structure of the dense region. The dense subgroups in each cluster are marked as "core dense subgroup", and the "extended boundary subgroup" away from the core is identified, forming multi-scale clustering data of mud characteristics.

[0158] In one embodiment, within the core boundary of each cluster, the density of the dense subgroup is calculated, and the region with a density higher than a certain threshold is identified as a dense subgroup. For example, within a radius of 5 meters in class A, the region with a density greater than 1.0 points / meter 2The area marked as dense area in the figure is the dense area. The dense area is refined, and the area with density higher than the threshold is divided into subgroups. There are two high-density subgroups at the radii of 3 meters and 4.5 meters in the dense subgroup in class A. The dense subgroup marked in class A is the core subgroup, and the extended boundary is the less dense area. The dense area in class B is refined into core subgroup, less core subgroup, and other multi-level subgroups. The obtained multi-scale clustering data of mud characteristics are as follows: class A: core subgroup (density 1.2 points / meter 2 , radius 3-4 meters), less dense area (5 meters), extended boundary (6 meters), class B: core subgroup (density 0.9 points / meter 2 , radius 4-5 meters), less core subgroup (6 meters), extended boundary (7 meters).

[0159] Optionally, S2 comprises:

[0160] S21, performing pressure multi-dimensional deconstruction diagram processing according to the slot hole pressure data to obtain mud multi-dimensional pressure deconstruction diagram data;

[0161] In an embodiment, by performing multi-dimensional deconstruction on the slot hole pressure data, the distribution of mud pressure at different depths and directions is visualized to obtain a mud multi-dimensional pressure deconstruction diagram. The slot hole pressure data is sorted, and the pressure values at different depths and the corresponding direction data are classified according to depth, direction, etc. For example, the slot hole depth is 20 meters, which is divided into one layer per meter, and the pressure values in four directions are measured. The depth, direction, and pressure value are represented as a deconstruction diagram using a three-dimensional graph, the depth is the vertical axis, the pressure value is the horizontal axis, and the pressure change in different directions is represented by color or line. A mud multi-dimensional pressure deconstruction diagram is generated to visually display the changes of pressure with depth and direction. For example, the pressure data collected at depths of 5 meters, 10 meters, 15 meters, and 20 meters in four directions (east, south, west, and north) is as follows: depth 5 meters: east 20 kPa, south 18 kPa, west 19 kPa, north 21 kPa, depth 10 meters: east 25 kPa, south 23 kPa, west 24 kPa, north 22 kPa, depth 15 meters: east 30 kPa, south 28 kPa, west 29 kPa, north 27 kPa, depth 20 meters: east 35 kPa, south 33 kPa, west 34 kPa, north 32 kPa. The data is displayed in a three-dimensional graph, with the vertical axis representing depth, the horizontal axis representing pressure, and color representing direction. The generated graph can help observe the distribution characteristics of pressure at different depths and directions.

[0162] S22, performing slot hole depth pressure correlation analysis according to the mud multi-dimensional pressure deconstruction diagram data to obtain mud pressure data;

[0163] In an embodiment, the depth variation of mud pressure is analyzed for correlation to determine the regular distribution of pressure at different depth levels. The pressure value of each depth level is extracted from the deconstructed graph data, the pressure difference between adjacent depth levels is calculated, and a correlation curve of depth-pressure variation is constructed. For example, the pressure variation per 1 meter of depth is calculated, and the average pressure and variation trend of each depth level are recorded. By calculating the standard deviation, mean value, and other statistical quantities of the pressure variation of each layer, the variation law of pressure with depth is determined. The layers with large pressure variation amplitude are marked as pressure fluctuation regions, and the layers with small variation are marked as stable regions. The analysis results are arranged into a table to show the distribution characteristics of pressure at different depths to identify sensitive points and conduction characteristics.

[0164] In an embodiment, according to the pressure deconstruction graph, the variation of pressure in the depth direction is analyzed to identify the correlation of pressure. The pressure difference between adjacent layers is calculated for each depth layer to construct a depth-pressure variation curve. For example: depth 5-10 meters: east direction pressure variation = 25-20 = 5 kPa, depth 10-15 meters: east direction pressure variation = 30-25 = 5 kPa, depth 15-20 meters: east direction pressure variation = 35-30 = 5 kPa. The average value and variance of the pressure variation at each depth are calculated to determine the law of pressure variation between different depths. If the variance is less than a certain threshold, it indicates that the pressure is relatively stable in this depth range.

[0165] S23, identifying pressure sensitive points according to mud pressure data to obtain mud pressure sensitive point data;

[0166] In an embodiment, the sensitive points of mud pressure at each depth are identified to determine the depth region most sensitive to pressure variation. A threshold range of pressure fluctuation is set, for example, defining a pressure variation of more than 10% between adjacent layers as a sensitive point. According to the variation rate of adjacent depths in the pressure data, the region with significant pressure variation is selected and marked as a sensitive point. For example, at depths of 5 meters, 10 meters, and 15 meters, the pressure variation rate exceeds 10%, and these points are marked as pressure sensitive points. The position, pressure value, and variation rate of each pressure sensitive point are recorded in a table to form a pressure sensitive point data table.

[0167] S24, stress conduction mapping of mud pressure sensitive point data to obtain mud stress conduction mapping data;

[0168] In an embodiment, the stress propagation path is simulated according to the pressure sensitive point data, and the propagation of pressure from the sensitive point to the surrounding area is analyzed. A stress propagation model is established with the sensitive point as the center. It is assumed that the pressure is gradually propagated to the surrounding formation through the mud, and the pressure is gradually reduced layer by layer during the propagation. The pressure propagation value in each direction around the sensitive point is calculated. According to the mud density and the formation characteristics, the stress propagation distance and the reduction rate are calculated, for example, the propagation pressure is reduced by 20% for every 1 meter of expansion. The propagation path is added to the deconstruction diagram, and the pressure reduction value in each direction is marked. At the sensitive point at a depth of 5 meters, the pressure value propagated to 7 meters is reduced to 60% of the original value, forming a multi-level stress propagation mapping.

[0169] S25, slot hole stress response simulation is performed according to the mud stress propagation mapping data, and slot hole stress response data is obtained;

[0170] In an embodiment, the stress response of the whole slot hole is simulated based on the data of the stress propagation mapping, and the stress state at different depths is analyzed. At each depth point in the slot hole, the stress in all directions is superimposed, and the total stress at the depth is calculated. It is assumed that the stress is affected by multiple directions at the same depth, and the total value of the superimposed pressure is calculated. In the depth-stress curve, the total stress value after superposition of each layer is recorded, and a stress response curve is generated. For example, after superposition of the sensitive point pressures at 5 meters, 10 meters and 15 meters, the slot hole wall surface as a whole shows multi-level stress response. According to the stress response curve, the peak and valley values of the stress change are analyzed, and the high pressure area and the low pressure area of the slot hole stress distribution are marked.

[0171] S26, stress concentration area screening is performed according to the slot hole stress response data, and slot hole wall surface stress data is obtained.

[0172] In an embodiment, the stress concentration area of the slot hole wall surface is identified according to the stress response data, and the high stress area with a risk of instability in the slot hole is screened out. A stress concentration threshold is set. For example, if the stress value at a certain depth exceeds 1.5 times the average stress, it is marked as a stress concentration area. According to the stress response data, the depths with stress values exceeding the threshold are screened out. It is assumed that the stress values at 10 meters and 15 meters exceed the threshold, and are marked as stress concentration areas. The position, stress value, propagation path and other information of all the concentration areas are integrated to form slot hole wall surface stress data, which represents the distribution of high stress on the slot hole wall surface.

[0173] Optionally, the stress propagation mapping comprises:

[0174] According to the mud pressure sensitive point data, the mechanical properties of the sensitive point are analyzed, and sensitive point mechanical property matrix data is obtained;

[0175] In an embodiment, the mechanical properties at the pressure-sensitive points of the mud are analyzed to form a mechanical property matrix data including the properties of the soil layer around the sensitive points and the mud. The position, pressure value, surrounding mud density, viscosity, and other mechanical properties of each sensitive point are extracted from the pressure-sensitive point data. The mechanical property parameters of each sensitive point, such as the yield stress, shear modulus, and permeability of the mud, are calculated according to the properties of each sensitive point. For example, if the mud density of a sensitive point is 1.2 g / cm 3 , and the viscosity is 30 mPa x s, the mechanical parameters such as the shear modulus of the point are calculated. The mechanical properties of all sensitive points are sorted into a matrix, with rows representing different sensitive points and columns representing different mechanical properties of each sensitive point. The matrix data formed can represent the mechanical state of the sensitive points. The obtained sensitive point mechanical property matrix data includes the density, viscosity, shear modulus, and other properties of the sensitive points, providing comprehensive mechanical information of each sensitive point.

[0176] According to the sensitive point mechanical property matrix data, the stress field is initialized to obtain initial stress field distribution map data;

[0177] In an embodiment, based on the mechanical properties of the sensitive points, the stress field of the entire slot is initialized to obtain an initial stress field distribution map. Using the data in the mechanical property matrix, the initial stress distribution of the sensitive points and their surrounding areas is calculated according to the pressure and shear modulus. For example, if the initial pressure of a sensitive point is 20 kPa and the shear modulus is 1 MPa, the initial stress field of the surrounding area is estimated according to its position and mechanical properties. The slot space is divided into several small grid cells, and the stress value of each cell is obtained by interpolating the mechanical properties of adjacent sensitive points. Through the interpolation method, an initial stress field covering the entire slot is generated. A three-dimensional distribution map is formed to show the stress value at each depth and direction, and the initial distribution of stress in the slot is intuitively displayed. The obtained initial stress field distribution map data shows the initial distribution of stress in the slot.

[0178] The initial stress field distribution map data is subjected to adjacent pressure conduction simulation to obtain pressure conduction sequence data;

[0179] In an embodiment, based on the initial stress field distribution map, the conduction process of pressure from the sensitive point to the adjacent area is simulated. Starting from the sensitive point, the conduction path is expanded to the adjacent area layer by layer, and a certain pressure is decreased at each layer. If the decrease coefficient is 0.9, the pressure is attenuated to 90% of the pressure of the previous layer when the path is expanded at each layer. For example, if the initial pressure of the sensitive point is 20 kPa, the first layer of adjacent conduction pressure is 20 kPa x 0.9 = 18 kPa, the second layer is 18 kPa x 0.9 = 16.2 kPa, and so on. The pressure values of each layer adjacent to each sensitive point are recorded layer by layer to generate pressure conduction sequence data, which shows the conduction process from the sensitive point to the adjacent area. The obtained pressure conduction sequence data shows the conduction process of pressure decreasing from the sensitive point to the adjacent area, which provides a basis for optimizing the conduction path.

[0180] According to the pressure conduction sequence data, the conduction path is optimized to obtain optimized conduction sequence data;

[0181] In an embodiment, according to the preliminary pressure conduction sequence, the conduction path is optimized to make the pressure conduction more reasonable. The effectiveness of each conduction path is analyzed, and the path with larger pressure and shorter conduction path is retained to reduce the invalid long-distance conduction. For example, if the pressure of a certain path decays to less than 5 kPa within two layers, it is considered as an invalid path. According to the screening result, the path is re-optimized, the pressure decay coefficient of each node in the path is adjusted, and the effective conduction path is retained. For example, the decay coefficient of the short distance path is set to 0.95 to retain more pressure values, and the optimized conduction sequence data is formed to record the pressure decay and the length of the conduction path. The obtained optimized conduction sequence data includes the optimized pressure conduction path, so that the pressure is better conducted on the effective path to form a better conduction distribution.

[0182] According to the optimized conduction sequence data, the geological stress decay simulation is performed to obtain stress decay distribution matrix data;

[0183] In an embodiment, the decay of pressure in the geological environment is simulated to form a stress decay distribution matrix. According to the structure of the stratum, a stress decay model is set. For example, the stress decay in clay layer is slow, and the decay coefficient is set to 0.9; the decay in sand layer is fast, and the coefficient is set to 0.7. According to the path in the optimized conduction sequence, the pressure decay is calculated layer by layer along the path direction. After the path passes through 2 meters in the clay layer, the pressure value decays from 20 kPa to 20 x 0.9 x 0.9 = 16.2 kPa. The pressure decay value of each layer in each conduction path is recorded to form a stress decay distribution matrix, which shows the gradual decay of stress in different strata.

[0184] According to the stress decay distribution matrix data, the stress conduction boundary of the initial stress field distribution map data is adjusted to obtain stress conduction boundary data;

[0185] In an embodiment, the stress conduction boundary is adjusted based on the stress decay distribution to ensure the rationality of stress conduction. A boundary threshold of stress conduction is set, and the area below 2 kPa is no longer subjected to stress conduction, which is marked as a boundary area. According to the decay matrix, all areas below the boundary threshold are screened out and set as conduction termination points. If a path passes through 5 meters in the sand layer and the stress decays to 1.8 kPa, 5 meters is taken as the conduction boundary. The termination point position of each path is recorded to form stress conduction boundary data, and the boundary condition of the conduction path is displayed.

[0186] According to the optimized conduction sequence data, stress decay distribution matrix data, and stress conduction boundary data, mapping reconstruction is performed to obtain mud stress conduction mapping data.

[0187] In an embodiment, the foregoing data is integrated to complete the stress conduction mapping of the mud. The optimized conduction sequence, stress decay matrix, and conduction boundary data are integrated into the same mapping framework, and the pressure values of each path and boundary are reconstructed together. Based on the integrated data, a three-dimensional stress conduction map is generated to display the stress conduction process of the sensitive point in the entire slot hole. The area with larger stress is marked as a high conduction area, and the area decaying to the boundary is marked as a low conduction area. The area with larger pressure fluctuation in the mapping map is subjected to smoothing processing to enhance the readability of the conduction mapping.

[0188] Optionally, S3 includes:

[0189] S31, stress distribution anomaly detection is performed according to the slot hole wall surface stress data to obtain stress anomaly point data;

[0190] In an embodiment, by analyzing the slot hole wall surface stress data, the abnormal points in the stress distribution are detected to identify the areas with stress concentration or sharp change. Based on the average value and standard deviation of the slot hole wall surface stress data, the determination threshold of stress anomaly is set. For example, if the average stress is 30 kPa and the standard deviation is 5 kPa, the threshold is set to 1.5 times of the average value (i.e. 45 kPa) or twice of the standard deviation (i.e. 40 kPa), and any point higher than the threshold is an abnormal point. The stress value of each wall surface point is checked one by one, and the points higher than the abnormal threshold are marked. If 50 kPa and 55 kPa are respectively detected on two adjacent points at a certain depth, the two points are marked as abnormal points. All the points marked as abnormal are recorded, including the depth position, stress value, and surrounding stress environment, for subsequent analysis.

[0191] S32, instability region analysis is performed according to the stress anomaly point data to obtain slot hole wall surface instability region data;

[0192] In an embodiment, according to the detected stress anomaly points, further analysis is performed on the possible instability region to determine the specific distribution range of the instability region in the slot hole wall surface. According to the distribution of the stress anomaly points, the region where the continuous anomaly points or the high stress value exceeds a certain range is set as the instability region. If there are 3 or more anomaly points within a continuous 5-meter depth, the depth range is considered as a potential instability region. The anomaly points that meet the conditions are aggregated as an instability region. For example, if there are multiple anomaly points in the depth range of 10 meters to 15 meters, this depth range is aggregated as an instability region. The position, depth range and stress value of the instability region are recorded for trend analysis, and the obtained slot hole wall surface instability region data indicates the specific position and stress characteristics of the instability region.

[0193] S33, instability trend analysis is performed on the slot hole wall surface instability region data to obtain slot hole wall surface instability trend data;

[0194] In an embodiment, the distribution characteristics and stress change trend of the instability region are analyzed to predict the future expansion or contraction trend of the instability region. The stress change trend of each instability region is extracted, including the stress increase / decrease rate of each anomaly point. Assuming that the stress in the instability region at a depth of 12 meters gradually increases from 30 kPa to 50 kPa over a period of time, the increase is 20 kPa. Linear fitting is performed on the stress change rate of adjacent points in the instability region to determine the overall stress change trend of the region. If the trend is positive, i.e. the stress continues to rise, the region has a tendency to expand instability; if it is negative, the instability weakens. The analyzed trend results are arranged in a table, and the stress change rate and instability expansion direction of each instability region are recorded.

[0195] S34, instability region depth identification is performed on the slot hole wall surface instability trend data to obtain instability region identification data;

[0196] In an embodiment, by analyzing the instability trend data, the depth range of the instability region is identified to determine the potential expansion depth of the instability region. According to the stress increase / decrease in the instability trend data, the depth range of the instability region is determined. For example, if the stress increase in the depth range of 12 meters to 15 meters is 20 kPa, and the stress increase in the depth range of 15 meters to 18 meters is 10 kPa, then the depth range of 12 meters to 18 meters is marked as the instability range. If the trend analysis shows that the region is still expanding, a certain expansion range is reserved below the existing instability depth. For example, if the stress continues to increase in the depth range of 15 meters to 18 meters, the instability depth further expands to 20 meters. The depth range, current expansion situation and extension depth of each instability region are recorded as a data table to form the instability region identification data.

[0197] S35, instability region dynamic mapping is performed according to the instability region identification data to obtain slot hole wall surface instability region data.

[0198] In an embodiment,

[0199] Optionally, S4 comprises: generating a dynamic mapping diagram of the unstable region according to the identified unstable region depth range and expansion trend, to intuitively show the distribution of the unstable region. The depth range, stress value and trend in the unstable region identification data are integrated into the same mapping framework. A three-dimensional dynamic mapping diagram of the slot hole wall surface is generated based on the identification data, and the unstable region is marked with color or lines. Unstable regions of different depths and trends can be distinguished by color depth. For example, high stress concentration areas are marked with dark red, and unstable expansion areas are marked with orange. The mapping diagram is updated in real time, and the color and range of the unstable region are adjusted over time to reflect the dynamic changes of the instability trend. The generated dynamic mapping diagram of the unstable region of the slot hole wall surface shows the distribution and expansion trend of the unstable region, providing visual reference data for slot hole stability monitoring and risk control.

[0200] S41, according to the slot hole wall surface unstable region data and the slot hole wall surface stress data, the stability characteristics are extracted, and the stability characteristic data is obtained;

[0201] In an embodiment, the stability characteristics are extracted by analyzing the slot hole wall surface unstable region data and the wall surface stress data, which lays the foundation for subsequent stability index calculation. The depth, stress value, expansion trend and other characteristics of the unstable region are analyzed. The unstable region depth is 8-12 meters, the average stress is 45kPa, and the stress change trend is rising. The distribution and change law of the wall surface stress are analyzed, including the average stress, the stress gradient and the maximum stress value. For example, the average stress of each depth of the slot hole wall surface is 30kPa, and the stress gradient is 5kPa / m. Various characteristics are sorted into a data table to form stability characteristic data, covering the depth, stress trend, wall surface average stress and gradient of the unstable region.

[0202] Stability characteristic data table 3 is as follows:

[0203] Feature Value Destabilization zone depth 8-12 m Average stress 45 kPa Stress variation trend Rising Wall average stress 30 kPa Stress gradient 5 kPa / m

[0204] S42, according to the stability characteristic data, the stability index is calculated, and the slot hole region stability index data is obtained;

[0205] In an embodiment, the stability index can be defined as the ratio of the unstable region stress to the wall surface average stress. The index formula is: S is the slot hole region stability index data, Q is the wall surface average stress, K is the unstable region average stress, and C is the stress gradient. According to the characteristic data, the formula is substituted. For example, the wall surface average stress is 30kPa, the unstable region stress is 45kPa, the stress gradient is 5kPa / m, and the stability index is 3.33.

[0206] S43. Perform multi-factor cross analysis according to the data of the instability region of the slot hole wall surface and the data of the stress of the slot hole wall surface, to obtain multi-factor cross analysis matrix data;

[0207] In an embodiment, the multi-factor cross analysis is used to analyze the mutual relationship of different factors (such as stress gradient, stress change trend, etc.) affecting stability. The main factors such as wall surface stress, stress gradient, instability region depth, stress trend, etc. are selected. Cross comparison analysis is performed on the selected factors to construct a matrix. The rows and columns of the matrix respectively represent different factors, for example:

[0208] The multi-factor cross analysis matrix Table 4 is as follows:

[0209] Factor Wall stress Stress gradient Destabilization depth Stress trend Wall stress High Medium Low Stress gradient High High Medium Destabilization depth Medium High High Stress trend Low Medium High

[0210] S44. Perform stress instability risk assessment according to the data of the slot hole region stability index and the data of the multi-factor cross analysis matrix, to obtain instability risk assessment matrix data;

[0211] In an embodiment, the stability index and the cross analysis matrix are combined to assess the instability risk of the slot hole, to obtain risk assessment matrix data. The risk score is set according to the stability index range. The S value less than 3 is high risk, 3-4 is medium risk, and greater than 4 is low risk. According to the score of the stability index and the relationship strength in the cross matrix, the risk score of each factor is calculated comprehensively. For example, the stability index of the 8-12 meter depth is 3.33, which belongs to medium risk. Record the instability risk assessment result of each depth to form the following matrix:

[0212] The instability risk assessment matrix Table 5 is as follows:

[0213] Depth (m) Wall stress Stress gradient Destabilization depth Stress trend Overall risk assessment 8-12 Medium High High Medium Moderate

[0214] The generated instability risk assessment matrix shows the contribution of each factor to the instability risk.

[0215] S45. Perform slot hole safety factor calculation according to the instability risk assessment matrix data, to obtain slot hole stability data.

[0216] In an embodiment, the safety factor can be defined as the ratio of the stability index to the total risk assessment score. The safety factor formula is: S 安 S is the stability index, and M is the total risk assessment score. The safety factor of the slot hole is calculated according to the stability index and the risk score matrix data. For example, the stability index of the 8-12 meter region is 3.33, and the total risk assessment is “medium”, corresponding to a score of 2. Then the safety factor is 1.665.

[0217] Thus, the embodiments should be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.

[0218] The foregoing is considered as illustrative only of the principles of the application. Numerous modifications and changes will readily occur to those skilled in the art, and the generic principles defined herein can be applied to other embodiments without departing from the spirit or scope of the application. Therefore, the scope of the application is indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are intended to be embraced therein.

Claims

1. A method for analyzing the stability of mud slurry wall protection in anti-seepage wall trenches, characterized in that, The method includes: S1. Obtain the geological data and mud characteristic data of the trench, and perform pressure simulation based on the geological data and mud characteristic data to obtain the trench pressure data. S2 includes: S21, processing the pressure multidimensional deconstruction diagram based on the trench pressure data to obtain the mud multidimensional pressure deconstruction diagram data; S22, performing trench depth pressure correlation analysis based on the mud multidimensional pressure deconstruction diagram data to obtain mud pressure data; S23, identifying pressure-sensitive points based on the mud pressure data to obtain mud pressure-sensitive point data; S24, performing stress transmission mapping on the mud pressure-sensitive point data to obtain mud stress transmission mapping data; S25, simulating trench stress response based on the mud stress transmission mapping data to obtain trench stress response data; S26, filtering stress concentration areas based on the trench stress response data to obtain trench wall stress data. S3. Based on the stress data of the slot wall, process the unstable region to obtain the unstable region data of the slot wall; S4. Based on the data of the unstable area of ​​the slot wall and the stress data of the slot wall, perform a stability analysis of the slot to obtain the stability data of the slot.

2. The method according to claim 1, characterized in that, S1 includes: S11. Obtain trench geological data and mud characteristic data through geological engineering databases or geological engineering input interfaces; S12. Based on the mud characteristic data, perform mud characteristic modeling to obtain a mud characteristic clustering model; S13. Based on the geodetic data, perform geological dynamic feature transformation to obtain geological dynamic feature sequence data; S14. Based on the mud characteristic clustering model and the dynamic characteristic sequence data, virtual reality strata modeling is performed to obtain a three-dimensional strata characteristic model. S15. Calculate the mud characteristic distribution depth based on the three-dimensional formation feature model to obtain mud characteristic distribution depth data; S16. Perform dynamic pressure simulation of the trench hole based on the depth data of mud characteristic distribution to obtain trench hole pressure data.

3. The method according to claim 2, characterized in that, The mud property modeling includes: Based on the mud characteristic data, mud characteristic features are extracted to obtain mud characteristic feature data; Feature encoding is performed based on mud characteristic data to obtain mud characteristic encoded data; Preliminary clustering of mud feature coding data yields mud characteristic clustering data. Based on the mud characteristic clustering data, the clustering scale is adjusted and the cluster boundaries are multi-scaled to obtain mud characteristic multi-scale clustering data; Label association is performed on mud characteristic data based on multi-scale clustering data of mud characteristics to obtain mud characteristic clustering label association data; A model is constructed based on the clustering labels associated with mud characteristics, resulting in a mud characteristic clustering model.

4. The method according to claim 3, characterized in that, The feature encoding includes: Local linear embedding processing is performed on the mud characteristic feature data to obtain mud characteristic feature mapping data; Based on the mud characteristic feature mapping data, the characteristics are abstracted and layered to obtain the mud abstract characteristic tensor data; The abstract property tensor data of mud is pre-processed for encoding to obtain mud compression feature data; Recursively encode the mud compression characteristic data to obtain mud characteristic coded data.

5. The method according to claim 3, characterized in that, Clustering scale adjustment and multi-scale cluster boundary optimization include: Clustering scale initialization is performed based on mud property clustering data to obtain initial scale data for mud properties. Density centers are identified based on initial scale data of mud properties to obtain mud property cluster center data; The data of mud property cluster centers are subjected to stepwise scaling to obtain mud property scaled data. Based on the extended scale data of mud properties, the change rate of cluster centers is calculated and the cluster change characteristics are extracted to obtain the change rate data of mud property cluster centers and the cluster change characteristic data of mud properties. Based on the data on the rate of change of the cluster centers of mud properties and the data on the characteristics of the cluster changes of mud properties, the boundary of the extended scale data of mud properties is adjusted to obtain multi-scale adjusted data of cluster properties. Based on the clustering characteristics, the data is adjusted at multiple scales to refine dense regions, resulting in multi-scale clustering data of mud characteristics.

6. The method according to claim 1, characterized in that, The stress transmission mapping includes: Based on the data of mud pressure sensitive points, the mechanical properties of the sensitive points are analyzed to obtain the mechanical property matrix data of the sensitive points; The stress field is initialized based on the mechanical property matrix data of the sensitive points to obtain the initial stress field distribution map data; The pressure transmission sequence data is obtained by performing a proximity pressure transmission simulation on the initial stress field distribution map data; Based on the pressure conduction sequence data, conduction path optimization is performed to obtain optimized conduction sequence data; Geological stress attenuation simulation was performed based on optimized transmission sequence data to obtain stress attenuation distribution matrix data; The stress transmission boundary is adjusted based on the stress attenuation distribution matrix data to obtain the stress transmission boundary data. Based on the optimized conduction sequence data, stress attenuation distribution matrix data, and stress conduction boundary data, mapping and reconstruction are performed to obtain mud stress conduction mapping data.

7. The method according to claim 1, characterized in that, S3 include: S31. Detect stress distribution anomalies based on the stress data of the slot wall to obtain stress anomaly point data; S32. Based on the stress anomaly point data, perform instability region analysis to obtain the instability region data of the slot wall surface; S33. Based on the data of the unstable area of ​​the slot wall, perform instability trend analysis to obtain the instability trend data of the slot wall; S34. Perform instability region depth identification on the instability trend data of the slot wall to obtain instability region identification data; S35. Based on the unstable region identification data, perform dynamic mapping of the unstable region to obtain the unstable region data of the slot wall.

8. The method according to claim 1, characterized in that, S4 includes: S41. Based on the data of the unstable region of the slot wall and the stress data of the slot wall, extract the stability features to obtain the stability feature data; S42. Calculate the stability index based on the stability characteristic data to obtain the stability index data of the slot area; S43. Based on the data of the unstable area of ​​the slot wall and the stress data of the slot wall, perform multi-factor cross-analysis to obtain multi-factor cross-analysis matrix data; S44. Based on the stability index data of the slotted area and the multi-factor cross-analysis matrix data, stress instability risk assessment is carried out to obtain instability risk assessment matrix data. S45. Calculate the safety factor of the slot based on the instability risk assessment matrix data to obtain the stability data of the slot.

Images