Pile hole model risk assessment method

Abstract

The application provides a pile hole model risk assessment method, which is characterized in that the method comprises the following steps: a target detection model establishment step, in which three-dimensional image data of a pile hole in different states are acquired, and the pile hole data are input into a neural network for training, verification and testing to obtain a target detection model; a pile hole anomaly analysis step, in which the collected pile hole data are used to form a three-dimensional pile hole by means of a 3D construction strategy, the three-dimensional pile hole is input into a preset target detection model to obtain pile abnormal points, and the abnormal points are mapped into the three-dimensional pile hole as a pile hole anomaly graph; an abnormal point analysis step, in which abnormal data and normal data of the abnormal points are obtained by means of an abnormal point analysis strategy, and an abnormal probability is acquired according to the abnormal data and the target detection model; and a scheme correction step, which is used to acquire normal data and abnormal data in the three-dimensional pile hole, and obtain a pile hole adjustment scheme by means of a scheme adjustment strategy according to historical data in the target detection model.

Description

Technical Field

[0001] This invention relates to the technical field of pile hole models, and more specifically to a risk assessment method for pile hole models. Background Technology

[0002] Cast-in-place piles are one of the main forms of foundation structures for railway lines. However, current inspection of cast-in-place pile boreholes is generally carried out after concrete pouring. If the inspection fails, the foundation will be scrapped, resulting in significant waste. Pre-construction inspection would not only guide the construction process but also provide crucial parameters for pile testing. Various techniques exist for pre-construction inspection of cast-in-place piles, including contact and laser ranging methods, leading to a series of borehole testing equipment. Among these, the ultrasonic borehole testing instrument, capable of penetrating turbid mud and water and performing precise non-contact ranging, is widely used in engineering projects. This equipment utilizes two pairs of orthogonally installed ultrasonic ranging sensors to measure the distance to the four walls of the borehole, thus providing a rough estimate of parameters such as borehole diameter and verticality. Currently, even after establishing a pile hole model, it is impossible to assess potential anomalies and risks during actual construction. Summary of the Invention

[0003] In view of the shortcomings of the existing technology, the purpose of this invention is to provide a risk assessment method for pile hole models to overcome the above-mentioned defects in the existing technology.

[0004] To achieve the above objectives, the present invention provides the following technical solution:

[0005] Risk assessment methods for pile hole models, including

[0006] The steps for establishing the target detection model are as follows: acquire 3D image data of pile holes under different conditions, and input them into the neural network according to the pile hole conditions for training, verification and testing to obtain the target detection model;

[0007] The pile hole anomaly analysis steps involve using 3D construction strategies to generate a 3D model of the pile hole from the collected pile hole data, inputting the 3D model into a preset target detection model to obtain pile anomaly points, and mapping the anomaly points into the 3D model of the pile hole as the pile hole anomaly model.

[0008] The anomaly analysis step involves obtaining abnormal and normal data of the anomaly points through anomaly analysis strategies, and obtaining the anomaly probability based on the abnormal data and the target detection model.

[0009] The scheme correction step is used to obtain normal and abnormal data in the 3D image of the pile hole, and to obtain the pile hole adjustment scheme through the scheme adjustment strategy based on the historical data in the target detection model.

[0010] Preferably, the outlier analysis strategy includes a data acquisition step, a data calculation step, and a data evaluation step.

[0011] The data acquisition step is used to acquire a three-dimensional image of the pile hole, and to acquire pile hole data and soil layer data based on the three-dimensional image of the pile hole.

[0012] The data calculation step uses pile hole data and soil layer data to calculate and obtain pile hole bearing capacity and settlement analysis data;

[0013] The data evaluation step involves obtaining normal and abnormal data through anomaly analysis algorithms based on the pile hole bearing capacity and settlement analysis data.

[0014] As a preferred option, the anomaly analysis algorithm includes

[0015] .

[0016]

[0017]

[0018] in, This represents the risk assessment value of outliers. Used to simulate the spatial distribution characteristics of soil layer data, and The standard deviation represents the degree of dispersion in soil layer data. Combining pile hole design parameters and historical maintenance parameters, where n is the number of factors considered. The weight of each parameter, It is the function corresponding to the i-th factor. The threshold is .

[0019] As a preferred embodiment, the proposed adjustment strategy includes analyzing the causes of anomalies based on normal data, abnormal data, and historical data of the anomalies, determining the location and range of the anomalies, generating several adjustment schemes based on the anomaly information and the models in the database, evaluating the generated adjustment schemes, and ranking them in descending order of feasibility.

[0020] Preferably, the evaluation algorithm is as follows:

[0021]

[0022] in and Designed to meet the actual needs of pile hole design parameters, historical data, and anomaly information. and These are the weighting coefficients. For the discovery and evaluation of pile hole design parameters, historical data, and anomaly information, Is with The corresponding weighting coefficients are: n represents the factors to be considered; G represents soil layer information; P represents pile hole design parameters; M represents historical data; A represents the range of abnormal point location data; and R represents risk, etc.

[0023] Preferably, the scheme adjustment strategy also includes a verification sub-strategy, which includes a simulation model. Appropriate convenience conditions are applied to the simulation model, and numerical analysis methods are used to test the model, calculate the stress on the pile hole, obtain the model feasibility value from the calculation results, and select a suitable adjustment scheme based on the magnitude of the feasibility value.

[0024] Preferably, the 3D component strategy includes:

[0025] Data input is used to input relevant parameters of the pile hole, including pile diameter, pile length, pile type, and soil layer parameters, etc.

[0026] Data processing is used to process the input pile hole parameters and generate and output a 3D model of the pile hole using a 3D rendering strategy.

[0027] Preferably, the 3D rendering strategy includes:

[0028] Generate point cloud data representing the stake points and divide the space;

[0029] The points in the point cloud are processed to remove outliers, and the point cloud data is projected onto a two-dimensional screen.

[0030] Rendering is performed using the graphics rendering pipeline, vertex data is processed using the vertex shader, fragment color is processed using the fragment shader, vertex data is converted into pixels on the screen through rasterization, visibility is handled through depth testing, and the nearest pixel is rendered.

[0031] The beneficial effects of this invention are as follows: After the three-dimensional pile hole diagram component is completed, the target detection model is used to detect abnormal points in the three-dimensional pile hole diagram. By using the normal data and abnormal data of the abnormal points, the risk status of the abnormal points is judged. Combined with historical data, the adjustment plan for the abnormal points is determined. Based on the adjustment plan, the adjustment plan is evaluated and the optimal adjustment plan is determined. Attached Figure Description

[0032] Figure 1 This is the control flowchart of the present invention. Detailed Implementation

[0033] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0034] It should be noted that when a component is described as "fixed to" another component, it can be directly on the other component or may have a component in between. When a component is considered "connected to" another component, it can be directly connected to the other component or may have a component in between. When a component is considered "set on" another component, it can be directly set on the other component or may have a component in between. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0035] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0036] The embodiments of the present invention will be further described in detail below with reference to the accompanying drawings:

[0037] Risk assessment methods for pile hole models, including

[0038] The steps for establishing the target detection model are as follows: 1. Acquire 3D image data of pile holes under different conditions. 2. Input the data into a neural network for training, validation, and testing based on the pile hole conditions to obtain the target detection model. 3. Collect a large amount of 3D image data of pile holes under different conditions to ensure that the data covers both normal and abnormal situations. 4. Preprocess the collected data, including denoising and contrast enhancement. 5. Input the preprocessed data into the neural network for training. 6. Adjust the network parameters so that the model can accurately identify targets in the pile hole, such as the pile body and soil layers. 7. Use an independent validation set and real-world testing to validate and test the model to ensure its accuracy.

[0039] The pile hole anomaly analysis steps involve using a 3D construction strategy to construct a 3D model of the pile hole from the collected pile hole data. This 3D model is then input into a preset target detection model to obtain pile anomaly points, which are then mapped onto the 3D model to form the pile hole anomaly map. The 3D component strategy is used to construct a 3D image from the collected pile hole data. This constructed 3D image is then input into a preset target detection model. The target detection model calculates and identifies anomaly points in the pile hole, which are then mapped onto the 3D image to form pile hole anomaly points, facilitating more intuitive observation and analysis.

[0040] The anomaly analysis process involves several steps: First, anomaly data and normal data are identified using anomaly analysis strategies. Anomaly probabilities are then calculated based on the anomaly data and the target detection model. The anomaly dataset is collected and preprocessed. The data is then analyzed according to the anomaly analysis strategy. Depending on the specific requirements of the strategy and the characteristics of the data, parameters or thresholds may need to be adjusted to optimize the anomaly detection effect. The characteristics of anomalies are compared with those of normal data points to verify whether they are true anomalies. Finally, the target detection model accurately identifies anomalies and normal data points and provides corresponding predicted probabilities. The collected anomaly data is then input into the target detection model for aggregation. Based on the characteristics of the input data and the calculation principles of the target detection algorithm, the anomaly probability of each anomaly is output.

[0041] Anomaly analysis strategies include data acquisition steps, data calculation steps, and data evaluation steps.

[0042] The data acquisition step is used to obtain a three-dimensional image of the pile hole, and to obtain pile hole data and soil layer data based on the three-dimensional image of the pile hole. The three-dimensional image of the pile hole in the pile hole anomaly analysis step is obtained, and the specific location, shape and size of the pile hole can be extracted from the three-dimensional image of the pile hole. Soil layer data is also extracted, including soil layer type, thickness, physical properties, etc.

[0043] The data calculation steps involve using pile hole data and soil layer data to calculate and obtain pile hole bearing capacity and settlement analysis data. Based on the pile hole data and soil layer data, the bearing capacity of the pile hole is calculated. The pile hole bearing capacity is a key indicator for evaluating the stability of the pile hole. Combined with the settlement prediction model, the settlement of the pile hole and the surrounding soil layer is collected and distributed.

[0044] The data evaluation process involves using anomaly analysis algorithms to identify normal and abnormal data based on the pile borehole bearing capacity and settlement analysis data. Normal data should conform to the expected pile borehole bearing capacity and settlement range, while abnormal data may exceed these ranges. The severity and impact of the anomalies are then assessed.

[0045] Anomaly analysis algorithms include

[0046] .

[0047]

[0048]

[0049] in, This represents the risk assessment value of outliers. Used to simulate the spatial distribution characteristics of soil layer data, and The standard deviation represents the degree of dispersion in soil layer data. Combining pile hole design parameters and historical maintenance parameters, where n is the number of factors considered. The weight of each parameter, It is the function corresponding to the i-th factor. The threshold is The system uses a risk assessment algorithm to assess the risk of outliers, determine the risk coefficient of outliers, and preset a risk threshold. When the risk assessment value is greater than the risk threshold, it is judged as dangerous data.

[0050] The scheme correction step is used to acquire normal and abnormal data in the 3D image of the pile hole, and obtain the pile hole adjustment scheme through the scheme adjustment strategy based on the historical data in the target detection model. Data is extracted from the 3D image of the pile hole, including key data such as depth, diameter, and shape. The controlled 3D data is divided into normal and abnormal data according to the anomaly analysis algorithm. Anomaly detection of the pile hole data is performed based on deep learning, and anomaly points are automatically identified. The identified anomaly points can be manually reviewed to ensure the accuracy of anomaly detection. Historical data similar to the current pile hole is obtained from the historical database of the target detection model. The processing methods and effects of anomaly points in the historical data are analyzed, and a reference is provided for the current user processing.

[0051] The adjustment strategy involves analyzing the causes of anomalies based on normal, abnormal, and historical data of anomalies, determining the location and extent of anomalies, and generating several adjustment plans based on anomaly information and models in the database. These plans are then evaluated and ranked from highest to lowest feasibility. The analysis of anomaly causes, such as changes in geological conditions and construction errors, is conducted using spatial analysis and data processing techniques to accurately determine the location and extent of anomalies. Combined with data from the database, several feasible adjustment plans are generated, including adjustment methods such as grouting reinforcement and borehole enlargement, as well as adjustment parameters such as grouting volume and borehole diameter. The generated adjustment plans are evaluated using an evaluation algorithm, and based on the evaluation results, they are ranked from highest to lowest. The optimal plan is then selected and implemented.

[0052] The evaluation algorithm is as follows:

[0053]

[0054] in and Designed to meet the actual needs of pile hole design parameters, historical data, and anomaly information. and These are the weighting coefficients. For the discovery and evaluation of pile hole design parameters, historical data, and anomaly information, Is with The corresponding weighting coefficients are: n represents the factors to be considered; G represents soil layer information; P represents pile hole design parameters; M represents historical data; A represents the range of abnormal point location data; and R represents the risk level. The higher the value of R, the higher the risk.

[0055] The scheme adjustment strategy also includes a verification sub-strategy. This sub-strategy includes a simulation model, to which appropriate conditions are applied, and numerical analysis methods are used to test the model, calculate the stress on the pile hole, and obtain the model's feasibility value. Based on the feasibility value, suitable adjustment schemes are selected. Within the verification sub-strategy, a high-precision three-dimensional simulation model of the component is created based on the actual dimensions of the pile hole, geological conditions, construction parameters, etc. Conditions consistent with actual conditions, such as boundary constraints and load conditions, are applied to the simulation model. These data, based on engineering experience and actual data, ensure the accuracy and reliability of the simulation results. Appropriate vertical analysis methods, such as the finite element method and finite difference method, are selected to monitor the simulation model. Numerical analysis algorithms accurately calculate the stress on the pile hole, including key data such as stress, strain, and displacement. The stress on the pile hole under different adjustment conditions is calculated and analyzed. Based on the calculation results, the model's feasibility value, such as the safety factor and stability index, is calculated. Based on the feasibility value, the generated adjustment schemes are selected, with the scheme having the highest feasibility value being implemented first.

[0056] 3D component strategies include:

[0057] Data input is used to input relevant parameters of the pile hole, including pile diameter, pile length, pile type, and soil parameters such as soil type, density, and bearing capacity.

[0058] Data processing is used to process the input pile hole parameters, generate and output a 3D model of the pile hole using a 3D rendering strategy, and process the input pile hole adoption number, such as data verification and unit conversion, and generate a 3D model of the pile hole using a 3D rendering strategy.

[0059] 3D rendering strategies include:

[0060] Generate point cloud data representing pile points and divide the space. Based on the parameters of the pile hole, generate point cloud data representing each part of the pile hole and divide the three-dimensional space into multiple small regions to facilitate subsequent point cloud processing and rendering.

[0061] The points in the point cloud are processed to remove outliers, and the point cloud data is projected onto a 2D screen. The algorithm identifies and extracts outliers in the point cloud, such as noise and outliers, and projects the processed point cloud data onto a 2D screen to prepare for subsequent graphics rendering.

[0062] Rendering is performed using the graphics rendering pipeline. Vertex shaders process vertex data, fragment shaders process fragment colors, rasterization converts vertex data into pixels on the screen, and depth testing handles visibility. The nearest pixel is then rendered. The graphics rendering pipeline handles vertex processing, fragment processing, rasterization, and depth testing. Vertex color matching is used to process vertex data, such as position, color, and texture group tables. Fragment shaders process fragment colors, such as calculating the final color based on lighting and materials. Vertex data is rasterized into pixels on the screen, and depth testing and visibility handling ensure that the nearest pixel is rendered.

[0063] The above are merely preferred embodiments of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principle of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A risk assessment method for pile hole models, characterized in that, include The steps for establishing the target detection model are as follows: acquire 3D image data of pile holes under different conditions, and input them into the neural network according to the pile hole conditions for training, verification and testing to obtain the target detection model; The pile hole anomaly analysis steps involve using a 3D construction strategy to build a three-dimensional pile hole map from the collected pile hole data, inputting the three-dimensional pile hole map into a preset target detection model to obtain pile anomaly points, and mapping the anomaly points into the three-dimensional pile hole map to obtain the pile hole anomaly map. The anomaly analysis step involves obtaining abnormal and normal data of the anomaly points through anomaly analysis strategies, and obtaining the anomaly probability based on the abnormal data and the target detection model. The anomaly analysis strategy includes data acquisition steps, data calculation steps, and data evaluation steps. The data acquisition step is used to acquire a three-dimensional image of the pile hole, and to acquire pile hole data and soil layer data based on the three-dimensional image of the pile hole. The data calculation step uses pile hole data and soil layer data to calculate and obtain pile hole bearing capacity and settlement analysis data; The data evaluation step involves obtaining normal and abnormal data through an anomaly analysis algorithm based on the pile hole bearing capacity and settlement analysis data. The scheme correction step is used to obtain normal and abnormal data in the 3D image of the pile hole, and to obtain the pile hole adjustment scheme through the scheme adjustment strategy based on the historical data in the target detection model. The adjustment strategy includes analyzing the causes of anomalies based on normal data, abnormal data, and historical data of anomalies, determining the location and scope of anomalies, generating adjustment plans based on anomaly information and models in the database, evaluating the generated adjustment plans using an evaluation algorithm, and ranking them from highest to lowest feasibility.

2. The risk assessment method for pile hole models according to claim 1, characterized in that, Anomaly analysis algorithms include in, This represents the risk assessment value of outliers. Used to simulate the spatial distribution characteristics of soil layer data, and The standard deviation represents the degree of dispersion in soil layer data. Combining pile hole design parameters and historical maintenance parameters, where n is the number of factors considered. The weight of each parameter, It is the function corresponding to the i-th factor. The threshold is .

3. The risk assessment method for pile hole models according to claim 1, characterized in that, The evaluation algorithm is as follows: in and Designed to meet the actual needs of pile hole design parameters, historical data, and anomaly information. and These are the weighting coefficients. For the discovery and evaluation of pile hole design parameters, historical data, and anomaly information, Is with The corresponding weighting coefficients are: n represents the factors to be considered, G represents soil layer information, P represents pile hole design parameters, M represents historical data, A represents the range of abnormal point location data, and R represents the risk level.

4. The risk assessment method for pile hole models according to claim 1, characterized in that, The proposed adjustment strategy also includes a verification sub-strategy, which includes a simulation model. Appropriate convenience conditions are applied to the simulation model, and numerical analysis methods are used to test the model, calculate the stress on the pile hole, obtain the model's feasibility value from the calculation results, and select a suitable adjustment scheme based on the magnitude of the feasibility value.

5. The risk assessment method for pile hole models according to claim 1, characterized in that, The 3D construction strategy includes: Data input is used to input relevant parameters of the pile hole, including pile diameter, pile length, pile type, and soil layer parameters, etc. Data processing is used to process the input pile hole parameters and generate and output a 3D model of the pile hole using a 3D rendering strategy.

6. The risk assessment method for pile hole models according to claim 1, characterized in that, The 3D rendering strategy includes: Generate point cloud data representing the stake points and divide the space; The points in the point cloud are processed to remove outliers, and the point cloud data is projected onto a two-dimensional screen. Rendering is performed using the graphics rendering pipeline, vertex data is processed using the vertex shader, fragment color is processed using the fragment shader, vertex data is converted into pixels on the screen through rasterization, visibility is handled through depth testing, and the nearest pixel is rendered.

Images