Blockage prediction method and system based on shield mud cake determination graph, and terminal

Abstract

The invention discloses a blocking prediction method, system and terminal based on a shield mud cake determination graph, and the method comprises the steps: obtaining a target shield mud cake determination graph, carrying out the mathematical modeling, and generating a two-dimensional coordinate space; calculating the area proportion of each risk area in the target shield mud cake determination graph, and generating a plurality of sample points in the two-dimensional coordinate space according to all the area proportions; generating a sample point label assignment requirement according to the target shield mud cake determination graph, dividing a classification label for each sample point according to the sample point label assignment requirement, generating sample data, and training a target model according to the sample data; when real-time blockage prediction is carried out, the liquid limit, the plastic limit and the moisture content of the muck in the target environment are obtained, preprocessing is carried out, the muck is input into the trained target model, and a blockage prediction classification label is output. According to the method, the data for training the model for identifying the mud cake risk of the shield tunneling machine can be obtained, so that the model is trained to predict the mud cake risk of the shield tunneling machine.

Description

Technical Field

[0001] The present invention relates to a data generation and processing method, and in particular to a blockage prediction method, system, terminal and computer-readable storage medium based on a shield mud cake determination diagram. Background Art

[0002] In engineering practice, many key empirical knowledge are usually stored in the form of analytical expressions and diagrams. The empirical formulas, empirical diagrams and classification standards commonly used in engineering design are convenient for intuitive presentation and quick reference, but due to the limitations of their form, the knowledge contained has not been fully utilized, which limits their application in intelligent analysis and data-driven models.

[0003] In current projects, shield tunneling is a major construction method widely used in tunnel construction. During the construction process, the "mud cake" problem is one of the common and important problems in shield tunneling. Its formation may lead to reduced tunneling efficiency and increased cutterhead wear, and even cause serious consequences such as construction interruption. Therefore, accurately predicting the risk of mud cake is crucial to ensuring the efficiency and safety of shield construction.

[0004] However, the current lack of samples in predicting mud cake risks leads to inaccurate predictions, which affects the safety of shield construction.

[0005] Therefore, the prior art still needs to be improved and developed. Summary of the invention

[0006] The main purpose of the present invention is to provide a blockage prediction method, system, terminal and computer-readable storage medium based on a shield mud cake determination diagram, aiming to solve the problem in the prior art that when predicting mud cake risks, the lack of samples leads to inaccurate predictions, affecting the safety of shield construction.

[0007] To achieve the above object, the present invention provides a blockage prediction method based on a shield mud cake determination diagram, and the blockage prediction method based on a shield mud cake determination diagram comprises the following steps: Obtaining a target shield structure mud cake determination diagram, performing mathematical modeling on the target shield structure mud cake determination diagram, and generating a two-dimensional coordinate space; Calculate the area ratio of each risk area in the target shield mud cake determination map, and generate multiple sample points in the two-dimensional coordinate space according to all the area ratios; Generate sample point label assignment requirements according to the target shield mud cake determination map, assign corresponding classification labels to each sample point according to the sample point label assignment requirements, generate sample data, train a target model according to the sample data, and obtain a trained target model; When performing real-time blockage prediction, the liquid limit, plastic limit and moisture content of the slag in the target environment are obtained, and after preprocessing the liquid limit, plastic limit and moisture content of the slag in the target environment, they are input into the trained target model for processing, and the blockage prediction classification label is output.

[0008] Optionally, the step of obtaining a target shield structure mud cake determination diagram, performing mathematical modeling on the target shield structure mud cake determination diagram, and generating a two-dimensional coordinate space specifically includes: Obtain the target shield structure mud cake determination diagram; Extracting the numerical range of the difference between the plastic limit and the water content and the numerical range of the difference between the liquid limit and the water content in the target shield mud cake determination diagram; The numerical boundary is determined according to the corresponding numerical range, and the two-dimensional coordinate space is generated according to the numerical boundary.

[0009] Optionally, the calculating the area ratio of each risk area in the target shield structure mud cake determination map and generating a plurality of sample points in the two-dimensional coordinate space according to all the area ratios specifically includes: According to the target shield mud cake, the scope of each risk area in the determination map is calculated, and the area ratio of each risk area is calculated; The total number of preset sample points is obtained, and according to all the area ratios, a scattering method is used to generate a preset number of sample points in the two-dimensional coordinate space.

[0010] Optionally, generating sample point label assignment requirements according to the target shield structure mud cake determination diagram specifically includes: Assigning values ​​to the target shield mud cake determination diagram according to the two-dimensional coordinate space, and constructing a mathematical expression of the boundary of each risk area; According to each of the mathematical expressions, the coordinate relationship of the points in each risk area is calculated, and according to each of the coordinate relationships, the label assignment requirements of the sample points are generated.

[0011] Optionally, the step of assigning a corresponding classification label to each of the sample points according to the sample point label assignment requirement, generating sample data, and training a target model according to the sample data to obtain a trained target model specifically includes: Obtaining the coordinates of each of the sample points in the two-dimensional coordinate space, and assigning a corresponding classification label to each of the sample points according to the coordinates of each of the sample points and the sample point label assignment requirements; Sample data is generated according to the classification label and the coordinates of each sample point, and a target model is trained according to the sample data to obtain a trained target model.

[0012] Optionally, generating sample data according to the classification label and the coordinates of each sample point, and training a target model according to the sample data to obtain a trained target model specifically includes: Generate multiple groups of data according to the classification label and the coordinates of each sample point, and aggregate all the data to obtain the sample data; The coordinates of each group of data in the sample data are input into the target model, and the target model is optimized according to the output of the target model and the classification label of each group of data. When the training conditions are met, the training is terminated and the trained target model is obtained.

[0013] Optionally, when performing real-time blockage prediction, the liquid limit, plastic limit and moisture content of the slag in the target environment are obtained, and the liquid limit, plastic limit and moisture content of the slag in the target environment are pre-processed and input into the trained target model for processing, and the blockage prediction classification label is output, which specifically includes: When performing real-time blockage prediction, the liquid limit, plastic limit and water content of the slag in the target environment are obtained, and the difference between the current liquid limit and water content is calculated according to the liquid limit and water content of the slag in the target environment, and the difference between the current plastic limit and water content is calculated according to the plastic limit and water content of the slag in the target environment; Generate current coordinates according to the difference between the current liquid limit and the water content and the difference between the current plastic limit and the water content; The current coordinates are input into the trained target model, and a blockage prediction classification label is output.

[0014] In addition, to achieve the above-mentioned purpose, the present invention further provides a congestion prediction system based on a shield mud cake determination diagram, wherein the congestion prediction system based on a shield mud cake determination diagram comprises: A two-dimensional coordinate space generation module is used to obtain a target shield structure mud cake determination diagram, perform mathematical modeling on the target shield structure mud cake determination diagram, and generate a two-dimensional coordinate space; A sample point generation module, used to calculate the area ratio of each risk area in the target shield mud cake determination map, and generate multiple sample points in the two-dimensional coordinate space according to all the area ratios; A training module is used to generate sample point label assignment requirements according to the target shield mud cake determination map, assign corresponding classification labels to each sample point according to the sample point label assignment requirements, generate sample data, train a target model according to the sample data, and obtain a trained target model; The application module is used to obtain the liquid limit, plastic limit and moisture content of the slag in the target environment when performing real-time blockage prediction, and after pre-processing the liquid limit, plastic limit and moisture content of the slag in the target environment, input them into the trained target model for processing, and output the blockage prediction classification label.

[0015] In addition, to achieve the above-mentioned purpose, the present invention also provides a terminal, wherein the terminal includes: a memory, a processor, and a congestion prediction program based on a shield structure mud cake determination map stored in the memory and executable on the processor, wherein the congestion prediction program based on a shield structure mud cake determination map implements the steps of the congestion prediction method based on a shield structure mud cake determination map as described above when executed by the processor.

[0016] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a congestion prediction program based on a shield mud cake determination map, and when the congestion prediction program based on a shield mud cake determination map is executed by a processor, the steps of the congestion prediction method based on a shield mud cake determination map as described above are implemented.

[0017] In the present invention, a target shield structure mud cake determination map is obtained, mathematical modeling is performed on the target shield structure mud cake determination map, and a two-dimensional coordinate space is generated; the area ratio of each risk area in the target shield structure mud cake determination map is calculated, and multiple sample points are generated in the two-dimensional coordinate space according to all the area ratios; sample point label assignment requirements are generated according to the target shield structure mud cake determination map, and corresponding classification labels are assigned to each sample point according to the sample point label assignment requirements, and sample data is generated, and a target model is trained according to the sample data to obtain a trained target model; when performing real-time blockage prediction, the liquid limit, plastic limit and moisture content of the slag in the target environment are obtained, and the liquid limit, plastic limit and moisture content of the slag in the target environment are pre-processed and then input into the trained target model for processing, and a blockage prediction classification label is output. The present invention converts the knowledge in the shield mud cake judgment diagram into data form, and can construct a large amount of mud cake sample data with low-fidelity characteristics based on the diagram. These data are used as a quantitative expression of empirical knowledge to make up for the problem of insufficient mud cake samples in actual engineering, thereby significantly improving the quantity and quality of the mud cake sample database, and correspondingly training a mud cake risk prediction model with higher prediction accuracy, that is, the trained target model, to predict the shield mud cake risk and ensure the safety of shield construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flow chart of a preferred embodiment of the blockage prediction method based on the shield mud cake determination diagram of the present invention; Figure 2 It is a schematic diagram of a shield mud cake determination diagram in a blockage prediction method based on a shield mud cake determination diagram of the present invention; Figure 3 It is a schematic diagram of sample point distribution in a two-dimensional coordinate space in a blockage prediction method based on a shield mud cake determination diagram of the present invention; Figure 4 It is a flow chart of a method for predicting blockage based on a shield mud cake determination diagram of the present invention; Figure 5 It is a structural diagram of a preferred embodiment of a blockage prediction system based on a shield mud cake determination diagram of the present invention; Figure 6 It is a structural diagram of a preferred embodiment of the terminal of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0020] In engineering practice, many key empirical knowledge are usually stored in the form of analytical expressions, charts, etc. The empirical formulas, empirical charts and classification standards commonly used in engineering design are convenient for intuitive presentation and quick reference. However, due to the limitations of their form, the knowledge contained has not been fully utilized, which limits their application in intelligent analysis and data-driven models. In current projects, shield tunneling is a major construction method widely used in tunnel construction. During the construction process, the "mud cake" problem is one of the common and important problems in shield tunneling. Its formation may lead to reduced tunneling efficiency, increased cutterhead wear, and even cause serious consequences such as construction interruption. Therefore, accurately predicting the risk of mud cake is crucial to ensuring the efficiency and safety of shield construction. However, when predicting the risk of mud cake based on transfer learning or multi-fidelity modeling methods, it is impossible to combine the knowledge in the empirical chart, resulting in a lack of samples, which limits the performance of the model, and therefore it is impossible to accurately predict the risk of shield mud cake.

[0021] In response to one or more of the above problems, the present invention obtains a target shield structure mud cake determination map, mathematically models the target shield structure mud cake determination map, and generates a two-dimensional coordinate space; calculates the area ratio of each risk area in the target shield structure mud cake determination map, and generates multiple sample points in the two-dimensional coordinate space according to all the area ratios; generates sample point label assignment requirements according to the target shield structure mud cake determination map, assigns corresponding classification labels to each sample point according to the sample point label assignment requirements, generates sample data, trains a target model according to the sample data, and obtains a trained target model; when performing real-time blockage prediction, obtains the liquid limit, plastic limit and moisture content of the slag in the target environment, and pre-processes the liquid limit, plastic limit and moisture content of the slag in the target environment, and then inputs them into the trained target model for processing, and outputs a blockage prediction classification label.

[0022] The blocking prediction method based on the shield mud cake determination diagram described in the preferred embodiment of the present invention is as follows: Figure 1As shown, the blockage prediction method based on the shield mud cake determination diagram includes the following steps: Step S10, obtaining a target shield structure mud cake determination diagram, performing mathematical modeling on the target shield structure mud cake determination diagram, and generating a two-dimensional coordinate space.

[0023] It should be noted that the shield mud cake determination diagram in the present invention is an empirical diagram for determining the risk of mud cake in shield construction. Figure 2 As shown in the figure, it is a shield mud cake judgment diagram, which uses the difference between the plastic limit and the water content (WP-Wn) and the difference between the liquid limit and the water content (WL-Wn) as the coordinate axes, and classifies different slag conditions through consistency index, where the consistency index used is the viscosity index (Ic) of the soil, where Ip in the figure represents the plasticity index of the soil. Through the target shield mud cake judgment diagram, a two-dimensional coordinate space is generated accordingly.

[0024] Further, the obtaining of the target shield structure mud cake determination diagram, mathematical modeling of the target shield structure mud cake determination diagram, and generation of a two-dimensional coordinate space specifically include: Obtain the target shield structure mud cake determination diagram; Extracting the numerical range of the difference between the plastic limit and the water content and the numerical range of the difference between the liquid limit and the water content in the target shield mud cake determination diagram; The numerical boundary is determined according to the corresponding numerical range, and the two-dimensional coordinate space is generated according to the numerical boundary.

[0025] Specifically, in the present invention, after obtaining the target shield structure mud cake determination diagram, the axis information presented in the target shield structure mud cake determination diagram is converted into a clear numerical range and scale, and the numerical ranges of the horizontal axis (difference between plastic limit and water content) and the vertical axis (difference between liquid limit and water content) in the target shield structure mud cake determination diagram are quantified to obtain a numerical range; Figure 2 As shown, the corresponding horizontal axis range is [-160%, 50%], and the vertical axis range is [-20%, 200%]. According to the obtained numerical range, the maximum and minimum values ​​of the difference between the plastic limit and the water content are determined, and this range is used as the numerical boundary of the horizontal axis; the maximum and minimum values ​​representing the difference between the liquid limit and the water content are determined, and this range is used as the numerical boundary of the vertical axis. A two-dimensional coordinate space is generated by the corresponding numerical boundaries. The two-dimensional coordinate space is a plane space composed of the horizontal coordinate, the vertical coordinate and the numerical boundary, in which the horizontal axis and the vertical axis are the difference between the plastic limit and the water content and the difference between the liquid limit and the water content, respectively.

[0026] It should be noted that for soil, the liquid limit and plastic limit are different moisture content stages of the soil, and the liquid limit moisture content is greater than the plastic limit moisture content, so the ordinates of all sample points generated later are greater than the abscissa.

[0027] Step S20, calculating the area ratio of each risk area in the target shield structure mud cake determination map, and generating a plurality of sample points in the two-dimensional coordinate space according to all the area ratios.

[0028] Specifically, in the present invention, the area of ​​each risk region in the target shield mud cake determination map is obtained, so that the corresponding point scattering method is used to generate sample points, and the corresponding sample data is constructed through the sample points.

[0029] Further, the calculating the area ratio of each risk area in the target shield mud cake determination map and generating a plurality of sample points in the two-dimensional coordinate space according to all the area ratios specifically includes: According to the target shield mud cake, the scope of each risk area in the determination map is calculated, and the area ratio of each risk area is calculated; The total number of preset sample points is obtained, and according to all the area ratios, a scattering method is used to generate a preset number of sample points in the two-dimensional coordinate space.

[0030] Specifically, in the target shield mud cake determination map, there are five risk areas, namely: well-dispersed area, slightly blocked area, severely blocked area, moderately blocked area and agglomerated area. The corresponding area ratio is calculated according to the range of each risk area. Figure 2 As shown, in Figure 2 In the shield mud cake determination diagram, the area of ​​each risk area is calculated, and the area of ​​the well-dispersed area can be obtained as follows: ; The area of ​​the slightly blocked area is: ; The area of ​​moderate congestion is: ; The area of ​​the united block region is: ; The area of ​​serious congestion is: ; The area ratio of each risk area can be obtained from the area correspondence, and then the total number of preset sample points is set, and the preset number of sample points is generated in the two-dimensional coordinate space according to the area ratio of the corresponding five risk areas, wherein the present invention adopts the scattering method to randomly generate sample points. That is, in the present invention, the preset number of sample points is randomly generated in the two-dimensional coordinate space according to the area ratio by scattering method, and the coordinate value of each sample point in the two-dimensional coordinate space is generated by a random function, and the random function is a standard uniform distribution pseudo-random number generator, wherein the random number generator is a general term, which can include two types: true random number generator and pseudo-random number generator. In one embodiment of the present invention, the preferred pseudo-random number generator is used, which generates a numerical sequence with random statistical characteristics through an algorithm, but its generation process is deterministic; compared with the pseudo-random number generator, the true random number generator relies on physical phenomena to generate numerical values ​​and has true randomness.

[0031] exist Figure 2 In , the area ratios of the corresponding five risk areas are 30:128:144.8:66.67: 87.5, so the corresponding sample points are generated in the two-dimensional coordinate space, such as Figure 3 As shown, when the total number of preset sample points is set to 10,000, the number of samples that should be generated in each area is 656, 2801, 3169, 1459 and 1915 respectively.

[0032] Step S30, generating sample point label assignment requirements according to the target shield mud cake determination map, assigning corresponding classification labels to each sample point according to the sample point label assignment requirements, generating sample data, training a target model according to the sample data, and obtaining a trained target model.

[0033] Specifically, in the present invention, after obtaining the sample points, a corresponding label is generated for each sample point, wherein the label of each sample point is one of well-dispersed, slightly blocked, severely blocked, moderately blocked, and agglomerated.

[0034] Furthermore, the generation of sample point label assignment requirements according to the target shield mud cake determination diagram specifically includes: Assigning values ​​to the target shield mud cake determination diagram according to the two-dimensional coordinate space, and constructing a mathematical expression of the boundary of each risk area; According to each of the mathematical expressions, the coordinate relationship of the points in each risk area is calculated, and according to each of the coordinate relationships, the label assignment requirements of the sample points are generated.

[0035] Specifically, in the present invention, in the two-dimensional coordinate space, each sample point can be represented by a specific numerical value (x, y), so that each region and boundary condition in the two-dimensional coordinate space can be described and sampled by a numerical method, wherein x represents the horizontal axis of the two-dimensional coordinate space, and y represents the vertical axis of the two-dimensional coordinate space. The boundary of each risk region is the boundary line of the viscosity index Ic. Figure 3 It can be expressed as mathematical expressions such as y=0%, y=-x, y=-3x and x=0%.

[0036] The conditions that the sample points in each risk area need to meet, i.e. the coordinate relationship, can be obtained through the corresponding mathematical expression.

[0037] like Figure 3 As shown, in Figure 3 The corresponding coordinate relationship is the sample point position in Table 1. The labels corresponding to each coordinate range can be divided according to the coordinate relationship.

[0038] Table 1: Sample point label assignment requirements

[0039] Table 1 can be used to Figure 3 The classification labels corresponding to the sample points in .

[0040] Furthermore, according to the sample point label assignment requirements, a corresponding classification label is assigned to each sample point, sample data is generated, and a target model is trained according to the sample data to obtain a trained target model, which specifically includes: Obtaining the coordinates of each of the sample points in the two-dimensional coordinate space, and assigning a corresponding classification label to each of the sample points according to the coordinates of each of the sample points and the sample point label assignment requirements; Sample data is generated according to the classification label and the coordinates of each sample point, and a target model is trained according to the sample data to obtain a trained target model.

[0041] Specifically, after obtaining the sample point label assignment requirements, each sample point can be assigned a classification label according to the coordinates of each sample point in the two-dimensional coordinate space, and sample data can be generated through the classification label and the corresponding coordinates.

[0042] Furthermore, generating sample data according to the classification label and the coordinates of each sample point, and training a target model according to the sample data to obtain a trained target model specifically includes: Generate multiple groups of data according to the classification label and the coordinates of each sample point, and aggregate all the data to obtain the sample data; The coordinates of each group of data in the sample data are input into the target model, and the target model is optimized according to the output of the target model and the classification label of each group of data. When the training conditions are met, the training is terminated and the trained target model is obtained.

[0043] Specifically, a set of data can be generated according to the classification label and coordinates of each sample point, and all the data can be aggregated to obtain sample data, and the sample data is used to train the target model. Among them, the target model is a model that can perform transfer learning or multi-fidelity modeling methods.

[0044] During the training process, the coordinates are input into the model, and the classification labels of the data in the sample data are compared with the model output to optimize the model parameters. When the training reaches the training conditions, the training ends and the trained target model is obtained. The training conditions are that the model accuracy meets the requirements or the model training times reach the preset training times.

[0045] In one embodiment of the present invention, a neural network can be trained based on sample data, and model hyperparameters can be found through Bayesian optimization. The structure of the model is set to a framework of 2 (input features, liquid limit-water content and plastic limit-water content) × 16 × 32 × 1 (blockage prediction classification label), and the learning rate is 0.001 to obtain a trained target model.

[0046] Step S40: When performing real-time blockage prediction, the liquid limit, plastic limit and moisture content of the slag in the target environment are obtained, and after pre-processing the liquid limit, plastic limit and moisture content of the slag in the target environment, they are input into the trained target model for processing, and the blockage prediction classification label is output.

[0047] Specifically, in the present invention, when the trained target model is obtained, in addition to being applied in actual working conditions, for engineering design optimization, the changing trend of mud cake blockage risk can be predicted by simulating different construction parameter combinations (such as shield machine operating parameters, construction processes, etc.) during the design stage. Based on the risk assessment results, the lowest risk and most efficient solution can be quickly screened out, realizing the organic combination of design and risk management, and improving engineering safety and economic benefits.

[0048] Furthermore, when performing real-time blockage prediction, the liquid limit, plastic limit and moisture content of the slag in the target environment are obtained, and the liquid limit, plastic limit and moisture content of the slag in the target environment are pre-processed and input into the trained target model for processing, and the blockage prediction classification label is output, which specifically includes: When performing real-time blockage prediction, the liquid limit, plastic limit and water content of the slag in the target environment are obtained, and the difference between the current liquid limit and water content is calculated according to the liquid limit and water content of the slag in the target environment, and the difference between the current plastic limit and water content is calculated according to the plastic limit and water content of the slag in the target environment; Generate current coordinates according to the difference between the current liquid limit and the water content and the difference between the current plastic limit and the water content; The current coordinates are input into the trained target model, and a blockage prediction classification label is output.

[0049] Specifically, in the present invention, in actual working conditions, the liquid limit, plastic limit and moisture content of the slag in the target environment are obtained, and the difference between the current liquid limit and moisture content is calculated according to the liquid limit and moisture content, and the difference between the current plastic limit and moisture content is calculated according to the plastic limit and moisture content, which are then input into the target model as coordinates. The model can then use the information of the target shield mud cake judgment diagram absorbed during training to directly output classification labels and realize real-time risk assessment.

[0050] Furthermore, in the present invention, by Figure 4 The process of the present invention is further described. In the present invention, mathematical modeling is first performed for the target shield mud cake determination diagram, and then the coordinate axis range of the diagram is extracted to determine the boundary conditions, and then sample points are generated. After the classification label is determined for each sample point, data structuring processing is performed, that is, sample data is obtained to train the corresponding target model to realize mud cake risk prediction in actual working conditions.

[0051] The present invention obtains a target shield structure mud cake determination map, mathematically models the target shield structure mud cake determination map, and generates a two-dimensional coordinate space; calculates the area ratio of each risk area in the target shield structure mud cake determination map, and generates multiple sample points in the two-dimensional coordinate space according to all the area ratios; generates sample point label assignment requirements according to the target shield structure mud cake determination map, assigns corresponding classification labels to each sample point according to the sample point label assignment requirements, generates sample data, trains a target model according to the sample data, and obtains a trained target model; when performing real-time blockage prediction, obtains the liquid limit, plastic limit and moisture content of the slag in the target environment, and pre-processes the liquid limit, plastic limit and moisture content of the slag in the target environment, and then inputs them into the trained target model for processing, and outputs a blockage prediction classification label. The present invention converts the knowledge in the shield mud cake judgment diagram into data form, and can construct a large amount of mud cake sample data with low-fidelity characteristics based on the diagram. These data are used as a quantitative expression of empirical knowledge to make up for the problem of insufficient mud cake samples in actual engineering, thereby significantly improving the quantity and quality of the mud cake sample database, and correspondingly training a mud cake risk prediction model with higher prediction accuracy, that is, the trained target model, to predict the shield mud cake risk.

[0052] Furthermore, if Figure 5 As shown, based on the above-mentioned blocking prediction method based on the shield mud cake determination diagram, the present invention also provides a blocking prediction system based on the shield mud cake determination diagram, wherein the blocking prediction system based on the shield mud cake determination diagram comprises: A two-dimensional coordinate space generating module 51 is used to obtain a target shield structure mud cake determination diagram, perform mathematical modeling on the target shield structure mud cake determination diagram, and generate a two-dimensional coordinate space; A sample point generating module 52 is used to calculate the area ratio of each risk area in the target shield mud cake determination map, and generate a plurality of sample points in the two-dimensional coordinate space according to all the area ratios; The training module 53 is used to generate sample point label assignment requirements according to the target shield mud cake determination diagram, divide corresponding classification labels for each sample point according to the sample point label assignment requirements, generate sample data, train the target model according to the sample data, and obtain the trained target model; The application module 54 is used to obtain the liquid limit, plastic limit and moisture content of the slag in the target environment when performing real-time blockage prediction, and after pre-processing the liquid limit, plastic limit and moisture content of the slag in the target environment, input them into the trained target model for processing, and output the blockage prediction classification label.

[0053] Furthermore, if Figure 6 As shown, based on the above-mentioned blockage prediction method and system based on the shield mud cake determination diagram, the present invention also provides a terminal accordingly, and the terminal includes a processor 10, a memory 20 and a display 30. Figure 6 Only some components of the terminal are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0054] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal. Further, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and various types of data installed on the terminal, such as the program code of the installation terminal. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, a congestion prediction program 40 based on a shield mud cake determination diagram is stored on the memory 20, and the congestion prediction program 40 based on a shield mud cake determination diagram can be executed by the processor 10, thereby realizing the congestion prediction method based on a shield mud cake determination diagram in the present invention.

[0055] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 20, such as executing the blockage prediction method based on the shield mud cake determination diagram.

[0056] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 30 is used to display information on the terminal and to display a visual user interface.

[0057] In one embodiment, when the processor 10 executes the congestion prediction program 40 based on the shield structure mud cake determination map in the memory 20, the steps of the above congestion prediction method based on the shield structure mud cake determination map are implemented.

[0058] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a blockage prediction program based on a shield mud cake determination diagram, and when the blockage prediction program based on a shield mud cake determination diagram is executed by a processor, the following steps are implemented: Obtaining a target shield structure mud cake determination diagram, performing mathematical modeling on the target shield structure mud cake determination diagram, and generating a two-dimensional coordinate space; Calculate the area ratio of each risk area in the target shield mud cake determination map, and generate multiple sample points in the two-dimensional coordinate space according to all the area ratios; Generate sample point label assignment requirements according to the target shield mud cake determination map, assign corresponding classification labels to each sample point according to the sample point label assignment requirements, generate sample data, train a target model according to the sample data, and obtain a trained target model; When performing real-time blockage prediction, the liquid limit, plastic limit and moisture content of the slag in the target environment are obtained, and after preprocessing the liquid limit, plastic limit and moisture content of the slag in the target environment, they are input into the trained target model for processing, and the blockage prediction classification label is output.

[0059] The step of obtaining a target shield structure mud cake determination diagram, mathematically modeling the target shield structure mud cake determination diagram, and generating a two-dimensional coordinate space specifically includes: Obtain the target shield structure mud cake determination diagram; Extracting the numerical range of the difference between the plastic limit and the water content and the numerical range of the difference between the liquid limit and the water content in the target shield mud cake determination diagram; The numerical boundary is determined according to the corresponding numerical range, and the two-dimensional coordinate space is generated according to the numerical boundary.

[0060] The step of calculating the area ratio of each risk area in the target shield mud cake determination map and generating a plurality of sample points in the two-dimensional coordinate space according to all the area ratios specifically includes: According to the target shield mud cake, the scope of each risk area in the determination map is calculated, and the area ratio of each risk area is calculated; The total number of preset sample points is obtained, and according to all the area ratios, a scattering method is used to generate a preset number of sample points in the two-dimensional coordinate space.

[0061] The step of generating sample point label assignment requirements according to the target shield mud cake determination diagram specifically includes: Assigning values ​​to the target shield mud cake determination diagram according to the two-dimensional coordinate space, and constructing a mathematical expression of the boundary of each risk area; According to each of the mathematical expressions, the coordinate relationship of the points in each risk area is calculated, and according to each of the coordinate relationships, the label assignment requirements of the sample points are generated.

[0062] The step of assigning a corresponding classification label to each sample point according to the sample point label assignment requirements, generating sample data, and training a target model according to the sample data to obtain a trained target model specifically includes: Obtaining the coordinates of each of the sample points in the two-dimensional coordinate space, and assigning a corresponding classification label to each of the sample points according to the coordinates of each of the sample points and the sample point label assignment requirements; Sample data is generated according to the classification label and the coordinates of each sample point, and a target model is trained according to the sample data to obtain a trained target model.

[0063] The step of generating sample data according to the classification label and the coordinates of each sample point, and training a target model according to the sample data to obtain a trained target model specifically includes: Generate multiple groups of data according to the classification label and the coordinates of each sample point, and aggregate all the data to obtain the sample data; The coordinates of each group of data in the sample data are input into the target model, and the target model is optimized according to the output of the target model and the classification label of each group of data. When the training conditions are met, the training is terminated and the trained target model is obtained.

[0064] Among them, when performing real-time blockage prediction, the liquid limit, plastic limit and moisture content of the slag in the target environment are obtained, and the liquid limit, plastic limit and moisture content of the slag in the target environment are pre-processed and input into the trained target model for processing, and the blockage prediction classification label is output, which specifically includes: When performing real-time blockage prediction, the liquid limit, plastic limit and water content of the slag in the target environment are obtained, and the difference between the current liquid limit and water content is calculated according to the liquid limit and water content of the slag in the target environment, and the difference between the current plastic limit and water content is calculated according to the plastic limit and water content of the slag in the target environment; Generate current coordinates according to the difference between the current liquid limit and the water content and the difference between the current plastic limit and the water content; The current coordinates are input into the trained target model, and a blockage prediction classification label is output.

[0065] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or terminal including the element.

[0066] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the program can be stored in a computer-readable storage medium that can be read by a computer, and the program can include the processes of the above-mentioned method embodiments when executed. The computer-readable storage medium can be a memory, a disk, an optical disk, etc.

[0067] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A blockage prediction method based on a shield mud cake determination diagram, characterized in that: The blockage prediction method based on the shield mud cake determination diagram includes: Obtaining a target shield structure mud cake determination diagram, performing mathematical modeling on the target shield structure mud cake determination diagram, and generating a two-dimensional coordinate space; Calculate the area ratio of each risk area in the target shield mud cake determination map, and generate multiple sample points in the two-dimensional coordinate space according to all the area ratios; Generate sample point label assignment requirements according to the target shield mud cake determination map, assign corresponding classification labels to each sample point according to the sample point label assignment requirements, generate sample data, train a target model according to the sample data, and obtain a trained target model; When performing real-time blockage prediction, the liquid limit, plastic limit and moisture content of the slag in the target environment are obtained, and after preprocessing the liquid limit, plastic limit and moisture content of the slag in the target environment, they are input into the trained target model for processing, and the blockage prediction classification label is output.

2. The blockage prediction method based on the shield mud cake determination diagram according to claim 1 is characterized in that: The step of obtaining a target shield structure mud cake determination diagram, performing mathematical modeling on the target shield structure mud cake determination diagram, and generating a two-dimensional coordinate space specifically includes: Obtain the target shield structure mud cake determination diagram; Extracting the numerical range of the difference between the plastic limit and the water content and the numerical range of the difference between the liquid limit and the water content in the target shield mud cake determination diagram; The numerical boundary is determined according to the corresponding numerical range, and the two-dimensional coordinate space is generated according to the numerical boundary.

3. The blockage prediction method based on the shield mud cake determination diagram according to claim 1 is characterized in that: The calculating the area ratio of each risk area in the target shield mud cake determination map and generating a plurality of sample points in the two-dimensional coordinate space according to all the area ratios specifically includes: According to the target shield mud cake determination map, the area ratio of each risk area is calculated; The total number of preset sample points is obtained, and according to all the area ratios, a scattering method is used to generate a preset number of sample points in the two-dimensional coordinate space.

4. The blockage prediction method based on the shield mud cake determination diagram according to claim 1 is characterized in that: The generating of the sample point label assignment requirements according to the target shield mud cake determination diagram specifically includes: Assigning values ​​to the target shield mud cake determination diagram according to the two-dimensional coordinate space, and constructing a mathematical expression of the boundary of each risk area; According to each of the mathematical expressions, the coordinate relationship of the points in each risk area is calculated, and according to each of the coordinate relationships, the label assignment requirements of the sample points are generated.

5. The blockage prediction method based on the shield mud cake determination diagram according to claim 1 is characterized in that: According to the sample point label assignment requirements, a corresponding classification label is assigned to each sample point, sample data is generated, and a target model is trained according to the sample data to obtain a trained target model, which specifically includes: Obtaining the coordinates of each of the sample points in the two-dimensional coordinate space, and assigning a corresponding classification label to each of the sample points according to the coordinates of each of the sample points and the sample point label assignment requirements; Sample data is generated according to the classification label and the coordinates of each sample point, and a target model is trained according to the sample data to obtain a trained target model.

6. The blockage prediction method based on the shield mud cake determination diagram according to claim 5 is characterized in that: The generating sample data according to the classification label and the coordinates of each sample point, and training the target model according to the sample data to obtain the trained target model specifically includes: Generate multiple groups of data according to the classification label and the coordinates of each sample point, and aggregate all the data to obtain the sample data; The coordinates of each group of data in the sample data are input into the target model, and the target model is optimized according to the output of the target model and the classification label of each group of data. When the training conditions are met, the training is terminated and the trained target model is obtained.

7. The blockage prediction method based on the shield mud cake determination diagram according to claim 1 is characterized in that: When performing real-time blockage prediction, the liquid limit, plastic limit and moisture content of the slag in the target environment are obtained, and the liquid limit, plastic limit and moisture content of the slag in the target environment are pre-processed and input into the trained target model for processing, and the blockage prediction classification label is output, which specifically includes: When performing real-time blockage prediction, the liquid limit, plastic limit and water content of the slag in the target environment are obtained, and the difference between the current liquid limit and water content is calculated according to the liquid limit and water content of the slag in the target environment, and the difference between the current plastic limit and water content is calculated according to the plastic limit and water content of the slag in the target environment; Generate current coordinates according to the difference between the current liquid limit and the water content and the difference between the current plastic limit and the water content; The current coordinates are input into the trained target model, and a blockage prediction classification label is output.

8. A blockage prediction system based on a shield mud cake determination diagram, characterized in that: The blocking prediction system based on the shield mud cake determination diagram includes: A two-dimensional coordinate space generation module is used to obtain a target shield structure mud cake determination diagram, perform mathematical modeling on the target shield structure mud cake determination diagram, and generate a two-dimensional coordinate space; A sample point generation module, used to calculate the area ratio of each risk area in the target shield mud cake determination map, and generate multiple sample points in the two-dimensional coordinate space according to all the area ratios; A training module is used to generate sample point label assignment requirements according to the target shield mud cake determination map, assign corresponding classification labels to each sample point according to the sample point label assignment requirements, generate sample data, train a target model according to the sample data, and obtain a trained target model; The application module is used to obtain the liquid limit, plastic limit and moisture content of the slag in the target environment when performing real-time blockage prediction, and after pre-processing the liquid limit, plastic limit and moisture content of the slag in the target environment, input them into the trained target model for processing, and output the blockage prediction classification label.

9. A terminal, characterized in that: The terminal includes: a memory, a processor, and a congestion prediction program based on a shield mud cake determination map stored in the memory and executable on the processor. When the congestion prediction program based on a shield mud cake determination map is executed by the processor, the steps of the congestion prediction method based on a shield mud cake determination map as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a congestion prediction program based on a shield mud cake determination diagram, and when the congestion prediction program based on a shield mud cake determination diagram is executed by a processor, the steps of the congestion prediction method based on a shield mud cake determination diagram as described in any one of claims 1 to 7 are implemented.

Images