Intelligent regulation and control method for limit radius shield tunnel in narrow and small space

Abstract

The invention relates to the technical field of shield tunnel construction, and particularly discloses a narrow space limit radius shield tunnel intelligent regulation and control method which comprises the steps that shield tunneling machine state information is obtained; acquiring formation pressure, water content and soil deformation data to obtain formation characteristic information; based on the stratum characteristic information, an optimal construction adjustment strategy is obtained through analysis; on the basis of the optimal construction adjustment strategy, deep reinforcement learning is combined with fuzzy PID control to calculate the optimal tunneling track of the shield tunneling machine, and a narrow space limit radius adaptability construction scheme is obtained; according to the method, the track of the shield tunneling machine is optimized based on deep reinforcement learning in combination with fuzzy PID control, dynamic posture correction is achieved, and the deviation of the tunneling track is reduced. The attitude estimation precision is improved through multi-sensor data fusion, the shield attitude angle error is reduced, the manual intervention frequency is effectively reduced, and the construction efficiency is improved; automatic thrust and torque optimization control is achieved, posture sudden change caused by stratum change is avoided, and the stability of the shield tunneling machine is improved.

Description

Technical Field

[0001] The invention belongs to the technical field of shield tunnel construction, and in particular relates to an intelligent control method for a shield tunnel with an extreme radius in a narrow space. Background Art

[0002] There are many technical challenges in shield tunnel construction with narrow space and extreme radius. Traditional shield construction methods mainly rely on manual experience and on-site monitoring, which often cannot achieve ideal control effects in complex and changeable construction environments. Especially in narrow space and extreme radius conditions, it is particularly difficult to accurately control the shield machine's excavation posture, cutter head torque, synchronous grouting pressure and other construction parameters.

[0003] In the prior art, the construction parameter adjustment of the shield machine mainly depends on the experience and judgment of the operator. However, due to the complexity and uncertainty of the construction environment, as well as the differences in the experience and skill levels of the operators, the adjustment of the construction parameters is often not accurate and timely. This not only affects the tunneling efficiency and construction accuracy of the shield machine, but may also increase construction risks and costs. In addition, the multi-source data in the shield construction process is insufficiently utilized. The shield machine will generate a large amount of data during the construction process, including posture, thrust, torque, tunneling speed, cutterhead speed, formation resistance, etc. These data contain rich construction information, but the prior art often does not fully explore and utilize these data, resulting in the lack of scientific basis and accuracy in the adjustment of construction parameters.

[0004] In response to this, the inventor proposed an intelligent control method for shield tunnels with extreme radius in narrow spaces to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent control method for a shield tunnel with an extreme radius in a narrow space, so as to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions: Intelligent control method for shield tunnel with extreme radius in narrow space, including: Acquire multi-source data during shield construction, and use multi-modal data fusion algorithm to fuse the data to obtain shield machine status information; Collect formation pressure, water content, and soil deformation data, and use a formation dynamic evolution neural network model combined with shield machine status information to predict formation response during shield tunneling and obtain formation characteristic information; Based on the formation characteristics information, reinforcement learning is used to optimize the excavation parameters, and the optimal construction adjustment strategy is obtained in combination with digital twin simulation analysis; Based on the optimal construction adjustment strategy, deep reinforcement learning combined with fuzzy PID control is used to calculate the optimal excavation trajectory of the shield machine, and an adaptive construction plan with the extreme radius in a narrow space is obtained.

[0007] Preferably, optimizing the adaptability to a special environment based on the optimal construction adjustment strategy to obtain an adaptable construction plan for a narrow space limit radius includes the following steps: According to the tunnel curvature radius and the minimum construction space constraints, a shield attitude dynamic adjustment model is constructed; The nonlinear trajectory optimization algorithm is used to calculate the optimal adjustment strategy of the shield posture in the extreme radius area; Combined with the feedback of stratum deformation, the construction parameters are adjusted in real time to improve the adaptability of shield construction in narrow spaces with extreme radius.

[0008] Preferably, the multimodal data fusion algorithm is Bayesian estimation, and the formula of Bayesian estimation is: ; P(H|D) represents the posterior probability of the construction environment information H under the sensor data D; P(D|H) represents the possibility of sensor data D being observed under specific construction environment information H, the likelihood function; P(H) represents the prior probability of construction environment information, which is modeled based on historical data; P(D) represents the total probability of sensor data and is used for normalization.

[0009] Preferably, the formula of the formation dynamic evolution neural network model is: ; ; Where: X t represents the input stratum monitoring data at construction time t; h t represents the hidden state at time t, h t-1 represents the hidden state at time t-1, indicating the formation evolution information; W h ,W x ,W y Represents the network weight parameters; b h ,b y represents the bias term; Yt represents the predicted formation response at time t; σ represents the activation function.

[0010] Preferably, based on the formation characteristic information, a reinforcement learning algorithm is used to optimize the excavation trajectory to obtain the optimal excavation path; comprehensive parameters such as thrust, torque, cutter head speed, synchronous grouting pressure, etc. are used to optimize the construction strategy using a multi-objective optimization method based on a genetic algorithm to obtain the optimal construction adjustment strategy.

[0011] Preferably, the expression of the multi-objective optimization method based on genetic algorithm includes: Fitness calculation: ; Where: fi(x) represents the i-th optimization objective; wi represents the weight of the target; Crossover operation: ; Among them: xnew is the new construction parameter combination after the intersection; x1, x2 parent parameter set; Mutation operation: ; Among them: Xmut is the new construction parameter combination after the mutation operation; N(0,σ 2 ) represents the random variation term that follows Gaussian distribution.

[0012] Preferably, the expression of deep reinforcement learning is: ; Where Q(st,at) represents the value of executing action at in state st; α represents the learning rate, which controls the update speed; rt represents the reward of the current step; γ represents the discount factor, which weighs the impact of future rewards on current decisions; Represents the value of the optimal action in the next state st+1.

[0013] Preferably, the expression combined with fuzzy PID control is: ; Where: e(t) represents the attitude error of the shield machine; Kp, Ki, and Kd represent PID control parameters, which are dynamically adjusted by fuzzy logic rules; The fuzzy logic adjustment rules are as follows: If |e(t)| is large, increase Kp to speed up the response; If e(t) remains unchanged for a long time, increase Ki to reduce the steady-state error; If e(t) changes too quickly, increase Kd to suppress oscillation.

[0014] Preferably, the multi-source data includes shield machine posture, thrust, torque, tunneling speed, cutter head rotation speed, formation resistance and shield tail clearance.

[0015] Compared with the prior art, the present invention has the following beneficial effects: (1) The present invention combines deep reinforcement learning (DRL) with fuzzy PID control to jointly optimize the shield machine trajectory, realize dynamic posture correction, and reduce the deviation of the excavation trajectory. Multi-sensor data fusion improves the accuracy of posture estimation, reduces the shield machine posture angle error, effectively reduces the number of manual interventions, and improves construction efficiency. Automatic thrust and torque optimization control avoids sudden posture changes caused by stratum changes, improves the stability of the shield machine, and reduces the risk of construction accidents.

[0016] (2) The present invention performs synchronous grouting optimization based on particle swarm optimization combined with genetic algorithm and finite element analysis, which reduces the probability of formation settlement and effectively prevents formation instability; real-time seepage pressure monitoring combined with adaptive PID control automatically adjusts the grouting pressure to avoid shield tail leakage; the slurry utilization rate is improved, the water-cement ratio is optimized, the slurry waste is reduced, and the construction material cost is reduced.

[0017] (3) The present invention integrates multi-sensor data and combines it with data-driven modeling to improve the ability to predict shield construction parameters and realize intelligent thrust, torque, and grouting pressure adaptive adjustment; multi-objective optimization ensures optimal construction efficiency and safety, reduces the number of shield machine posture adjustments, shortens construction time, and saves construction costs. The tunnel axis deviation is small, ensuring that the construction accuracy reaches a high standard. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of the intelligent control method for a shield tunnel with an extreme radius in a narrow space of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example 1

[0020] See also Figure 1 As shown, the intelligent control method of the shield tunnel with an extreme radius in a narrow space includes: Acquire multi-source data during shield construction, and use multi-modal data fusion algorithm to fuse the data to obtain shield machine status information; Collect formation pressure, water content, and soil deformation data, and use a formation dynamic evolution neural network model combined with shield machine status information to predict formation response during shield tunneling and obtain formation characteristic information; Based on the formation characteristics information, reinforcement learning is used to optimize the excavation parameters, and the optimal construction adjustment strategy is obtained in combination with digital twin simulation analysis; Based on the optimal construction adjustment strategy, deep reinforcement learning combined with fuzzy PID control is used to calculate the optimal excavation trajectory of the shield machine, obtain an adaptive construction plan for the extreme radius of a narrow space, and adjust the excavation posture, cutter head torque, and synchronous grouting pressure construction parameters of the shield machine for precise control of the shield machine.

[0021] Specifically, based on the optimal construction adjustment strategy, the special environment adaptability optimization is performed to obtain a construction plan with an adaptability to the extreme radius of a narrow space, including the following steps: According to the tunnel curvature radius and the minimum construction space constraints, a shield attitude dynamic adjustment model is constructed; The nonlinear trajectory optimization algorithm is used to calculate the optimal adjustment strategy of the shield posture in the extreme radius area; Combined with the feedback of stratum deformation, the construction parameters are adjusted in real time to improve the adaptability of shield construction in narrow spaces with extreme radius.

[0022] Specifically, the multimodal data fusion algorithm is Bayesian estimation, and the formula of Bayesian estimation is: ; P(H|D) represents the posterior probability of the construction environment information H under the sensor data D; P(D|H) represents the possibility of sensor data D being observed under specific construction environment information H, the likelihood function; P(H) represents the prior probability of construction environment information, which is modeled based on historical data; P(D) represents the total probability of sensor data and is used for normalization.

[0023] The algorithm is used to integrate shield machine sensor data (such as thrust, torque, settlement, etc.) to provide a more stable and noise-resistant construction environment assessment, which can effectively improve data accuracy and reduce the impact of single sensor errors on construction parameter adjustments.

[0024] Specifically, the formula of the formation dynamic evolution neural network model is: ; ; Where: X t represents the input stratum monitoring data at construction time t; h trepresents the hidden state at time t, h t-1 represents the hidden state at time t-1, indicating the formation evolution information; W h ,W x ,W y Represents the network weight parameters; b h ,b y represents the bias term; Yt represents the predicted formation response at time t; σ represents the activation function.

[0025] This model is used to predict the deformation trend of the stratum, help construction personnel adjust construction parameters in advance, prevent over-excavation, stratum collapse and other problems, and improve the safety of shield construction.

[0026] Specifically, based on the formation characteristic information, a reinforcement learning algorithm is used to optimize the excavation trajectory to obtain the optimal excavation path; comprehensive thrust, torque, cutter head speed, synchronous grouting pressure and other parameters are used, and a multi-objective optimization method based on a genetic algorithm is used to optimize the construction strategy to obtain the optimal construction adjustment strategy; Collect grouting related parameters to obtain soil pressure, seepage pressure, shield tail gap pressure, slurry flow, slurry density, and obtain grouting monitoring data; Process the grouting monitoring data and use particle swarm optimization (PSO) + genetic algorithm (GA-MOO) to calculate the optimal grouting parameters, which are used to optimize the water-cement ratio (W / C), grouting flow rate, and grouting pressure to obtain the optimal grouting parameters; Process the optimal grouting parameters and calculate the ground deformation by combining finite element analysis (FEM) to adjust the grouting strategy, ensure that the ground settlement is controlled within 4mm, and obtain a stable grouting plan for the ground; The grouting scheme for stabilizing the formation is based on adaptive PID control, which is used to dynamically adjust the grouting pressure, optimize the sealing effect of the shield tunnel, and obtain precise grouting filling effect.

[0027] Specifically, the expression of the multi-objective optimization method based on genetic algorithm includes: Fitness calculation: ; Where: fi(x) represents the i-th optimization objective; wi represents the weight of the target; Crossover operation: ; Among them: xnew is the new construction parameter combination after the intersection; x1, x2 parent parameter set; Mutation operation: ; Among them: Xmut is the new construction parameter combination after the mutation operation; N(0,σ 2 ) represents the random variation term that follows Gaussian distribution.

[0028] The algorithm is used to optimize construction parameters (such as thrust, torque, cutterhead speed, and synchronous grouting pressure) so that the shield machine can maintain an efficient and stable construction state under complex geological conditions.

[0029] Specifically, the expression of deep reinforcement learning is: ; Where Q(st,at) represents the value of executing action at in state st; α represents the learning rate, which controls the update speed; rt represents the reward of the current step; γ represents the discount factor, which weighs the impact of future rewards on current decisions; Represents the value of the optimal action in the next state st+1.

[0030] The algorithm enables the shield machine to automatically learn the optimal excavation trajectory, reduce posture deviation in narrow spaces and extreme radius construction environments, and improve construction accuracy and efficiency.

[0031] Specifically, the expression combined with fuzzy PID control is: ; Where: e(t) represents the attitude error of the shield machine; Kp, Ki, and Kd represent PID control parameters, which are dynamically adjusted by fuzzy logic rules; The fuzzy logic adjustment rules are as follows: If |e(t)| is large, increase Kp to speed up the response; If e(t) remains unchanged for a long time, increase Ki to reduce the steady-state error; If e(t) changes too quickly, increase Kd to suppress oscillation.

[0032] The algorithm is used to dynamically adjust the shield machine's posture, reduce yaw and posture deviation during excavation, and improve the shield machine's accuracy and stability.

[0033] Specifically, the multi-source data includes shield machine posture, thrust, torque, tunneling speed, cutter head rotation speed, formation resistance and shield tail clearance.

[0034] From the above, it can be seen that this method proposes a complete set of intelligent control solutions for the key issues in the construction process of shield tunnels with extreme radius in narrow spaces, including key links such as intelligent excavation trajectory optimization, intelligent optimization of synchronous grouting, and adaptive adjustment of construction parameters.

[0035] The present invention is based on deep reinforcement learning (DRL) combined with fuzzy PID control to jointly optimize the shield machine trajectory, realize dynamic posture correction, and reduce the deviation of the excavation trajectory. Multi-sensor data fusion improves the accuracy of posture estimation, realizes the reduction of shield posture angle error, effectively reduces the number of manual interventions, and improves construction efficiency. Automatic thrust and torque optimization control avoids sudden posture changes caused by stratum changes, improves the stability of the shield machine, and reduces the risk of construction accidents; The present invention performs synchronous grouting optimization based on particle swarm optimization (PSO) combined with genetic algorithm (GA-MOO) and finite element analysis (FEM), which reduces the probability of formation settlement and effectively prevents formation instability; real-time permeability pressure monitoring combined with adaptive PID control automatically adjusts the grouting pressure to avoid shield tail leakage; the slurry utilization rate is improved, the water-cement ratio is optimized, the slurry waste is reduced, and the construction material cost is reduced; The present invention combines multi-sensor fusion (IMU, laser ranging, pressure sensor) with data-driven modeling to improve the ability to predict shield construction parameters and realize intelligent thrust, torque, and grouting pressure adaptive adjustment. Multi-objective optimization (MOO) ensures optimal construction efficiency and safety, reduces the number of shield machine posture adjustments, shortens construction time, and saves construction costs. The tunnel axis deviation is small, ensuring that the construction accuracy reaches a high standard.

[0036] Example 2 This method is not only applicable to shield tunnels with extreme radius in narrow spaces, but also has wide application value in urban subways, underground integrated pipeline corridors, cross-river tunnels, high-speed rail tunnels and other projects. In the future, it can be expanded to a fully automatic intelligent shield construction system, promoting tunnel construction towards intelligent, unmanned and high-precision directions; Extreme radius shield construction is often used in narrow sections of subways and tunnels with small turning radius. This method can improve excavation accuracy, reduce settlement, shield tail leakage, and tunnel axis deviation, ensure construction safety, and improve urban rail transit construction efficiency. Furthermore, the intelligent excavation trajectory optimization of the extreme radius shield tunnel: 1. Implementation background: In a subway tunnel project in a certain city, a 6m diameter shield machine needs to excavate in a space with a minimum curve radius of 250m, and the geological conditions along the line are complex (including silty clay and sand and gravel layers). Traditional manual adjustment methods are difficult to ensure high-precision excavation, and are prone to problems such as posture deviation and segment misalignment. This embodiment is based on deep reinforcement learning (DRL) combined with an adaptive fuzzy PID control algorithm to optimize the shield machine posture adjustment and improve excavation accuracy.

[0037] 2. Data acquisition method: (1) Shield machine posture data collection: Equipment: IMU inertial navigation, laser rangefinder, attitude sensor; The sampling frequency is shown in Table 1; Table 1

[0038] (2) Multi-sensor data fusion (based on Bayesian estimation) Bayesian estimation is used to calculate the optimal estimate of the shield machine posture, and the equation is: ;

[0039] P(H|D) represents the posterior probability of the construction environment information H under the sensor data D; P(D|H) represents the possibility of sensor data D being observed under specific construction environment information H, the likelihood function; P(H) represents the prior probability of construction environment information, which is modeled based on historical data; P(D) represents the total probability of sensor data and is used for normalization.

[0040] The algorithm is used to integrate shield machine sensor data (such as thrust, torque, settlement, etc.) to provide a more stable and noise-resistant construction environment assessment, which can effectively improve data accuracy and reduce the impact of single sensor errors on construction parameter adjustments.

[0041] 3. Trajectory optimization calculation process: (1) Deep Reinforcement Learning (DRL) ; Training process: State space St: St = (θt, φt, ψt, vt, Tt) Action space at: at=(N,F,P) Where: N: Cutter speed adjustment (1~3rpm) F: Shield machine propulsion force (5-15MPa) P: Correction cylinder pressure adjustment (20~100kPa) Reward function: ; Among them, α, β, and γ ensure that the attitude error is minimized.

[0042] After training for 20,000 rounds: Posture deviation reduced by 40% (from 0.5° to 0.3°) The excavation trajectory error was reduced from 30mm to 10mm (improved accuracy by 66%) (2) Fuzzy PID control strategy Using fuzzy PID for real-time attitude correction: ; Error adjustment rules: If |e(t)|>2°, increase Kp for quick adjustment; If |e(t)|<0.5°, reduce Kd to avoid oscillation.

[0043] From the above, we can see that the implementation effects include The construction time is reduced by 15%, saving a lot of construction costs.

[0044] The number of shield machine posture adjustments is reduced by 50%, reducing the risk of segment misalignment.

[0045] The profile error in the tunnel was reduced by 66% (from 30mm to 10mm).

[0046] Example 3 Intelligent optimization of synchronous grouting in extreme radius shield tunnels: 1. Implementation background: The shield construction of a high-speed railway underground tunnel passes through a soft soil layer with a limit radius of only 300m. The traditional manual adjustment of synchronous grouting parameters makes it difficult to control the slurry penetration range, resulting in stratum instability and shield tail leakage. This embodiment uses particle swarm optimization (PSO) + genetic algorithm (GA-MOO) to optimize synchronous grouting and reduce stratum disturbance.

[0047] 2. Data acquisition method: (1) Monitoring point layout: 50 sets of pore water pressure sensors are deployed around the tunnel: The sampling parameters are shown in Table 2: Table 2

[0048] (2) Soil deformation calculation (FEM) Calculate the stress distribution of the soil around the tunnel: ; in: E: elastic modulus of soil layer; ν: Poisson's ratio; u: soil displacement; 3. Construction parameter optimization calculation process: (1) Construction parameter optimization (PSO+GA-MOO) Objective to optimize grouting pressure P and flow rate Q: ; f1(x): Minimization of formation deformation; f2(x): maximization of slurry uniformity; Particle Swarm Optimization Updates: ; Iterate 500 times and get the optimal result: Grouting pressure: 200-250 kPa; Grouting flow rate: 12-15L / min; (2) Intelligent grouting control of shield machine: ; If the penetration pressure is >250kPa, reduce the grouting pressure by 10%; If the shield tail leaks, adjust the slurry water-cement ratio (W / C=0.6); As can be seen from the above, the implementation effects include: Ground subsidence was reduced by 60% (from 10mm to 4mm).

[0049] Shield tail leakage is reduced by 90%, improving construction safety.

[0050] The slurry utilization rate is increased by 20%, saving a lot of material costs.

[0051] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent control method for a shield tunnel with a limited radius in a narrow space, characterized in that: include: Acquire multi-source data during shield construction, and use multi-modal data fusion algorithm to fuse the data to obtain shield machine status information; Collect formation pressure, water content, and soil deformation data, and use a formation dynamic evolution neural network model combined with shield machine status information to predict formation response during shield tunneling and obtain formation characteristic information; Based on the formation characteristics information, reinforcement learning is used to optimize the excavation parameters, and the optimal construction adjustment strategy is obtained in combination with digital twin simulation analysis; Based on the optimal construction adjustment strategy, deep reinforcement learning combined with fuzzy PID control is used to calculate the optimal excavation trajectory of the shield machine, and an adaptive construction plan with the extreme radius in a narrow space is obtained.

2. The intelligent control method for a narrow space extreme radius shield tunnel according to claim 1 is characterized in that: Based on the optimal construction adjustment strategy, the special environment adaptability optimization is performed to obtain a construction plan with an adaptability to the extreme radius of a narrow space, including the following steps: According to the tunnel curvature radius and the minimum construction space constraints, a shield attitude dynamic adjustment model is constructed; The nonlinear trajectory optimization algorithm is used to calculate the optimal adjustment strategy of the shield posture in the extreme radius area; Combined with ground deformation feedback, construction parameters are adjusted in real time to improve the adaptability of shield construction in narrow spaces with extreme radius.

3. The intelligent control method for a narrow space extreme radius shield tunnel according to claim 1 is characterized in that: The multimodal data fusion algorithm is Bayesian estimation, and the formula of Bayesian estimation is: ； P(H|D) represents the posterior probability of the construction environment information H under the sensor data D; P(D|H) represents the possibility of sensor data D being observed under specific construction environment information H, the likelihood function; P(H) represents the prior probability of construction environment information, which is modeled based on historical data; P(D) represents the total probability of sensor data and is used for normalization.

4. The intelligent control method for a narrow space extreme radius shield tunnel according to claim 1 is characterized in that: The formula of the formation dynamic evolution neural network model is: ； ； Where: X t represents the input stratum monitoring data at construction time t; h t represents the hidden state at time t, h t-1 represents the hidden state at time t-1, indicating the formation evolution information; W h ,W x ,W y Represents the network weight parameters; b h ,b y represents the bias term; Yt represents the predicted formation response at time t; σ represents the activation function.

5. The intelligent control method for a narrow space extreme radius shield tunnel according to claim 1 is characterized in that: Based on the formation characteristic information, a reinforcement learning algorithm is used to optimize the excavation trajectory to obtain the optimal excavation path; based on the thrust, torque, cutter head speed, and synchronous grouting pressure parameters, a multi-objective optimization method based on a genetic algorithm is used to optimize the construction strategy and obtain the optimal construction adjustment strategy.

6. The intelligent control method for a narrow space extreme radius shield tunnel according to claim 5 is characterized in that: The expression of the multi-objective optimization method based on genetic algorithm includes: Fitness calculation: ； Where: fi(x) represents the i-th optimization objective; wi represents the weight of the target; Crossover operation: ； Among them: xnew is the new construction parameter combination after the intersection; x1, x2 parent parameter set; Mutation operation: ； Among them: Xmut is the new construction parameter combination after the mutation operation; N(0,σ 2 ) represents the random variation term that follows Gaussian distribution.

7. The intelligent control method for a narrow space extreme radius shield tunnel according to claim 1 is characterized in that: The expression of deep reinforcement learning is: ； Where Q(st,at) represents the value of executing action at in state st; α represents the learning rate, which controls the update speed; rt represents the reward of the current step; γ represents the discount factor, which weighs the impact of future rewards on current decisions; Represents the value of the optimal action in the next state st+1.

8. The intelligent control method for a narrow space extreme radius shield tunnel according to claim 1 is characterized in that: The expression combined with fuzzy PID control is: ； Where: e(t) represents the attitude error of the shield machine; Kp, Ki, and Kd represent PID control parameters, which are dynamically adjusted by fuzzy logic rules; The fuzzy logic adjustment rules are as follows: If |e(t)| is large, increase Kp to speed up the response; If e(t) remains unchanged for a long time, increase Ki to reduce the steady-state error; If e(t) changes too quickly, increase Kd to suppress oscillation.

9. The intelligent control method for a narrow space extreme radius shield tunnel according to claim 1 is characterized in that: The multi-source data include shield machine posture, thrust, torque, tunneling speed, cutter head rotation speed, formation resistance and shield tail clearance.

Images