Shield tunneling machine escape body traction control system and method applying omni-directional traction force

Abstract

The invention relates to the technical field of shield tunneling machine detrapping, in particular to a shield tunneling machine detrapping body traction control system and method applying omnidirectional traction force, and the method comprises the steps: predicting the current propulsion resistance of a shield tunneling machine based on a long-short-term memory network according to historical shield construction data; traction devices are arranged at the front end, the rear end, the side faces and the bottom of the shield tunneling machine through distributed hydraulic cylinders, so that the shield tunneling machine has the omni-directional traction capacity, and free traction in the X-Y-Z three-axis direction is achieved. On the basis of the predicted propelling resistance, the predicted total propelling force is calculated by applying a force balance equation, the distribution proportion of the total oil cylinder propelling force and the total traction force is reasonably determined, the stability and efficiency of the propelling process are ensured, meanwhile, the posture deviation of the shield tunneling machine is obtained in real time, the total traction force is decomposed into traction force components in the X, Y and Z axial directions, and the stability and efficiency of the shield tunneling machine are improved. The pulling force of the traction device is accurately controlled, the abnormal posture is corrected in time, and the accuracy of the escape tunneling direction is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of shield machine escape, in particular to a shield machine escape body traction control system and method using omnidirectional traction force. Background Art

[0002] A shield machine is a specialized piece of engineering equipment used for tunneling, integrating excavation, support, slag removal, and propulsion. Its core structure consists of a cutterhead (for cutting the ground), a shield (for ensuring construction safety), a propulsion system (with hydraulic cylinders providing thrust), and a segment assembly system. The shield machine uses a rotating cutterhead to break up the rock and soil, while simultaneously supporting the surrounding ground with the shield. Precast concrete segments are then assembled behind the cutterhead to form the tunnel structure. It is widely used in tunneling projects for subways, railways, highways, and water conservancy projects, particularly in complex geological conditions and densely populated urban areas, minimizing ground subsidence and ensuring construction safety.

[0003] When a shield machine gets stuck during tunnel construction (commonly known as "shield jamming" or "machine jamming"), it is a serious engineering accident that may lead to construction delays, increased costs, and even safety accidents. The common cause of shield machine jams is complex geological conditions, namely uneven soft and hard strata. For example, encountering unexplored boulders, isolated rocks, hard rocks, or weak interlayers may lead to abnormal cutterhead torque or increased propulsion resistance, or clay or mudstone may adhere to the cutterhead, reducing excavation efficiency, and imbalance of groundwater pressure may cause water and sand gushing, resulting in the shield body being wrapped.

[0004] A Chinese patent with authorization publication number CN111828026B discloses a method for freeing a shield machine, which includes the following steps: providing a thrust cylinder, fixing one end of the thrust cylinder to the shield machine, and abutting the other end against the annular surface of a newly assembled segment of the shield machine; providing an articulated cylinder, hingedly connecting the articulated cylinder inside the shield machine; providing a driving member, abutting one end of the driving member against the articulated cylinder, and abutting the other end against the annular surface of the newly assembled segment of the shield machine; applying thrust to the shield machine through the driving member and the thrust cylinder to free the shield machine.

[0005] As mentioned in the above application, when the existing shield machine is trapped, when the thrust of the thrust cylinder is limited and cannot provide sufficient thrust to free the shield machine, it is generally necessary to add a thrust cylinder and increase the thrust through the thrust cylinder to free the shield machine. The posture of the shield machine and the direction of the traction force are not taken into consideration. During the process of freeing, if the posture adjustment is ignored, the shield machine may tilt, further aggravating the trapped situation, and even causing greater damage to the equipment and the construction environment. Summary of the Invention

[0006] In order to solve the above problems, the present invention provides a shield machine escape body traction control system and method using omnidirectional traction force.

[0007] The present invention adopts the following technical solutions, and utilizes a shield machine escape body traction control method with omnidirectional traction force, including:

[0008] According to historical shield construction data, the current thrust resistance of the shield machine is predicted based on the long short-term memory network;

[0009] Distributed hydraulic cylinders are used to arrange traction devices at the front, rear, sides and bottom of the shield machine, giving it omnidirectional traction capabilities. The traction devices are connected to the shield machine through an articulated structure to achieve free traction in the X, Y and Z axes.

[0010] Based on the propulsion resistance, the estimated total propulsion force is obtained according to the force balance equation, and the distribution ratio of the total cylinder propulsion force and the total traction force is determined based on the total propulsion force;

[0011] The posture deviation of the shield machine is obtained, and the total traction force is decomposed into the three axial traction force components of X, Y, and Z. Based on the decomposition of the total traction force into the three axial traction force components of X, Y, and Z, the pulling force of the traction device is controlled.

[0012] As a further description of the above technical solution: Based on historical shield construction data, the method for predicting the current propulsion resistance of the shield machine based on the long short-term memory network includes:

[0013] Obtain historical shield construction data from the shield machine database. The historical shield construction data includes geological conditions, construction parameters, and historical propulsion resistance. Build a propulsion resistance training set and a propulsion resistance test set based on the historical shield construction data.

[0014] Construct a regression network model, use the geological conditions and construction parameters in the propulsion resistance training set as input data of the regression network model, use the historical propulsion resistance in the propulsion resistance training set as output data of the regression network model, train the regression network model, and obtain an initial coefficient prediction regression network;

[0015] The initial coefficient prediction regression network is validated using a propulsion resistance test set, and an initial coefficient prediction regression network with a prediction error less than or equal to a preset error threshold is output as a propulsion resistance prediction model; the regression network model is specifically a long short-term memory network model;

[0016] The geological conditions and construction parameters of the current shield machine are collected, input into the trained propulsion resistance prediction model, and the propulsion resistance is output.

[0017] As a further description of the above technical solution: the geological conditions include stratum characteristics and the strength, density and water content corresponding to the stratum characteristics; the stratum characteristics include soft soil, sand, clay and rock categories, wherein the geological conditions are directly obtained through drilling, sampling and testing; the construction parameters of the shield machine are obtained, and the construction parameters include the specifications of the shield machine, the cutter head diameter, and the tool configuration.

[0018] As a further description of the above technical solution: the method for determining the distribution ratio of the total cylinder propulsion force and the total traction force based on the total propulsion force includes:

[0019] Using 3D modeling software to create a geometric model of the shield machine, the geometric model including key components, wherein the key components include a cutterhead, a main machine, a propulsion system, and a traction device;

[0020] Divide the geometric model into mesh elements for finite element analysis based on the preset mesh density, balancing calculation accuracy and efficiency;

[0021] Setting material properties for each key component in the geometric model. The material properties include elastic modulus, Poisson's ratio, and density. It should be noted that the material properties set for each key component must be consistent with the actual material properties.

[0022] According to the actual construction situation, the boundary conditions of the geometric model are set, including fixed support and free surface;

[0023] The ratio of propulsion force and total traction force is adjusted in the geometric model, different combinations of propulsion force and total traction force are input, and the deformation and escape time of the shield machine under different combinations are evaluated.

[0024] As a further description of the above technical solution: the method for evaluating the deformation and escape time of the shield machine under different combinations includes:

[0025] A deformation threshold is preset, and combinations of propulsion force and total traction force below the deformation threshold are obtained. The obtained propulsion force and total traction force combinations are sorted in sequence according to the length of the escape time to establish a parameter set. The order of arrangement in the parameter set is sorted in increasing order according to the escape time;

[0026] Based on the maximum thrust of the shield machine and the maximum traction of the traction device, the optimal combination of thrust and total traction is obtained.

[0027] As a further description of the above technical solution: the method for obtaining the optimal combination of propulsion force and total traction force includes:

[0028] Step 1: Obtain the propulsion force and total traction force combination corresponding to the shortest escape time within the parameter set;

[0029] Step 2: Compare the values ​​of the propulsion force and total traction force combination to see if they exceed the maximum propulsion force of the shield machine and the maximum traction force of the traction device. If one of the values ​​exceeds the maximum propulsion force, the propulsion force and total traction force combination is discarded and removed from the parameter set.

[0030] Step 3, repeat step 1 above until the values ​​of the propulsion force and total traction force combination corresponding to the shortest escape time do not exceed the maximum propulsion force of the shield machine and the maximum traction force of the traction device. At this time, the propulsion force and total traction force combination is recorded as the optimal propulsion force and total traction force combination.

[0031] As a further description of the above technical solution: the method of decomposing the total traction force into the three axial traction force components X, Y, and Z includes:

[0032] Based on the shield machine's control system and the pre-set shield route, the current yaw angle and pitch angle of the shield machine are obtained, where the yaw angle is the left and right deflection angle of the shield machine in the horizontal direction, and the pitch angle is the deflection angle of the shield machine in the vertical direction;

[0033] The total traction force component in the X-axis direction is obtained based on the yaw angle calculation;

[0034] The total traction force component in the Y-axis direction is obtained based on the pitch angle calculation;

[0035] The total traction force component in the Z-axis direction is obtained based on the total traction force component in the X-axis direction, the total traction force component in the Y-axis direction, and the total traction force.

[0036] As a further description of the above technical solution: it also includes:

[0037] The attitude parameters of the shield machine are acquired in real time and analyzed. When the shield machine has an abnormal attitude, an escape adjustment instruction is generated, and the traction and propulsion forces are recalculated and distributed based on the escape adjustment instruction.

[0038] As a further description of the above technical solution: the method for generating the escape adjustment instruction includes:

[0039] Using an attitude sensor to obtain real-time attitude parameters of the shield machine, the attitude parameters include pitch angle and yaw angle;

[0040] The real-time posture parameters are compared with the standard posture parameters to obtain the posture deviation. If the posture deviation exceeds the allowable range, it is determined that there is a posture abnormality.

[0041] A shield machine escape body traction control system using omnidirectional traction force, which is used to implement the shield machine escape body traction control method using omnidirectional traction force, and the system includes:

[0042] The resistance prediction module predicts the current thrust resistance of the shield machine based on historical shield construction data and long-short-term memory networks;

[0043] The omnidirectional traction design module uses distributed hydraulic cylinders to arrange traction devices at the front, rear, sides, and bottom of the shield machine, giving it omnidirectional traction capabilities. The traction devices are connected to the shield machine through an articulated structure to achieve free traction in the X, Y, and Z axes.

[0044] A propulsion force distribution module obtains the estimated total propulsion force based on the propulsion resistance and the force balance equation, and determines the distribution ratio of the total cylinder propulsion force and the total traction force based on the total propulsion force;

[0045] The traction force distribution module obtains the posture deviation of the shield machine and decomposes the total traction force into the three axial traction force components of X, Y, and Z. Based on the decomposition of the total traction force into the three axial traction force components of X, Y, and Z, the pulling force of the traction device is controlled.

[0046] Beneficial effects:

[0047] The shield machine escape body traction control system and method using omnidirectional traction provided by the present invention calculates the expected total propulsion force based on the predicted propulsion resistance using the force balance equation, and reasonably determines the distribution ratio of the total cylinder propulsion force and the total traction force, thereby ensuring the stability and efficiency of the propulsion process. At the same time, the posture deviation of the shield machine is obtained in real time, the total traction force is decomposed into the three axial traction components of X, Y, and Z, the pulling force of the traction device is accurately controlled, the posture abnormality is corrected in time, and the accuracy of the escape excavation direction is ensured. In summary, the method significantly improves the shield machine's autonomous escape and posture adjustment capabilities in complex environments through the organic combination of intelligent prediction, omnidirectional traction, and precise control.

[0048] Furthermore, by real-time monitoring and adjustment of the shield machine's posture, it is ensured that it excavates according to the designed trajectory, reduces deviations, promptly detects and corrects posture abnormalities, prevents the increase in the risk of escape due to accumulation of deviations, and ensures the safety of the construction process. By automatically generating adjustment instructions and adjusting the distribution of propulsion and traction in real time, manual intervention is reduced and the safety and effectiveness of escape operations are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The present invention will be further explained below in conjunction with the accompanying drawings and embodiments:

[0050] Figure 1 Flowchart of the shield machine escape body traction control method using omnidirectional traction force provided in Example 1 of the present invention;

[0051] Figure 2 A flowchart of a method for predicting the current propulsion resistance of a shield machine based on a long short-term memory network provided in Example 1 of the present invention;

[0052] Figure 3 A flow chart of a method for obtaining an optimal combination of propulsion force and total traction force provided in Example 1 of the present invention;

[0053] Figure 4 This is a module connection diagram of a shield machine escape body traction control system that applies omnidirectional traction force according to embodiment 3 of the present invention. DETAILED DESCRIPTION

[0054] In order to make the technical means, creative features, objectives and effects of the present invention easier to understand, the present invention is further described below with reference to specific diagrams. It should be noted that the embodiments and features in the embodiments of this application can be combined with each other unless they conflict.

[0055] Example 1:

[0056] See also Figure 1-Figure 3 The embodiment of the present invention provides a technical solution: a shield machine escape body traction control method using omnidirectional traction, which is used to provide precise multi-dimensional force control through an all-directionally adjustable traction system, so that the shield machine can obtain stable pulling force in different directions and achieve smooth escape. The control method includes:

[0057] According to the historical shield construction data, the current propulsion resistance of the shield machine is predicted based on the long short-term memory network.

[0058] Based on historical shield construction data, the methods for predicting the current thrust resistance of the shield machine based on the long short-term memory network include:

[0059] Obtain historical shield construction data from the shield machine database. The historical shield construction data includes geological conditions, construction parameters, and historical propulsion resistance. Build a propulsion resistance training set and a propulsion resistance test set based on the historical shield construction data.

[0060] It should be noted that historical shield construction data is the basis for model learning. There is an intrinsic relationship between geological conditions (stratum characteristics and the strength, density and water content corresponding to the stratum characteristics) and construction parameters (such as shield machine specifications, cutterhead diameter, and tool configuration) and propulsion resistance. These relationships can be mined through historical data to build a prediction model.

[0061] The acquired historical shield construction data can also be cleaned, including checking missing values ​​in the data. For a small number of missing values, the mean, median or mode can be used to fill in the missing values; for samples with a large number of missing values, consider deleting them. The small and large missing values ​​can be judged by setting thresholds. Missing values ​​and outliers will affect the training effect of the model and cause the model to learn the wrong pattern. Cleaning the data can improve the data quality, enable the model to better learn the real relationship in the data, and standardize the geological condition parameters and construction parameters. For example, use Z-score standardization to convert the data into a distribution with a mean of 0 and a standard deviation of 1. Standardization can eliminate the influence of dimension, enable the model to treat each feature equally, and improve the convergence speed and stability of the model.

[0062] The propulsion resistance training set and the propulsion resistance test set can be divided in a ratio of 8:2 or 7:3. The propulsion resistance training set is used for model parameter learning, and the propulsion resistance test set is used to evaluate the performance of the model on unseen data. By dividing the data set, overfitting of the model can be avoided and the generalization ability of the model can be ensured.

[0063] Construct a regression network model, use the geological conditions and construction parameters in the propulsion resistance training set as input data of the regression network model, use the historical propulsion resistance in the propulsion resistance training set as output data of the regression network model, train the regression network model, and obtain an initial coefficient prediction regression network;

[0064] It should be noted that the shield construction process is a continuous process. Changes in geological conditions and construction parameters at different time points will affect the propulsion resistance. The memory units of the long short-term memory network (LSTM) can remember past information, thereby better predicting the current propulsion resistance.

[0065] The initial coefficient prediction regression network is validated using a propulsion resistance test set, and an initial coefficient prediction regression network with a prediction error less than or equal to a preset error threshold is output as a propulsion resistance prediction model; the regression network model is specifically a long short-term memory network model;

[0066] The geological conditions and construction parameters of the current shield machine are collected, input into the trained propulsion resistance prediction model, and the propulsion resistance is output.

[0067] The geological conditions include stratum characteristics and the strength, density, and water content corresponding to the stratum characteristics; the stratum characteristics include soft soil, sand, clay, and rock types, wherein the geological conditions are directly obtained through drilling, sampling, and testing; obtaining the construction parameters of the shield machine, which include the specifications of the shield machine, the cutterhead diameter, and the tool configuration;

[0068] The specifications of the shield machine include weight, length, maximum thrust and rated torque, all of which are related to the propulsion resistance encountered when trapped. The tool configuration includes a central fishtail knife, a cutter, a peripheral scraper and a contour knife.

[0069] Distributed hydraulic cylinders are used to rationally arrange traction devices at the front, rear, sides and bottom of the shield machine, giving it omnidirectional traction capability. The traction device is connected to the shield machine through an articulated structure to achieve free traction in the XYZ three-axis directions.

[0070] According to the force balance equation, based on the propulsion resistance, the estimated total propulsion force is obtained, and based on the total propulsion force, the distribution ratio of the total cylinder propulsion force and the total traction force is determined.

[0071] It should be noted that when the shield machine is getting out of trouble, the thrust cylinder and traction device on the shield machine need to jointly generate thrust to propel the shield machine forward and get out of trouble. That is, the total thrust is equal to the total cylinder thrust plus the total traction thrust.

[0072] Methods for calculating the expected total propulsive force based on the force balance equation include:

[0073] The force balance equation is expressed as: , where is the total propulsion force, is the propulsion resistance, a is the acceleration of the shield machine, is the mass of the shield machine. It should be noted that when advancing at a uniform speed, a=0;

[0074] The method for determining the distribution ratio of the total cylinder propulsion force and the total traction force based on the total propulsion force includes:

[0075] Using 3D modeling software (such as SolidWorks) to create a detailed geometric model of the shield machine, including all key components, including the cutterhead, main machine, propulsion system, and traction device;

[0076] Based on the preset mesh density, the geometric model is divided into the mesh elements required for finite element analysis, balancing calculation accuracy and efficiency;

[0077] Material properties are set for each key component in the geometric model. The material properties include elastic modulus, Poisson's ratio, and density. It should be noted that the material properties set for each key component are consistent with the actual material properties.

[0078] Based on the actual construction situation, the boundary conditions of the geometric model are set. Boundary conditions include fixed supports and free surfaces. For example, for fixed parts in the model, such as the base of the shield machine or the part in contact with the ground, fixed constraints are applied to limit their displacement in a specific direction.

[0079] The ratio of thrust and total traction force was systematically adjusted in the geometric model. Different combinations of thrust and total traction force were input to evaluate the deformation and escape time of the shield machine under different combinations.

[0080] A deformation threshold is preset, and combinations of propulsion force and total traction force below the deformation threshold are obtained. The obtained propulsion force and total traction force combinations are sorted in sequence according to the length of the escape time to establish a parameter set. The order of arrangement in the parameter set is sorted in increasing order according to the escape time;

[0081] Based on the maximum thrust of the shield machine and the maximum traction of the traction device, the optimal combination of thrust and total traction is obtained.

[0082] Specifically, through finite element analysis, the response of the shield machine under different combinations of propulsion force and total traction force can be simulated to find the optimal force distribution scheme, thereby enhancing the shield machine's ability to escape from difficult conditions. Moreover, by rationally distributing the propulsion force and total traction force, the deformation and escape time of the shield machine can be reduced, construction efficiency can be improved, and project costs can be reduced. By analyzing the deformation and stress of the shield machine under different force combinations, it is ensured that the selected force distribution scheme will not cause damage to the shield machine structure, thereby ensuring construction safety.

[0083] Based on the maximum thrust of the shield machine and the maximum traction of the traction device, the steps to obtain the optimal thrust and total traction combination are as follows:

[0084] Step 1: Obtain the propulsion force and total traction force combination corresponding to the shortest escape time within the parameter set;

[0085] Step 2: Compare the values ​​of the propulsion force and total traction force combination to see if they exceed the maximum propulsion force of the shield machine and the maximum traction force of the traction device. If one of the values ​​exceeds the maximum propulsion force, the propulsion force and total traction force combination is discarded and removed from the parameter set.

[0086] Step 3, repeat step 1 above until the values ​​of the propulsion force and total traction force combination corresponding to the shortest escape time do not exceed the maximum propulsion force of the shield machine and the maximum traction force of the traction device. At this time, the propulsion force and total traction force combination is recorded as the optimal propulsion force and total traction force combination.

[0087] Obtain the posture deviation of the shield machine and decompose the total traction force into three axial traction force components: X, Y, and Z;

[0088] Methods for decomposing the total traction force into the three axial traction force components X, Y, and Z include:

[0089] Based on the shield machine's control system and the pre-set shield route, the current yaw angle and pitch angle of the shield machine are obtained, where the yaw angle is the left and right deflection angle of the shield machine in the horizontal direction, and the pitch angle is the deflection angle of the shield machine in the vertical direction;

[0090] The total traction force component in the X-axis direction is obtained based on the yaw angle calculation;

[0091] The calculation formula of the total traction force component in the X-axis direction is: ;

[0092] in, To decompose the total traction force component in the X-axis direction, is the yaw angle, To characterize the degree of horizontal deviation of the shield machine, is the total traction force;

[0093] The total traction force component in the Y-axis direction is obtained based on the pitch angle calculation;

[0094] The calculation formula of the total traction force component in the Y-axis direction is: ;

[0095] in, To decompose the total traction force component in the Y-axis direction, is the pitch angle, To characterize the degree of vertical deviation of the shield machine, is the total traction force;

[0096] The total traction force component in the Z-axis direction is obtained based on the total traction force component in the X-axis direction, the total traction force component in the Y-axis direction and the total traction force;

[0097] The calculation formula of the total traction force component in the Z-axis direction is: ;

[0098] in, To decompose the total traction force component in the Z-axis direction, is the total traction force.

[0099] It should be noted that the total traction In order to meet the propulsion requirements and correct the deviation, the sine function is used to extract the component positively correlated with the deviation angle (for correction), and the cosine function is used to obtain the remaining force projected into the propulsion direction. When the deviation angle is large, more traction is needed to correct the deviation (X and Y directions), and the component in the propulsion direction is naturally reduced; when the deviation angle is small, most of the traction can be used for propulsion (Z axis), thereby achieving the best correction and propulsion effect. Through this decomposition method based on posture deviation, the total traction can be effectively distributed to the three axes, ensuring that the shield machine has sufficient propulsion force during construction and can correct left and right and up and down deviations in time, ensuring the smoothness and safety of the entire construction process.

[0100] The total traction force obtained is decomposed into traction force components in three axial directions X, Y, and Z, and the pulling force of the traction device is controlled.

[0101] Specifically, the posture deviation of the shield machine is obtained in real time, the total traction force is decomposed into the three axial traction force components of X, Y, and Z, the pulling force of the traction device is accurately controlled, and the posture abnormality is corrected in time to ensure the accuracy of the excavation direction.

[0102] In this embodiment, by integrating advanced prediction technology and an omnidirectional traction system, the shield machine can achieve autonomous escape and posture control under complex geological conditions. First, a long short-term memory network (LSTM) is used to conduct deep learning on geological conditions, construction parameters, and historical shield construction data to accurately predict the current propulsion resistance, providing a scientific basis for subsequent force distribution.

[0103] In terms of structural design, distributed hydraulic cylinders are used to arrange traction devices at the front, rear, sides, and bottom of the shield machine. These devices are connected to the shield machine via an articulated structure, enabling free traction in the X, Y, and Z axes, giving the shield machine omnidirectional traction capabilities. This design enables the shield machine to autonomously adjust through multi-directional traction when encountering complex geological conditions or posture deviations, enhancing its ability to escape difficulties.

[0104] Based on the predicted propulsion resistance, the force balance equation is applied to calculate the expected total propulsion force, and the distribution ratio of the total cylinder propulsion force and the total traction force is reasonably determined to ensure the stability and efficiency of the propulsion process. At the same time, the posture deviation of the shield machine is obtained in real time, and the total traction force is decomposed into the three axial traction components of X, Y, and Z. The pulling force of the traction device is accurately controlled, and the posture abnormality is corrected in time to ensure the accuracy of the excavation direction. In summary, this method significantly improves the shield machine's autonomous escape and posture adjustment capabilities in complex environments through the organic combination of intelligent prediction, omnidirectional traction and precise control, and is superior to traditional propulsion systems.

[0105] Example 2

[0106] The embodiment of the present invention provides a technical solution: obtaining the attitude parameters of the shield machine in real time, analyzing the attitude parameters, generating an escape adjustment instruction when the shield machine has an abnormal attitude, and recalculating and distributing the traction force and the propulsion force based on the escape adjustment instruction;

[0107] The method of generating a bailout adjustment instruction includes:

[0108] Using attitude sensors (such as gyroscopes and accelerometers) to obtain real-time attitude parameters of the shield machine, the attitude parameters including pitch angle and yaw angle;

[0109] The real-time posture parameters are compared with the standard posture parameters to obtain the posture deviation. If the posture deviation exceeds the allowable range, it is determined that there is a posture abnormality.

[0110] It should be noted that the standard attitude parameters are the shield machine's excavation trajectory, which engineers develop during the tunnel design phase based on geological conditions, route alignment, and construction requirements. This trajectory includes the horizontal and longitudinal positions of each segment, as well as the corresponding pitch and yaw angles. A deviation threshold is preset, and when the difference between the real-time collected attitude parameters and the standard attitude parameters exceeds the deviation threshold, an attitude anomaly is determined.

[0111] When an abnormal posture occurs, an escape adjustment instruction is generated.

[0112] It should be noted that when the escape adjustment instruction is generated, the above-mentioned shield machine escape body traction control method using omnidirectional traction force in Example 1 is repeated again to re-obtain the distribution ratio of the total thrust, total cylinder thrust and total traction force and the decomposition of the total traction force into the three axial traction components X, Y and Z.

[0113] In this embodiment, by real-time monitoring and adjustment of the shield machine's posture, it is ensured that it excavates according to the designed trajectory, reduces deviations, promptly detects and corrects posture abnormalities, prevents the increase in the risk of escape due to accumulation of deviations, and ensures the safety of the construction process. By automatically generating adjustment instructions and adjusting the distribution of propulsion and traction in real time, manual intervention is reduced and the safety and effectiveness of the escape operation are improved.

[0114] Example 3

[0115] See also Figure 4 A shield machine escape body traction control system using omnidirectional traction force is used to implement the shield machine escape body traction control method using omnidirectional traction force, and the system includes:

[0116] The resistance prediction module predicts the current thrust resistance of the shield machine based on historical shield construction data and long-short-term memory networks;

[0117] The omnidirectional traction design module uses distributed hydraulic cylinders to arrange traction devices at the front, rear, sides, and bottom of the shield machine, giving it omnidirectional traction capabilities. The traction devices are connected to the shield machine through an articulated structure to achieve free traction in the X, Y, and Z axes.

[0118] A propulsion force distribution module obtains the estimated total propulsion force based on the propulsion resistance and the force balance equation, and determines the distribution ratio of the total cylinder propulsion force and the total traction force based on the total propulsion force;

[0119] The traction force distribution module obtains the posture deviation of the shield machine and decomposes the total traction force into the three axial traction force components of X, Y, and Z. Based on the decomposition of the total traction force into the three axial traction force components of X, Y, and Z, the pulling force of the traction device is controlled.

[0120] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above-described embodiments. The above-described embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A shield machine escape body traction control method using omnidirectional traction, characterized in that: include: According to historical shield construction data, the current thrust resistance of the shield machine is predicted based on the long short-term memory network; Distributed hydraulic cylinders are used to arrange traction devices at the front, rear, sides and bottom of the shield machine, giving it omnidirectional traction capabilities. The traction devices are connected to the shield machine through an articulated structure to achieve free traction in the X, Y and Z axes. Based on the propulsion resistance, the estimated total propulsion force is obtained according to the force balance equation, and the distribution ratio of the total cylinder propulsion force and the total traction force is determined based on the total propulsion force; The posture deviation of the shield machine is obtained, and the total traction force is decomposed into the three axial traction force components of X, Y, and Z. Based on the decomposition of the total traction force into the three axial traction force components of X, Y, and Z, the pulling force of the traction device is controlled.

2. The shield machine escape body traction control method using omnidirectional traction according to claim 1 is characterized in that: Based on historical shield construction data, the methods for predicting the current thrust resistance of the shield machine based on the long short-term memory network include: Obtain historical shield construction data from the shield machine database. The historical shield construction data includes geological conditions, construction parameters, and historical propulsion resistance. Build a propulsion resistance training set and a propulsion resistance test set based on the historical shield construction data. Construct a regression network model, use the geological conditions and construction parameters in the propulsion resistance training set as input data of the regression network model, use the historical propulsion resistance in the propulsion resistance training set as output data of the regression network model, train the regression network model, and obtain an initial coefficient prediction regression network; The initial coefficient prediction regression network is validated using a propulsion resistance test set, and an initial coefficient prediction regression network with a prediction error less than or equal to a preset error threshold is output as a propulsion resistance prediction model; the regression network model is specifically a long short-term memory network model; The geological conditions and construction parameters of the current shield machine are collected, input into the trained propulsion resistance prediction model, and the propulsion resistance is output.

3. The shield machine escape body traction control method using omnidirectional traction force according to claim 2 is characterized in that: The geological conditions include stratum characteristics and the strength, density and water content corresponding to the stratum characteristics; the stratum characteristics include soft soil, sand, clay and rock categories, wherein the geological conditions are directly obtained through drilling, sampling and testing; the construction parameters of the shield machine are obtained, and the construction parameters include the specifications of the shield machine, the cutterhead diameter, and the tool configuration.

4. The shield machine escape body traction control method using omnidirectional traction according to claim 1, characterized in that: The method for determining the distribution ratio of the total cylinder propulsion force and the total traction force based on the total propulsion force includes: Using 3D modeling software to create a geometric model of the shield machine, the geometric model including key components, wherein the key components include a cutterhead, a main machine, a propulsion system, and a traction device; Divide the geometric model into mesh elements for finite element analysis based on the preset mesh density; Setting material properties for key components in the geometric model, including elastic modulus, Poisson's ratio, and density; According to the actual construction situation, the boundary conditions of the geometric model are set, including fixed support and free surface; The ratio of propulsion force and total traction force is adjusted in the geometric model, different combinations of propulsion force and total traction force are input, and the deformation and escape time of the shield machine under different combinations are evaluated.

5. The shield machine escape body traction control method using omnidirectional traction force according to claim 4 is characterized in that: The method for evaluating the deformation and escape time of the shield machine under different combinations includes: A deformation threshold is preset, and combinations of propulsion force and total traction force below the deformation threshold are obtained. The obtained propulsion force and total traction force combinations are sorted in sequence according to the length of the escape time to establish a parameter set. The order of arrangement in the parameter set is sorted in increasing order according to the escape time; Based on the maximum thrust of the shield machine and the maximum traction of the traction device, the optimal combination of thrust and total traction is obtained.

6. The shield machine escape body traction control method using omnidirectional traction according to claim 5, characterized in that: The method for obtaining the optimal propulsion force and total traction force combination includes: Step 1: Obtain the propulsion force and total traction force combination corresponding to the shortest escape time within the parameter set; Step 2: Compare the values ​​of the propulsion force and total traction force combination to see if they exceed the maximum propulsion force of the shield machine and the maximum traction force of the traction device. If one of the values ​​exceeds the maximum propulsion force, the propulsion force and total traction force combination is discarded and removed from the parameter set. Step 3, repeat step 1 until the values ​​of the propulsion force and total traction force combination corresponding to the shortest escape time do not exceed the maximum propulsion force of the shield machine and the maximum traction force of the traction device. At this time, the propulsion force and total traction force combination is recorded as the optimal propulsion force and total traction force combination.

7. The shield machine escape body traction control method using omnidirectional traction force according to claim 1, characterized in that: The method of decomposing the total traction force into three axial traction force components X, Y, and Z includes: Based on the shield machine's control system and the pre-set shield route, the current yaw angle and pitch angle of the shield machine are obtained, where the yaw angle is the left and right deflection angle of the shield machine in the horizontal direction, and the pitch angle is the deflection angle of the shield machine in the vertical direction; The total traction force component in the X-axis direction is obtained based on the yaw angle calculation; The total traction force component in the Y-axis direction is obtained based on the pitch angle calculation; The total traction force component in the Z-axis direction is obtained based on the total traction force component in the X-axis direction, the total traction force component in the Y-axis direction, and the total traction force.

8. The shield machine escape body traction control method using omnidirectional traction force according to claim 1, characterized in that: Also includes: The attitude parameters of the shield machine are acquired in real time and analyzed. When the shield machine has an abnormal attitude, an escape adjustment instruction is generated, and the traction and propulsion forces are recalculated and distributed based on the escape adjustment instruction.

9. The shield machine escape body traction control method using omnidirectional traction force according to claim 8, characterized in that: The method for generating an escape adjustment instruction includes: Using an attitude sensor to obtain real-time attitude parameters of the shield machine, the attitude parameters include pitch angle and yaw angle; The real-time posture parameters are compared with the standard posture parameters to obtain the posture deviation. If the posture deviation exceeds the allowable range, it is determined that there is a posture abnormality.

10. A shield machine escape body traction control system using omnidirectional traction, which is used to implement the shield machine escape body traction control method using omnidirectional traction according to any one of claims 1 to 9, characterized in that: The system comprises: The resistance prediction module predicts the current thrust resistance of the shield machine based on historical shield construction data and long-short-term memory networks; The omnidirectional traction design module uses distributed hydraulic cylinders to arrange traction devices at the front, rear, sides, and bottom of the shield machine, giving it omnidirectional traction capabilities. The traction devices are connected to the shield machine through an articulated structure to achieve free traction in the X, Y, and Z axes. A propulsion force distribution module obtains the estimated total propulsion force based on the propulsion resistance and the force balance equation, and determines the distribution ratio of the total cylinder propulsion force and the total traction force based on the total propulsion force; The traction force distribution module obtains the posture deviation of the shield machine and decomposes the total traction force into the three axial traction force components of X, Y, and Z. Based on the decomposition of the total traction force into the three axial traction force components of X, Y, and Z, the pulling force of the traction device is controlled.

Images