A decision method and system for retaining wall deformation control measures based on fault tree analysis

Abstract

This invention relates to a method and system for decision-making on retaining wall deformation control measures based on fault tree analysis. The method includes the following steps: using foundation pit monitoring data as input parameters for a retaining wall maximum deformation prediction model, and obtaining the predicted maximum deformation value of the retaining wall through the model; acquiring the retaining wall deformation in real time using the foundation pit monitoring data; when the retaining wall deformation exceeds the predicted maximum deformation value, making a deformation control scheme decision based on the foundation pit monitoring data and the retaining wall deformation control measure decision-making model, thereby obtaining the retaining wall deformation control measures. Compared with existing technologies, this invention achieves both the prediction of retaining wall deformation and the decision-making on retaining wall deformation control measures, improving construction efficiency.

Description

Technical Field

[0001] This invention relates to the field of foundation pit engineering, and in particular to a method and system for controlling retaining wall deformation based on fault tree analysis. Background Technology

[0002] Excavation pit support primarily provides a safe operating space for underground engineering construction. However, significant deformation or even collapse of the pit can severely impact adjacent structures and generate substantial negative social effects. Regardless of the support method used, the retaining wall will inevitably deform inwards, causing displacement of the surrounding soil and ultimately affecting nearby structures. Furthermore, in urban areas, excavation pit projects are often located near densely packed buildings, placing high demands on deformation control. Even slight negligence can have significant consequences for the structure itself and the surrounding environment. In recent years, the scale and depth of excavations have increased, leading to a corresponding rise in their impact on the surrounding environment. Existing research often employs comprehensive numerical methods to analyze the environmental impact of excavation, a method that is complex and time-consuming. Design reassessment is typically only undertaken when monitoring data approaches or exceeds warning thresholds, which in turn consumes considerable time and manpower, delaying construction. Summary of the Invention

[0003] The purpose of this invention is to overcome the shortcomings of the existing technology by providing a decision-making method and system for retaining wall deformation control measures based on fault tree analysis, which realizes the prediction of retaining wall deformation and the decision-making of retaining wall deformation control measures, thereby improving construction efficiency.

[0004] The objective of this invention can be achieved through the following technical solutions:

[0005] A decision-making method for retaining wall deformation control measures based on fault tree analysis includes the following steps:

[0006] The foundation pit monitoring data is used as the input parameter of the retaining wall maximum deformation prediction model, and the maximum deformation prediction value of the retaining wall is obtained through the retaining wall maximum deformation prediction model.

[0007] The retaining wall deformation is acquired in real time through the foundation pit monitoring data. When the retaining wall deformation exceeds the maximum predicted value of the retaining wall deformation, a deformation control scheme decision is made based on the foundation pit monitoring data and the retaining wall deformation control measure decision model to obtain the retaining wall deformation control measures.

[0008] The steps for constructing the retaining wall deformation control measure decision model include: obtaining the cause of the accident and the severity of the deformation based on the case of excessive deformation of the retaining wall in the foundation pit; obtaining the probability of each accident tree bottom event in the case of excessive deformation of the foundation pit; obtaining the retaining wall deformation control measures corresponding to the bottom events of the foundation pit retaining wall deformation accident tree based on the foundation pit retaining wall deformation accident tree; establishing the correspondence between the deformation control measures and the foundation pit monitoring data; and obtaining the retaining wall deformation control measure decision model.

[0009] Furthermore, the foundation pit monitoring data includes foundation pit soil parameters, foundation pit geometric parameters, and retaining structure parameters.

[0010] Furthermore, the soil parameters of the foundation pit include soil layer thickness, soil layer unit weight, cohesion, internal friction angle, triaxial loading modulus, one-dimensional compression modulus, unloading-heavy load modulus, shear strain corresponding to 70% stiffness, and small strain shear modulus.

[0011] Furthermore, the geometric parameters of the foundation pit include the excavation depth, excavation width, retaining wall length, bending stiffness of the retaining structure, and groundwater depth.

[0012] Furthermore, the enclosure structure parameters include support axial force, support lateral spacing, support axial stiffness, support bending stiffness, and support distance from the ground.

[0013] Furthermore, the foundation pit retaining wall deformation accident tree includes a top event, intermediate events, and a bottom event. The top event is excessive deformation of the foundation pit retaining wall. The intermediate events include multiple events such as retaining wall failure, internal support failure, failure caused by increased groundwater level, failure caused by ineffective water control, and failure caused by soil pressure. The bottom event is the basic event that causes excessive deformation of the foundation pit retaining wall.

[0014] Furthermore, the basic events include multiple events such as insufficient embedment depth, excessive loading at the edge, and over-excavation of the foundation pit.

[0015] Furthermore, the maximum deformation prediction model of the retaining wall is a BP neural network, the activation function of the BP neural network is a linear rectified function, the loss function is the mean square error, and the optimization function is the adaptive moment estimation.

[0016] Furthermore, the deformation control measures include applying a water-stop curtain, dewatering outside the pit, reinforcing the bottom of the pit, unloading soil outside the pit and backfilling soil inside the pit, increasing the stiffness of the supports, adjusting the axial force of the supports, adjusting the spacing of the supports, increasing the bending stiffness of the retaining wall, and early pouring of the bottom slab and removal of the surcharge.

[0017] According to another aspect of the present invention, a decision system for retaining wall deformation control measures based on fault tree analysis is provided, comprising:

[0018] The retaining wall maximum deformation prediction module is used to take the foundation pit monitoring data as input to the retaining wall maximum deformation prediction model, and obtain the predicted value of the maximum deformation of the retaining wall through the retaining wall maximum deformation prediction model.

[0019] The retaining wall deformation control measure decision module is used to obtain the retaining wall deformation in real time through the foundation pit monitoring data. When the retaining wall deformation exceeds the maximum predicted value of the retaining wall deformation, the module makes a deformation control scheme decision based on the foundation pit monitoring data and the retaining wall deformation control measure decision model to obtain the retaining wall deformation control measures.

[0020] The steps for constructing the retaining wall deformation control measure decision model include: summarizing and statistically analyzing the causes and severity of excessive deformation accidents of the retaining wall in the foundation pit based on the case studies; obtaining the probability of each accident tree bottom event in the excessive deformation accident; compiling retaining wall deformation control measures corresponding to the bottom events of the foundation pit retaining wall deformation accident tree based on the foundation pit retaining wall deformation accident tree; establishing the correspondence between the deformation control measures and the input parameters of the maximum deformation prediction model of the retaining wall; and obtaining the retaining wall deformation control measure decision model.

[0021] Compared with the prior art, the present invention has the following beneficial effects:

[0022] 1. This invention summarizes and statistically analyzes accident cases of excessive deformation of retaining walls in foundation pits to determine the causes and deformation degrees of the accidents, obtains the probability of each accident tree bottom event in the case of excessive deformation of foundation pits, compiles retaining wall deformation control measures corresponding to the bottom events of the accident tree based on the foundation pit retaining wall deformation accident tree, establishes the correspondence between the deformation control measures and the input parameters of the maximum deformation prediction model of the retaining wall, obtains the retaining wall deformation control measure decision model, and provides control measures for retaining wall deformation based on foundation pit monitoring data through the retaining wall deformation control measure decision model, thereby improving construction efficiency.

[0023] 2. This invention uses a retaining wall maximum deformation prediction model, taking foundation pit monitoring data as input to the model prediction, to obtain the predicted value of the maximum deformation of the retaining wall. It comprehensively considers the influence of foundation pit soil parameters, foundation pit geometric parameters, and retaining structure parameters on the deformation of the retaining wall, providing reference values ​​for retaining wall deformation accidents, reducing the probability of accidents, and improving construction safety. Attached Figure Description

[0024] Figure 1 This is a flowchart illustrating a decision-making method for retaining wall deformation control measures based on fault tree analysis proposed in this invention.

[0025] Figure 2 This is a schematic diagram of the structure of the retaining wall maximum deformation prediction model;

[0026] Figure 3 A schematic diagram of the accident tree for excessive deformation of the retaining wall in the foundation pit;

[0027] Figure 4 This is a plan view of the foundation pit.

[0028] Figure 5 This is a cross-sectional view of the foundation pit support.

[0029] Figure 6 Deformation diagram of the retaining wall after deformation control measures. Detailed Implementation

[0030] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. These embodiments are based on the technical solution of the present invention and provide detailed implementation methods and specific operating procedures. However, the scope of protection of the present invention is not limited to the following embodiments.

[0031] Example 1

[0032] This embodiment provides a decision-making method for retaining wall deformation control measures based on fault tree analysis, such as... Figure 1 As shown, it includes the following steps:

[0033] S1. Use the foundation pit monitoring data as the input parameter of the retaining wall maximum deformation prediction model, and obtain the predicted value of the retaining wall maximum deformation through the retaining wall maximum deformation prediction model.

[0034] A model for predicting the maximum deformation of retaining walls was established, and an automated modeling program was developed based on the Python language interface provided by PLAXIS to achieve automated batch calculation of two-dimensional modeling of foundation pits. This program has the following features: automatic generation of soil and structure and assignment of material parameters; automatic setting of groundwater level conditions; automatic mesh generation; automatic setting of excavation conditions and calculation; and automatic writing of the maximum horizontal deformation of the retaining wall and the aforementioned material parameters obtained from each calculation into a database. The parameters in the sample database include input parameters, intermediate model parameters, and output parameters. The input parameters are foundation pit monitoring data, including foundation pit soil parameters, foundation pit geometric parameters, and retaining structure parameters. Considering the HSS constitutive model, the foundation pit soil parameters include soil layer thickness, soil layer unit weight, cohesion, internal friction angle, triaxial loading modulus, one-dimensional compression modulus, unloading-heavy loading modulus, shear strain corresponding to 70% stiffness, and small strain shear modulus. Nine soil layers are considered, and each layer includes the above nine parameters, resulting in 81 input parameters. The geometric parameters of the foundation pit include excavation depth, excavation width, retaining wall length, bending stiffness of the retaining structure, and groundwater depth, with 5 input parameters. The retaining structure parameters include brace axial force, brace lateral spacing, brace axial stiffness, brace bending stiffness, and brace distance from the ground, totaling 16 input parameters for four bracing systems. In total, there are 102 input parameters, and the output parameter is the maximum deformation value of the retaining wall.

[0035] The maximum deformation prediction model for the retaining wall uses a backpropagation (BP) neural network, with ReLU as the activation function and mean squared error as the loss function. The optimization function uses adaptive moment estimation, with parameters set to LR = 0.01, β1 = 0.9, and β2 = 0.99; a schematic diagram of the internal structure of the BP neural network is shown below. Figure 2 As shown. The internal structure of the BP neural network during computation consists of five hidden layers, with 102, 73, 58, 48, and 22 neurons in each layer, respectively. That is, the neural network structure is 102-102-73-58-48-22-1. The input layer has a total of 102 parameters, and the output parameter is the maximum horizontal deformation of the retaining wall of the foundation pit, which is 1 parameter. The BP neural network was trained after 15349 iterations.

[0036] The basic parameters of the predicted data are shown in Table 1, based on 50 randomly generated finite element method examples:

[0037] Table 1 Basic parameters of the predicted data

[0038]

[0039] The prediction results are shown in Table 2:

[0040] Table 2 Prediction Results

[0041]

[0042] The prediction error percentage is mostly within 10%, and the absolute value of most prediction errors is less than 2 mm. Therefore, based on the finite element database training, the model's prediction accuracy can meet the requirements for various excavation conditions of the foundation pit generated by the finite element examples.

[0043] S2. Obtain the retaining wall deformation in real time through the foundation pit monitoring data. When the retaining wall deformation exceeds the maximum predicted value of the retaining wall deformation, make a deformation control plan decision based on the foundation pit monitoring data and the retaining wall deformation control measure decision model to obtain the retaining wall deformation control measures.

[0044] A fault tree for the deformation of the retaining wall in the foundation pit is constructed, following a top-down order. The top event is excessive deformation of the retaining wall. Intermediate events are analyzed layer by layer, starting with the retaining structure, earth pressure issues, and water leakage problems. These events are categorized into retaining wall failure, internal support failure, failure caused by increased groundwater level, failure caused by ineffective water containment, and failure caused by earth pressure, etc. The logic gate symbol is an "OR gate". Based on the characteristics of the foundation pit retaining wall support structure system and its failure, and the fault tree principle, a fault tree for excessive deformation of the foundation pit retaining wall is constructed level by level, such as... Figure 3As shown, A1, A2, and A3 correspond to intermediate events such as water leakage, retaining structure problems, and earth pressure problems, respectively; intermediate events B1, B2, B3, B4, B5, and B6 are the design factors, construction factors, and environmental factors caused by these events; B1 is water leakage caused by surrounding environmental factors, B2 is water leakage caused by construction factors, B3 is retaining structure problems caused by construction factors, B4 is retaining structure problems caused by design factors, B5 is earth pressure problems caused by design factors, and B6 is earth pressure problems caused by construction factors; C1 is climate-related, C2 is municipal-related, C3 is water leakage on the side of the foundation pit, C4 is water leakage at the bottom of the pit, C5 is the cause of the retaining wall construction, C6 is the cause of the support construction, C7 is the cause of the retaining wall design, C8 is the cause of the support design, C9 is the cause of the lateral earth pressure, and C10 is the cause of the earth pressure at the bottom of the pit; D1 is the problem of the water-stop curtain, and D2 is the problem of the dewatering well; X1-X15 are the basic events causing the accident, such as insufficient embedment depth, excessive load on the edge, and over-excavation of the foundation pit. Based on the above fault tree structure, the Boolean algebraic expression of the fault tree obtained through logical operations is as follows:

[0045] T=A1+A2+A3=(B1+B2)+(B3+B4)+(B5+B6)=(C1+C2)+(C3+C4)+(C5+C6)+(C7+C8)+(C9+C10)+X12=X1+X2+(D1+D2)+ X5+X6+(X7+X8)+X9+(X10+X11)+X12+X13+(X14+X15)=X1+X2+X3+X4+X5+X6+X7+X8+X9+X10+X11+X12+X13+X14+X15

[0046] As shown in the above formula, a total of 15 minimal cut sets are obtained, namely {X1}, {X2}, {X3}, {X4}, {X5}, {X6}, {X7}, {X8}, {X9}, {X... 10}, {X 11}, {X 12}, {X 13}, {X 14}, {X 15 Each minimal cut set represents a mode that leads to an accident, indicating that there are 15 potential failure modes that can lead to excessive deformation of the foundation pit retaining wall. Each minimal cut set contains only one bottom event, which shows that in the foundation pit retaining wall support structure system, even a very small unsafe factor (event) can often lead to the failure of the entire system.

[0047] Using a literature review approach, we statistically collected recent cases of excessive deformation accidents involving foundation pit retaining walls. We then summarized and statistically analyzed the causes of these accidents and the severity of the deformation, obtaining the probability of various events in these accidents, as shown in Table 3.

[0048] Table 3 shows the probability of the bottom event in accidents involving excessive deformation of the foundation pit.

[0049]

[0050]

[0051] The steps for constructing a decision model for retaining wall deformation control measures include: summarizing and statistically analyzing accident causes based on cases of excessive retaining wall deformation in foundation pits, obtaining the probability of each accident tree bottom event in an accident of excessive deformation in foundation pits, compiling retaining wall deformation control measures corresponding to the bottom events of the accident tree based on the foundation pit retaining wall deformation accident tree, establishing the correspondence between deformation control measures and the input parameters of the maximum deformation prediction model of the retaining wall, and obtaining the decision model for retaining wall deformation control measures.

[0052] Based on the deformation fault tree of the retaining wall in the foundation pit, deformation control measures corresponding to the bottom events of the fault tree were developed; the correspondence between the deformation control measures and the neural network input parameters was established. Control measures for excessive retaining wall deformation were developed based on the maximum deformation prediction model of the retaining wall, and each retaining wall deformation control measure was closely related to the neural network input parameters. The relationship between the retaining wall control measures and the neural network input parameters is shown in Table 4.

[0053] Table 4 Relationship between retaining wall control measures and foundation pit monitoring data

[0054]

[0055] A decision model for retaining wall deformation control measures based on fault tree analysis was established. This model was constructed by analyzing the retaining wall deformation fault tree and comprehensively considering real-time monitoring data from the construction site. The parameters of the decision model are shown in Table 5.

[0056] Table 5 Decision Model Parameters

[0057]

[0058]

[0059] The first column of Table 5 shows the input parameters of the decision model; the second column shows the range of variation of the input parameters; the third column shows the warning values ​​for each parameter index, which are 70% of the maximum range; the fourth column shows the model output parameters, which are the preferred variant control measures to be adopted when the warning values ​​are reached. The specific control measures have been simplified and represented by numerical codes. The variant control measures and numerical codes are shown in Table 6.

[0060] Table 6 Deformation Control Measures and Numbers

[0061]

[0062] The input and output parameters of the decision model for retaining wall deformation control measures are implemented using a decision tree algorithm.

[0063] Based on monitoring data from the foundation pit engineering project and the retaining wall deformation fault tree, a database of decision-making models for retaining wall deformation control measures was generated. Partial database data is shown in Table 7.

[0064] Table 7 Database

[0065]

[0066]

[0067] The first column of Table 7 contains the input parameter numbers of the decision model. Each column in Table 7 (columns 2-10) corresponds to one data point. The last row of the table contains the output parameters of the decision model.

[0068] In another preferred embodiment, the step further includes:

[0069] S3. Predict the maximum horizontal deformation of the retaining wall after the implementation of control measures using the maximum deformation prediction model of the retaining wall.

[0070] The planned construction area for a certain project is approximately 13,372.8 m². 2 The building area is approximately 96,200 square meters. 2 The above-ground building area is approximately 53,500 square meters. 2 The underground building area is approximately 42,700 square meters. 2 The foundation pit layout is as follows: Figure 4 As shown, the cross-section of the foundation pit support is as follows: Figure 5 As shown in Table 8, the actual maximum deformation of the retaining wall detected at monitoring point CX17 was 29.09 mm, the predicted maximum deformation was 28.91 mm, and the control value was 28.00 mm. When the excavation depth reached 16.75 m, the maximum horizontal deformation of the retaining wall under this condition reached 29.09 mm, and the assumed control value was 28 mm. Therefore, to effectively control the maximum horizontal deformation of the retaining wall, a deformation control measure decision model was used based on the foundation pit monitoring data to determine the deformation control scheme. The input parameters of the decision model under this condition are shown in Table 8.

[0071] Table 8 Input parameters for the decision model

[0072]

[0073] The decision model outputs scheme number 2, with the specific measure being dewatering outside the pit. A maximum deformation prediction model for the retaining wall is used to predict the maximum horizontal deformation of the retaining wall after implementing the control measures. A deformation control measure of 60cm dewatering outside the pit is adopted, corresponding to a 0.6m decrease in the groundwater level as per the neural network input parameter. After updating the neural network model input parameters, the maximum horizontal deformation of the retaining wall is predicted. The prediction results are as follows: Figure 6 As shown, the maximum horizontal deformation of the retaining wall is 27.9 mm, which meets the deformation control value required by the specification.

[0074] Example 2

[0075] This embodiment provides a decision-making system for retaining wall deformation control measures based on fault tree analysis, including:

[0076] The retaining wall maximum deformation prediction module is used to take the foundation pit monitoring data as input to the retaining wall maximum deformation prediction model, and obtain the predicted value of the retaining wall maximum deformation through the retaining wall maximum deformation prediction model.

[0077] The retaining wall deformation control measure decision module is used to make a deformation control scheme decision based on the foundation pit monitoring data and the retaining wall deformation control measure decision model when the retaining wall deformation exceeds the maximum predicted value of the retaining wall deformation.

[0078] The steps for constructing the decision model for retaining wall deformation control measures include: summarizing and statistically analyzing the causes and severity of accidents based on cases of excessive deformation of retaining walls in foundation pits; obtaining the probability of each accident tree bottom event in an accident of excessive deformation of foundation pits; compiling retaining wall deformation control measures corresponding to the bottom events of the accident tree based on the accident tree of retaining wall deformation; establishing the correspondence between deformation control measures and the input parameters of the maximum deformation prediction model of retaining walls; and obtaining the decision model for retaining wall deformation control measures.

[0079] The rest is the same as in Example 1.

[0080] The preferred embodiments of the present invention have been described in detail above. It should be understood that those skilled in the art can make numerous modifications and variations based on the concept of the present invention without creative effort. Therefore, all technical solutions that can be obtained by those skilled in the art based on the concept of the present invention through logical analysis, reasoning, or limited experimentation on the basis of existing technology should be within the scope of protection defined by the claims.

Claims

1. A decision-making method for retaining wall deformation control measures based on fault tree analysis, characterized in that, Includes the following steps: The foundation pit monitoring data is used as the input parameter of the retaining wall maximum deformation prediction model, and the maximum deformation prediction value of the retaining wall is obtained through the retaining wall maximum deformation prediction model. The retaining wall deformation is acquired in real time through the foundation pit monitoring data. When the retaining wall deformation exceeds the maximum predicted value of the retaining wall deformation, a deformation control scheme decision is made based on the foundation pit monitoring data and the retaining wall deformation control measure decision model to obtain the retaining wall deformation control measures. The steps for constructing the retaining wall deformation control measure decision model include: obtaining the cause of the accident and the severity of the deformation based on the case of excessive deformation of the retaining wall in the foundation pit; obtaining the probability of each accident tree bottom event in the case of excessive deformation of the foundation pit; obtaining the retaining wall deformation control measures corresponding to the bottom events of the foundation pit retaining wall deformation accident tree based on the foundation pit retaining wall deformation accident tree; establishing the correspondence between the deformation control measures and the foundation pit monitoring data; and obtaining the retaining wall deformation control measure decision model.

2. The decision-making method for retaining wall deformation control measures based on fault tree analysis according to claim 1, characterized in that, The foundation pit monitoring data includes foundation pit soil parameters, foundation pit geometric parameters, and retaining structure parameters.

3. The decision-making method for retaining wall deformation control measures based on fault tree analysis according to claim 2, characterized in that, The soil parameters of the foundation pit include soil layer thickness, soil layer unit weight, cohesion, internal friction angle, triaxial loading modulus, one-dimensional compression modulus, unloading-heavy load modulus, shear strain corresponding to 70% stiffness, and small strain shear modulus.

4. The decision-making method for retaining wall deformation control measures based on fault tree analysis according to claim 2, characterized in that, The geometric parameters of the foundation pit include the excavation depth, the excavation width, the retaining wall length, the bending stiffness of the retaining structure, and the groundwater depth.

5. The decision-making method for retaining wall deformation control measures based on fault tree analysis according to claim 2, characterized in that, The parameters of the enclosure structure include the axial force of the supports, the lateral spacing of the supports, the axial stiffness of the supports, the bending stiffness of the supports, and the distance of the supports from the ground.

6. The decision-making method for retaining wall deformation control measures based on fault tree analysis according to claim 1, characterized in that, The foundation pit retaining wall deformation accident tree includes top events, intermediate events, and bottom events. The top event is excessive deformation of the foundation pit retaining wall. The intermediate events include multiple events such as retaining wall failure, internal support failure, failure caused by increased groundwater level, failure caused by ineffective water stoppage, and failure caused by soil pressure. The bottom event is the basic event that causes excessive deformation of the foundation pit retaining wall.

7. The decision-making method for retaining wall deformation control measures based on fault tree analysis according to claim 6, characterized in that, The basic events include multiple events such as insufficient embedment depth, excessive loading at the edge, and over-excavation of the foundation pit.

8. The decision-making method for retaining wall deformation control measures based on fault tree analysis according to claim 1, characterized in that, The maximum deformation prediction model for the retaining wall is a BP neural network. The activation function of the BP neural network is a linear rectified function, the loss function is the mean square error, and the optimization function is the adaptive moment estimation.

9. The decision-making method for retaining wall deformation control measures based on fault tree analysis according to claim 1, characterized in that, The deformation control measures include applying a water-stop curtain, dewatering outside the pit, reinforcing the bottom of the pit, unloading soil outside the pit and backfilling soil inside the pit, increasing the stiffness of the supports, adjusting the axial force of the supports, adjusting the spacing of the supports, increasing the bending stiffness of the retaining wall, pouring the bottom slab as early as possible, and removing the surcharge.

10. A decision-making system for retaining wall deformation control measures based on fault tree analysis, characterized in that, include: The retaining wall maximum deformation prediction module is used to take the foundation pit monitoring data as input to the retaining wall maximum deformation prediction model, and obtain the predicted value of the maximum deformation of the retaining wall through the retaining wall maximum deformation prediction model. The retaining wall deformation control measure decision module is used to obtain the retaining wall deformation in real time through the foundation pit monitoring data. When the retaining wall deformation exceeds the maximum predicted value of the retaining wall deformation, the module makes a deformation control scheme decision based on the foundation pit monitoring data and the retaining wall deformation control measure decision model to obtain the retaining wall deformation control measures. The steps for constructing the retaining wall deformation control measure decision model include: summarizing and statistically analyzing the causes and severity of excessive deformation accidents of the retaining wall in the foundation pit based on the case studies; obtaining the probability of each accident tree bottom event in the excessive deformation accident; compiling retaining wall deformation control measures corresponding to the bottom events of the foundation pit retaining wall deformation accident tree based on the foundation pit retaining wall deformation accident tree; establishing the correspondence between the deformation control measures and the input parameters of the maximum deformation prediction model of the retaining wall; and obtaining the retaining wall deformation control measure decision model.

Images