A shield tunneling posture planning method for multi-target control optimization

Abstract

This invention discloses a method for planning the tunneling posture of a tunnel boring machine (TBM) for multi-objective control optimization, belonging to the field of intelligent control technology. The method includes: collecting relevant data of the TBM and calculating score weights; calculating and updating the normal vector and the rear center spatial position based on the relevant data; calculating the intersection point of the TBM's rear face with the target curve based on the updated normal vector and the updated rear center spatial position, and calculating the update deviation; establishing a local coordinate system; calculating the center position and normal vector in the local coordinate system of the segment end face; calculating the future minimum tail clearance and the future maximum cylinder stroke difference; calculating a weighted score based on the score weights, update deviation, future minimum tail clearance, and future maximum cylinder stroke difference; and obtaining the optimal yaw angle and pitch angle based on the weighted score. This invention ensures that the TBM tunnels according to the planned target curve, while also controlling the gap between the TBM and the segments at the tail of the TBM to be not too small and the stroke difference between different cylinders of the TBM to be not too large.

Description

Technical Field

[0001] This invention belongs to the field of intelligent control technology, specifically relating to a method for planning the tunneling posture of a tunnel boring machine for multi-objective control optimization. Background Technology

[0002] Currently, the attitude control of tunnel boring machines (TBMs) mainly relies on the experience of the TBM operators. First, the TBM displays the deviation from the target curve, the tail clearance, and the difference in cylinder stroke. Then, engineers determine, based on their experience, which direction the TBM needs to be adjusted, i.e., how to adjust the TBM's attitude. Finally, the TBM operators input the planned attitude into the TBM, and the TBM adjusts the pressure distribution of multiple cylinders to achieve the target attitude. Currently available patents address single, existing indicators (deviation, tail clearance, or cylinder stroke difference) and then control the cylinder pressure distribution to achieve the input TBM attitude. There is no method for planning and determining the TBM's attitude using multiple indicators as control targets.

[0003] Currently, relying primarily on manual methods is not in line with the trend towards digitalization and intelligentization. Furthermore, the effectiveness of manual control is highly dependent on the experience of the personnel, leading to unstable control results. Partially automated trajectory control methods focus only on the single indicator of the deviation between the tunnel boring machine (TBM) and the target curve, failing to consider multiple indicators simultaneously. If the tail clearance is too small, it may cause segment fracturing and excessive wear of the tail brush; if the hydraulic cylinder stroke difference is too large, it may lead to a TBM safety accident. Therefore, multiple indicators should be simultaneously optimized and controlled to ensure the safety, efficiency, and quality of TBM tunneling. Summary of the Invention

[0004] This invention aims to address the shortcomings of existing technologies by proposing a shield tunneling attitude planning method for multi-objective control optimization. In each step, the optimal shield pitch angle and yaw angle are obtained by optimizing the weighted score of the tail clearance, cylinder stroke difference, and shield deviation.

[0005] To achieve the above objectives, the present invention provides the following solution: a method for planning the tunneling posture of a tunnel boring machine for multi-objective control optimization, comprising the following steps:

[0006] Step 1: Collect standard data of the tunnel boring machine (TBM), deviation data between the TBM and the target curve, and the current pitch and yaw angles; and calculate the score weights based on the standard data and the deviation data; the standard data includes: the standard value of the engineering deviation, the standard value of the tail shield gap, the standard value of the hydraulic cylinder stroke difference, the standard tail shield gap, the current normal vector of the TBM, and the current spatial position of the rear center of the TBM; the deviation data includes: the current deviation, the current tail shield gap, and the current hydraulic cylinder stroke difference;

[0007] Step 2: Based on the planned pitch angle and yaw angle, as well as the planned normal vector and rear center spatial position of the tunnel boring machine (TBM), calculate the updated normal vector and updated rear center spatial position of the TBM after it has traveled a certain distance forward. During the iteration process, the initial planned pitch angle and yaw angle, as well as the planned normal vector and rear center spatial position of the TBM, adopt the current pitch angle and yaw angle, as well as the current normal vector and rear center spatial position of the TBM from Step 1.

[0008] Step 3: Calculate the intersection point of the rear face of the tunnel boring machine and the target curve based on the updated normal vector and the updated rear center spatial point of the tunnel boring machine, and calculate the update deviation between the intersection point and the updated rear center spatial point of the tunnel boring machine.

[0009] Step 4: Establish a local coordinate system with the updated rear center spatial point of the tunnel boring machine as the local coordinate origin and the updated normal vector of the tunnel boring machine as the x-axis; calculate the center point and normal vector in the local coordinate system of the end face of the tunnel segment.

[0010] Step 5: Based on the positional relationship between the tunnel boring machine and the tunnel segments, calculate the future minimum tail clearance and the future maximum cylinder stroke difference;

[0011] Step 6: Calculate the weighted score based on the scoring weights in Step 1, the update deviations in Step 3, and the future minimum shield tail clearance and the future maximum cylinder stroke difference in Step 5;

[0012] Step 7: Based on the weighted score, determine whether the yaw angle and the pitch angle are the optimal yaw angle and the optimal pitch angle; if yes, output the optimal yaw angle and the optimal pitch angle; if no, return to step 2 for iterative loop until yes.

[0013] More preferably, in step 1, the method for calculating the score weight includes:

[0014]

[0015] Θ=δ now / δ * +d maxnow / d * +(c′-c minnow ) / (c′-c * )

[0016] In the formula, Ψ δ Indicates the weight of the bias score; Ψ d Indicates the weighting of the hydraulic cylinder stroke difference score; Ψ c Indicates the weight of the shield tail gap score; δ nowΘ represents the current deviation; θ represents the current score; δ represents the current score. * The standard value representing the deviation; d maxnow This indicates the maximum cylinder stroke difference of the current tunnel boring machine; d * c represents the standard value of the cylinder stroke difference; c′ represents the standard shield tail clearance; c * The standard value representing the shield tail gap; c minnow This indicates the minimum tail clearance of the current tunnel boring machine.

[0017] More preferably, in step 2, the method for calculating the updated normal vector of the tunnel boring machine includes:

[0018]

[0019] In the formula, θ represents the updated normal vector of the tunnel boring machine; φ represents the pitch angle; and φ represents the yaw angle.

[0020] The method for calculating the updated back-end spatial position of the tunnel boring machine includes:

[0021]

[0022] In the formula, O Mnow Indicates the current spatial position of the rear center of the tunnel boring machine; O M d represents the updated rear center spatial position of the tunnel boring machine; d represents the forward distance of the tunnel boring machine. This represents the normal vector of the current tunnel boring machine.

[0023] More preferably, the method for calculating the center point in the local coordinate system of the end face of the tunnel segment includes:

[0024] O′=(O S -O M )·R(γ,θ,φ),

[0025] In the formula, O S Indicates the center point of the end face of the tunnel segment in the global coordinate system; O M R(γ,θ,φ) represents the updated rear center spatial position of the tunnel boring machine; R(γ,θ,φ) represents the rotation matrix.

[0026] The methods for calculating the normal vector in the local coordinate system at the end of the tunnel segment include:

[0027]

[0028] In the formula, This represents the normal vector of the end face of the pipe segment in the global coordinate system;

[0029] The rotation matrix is ​​established using the planned pitch and yaw angles of the tunnel boring machine.

[0030]

[0031] In the formula, θ represents the pitch angle; φ represents the yaw angle; and γ represents the roll angle.

[0032] More preferably, in step 5, based on the positional relationship between the tunnel boring machine and the tunnel segments, the position of the tunnel segment relative to the tunnel boring machine is obtained: O′=(x′,y′,z′).

[0033] The method for calculating the maximum future cylinder stroke difference includes:

[0034]

[0035] In the formula, d max Indicates the maximum future cylinder stroke difference; D C This represents the diameter of the circle formed by the strokes of multiple hydraulic cylinders in a tunnel boring machine.

[0036] The calculation method for the future minimum shield tail gap includes:

[0037] For any point J′ on the segment in the local coordinate system:

[0038]

[0039] In the formula, D S This indicates the diameter of the outer end face of the segment; α represents the angle between O′J′ and the horizontal plane.

[0040] in,

[0041]

[0042] The shield tail gap at point J′ is:

[0043] c(α)=0.5D M -|J′|sin(arccos(J′·(1,0,0))),

[0044] In the formula, D M Indicates the diameter of the shield tail of the tunnel boring machine;

[0045] The minimum value of function c(α) is calculated using the gradient descent method, thus obtaining the future minimum shield tail gap:

[0046]

[0047] More preferably, in step 6, the method for calculating the weighted score includes:

[0048] Score = Ψ δ ·δ / δ * +Ψ d ·dmax / d * +Ψ c ·(c′-c min ) / (c′-c * );

[0049] In the formula, δ represents the update bias; Ψ δ Indicates the weight of the bias score; Ψ d Indicates the weighting of the hydraulic cylinder stroke difference score; Ψ c Indicates the weight of the shield tail gap score; δ * The standard value representing the deviation; d * c represents the standard value of the cylinder stroke difference; c′ represents the standard shield tail clearance; c * This indicates the standard value for the shield tail gap.

[0050] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0051] This invention proposes a method to effectively calculate multiple future indicators under given pitch and yaw angles, and then simultaneously optimize the pitch and yaw angles of the tunnel boring machine using these multiple indicators as optimization targets. Existing technologies only offer methods for calculating and optimizing individual indicators, and these methods require geometric modeling, which is cumbersome and computationally intensive. This invention only requires vector operations, significantly reducing computational costs. Attached Figure Description

[0052] To more clearly illustrate the technical solution of the present invention, the drawings used in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is a schematic diagram of a shield tunneling posture planning method for multi-objective control optimization according to an embodiment of the present invention. Detailed Implementation

[0054] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0056] Example 1:

[0057] like Figure 1 As shown, this embodiment provides a shield tunneling attitude planning method for multi-objective control optimization. The shield tunneling process is a cyclic iterative process. The method designed in this invention obtains the optimal shield pitch angle and yaw angle at each step by optimizing the weighted score of the tail clearance, cylinder stroke difference, and shield deviation. Specifically, the optimization process at each step includes the following steps:

[0058] Step 1: Collect standard data of the tunnel boring machine (TBM), deviation data between the TBM and the target curve, and the current pitch and yaw angles; and calculate the score weights based on the standard data and deviation data. The standard data includes: the standard value of the engineering deviation, the standard value of the tail shield gap, the standard value of the hydraulic cylinder stroke difference, the standard tail shield gap, the current normal vector of the TBM, and the current spatial position of the rear center of the TBM. The deviation data includes: the current deviation, the current tail shield gap, and the current hydraulic cylinder stroke difference.

[0059] The methods for calculating score weights include:

[0060]

[0061] Θ=δ now / δ * +d maxnow / d * +(c′-c minnow ) / (c′-c * )

[0062] In the formula, Ψ δ Indicates the weight of the bias score; Ψ d Indicates the weighting of the hydraulic cylinder stroke difference score; Ψ c Indicates the weight of the shield tail gap score; δ now Θ represents the current deviation; θ represents the current score; δ represents the current score. * The standard value representing the deviation; d maxnow This indicates the maximum cylinder stroke difference of the current tunnel boring machine; d * c represents the standard value of the cylinder stroke difference; c′ represents the standard shield tail clearance; c * The standard value representing the shield tail gap; c minnow This indicates the minimum tail clearance of the current tunnel boring machine.

[0063] Step 2: Based on the planned pitch and yaw angles, the planned normal vector of the tunnel boring machine (TBM), and the rear center spatial position of the TBM, calculate the updated normal vector and the updated rear center spatial position of the TBM after it has traveled a certain distance forward. During the iteration process, the initial planned pitch and yaw angles, the planned normal vector of the TBM, and the rear center spatial position of the TBM adopt the current pitch and yaw angles, the current normal vector of the TBM, and the current rear center spatial position of the TBM from Step 1.

[0064] The optimizer determines the pitch and yaw angles that the tunnel boring machine should control in the future, and then calculates the normal vector of the tunnel boring machine and the corresponding rear center spatial position based on the pitch and yaw angles.

[0065] The methods for calculating the updated normal vector include:

[0066]

[0067] In the formula, θ represents the updated normal vector of the tunnel boring machine; φ represents the pitch angle; and φ represents the yaw angle.

[0068] The current rear center spatial position of the tunnel boring machine is O. Mnow Therefore, after calculating the distance 'd' that the tunnel boring machine travels forward, the updated rear center spatial location of the tunnel boring machine can be determined as follows:

[0069]

[0070] In the formula, O M d represents the updated rear center spatial position of the tunnel boring machine; d represents the forward distance of the tunnel boring machine. This represents the normal vector of the current tunnel boring machine.

[0071] Step 3: Calculate the intersection point of the rear face of the tunnel boring machine and the target curve based on the updated normal vector and the updated rear center spatial point of the tunnel boring machine, and calculate the update deviation between the intersection point and the updated rear center spatial point of the tunnel boring machine.

[0072] Since step 2 calculates the updated normal vector and the updated rear center spatial point of the tunnel boring machine (TBM), it's equivalent to locating a surface in space (with a point on this surface and its normal vector known), and the target curve is the known spatial curve. An iterative solution method is used to find the point on the curve closest to the surface, which is taken as the intersection point of the known TBM rear face and the curve. The intersection point and O are then calculated. M The spatial distance, i.e., the update deviation δ between the tunnel boring machine and the target curve.

[0073] Step 4: Establish a local coordinate system with the updated rear center point of the tunnel boring machine as the local coordinate origin and the updated normal vector of the tunnel boring machine as the x-axis; calculate the center point and normal vector in the local coordinate system of the end face of the tunnel segment.

[0074] Establish the rotation matrix based on the planned pitch and yaw angles of the tunnel boring machine:

[0075]

[0076] In the formula, θ represents the pitch angle; φ represents the yaw angle; and γ represents the roll angle.

[0077] The current position of the tunnel segment in the global coordinate system can be read from the tunnel boring machine system. The calculation method for the center point in the local coordinate system of the end face of the tunnel segment includes:

[0078] O′=(O S -O M )·R(γ,θ,φ), (5)

[0079] In the formula, O S Indicates the center point of the end face of the tunnel segment in the global coordinate system; O M R represents the updated rear center spatial position of the tunnel boring machine; R(γ,θ,φ) represents the rotation matrix.

[0080] The methods for calculating the normal vector in the local coordinate system at the end of the tunnel segment include:

[0081]

[0082] In the formula, This represents the normal vector of the end face of the pipe segment in the global coordinate system.

[0083] Step 5: Based on the positional relationship between the tunnel boring machine and the tunnel segments, calculate the future minimum tail clearance and the future maximum hydraulic cylinder stroke difference.

[0084] Since the shield gap and cylinder stroke are both related to the positions of the tunnel segments and the tunnel boring machine, and only to their relative positions, the position of the tunnel segment relative to the tunnel boring machine calculated in the previous step can be simplified.

[0085] Specifically, based on the positional relationship between the tunnel boring machine (TBM) and the tunnel segments, the position of the tunnel segment relative to the TBM is obtained: O′=(x′,y′,z′).

[0086] The calculation methods for the maximum cylinder stroke difference in the future include:

[0087]

[0088] In the formula, d max Indicates the maximum future cylinder stroke difference; D C This indicates the diameter of the circle formed by the strokes of multiple hydraulic cylinders in a tunnel boring machine.

[0089] The calculation methods for the minimum shield tail clearance in the future include:

[0090] For any point J′ of the segment in the local coordinate system:

[0091]

[0092] In the formula, D S This indicates the diameter of the outer end face of the segment; α represents the angle between O′J′ and the horizontal plane.

[0093] in,

[0094]

[0095] The shield tail gap at point J′ is:

[0096] c(α)=0.5D M -|J′|sin(arccos(J′·(1, 0, 0))), (10)

[0097] In the formula, D M Indicates the diameter of the shield tail of the tunnel boring machine;

[0098] The minimum value of function c(α) is calculated using the gradient descent method, thus obtaining the future minimum shield tail gap:

[0099]

[0100] Step 6: Calculate the weighted score based on the score weights in Step 1, the update bias in Step 3, and the future minimum shield tail clearance and the future maximum cylinder stroke difference in Step 5.

[0101] Methods for calculating weighted scores include:

[0102] Score = Ψ δ ·δ / δ * +Ψ d ·d max / d * +Ψ c ·(c′-c min ) / (c′-c * (12)

[0103] Step 7: Based on the weighted score, determine whether the yaw angle and pitch angle are the optimal yaw angle and optimal pitch angle; if yes, output the optimal yaw angle and optimal pitch angle; if no, return to step 2 for iterative loop until yes.

[0104] Due to the deviation between the tunnel boring machine and the target curve, indicators such as the tail clearance and cylinder stroke difference are best kept as small as possible. Therefore, the optimization algorithm determines whether the weighted scores corresponding to the current pitch and yaw angles are optimal. If they are optimal, the optimization ends; otherwise, the optimizer generates new pitch and yaw angles and recalculates the weighted scores. The method for determining the optimal yaw and pitch angles includes: if the rate of change of the weighted score is lower than a set threshold during 100 consecutive iterations, it is considered optimal.

[0105] The embodiments described above are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made to the technical solutions of the present invention by those skilled in the art without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims

1. A method for planning the tunneling posture of a tunnel boring machine oriented towards multi-objective control optimization, characterized in that, Includes the following steps: Step 1: Collect standard data of the tunnel boring machine (TBM), deviation data between the TBM and the target curve, and the current pitch and yaw angles; and calculate the score weights based on the standard data and the deviation data; the standard data includes: the standard value of the engineering deviation, the standard value of the tail shield gap, the standard value of the hydraulic cylinder stroke difference, the standard tail shield gap, the current normal vector of the TBM, and the current spatial position of the rear center of the TBM; the deviation data includes: the current deviation, the current tail shield gap, and the current hydraulic cylinder stroke difference; Step 2: Based on the planned pitch angle and yaw angle, as well as the planned normal vector and rear center spatial position of the tunnel boring machine (TBM), calculate the updated normal vector and updated rear center spatial position of the TBM after it has traveled a certain distance forward. During the iteration process, the initial planned pitch angle and yaw angle, as well as the planned normal vector and rear center spatial position of the TBM, adopt the current pitch angle and yaw angle, as well as the current normal vector and rear center spatial position of the TBM from Step 1. Step 3: Calculate the intersection point of the rear face of the tunnel boring machine and the target curve based on the updated normal vector and the updated rear center spatial point of the tunnel boring machine, and calculate the update deviation between the intersection point and the updated rear center spatial point of the tunnel boring machine. Step 4: Establish a local coordinate system with the updated rear center spatial point of the tunnel boring machine as the local coordinate origin and the updated normal vector of the tunnel boring machine as the x-axis; calculate the center point and normal vector in the local coordinate system of the end face of the tunnel segment. Step 5: Based on the positional relationship between the tunnel boring machine and the tunnel segments, calculate the future minimum tail clearance and the future maximum cylinder stroke difference; Step 6: Calculate the weighted score based on the scoring weights in Step 1, the update deviations in Step 3, and the future minimum shield tail clearance and the future maximum cylinder stroke difference in Step 5; Step 7: Based on the weighted score, determine whether the yaw angle and the pitch angle are the optimal yaw angle and the optimal pitch angle; if yes, output the optimal yaw angle and the optimal pitch angle; if no, return to step 2 for iterative loop until yes. The methods for determining the optimal yaw angle and optimal pitch angle include: if the rate of change of the weighted score is lower than a set threshold during 100 consecutive iterations, it is determined to be optimal.

2. The shield tunneling posture planning method for multi-objective control optimization according to claim 1, characterized in that, In step 1, the method for calculating the score weights includes: ， In the formula, Indicates the weight of the deviation score; This indicates the weighting of the hydraulic cylinder stroke difference score; Indicates the weight of the shield tail gap score; δ now Indicates the current deviation; Indicates the current score; δ * The standard value representing the deviation; d maxnow This indicates the maximum cylinder stroke difference of the current tunnel boring machine; d * This represents the standard value indicating the difference in cylinder stroke. Indicates the standard shield tail clearance; c * The standard value representing the shield tail gap; c minnow This indicates the minimum tail clearance of the current tunnel boring machine.

3. The shield tunneling attitude planning method for multi-objective control optimization according to claim 1, characterized in that, In step 2, the method for calculating the updated normal vector of the tunnel boring machine includes: ， In the formula, θ represents the updated normal vector of the tunnel boring machine; θ represents the pitch angle. Indicates the yaw angle; The method for calculating the updated back-end spatial position of the tunnel boring machine includes: ， In the formula, O Mnow Indicates the current spatial position of the rear center of the tunnel boring machine; O M d represents the updated rear center spatial position of the tunnel boring machine; d represents the forward distance of the tunnel boring machine. This represents the normal vector of the current tunnel boring machine.

4. The shield tunneling attitude planning method for multi-objective control optimization according to claim 1, characterized in that, The methods for calculating the center point in the local coordinate system of the end face of the tunnel segment include: ， In the formula, O S Indicates the center point of the end face of the tunnel segment in the global coordinate system; O M This indicates the updated central spatial location of the tunnel boring machine's rear end; Represents the rotation matrix; The methods for calculating the normal vector in the local coordinate system at the end of the tunnel segment include: ， In the formula, This represents the normal vector of the end face of the pipe segment in the global coordinate system; The rotation matrix is ​​established using the planned pitch and yaw angles of the tunnel boring machine. ， In the formula, θ represents the pitch angle; γ represents the yaw angle; γ represents the roll angle.

5. The shield tunneling attitude planning method for multi-objective control optimization according to claim 4, characterized in that, In step 5, based on the positional relationship between the tunnel boring machine (TBM) and the tunnel segments, the position of the tunnel segments relative to the TBM is obtained: , ; The method for calculating the maximum future cylinder stroke difference includes: ， In the formula, d max represents the maximum future difference in ram travel; D C represents the diameter of the circle formed by the multiple ram travels of the shield machine The calculation method for the future minimum shield tail gap includes: For any point on the segment, its position in the local coordinate system : ， In the formula, D S Indicates the diameter of the outer end face of the segment; α represents Angle relative to the horizontal plane; in, ； Points The shield tail gap at that location is: ， In the formula, D M Indicates the diameter of the shield tail of the tunnel boring machine; The function is calculated using the gradient descent method. The minimum value of the future minimum shield tail gap is obtained by finding the minimum value of the shield tail gap. 。 6. The shield tunneling posture planning method for multi-objective control optimization according to claim 5, characterized in that, In step 6, the method for calculating the weighted score includes: ； In the formula, δ represents the update bias; Indicates the weight of the deviation score; This indicates the weighting of the hydraulic cylinder stroke difference score; Indicates the weight of the shield tail gap score; δ * The standard value representing the deviation; d * This represents the standard value indicating the difference in cylinder stroke. Indicates the standard shield tail clearance; c * This indicates the standard value for the shield tail gap.

Images