Shield attitude autonomous adjustment control method and system

Abstract

The invention discloses a shield attitude autonomous adjustment control method and system, and belongs to the technical field of shield attitude adjustment. Comprising the following steps: acquiring key tunneling parameters and shield attitude parameters during tunneling of a shield tunneling machine, and performing data preprocessing; related tunneling parameters are screened out to construct a shield attitude prediction model, the related tunneling parameters are used as input, the shield attitude parameters are used as output, and the shield attitude prediction model is used for predicting the tunneling prediction attitude of the shield tunneling machine in a future preset range; determining a shield deviation rectification path planning curve based on a judgment result if the broken tunneling prediction attitude meets the requirement; and establishing a grouped oil cylinder pressure prediction model, and predicting a pressure decision value of each grouped oil cylinder according to the determined shield deviation rectification path planning curve. A complete shield attitude autonomous control system is provided, the problems of inaccurate shield attitude judgment, unstable deviation correction operation control and the like are solved, the phenomena of excessive shield attitude fluctuation, snakelike deviation correction and the like are avoided, and accurate control over the shield attitude is achieved.

Description

Technical Field

[0001] The invention belongs to the technical field of shield attitude adjustment, and particularly relates to a shield attitude autonomous adjustment control method and system. Background Technique

[0002] A shield machine is a large-scale tunnel construction equipment integrating multiple disciplines such as machinery, hydraulics, electricity, and control. Due to the characteristics of high automation, good safety performance, and fast construction speed in shield construction, shield machines are widely used in projects such as urban subway tunnels, municipal pipe networks, and cross-sea tunnels. However, with the economic development, the construction difficulty of tunnel projects has been increasing continuously. Shield machines are faced with uncertain geological environments, high-difficulty working conditions, and complex supporting equipment, and it is often difficult to ensure the construction quality of tunnels. The degree of coincidence between the actual axis of the shield machine and the tunnel design axis is the key factor determining the tunnel construction quality.

[0003] Attitude control during shield tunneling is of utmost importance. If the attitude deviation is too large, it is extremely easy to cause the actual tunneling trajectory to deviate from the design axis, and the segments are prone to staggering, and even safety hazards such as water leakage may occur. In the actual shield construction process, the control of the shield machine attitude mainly depends on the shield driver to control the pressure of the sectional cylinders of the shield machine propulsion system according to the results of the measurement system and the design axis information, so as to realize the control of the shield machine attitude. Its deviation correction effect often depends on the technology, experience, and sense of responsibility of the shield driver, and the tunnel forming quality cannot be guaranteed. Summary of the Invention

[0004] The invention provides a shield attitude autonomous adjustment control method and system to solve the technical problems existing in the above background technique.

[0005] The invention is realized through the following technical solutions: A shield attitude autonomous adjustment control method includes the following steps: Obtain the key tunneling parameters and shield attitude parameters during shield machine tunneling, and respectively perform data preprocessing to obtain data parameters of the same order of magnitude; Based on the data parameters of the same order of magnitude, screen out relevant tunneling parameters, and there is a predetermined degree of correlation between the relevant tunneling parameters and the shield attitude parameters; Construct a shield attitude prediction model, use the relevant tunneling parameters as inputs and the shield attitude parameters as outputs, and use the shield attitude prediction model to predict the tunneling prediction attitude of the shield machine within a predetermined range in the future; Construct tunneling constraint conditions, perform corresponding analysis on the predicted parameter values of the tunneling prediction attitude and the tunneling constraint conditions to obtain a judgment result; determine the shield deviation correction path planning curve based on the judgment result; Establish a sectional cylinder pressure prediction model, and predict the pressure decision values of each sectional cylinder according to the determined shield deviation correction path planning curve.

[0006] In a further embodiment, the following steps are further included: Construct a PID control model based on an intelligent algorithm and establish a communication relationship with the shield machine PLC ; Transmit the pressure decision value to the PID control model for controlling the proportional valves and overflow valves of the grouped cylinders of the shield machine to achieve autonomous control of the shield attitude.

[0007] In a further embodiment, the key tunneling parameters at least include: A the pressure of the grouped cylinders, B the pressure of the grouped cylinders, C the pressure of the grouped cylinders, D the pressure of the grouped cylinders, E the pressure of the grouped cylinders, F the pressure of the grouped cylinders, tunneling thrust, propulsion speed, cutter head torque, cutter head rotation speed, penetration degree, tail gap, grouting volume, grease injection volume, slurry inlet flow rate, slurry outlet flow rate, excavation chamber pressure and air cushion chamber pressure; The shield attitude parameters at least include: the horizontal deviation value of the shield head, the vertical deviation value of the shield head, the horizontal deviation value of the shield tail and the vertical deviation value of the shield tail.

[0008] In a further embodiment, the preprocessing process of the data parameters of the same magnitude includes: Perform data partitioning, data cleaning, and data elimination on the key tunneling parameters and shield attitude parameters respectively to obtain effective parameter data; Perform local dimensionless processing on the effective parameter data to make them of the same magnitude.

[0009] In a further embodiment, the screening process of the relevant tunneling parameters is as follows: Calculate the importance scores of the key tunneling parameters using a gradient decision tree , and sort the key tunneling parameters in descending order according to their importance scores ; Define the key tunneling parameters ranked in the top predetermined number as the relevant tunneling parameters; Among them, the calculation formula of the importance score is as follows: ; In the formula, represents a node, represents the number of all trees, represents m the number of non-leaf nodes of trees, m represents the j th non-leaf node of the is the loss function, , respectively represent the sum of the first-order derivatives and the sum of the second-order derivatives of all samples falling on the m th non-leaf node of the j th tree, , respectively represent the sum of the first-order derivatives on the left node L and the sum of the first-order derivatives on the right node R of the m th non-leaf node on the j th tree, , respectively represent the sum of the second-order derivatives on the left node L and the sum of the second-order derivatives on the right node R of the m th non-leaf node on the j th tree, represents the hyperparameter of the regularization term.

[0010] In a further embodiment, the tunneling constraint conditions include: the constraint condition of the shield head horizontal deviation, the constraint condition of the shield head vertical deviation, the constraint condition of the shield tail horizontal deviation, and the constraint condition of the shield tail vertical deviation; The predicted parameter values include: the predicted value of the shield head horizontal deviation , the predicted value of the shield head vertical deviation , the predicted value of the shield tail horizontal deviation , and the predicted value of the shield tail horizontal deviation ; Correspondingly, the analysis process of the judgment result is: if the judgment formula is satisfied, the judgment result is in line with the tunneling requirements; otherwise, the judgment result is not in line with the tunneling requirements; The expression form of the judgment formula is as follows: ; In the formula, 、 、 and are the standard values of the shield head horizontal deviation, the shield head vertical deviation, the shield tail horizontal deviation, and the shield tail horizontal deviation respectively.

[0011] In a further embodiment, the method for determining the shield tunneling deviation correction path planning curve is as follows: If the judgment result is in line with the tunneling requirements, tunneling is carried out according to the current shield tunneling deviation correction path planning curve; If the judgment result is not in line with the tunneling requirements, a shield attitude deviation correction path planning parameter equation is established based on the current attitude information and the tunneling constraint conditions; a new shield tunneling deviation correction path planning curve is determined according to the shield attitude deviation correction path planning parameter equation, and tunneling is carried out according to the new shield tunneling deviation correction path planning curve.

[0012] In a further embodiment, the expression form of the grouped cylinder pressure prediction model is as follows: ; Wherein, is the number of samples, represents the parameter value of sample , represents the predicted value of the first decision trees together for sample , represents the t th decision tree model complexity, is the loss function, is the objective function; Correspondingly, the process for determining the pressure decision value is: taking the shield attitude parameters on the determined shield deviation correction path planning curve as the input, and using the grouped cylinder pressure prediction model to obtain the pressure decision values of each grouped cylinder.

[0013] In a further embodiment, the process for establishing the parameter equation of the shield attitude deviation correction path planning is as follows: Obtain the current attitude information, including the axis coordinates of the shield tunnel, the minimum turning radius of the shield machine , the minimum turning radius of the tunnel , the tail clearance , the segment length and the cylinder stroke difference; Taking the shortest path as the goal, use the following formula to calculate the minimum deviation correction curvature radius : ; Wherein, is the allowable deviation correction radius of the tail clearance, and its calculation formula is: ; is the minimum allowable deviation correction radius of the cylinder stroke difference, and its calculation formula is: , is the radius of the propulsion cylinder, is the distance from the cutter head of the shield to the tail; Based on the minimum deviation correction curvature radius , construct a parameter equation for the shield attitude deviation correction path planning that satisfies the tunneling constraint conditions, expressed as: ; ; Wherein, , are the coordinates of the starting point and the ending point of the deviation correction curve respectively, is the coordinate of a fitting point after the end point, is the coordinate of the shield tail center, is the radius of curvature of the deviation correction curve, and are respectively the first-order and second-order derivatives of the equation , and , and d are all coefficients, represents being limited by.

[0014] A shield attitude autonomous adjustment control system for implementing the shield attitude autonomous adjustment control method as described above, comprising: A data acquisition module, configured to obtain key tunneling parameters and shield attitude parameters during the tunneling of the shield machine; A data processing module, configured to perform data preprocessing on the key tunneling parameters and shield attitude parameters to obtain data parameters of the same order of magnitude; screening out relevant tunneling parameters based on the data parameters of the same order of magnitude, and there is a predetermined degree of correlation between the relevant tunneling parameters and the shield attitude parameters; An intelligent decision-making module, configured to build a shield attitude prediction model, using the relevant tunneling parameters as inputs and the shield attitude parameters as outputs, and predicting the tunneling prediction attitude of the shield machine within a predetermined range in the future by using the shield attitude prediction model; performing corresponding analysis on the prediction parameter values of the tunneling prediction attitude and the tunneling constraint conditions to obtain a judgment result; determining the shield deviation correction path planning curve based on the judgment result; establishing a grouped oil cylinder pressure prediction model, and predicting the pressure decision values of each grouped oil cylinder according to the determined shield deviation correction path planning curve; An autonomous control module, configured to build a PID control model based on an intelligent algorithm, and establish a PLC communication relationship with the shield machine; transmitting the pressure decision values to the PID control model for controlling the proportional valves and overflow valves of the grouped oil cylinders of the shield machine to achieve autonomous control of the shield attitude.

[0015] Advantages of the present invention: The shield attitude autonomous control method provided by the present invention predicts the shield attitude within a certain mileage range in the future by building a shield attitude prediction model, and judges whether the shield attitude within a certain mileage range in the future meets the requirements according to the actual construction shield tunneling constraint conditions, and then establishes a shield attitude deviation correction path planning parameter equation and gives a shield attitude deviation correction path planning curve. Subsequently, based on the shield attitude deviation correction path planning curve and combined with the shield attitude parameters, an association relationship between the relevant parameters of the shield deviation correction curve and the grouped oil cylinders is established, and the pressure and stroke decision values of each grouped oil cylinder are given. Finally, by establishing a PLC communication relationship with the shield machine and using PIDThe controller realizes the control of the pressure and stroke of the sectional oil cylinder, and finally realizes the autonomous control of the shield attitude.

[0016] The present invention provides a complete autonomous control system for the shield attitude, solves the problems of inaccurate judgment of the shield attitude and unstable control of the deviation correction operation during the manual operation process, can effectively avoid phenomena such as excessive fluctuation of the shield attitude and snake-shaped deviation correction, and realizes the autonomous and precise control of the shield attitude. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flowchart of the method for autonomous adjustment and control of the shield attitude in Embodiment 1.

[0018] Figure 2 It is a block diagram of the architecture of the system for autonomous adjustment and control of the shield attitude in Embodiment 2. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. This description is only a part of the embodiments of the present invention and does not represent all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0020] Embodiment 1 As Figure 1 shown, this embodiment discloses a method for autonomous adjustment and control of the shield attitude, including the following steps: Obtain the key tunneling parameters and shield attitude parameters during the tunneling of the shield machine, and respectively perform data preprocessing to obtain data parameters of the same order of magnitude; Based on the data parameters of the same order of magnitude, screen out the relevant tunneling parameters, and there is a predetermined degree of correlation between the relevant tunneling parameters and the shield attitude parameters; Use GRU a neural network to construct a shield attitude prediction model, use the relevant tunneling parameters as inputs and the shield attitude parameters as outputs, and use the shield attitude prediction model to predict the tunneling prediction attitude of the shield machine within a predetermined range in the future; the predetermined range in the future is in meters and can be a length such as 20 meters, 30 meters, etc.

[0021] Construct tunneling constraint conditions, perform corresponding analysis on the predicted parameter values of the tunneling prediction attitude and the tunneling constraint conditions to obtain a judgment result; determine the shield deviation correction path planning curve based on the judgment result; Establish a grouped oil cylinder pressure prediction model, and predict the pressure decision values of each grouped oil cylinder according to the determined shield deviation correction path planning curve.

[0022] In a further embodiment, the key tunneling parameters at least include: AGroup cylinder pressure, B Group cylinder pressure, C Group cylinder pressure, D Group cylinder pressure, E Group cylinder pressure, F Group cylinder pressure, tunneling thrust, propulsion speed, cutterhead torque, cutterhead rotation speed, penetration rate, tail clearance, grouting volume, grease injection volume, slurry inflow rate, slurry outflow rate, excavation chamber pressure and air cushion chamber pressure; The shield attitude parameters at least include: shield head horizontal deviation value, shield head vertical deviation value, shield tail horizontal deviation value and shield tail vertical deviation value.

[0023] Considering that due to the physical meaning and engineering actual situation of the key tunneling parameters and shield attitude parameters themselves, their original magnitudes often vary greatly. For example, the tunneling thrust generally has a large value and may be measured in kilonewtons or even larger units, while the tail clearance value is relatively small and is measured in millimeters. When performing statistical analyses such as calculating the coefficient of variation of each parameter to measure the data dispersion degree and extracting key features through principal component analysis, if non-dimensionalization is not performed to make them in the same magnitude, then the parameters with large magnitudes will dominate in the calculation results, masking the true data characteristics and change situations of the parameters with small magnitudes, resulting in inaccurate conclusions about the influence of each parameter on the overall tunneling of the shield machine in the final analysis.

[0024] Therefore, the processing process of data parameters in the same magnitude includes: separately performing data partitioning, data cleaning, and data elimination on the key tunneling parameters and shield attitude parameters to obtain effective parameter data; performing local non-dimensionalization processing on the effective parameter data to make them in the same magnitude.

[0025] The processing process of data partitioning can be: partitioning according to different strata (such as soft soil layers, rock layers, etc.) that the shield machine passes through, because the performance and variation laws of each parameter under different strata conditions often have large differences. It is beneficial to analyze the characteristics of data in each region more pertinently later and discover the variation trends and mutual relationships of parameters under specific working conditions. Further understood as, when the stratum type changes, it is marked as the starting point of a new partition. Then all parameter data within the same stratum interval are grouped into one partition, and the data of different partitions are stored separately for convenient subsequent individual processing and analysis.

[0026] The processing process of data cleaning can be: checking each part of the data after partitioning and removing the data with obvious errors or that do not conform to the actual physical meaning. Among the shield machine parameters, possible error data such as extremely large abnormal values of the tunneling thrust caused by sensor failures (far exceeding the reasonable range of this parameter under normal construction conditions), or data loss of the tail clearance caused by communication interference, etc. Cleaning these data can ensure the data quality of subsequent analysis and processing and avoid misleading the results by incorrect data.

[0027] Correspondingly, after data cleaning, there may still be some data that, although not significantly incorrect, is not highly relevant to the analysis objective, or is redundant in a specific analysis scenario. These data are removed to make the remaining data more focused on the key tunneling performance and attitude characteristics of the shield machine. For example, when studying the relationship between the attitude parameters and the tunneling speed of the shield machine during tunneling in stable strata, some data recorded due to short-term external disturbances that have little relevance to the overall analysis can be removed.

[0028] The dimensionless processing mentioned in this embodiment can be normalization processing or standardization processing.

[0029] Combined with the above description, the screening process of relevant tunneling parameters is as follows: Calculate the importance scores of key tunneling parameters using a gradient decision tree and sort the key tunneling parameters in descending order according to their importance scores; define the key tunneling parameters ranked in the top predetermined number as relevant tunneling parameters; Among them, the calculation formula of the importance score is as follows: ; ; In the formula, represents a node, represents the number of all trees, represents m the number of non-leaf nodes of the th tree, m represents the j th non-leaf node of the th tree, is the loss function, and m respectively represent the sum of the first-order derivatives and the sum of the second-order derivatives of all samples falling on the j th non-leaf node of the th tree, and m respectively represent the sum of the first-order derivatives and the sum of the second-order derivatives of the left node L and the right node R of the j th non-leaf node of the th tree, and m respectively represent the sum of the first-order derivatives and the sum of the second-order derivatives of the left node L and the right node R of the j th non-leaf node of the th tree;

[0030] According to the current tunneling scenario and geological conditions, taking the existence of A - F groups of oil cylinders as an example, calculate the importance scores of the key tunneling parameters for each group of oil cylinders. The predetermined ranking is the top three before customization. For example, the tunneling thrust of the A group of oil cylinders ranked in the top three, A the propulsion speed of the C group of oil cylinders, and

[0031] the cutter head torque of the A group of oil cylinders are selected as the relevant tunneling parameters. B The pressure of the C group of oil cylinders is 0.13 points, D the pressure of the E group of oil cylinders is 0.13 points, F the pressure of the

[0032] In this embodiment, the top 10 parameters with the highest scores are selected as the key tunneling parameters, which are respectively A the pressure of the B group of oil cylinders, C the pressure of the D group of oil cylinders, E the pressure of the F group of oil cylinders, the tunneling thrust, the propulsion speed, the cutter head torque, the cutter head rotation speed, the penetration degree, and the shield tail clearance.

[0033] In a further embodiment, the tunneling constraint conditions include: the constraint conditions of the shield head horizontal deviation, the constraint conditions of the shield head vertical deviation, the constraint conditions of the shield tail horizontal deviation, and the constraint conditions of the shield tail vertical deviation.

[0034] Correspondingly, the predicted parameter values of the tunneling predicted attitude are analyzed corresponding to the tunneling constraint conditions to obtain a judgment result. Among them, the predicted parameter values include: the predicted value of the shield head horizontal deviation and the predicted value of the shield head vertical deviation , the predicted value of the shield tail horizontal deviation and the predicted value of the shield tail horizontal deviation ; If the following formula is satisfied, the judgment result meets the requirements; otherwise, it does not. ; In the formula, 、 、 and are respectively the standard value of the shield head horizontal deviation, the standard value of the shield head vertical deviation, the standard value of the shield tail horizontal deviation, and the standard value of the shield tail horizontal deviation.

[0035] For example, in this embodiment, 、 、 and take the following values: , so the above formula is updated to: .

[0036] Furthermore, the method for determining the shield deviation correction path planning curve is as follows: If the judgment result meets the tunneling requirements, then tunnel according to the current shield deviation correction path planning curve; If the judgment result does not meet the tunneling requirements, then establish a shield attitude deviation correction path planning parameter equation based on the current attitude information and tunneling constraint conditions; determine a new shield deviation correction path planning curve according to the shield attitude deviation correction path planning parameter equation, and tunnel according to the new shield deviation correction path planning curve.

[0037] The expression form of the grouped cylinder pressure prediction model is as follows: ; In the formula, is the number of samples, represents the parameter value of sample , represents the prediction value of the first decision trees together for sample , represents the t th decision tree model complexity, is the loss function, is the objective function; Correspondingly, the process for determining the pressure decision value is: taking the shield attitude parameters (shield head horizontal deviation value, shield head vertical deviation value, shield tail horizontal deviation value, and shield tail vertical deviation value) on the determined shield deviation correction path planning curve as the input, using the grouped cylinder pressure prediction model to obtain the pressure decision values of each grouped cylinder, and combining the above example, the pressure decision values are specifically A - F the pressure decision values of the cylinder groups.

[0038] Furthermore, the establishment process of the shield attitude correction path planning parametric equation is as follows: Obtain the current attitude information, including the axis coordinates of the shield tunnel, the minimum turning radius of the shield machine , the minimum turning radius of the tunnel , the clearance between the shield tail , the segment length and the difference in cylinder strokes; Taking the shortest path as the goal, calculate the minimum correction curvature radius using the following formula : ; In the formula, is the correction radius allowed by the clearance between the shield tail, and its calculation formula is: ; is the minimum correction radius allowed by the difference in cylinder strokes, and its calculation formula is: , is the radius of the propulsion cylinder, is the distance from the cutting edge of the shield cutterhead to the shield tail; Based on the minimum correction curvature radius , construct the shield attitude correction path planning parametric equation that satisfies the tunneling constraint conditions; The shield attitude correction path planning parametric equation is constructed using a cubic parabola, and the equation is: ; To make the shield correction planning curve smooth and facilitate the shield machine to fit the tunnel design axis for correction, the following conditions need to be met: ; ; ; ; ; In the formula, , are the starting and ending coordinates of the correction curve respectively, is the coordinate of the first fitting point after the end point, is the coordinate of the shield tail center, is the curvature radius of the correction curve, , are the first and second derivatives of the equation respectively, , , and d are all coefficients.

[0039] In a further embodiment, based on the pressure decision values of each grouped oil cylinder obtained from the above steps, it further includes: constructing an PID intelligent algorithm-based PLC control model and establishing a communication relationship with the shield machine; transmitting the pressure decision value to the PID control model to control the proportional valves and overflow valves of the grouped oil cylinders of the shield machine, so as to achieve autonomous control of the shield attitude.

[0040] Embodiment 2 This embodiment discloses an autonomous shield attitude adjustment control system for implementing the autonomous shield attitude adjustment control method as described in Embodiment 1. As Figure 2 shown, it includes: A data acquisition module, which is configured to obtain the key tunneling parameters and shield attitude parameters during the tunneling of the shield machine; A data processing module, which is configured to perform data preprocessing on the key tunneling parameters and shield attitude parameters to obtain data parameters of the same order of magnitude; screening out relevant tunneling parameters based on the data parameters of the same order of magnitude, and there is a predetermined degree of correlation between the relevant tunneling parameters and the shield attitude parameters; An intelligent decision-making module, which is configured to construct a shield attitude prediction model, use the relevant tunneling parameters as inputs and the shield attitude parameters as outputs, and predict the tunneling prediction attitude of the shield machine within a future predetermined range by using the shield attitude prediction model; constructing tunneling constraint conditions, judging whether the tunneling prediction attitude meets the requirements, and determining the shield deviation correction path planning curve based on the judgment result; establishing a grouped oil cylinder pressure prediction model, and predicting the pressure decision values of each grouped oil cylinder according to the determined shield deviation correction path planning curve; An autonomous control module, which is configured to construct an PID intelligent algorithm-based PLC control model and establish a communication relationship with the shield machine; transmitting the pressure decision value to the PID control model to control the proportional valves and overflow valves of the grouped oil cylinders of the shield machine, so as to achieve autonomous control of the shield attitude.

Claims

1. A shield machine posture autonomous adjustment control method, characterized in that: The following steps are involved: Obtain key tunneling parameters and shield attitude parameters during shield machine tunneling, and perform data preprocessing to obtain data parameters of the same order of magnitude; Based on the data parameters of the same magnitude, relevant excavation parameters are selected, wherein the relevant excavation parameters have a predetermined degree of correlation with the shield attitude parameters; Construct a shield machine attitude prediction model, take relevant tunneling parameters as input and shield machine attitude parameters as output, and use the shield machine attitude prediction model to predict the tunneling prediction attitude of the shield machine within the predetermined range in the future; Construct excavation constraint conditions, and analyze the predicted parameter values ​​of the excavation prediction posture and the excavation constraint conditions to obtain the judgment result; determine the shield deviation correction path planning curve based on the judgment result; A group cylinder pressure prediction model is established, and the pressure decision value of each group cylinder is predicted according to the determined shield correction path planning curve.

2. A shield machine posture autonomous adjustment control method according to claim 1, characterized in that: The following steps are also included: Build an intelligent algorithm based PID Control model, build and shield machine PLC correspondence relationship; The pressure decision value is transmitted to PID The control model is used to control the shield machine's grouped cylinder proportional valves and overflow valves to achieve autonomous control of the shield machine's posture.

3. The shield machine posture autonomous adjustment control method according to claim 1 is characterized in that: The key excavation parameters include at least: A Cylinder pressure, B Cylinder pressure, C Cylinder pressure, D Cylinder pressure, E Cylinder pressure, F Cylinder pressure, driving thrust, propulsion speed, cutter head torque, cutter head speed, penetration, shield tail gap, grouting volume, grease injection volume, grouting flow rate, grouting flow rate, excavation chamber pressure and air cushion chamber pressure; The shield posture parameters at least include: a shield head horizontal deviation value, a shield head vertical deviation value, a shield tail horizontal deviation value and a shield tail vertical deviation value.

4. The shield machine posture autonomous adjustment control method according to claim 1 is characterized in that: The preprocessing process of the data parameters of the same magnitude includes: The key excavation parameters and shield attitude parameters are partitioned, cleaned and eliminated to obtain effective parameter data; The effective parameter data are locally dimensionless processed to make them at the same order of magnitude.

5. The shield machine posture autonomous adjustment control method according to claim 1 is characterized in that: The screening process of the relevant excavation parameters is as follows: Calculating the importance scores of key tunneling parameters using gradient decision trees and score the key excavation parameters according to their importance Sorting the parameters from high to low; defining the key excavation parameters ranked in the front as relevant excavation parameters; Among them, the importance score The calculation formula is as follows: ； In the formula, Represents a node, represents the number of all trees, express m The number of non-leaf nodes in a tree, Indicates m The tree j The partitioning features of non-leaf nodes, is the loss function, , Respectively indicate that they fall in m The tree j The sum of the first-order derivatives and the sum of the second-order derivatives of all samples on non-leaf nodes, , Respectively indicate that they fall in m The first j The sum of the first-order derivatives on the left node L and the first-order derivatives on the right node R of the non-leaf nodes, , Respectively indicate that they fall in m The first j The sum of the second-order derivatives on the left node L and the second-order derivatives on the right node R of the non-leaf nodes, represents the hyperparameter of the regularization term.

6. The shield machine posture autonomous adjustment control method according to claim 1 is characterized in that: The excavation constraint conditions include: constraint conditions for horizontal deviation of the shield head, constraint conditions for vertical deviation of the shield head, constraint conditions for horizontal deviation of the shield tail, and constraint conditions for vertical deviation of the shield tail; The predicted parameter values ​​include: , shield head vertical deviation prediction value , Shield tail horizontal deviation prediction value and the predicted value of shield tail horizontal deviation ; Correspondingly, the analysis process of the judgment result is: if the judgment formula is satisfied, the judgment result is that the excavation requirement is met; otherwise, the judgment result is that the excavation requirement is not met; The expression form of the judgment formula is as follows: ； In the formula, 、 、 and They are respectively the standard value of horizontal deviation of the shield head, the standard value of vertical deviation of the shield head, the standard value of horizontal deviation of the shield tail and the standard value of horizontal deviation of the shield tail.

7. The shield machine posture autonomous adjustment control method according to claim 1 is characterized in that: The method for determining the shield deviation correction path planning curve is as follows: If the judgment result is that it meets the excavation requirements, excavation will be carried out according to the current shield deviation correction path planning curve; If the judgment result is that it does not meet the excavation requirements, a shield posture correction path planning parameter equation is established based on the current posture information and excavation constraints; A new shield deviation correction path planning curve is determined according to the shield attitude deviation correction path planning parameter equation, and excavation is carried out according to the new shield deviation correction path planning curve.

8. The shield machine posture autonomous adjustment control method according to claim 1 is characterized in that: The grouped cylinder pressure prediction model is expressed as follows: ； In the formula, is the sample size, Representation sample Parameter value, Before Decision trees are used together to analyze the samples The predicted value of Indicates t Decision Tree Model The complexity of is the loss function, is the objective function; Correspondingly, the process of determining the pressure decision value is as follows: taking the shield posture parameters on the determined shield correction path planning curve as input, and using the grouped cylinder pressure prediction model to obtain the pressure decision value of each grouped cylinder.

9. The shield machine posture autonomous adjustment control method according to claim 7 is characterized in that: The process of establishing the shield posture correction path planning parameter equation is as follows: Get the current posture information, including the axis coordinates of the shield tunnel and the minimum turning radius of the shield machine , Minimum turning radius of tunnel Shield tail clearance , Segment length and cylinder stroke difference; Taking the shortest path as the goal, the minimum correction curvature radius is calculated using the following formula: : ； In the formula, is the correction radius allowed by the shield tail gap, and its calculation formula is: ; is the minimum deviation correction radius allowed by the cylinder stroke difference, and its calculation formula is: , is the radius of the thrust cylinder, It is the distance from the cutterhead to the shield tail; Based on the minimum correction curvature radius , the shield attitude correction path planning parameter equation that meets the tunneling constraints is constructed and expressed as: ； ； In the formula, , are the starting and ending coordinates of the correction curve, is the coordinate of the fitting point after the end point, is the center coordinate of the shield tail, is the curvature radius of the correction curve, , The equations are The first and second derivatives of , , and d are coefficients, Indicates restricted by.

10. A shield machine posture autonomous adjustment control system, used to implement the shield machine posture autonomous adjustment control method as claimed in any one of claims 1 to 9, characterized in that: include: The data acquisition module is configured to obtain key tunneling parameters and shield attitude parameters during tunneling of the shield machine; The data processing module is configured to perform data preprocessing on key excavation parameters and shield attitude parameters to obtain data parameters of the same magnitude; based on the data parameters of the same magnitude, relevant excavation parameters are screened out, and the relevant excavation parameters have a predetermined degree of correlation with the shield attitude parameters; The intelligent decision-making module is configured to construct a shield attitude prediction model, taking relevant tunneling parameters as input and shield attitude parameters as output, and using the shield attitude prediction model to predict the tunneling prediction attitude of the shield machine within a predetermined range in the future; The predicted parameter values ​​of the tunneling prediction posture are analyzed correspondingly with the tunneling constraint conditions to obtain the judgment result; the shield deviation correction path planning curve is determined based on the judgment result; a group cylinder pressure prediction model is established, and the pressure decision value of each group cylinder is predicted according to the determined shield deviation correction path planning curve; Autonomous control module, which is set up to build an intelligent algorithm based PID Control model, build and shield machine PLC Communication relationship; transmitting the pressure decision value to the PID control model to control the shield machine group cylinder proportional valve and overflow valve to achieve autonomous control of the shield machine posture.

Images