Shield tunneling axis direction control system and control method based on multi-sensor fusion

Abstract

The invention discloses a shield tunneling axis direction control system and method based on multi-sensor fusion. The shield tunneling axis direction control system comprises a sensor module, a data processing module, a control module and a man-machine interaction module. The sensor module is used for collecting various state information of the shield tunneling machine in real time, and comprises a laser total station, a wireless communication module, a wireless communication module and a power supply module, wherein the laser total station is used for measuring the absolute position and posture of the shield tunneling machine; the gyroscope is used for measuring the real-time attitude of the shield tunneling machine, and the real-time attitude comprises a pitch angle, a yaw angle and a roll angle; the accelerometer is used for measuring the acceleration of the shield tunneling machine and assisting in judging the motion state of the shield tunneling machine; the displacement sensor is used for measuring the displacement change of the shield tunneling machine and ensuring the accuracy of the tunneling direction; and the pressure sensor is used for measuring the pressure of a thrust oil cylinder of the shield tunneling machine and assisting in judging the thrust state of the shield tunneling machine. Through multi-sensor fusion, precise control over the shield tunneling axis direction is achieved, and the tunneling precision is remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of tunnel engineering shield construction, and particularly relates to a shield tunneling axis direction control system and control method based on multi-sensor fusion. BACKGROUND

[0002] In shield tunnel construction, the tunneling axis direction control of the shield machine is a key link to ensure construction quality and safety. The accuracy of the tunneling axis direction directly affects the forming quality of the tunnel, the construction precision, and the safety of the surrounding environment. If the tunneling direction of the shield machine deviates from the design axis, it may cause serious consequences.

[0003] Traditional shield tunneling axis direction control mainly relies on the experience of the shield driver. The shield driver manually adjusts the advancing direction of the shield machine by observing the real-time data (such as attitude, position, speed, etc.) of the shield machine and construction drawings. However, this method has significant limitations. SUMMARY

[0004] The present application aims to at least partially solve one of the technical problems in the related art. To this end, one object of the present application is to propose a shield tunneling axis direction control system and control method based on multi-sensor fusion, which is suitable for accurate control of the tunneling axis direction of the shield machine in shield tunnel construction.

[0005] In a first aspect, the present application proposes a shield tunneling axis direction control system based on multi-sensor fusion, which comprises a sensor module, a data processing module, a control module, and a human-computer interaction module.

[0006] The sensor module is used to collect various state information of the shield machine in real time. The sensor module comprises:

[0007] Laser total station: used to measure the absolute position and attitude of the shield machine;

[0008] Gyroscope: used to measure the real-time attitude of the shield machine, including pitch angle, yaw angle, and roll angle;

[0009] Accelerometer: used to measure the acceleration of the shield machine to assist in determining the motion state of the shield machine;

[0010] Displacement sensor: used to measure the displacement change of the shield machine to ensure the accuracy of the tunneling direction;

[0011] Pressure sensor: used to measure the pressure of the shield machine's advancing cylinder to assist in determining the thrust state of the shield machine;

[0012] The data processing module is used to preprocess the data collected by the sensor module.

[0013] The control module performs operation according to data output by the data processing module, controls the advancing direction of the shield machine in combination with a real-time feedback mechanism, and performs fault judgment operation simultaneously.

[0014] The human-computer interaction module is used for providing a shield machine operation interface, for monitoring and intervening in the tunneling process of the shield machine by a construction worker, for displaying real-time data collected by the sensor module, and for alarming a fault signal fed back by the control module.

[0015] In a second aspect, the present application provides a shield tunneling axis direction control method based on multi-sensor fusion, which comprises any scheme of the shield tunneling axis direction control system based on multi-sensor fusion.

[0016] S1, data acquisition and preprocessing:

[0017] Data acquisition: shield machine state information data collected by the sensor module in real time is acquired, and the data is transmitted to the data processing module;

[0018] Data preprocessing: the data processing module performs preprocessing operation on the collected data;

[0019] S2, shield machine operation control:

[0020] Direction adjustment: the control module calculates the deviation of the actual tunneling direction of the shield machine from the design axis by using the data preprocessed in step S1;

[0021] Parameter adjustment: the control module adjusts the advancing cylinder pressure and cutterhead rotating speed parameters of the shield machine, so as to realize accurate control of the tunneling direction;

[0022] Real-time feedback: the control module monitors the tunneling state of the shield machine in real time, and dynamically adjusts according to the feedback data;

[0023] Real-time monitoring: the running state of the shield machine is monitored in real time to determine whether there is a potential fault in the shield machine;

[0024] Fault alarm: when it is determined that there is a potential fault, an alarm signal is triggered;

[0025] Fault recording: the time, position and cause information of the fault are recorded;

[0026] S3, manual intervention:

[0027] Real-time monitoring: the construction worker monitors the tunneling state of the shield machine in real time through the human-computer interaction module;

[0028] Manual adjustment: the construction worker manually adjusts the tunneling direction of the shield machine through the operation interface;

[0029] Emergency stop: The construction personnel triggers an emergency stop command through the operation interface, and the tunneling of the shield machine is stopped.

[0030] Preferably, in step S1:

[0031] Data fusion is performed using extended Kalman filter (EKF):

[0032] State equation:

[0033] x k =f(x k-1 ,u k )+w k

[0034] where x k is the state vector, u k is the control input vector at time k, w k is the process noise;

[0035] Observation equation:

[0036] z k =h(x k )+v k

[0037] where z k is the observation vector, v k is the observation noise;

[0038] Kalman gain calculation:

[0039]

[0040] where K k is the Kalman gain matrix, P k∣k-1 is the prior estimation covariance matrix, H k is the observation matrix that maps the state space to the observation space, R k is the observation noise covariance matrix;

[0041] Adaptive wavelet denoising:

[0042]

[0043] where x j0,k is the denoised signal, c j,k is the scale coefficient, d j0,k is the wavelet coefficient, φ j,k (t) is the scale function, ψ i (t) is the wavelet function, j0 is the initial decomposition scale, and J is the maximum decomposition scale;

[0044] Robust weighted average fusion:

[0045]

[0046] x i is the measurement value of the i th sensor, w i is the weight of the i th sensor, is the measurement variance of the i th sensor, n is the number of sensors participating in fusion.

[0047] Preferably, in step S1:

[0048] Different sampling rate sensor data synchronization:

[0049]

[0050] x sync is the synchronized data, w i is the weight of the i th sensor, τ i is the time delay compensation amount of the i th sensor, t k is the synchronization time point.

[0051] Preferably, in step S2:

[0052] The deviation formula of the actual tunneling direction from the design axis is:

[0053] Δθ=θ 实际 -θ 设计

[0054] where Δθ is the deviation angle, θ 实际 is the actual tunneling direction of the shield machine, θ 设计 is the direction of the design axis;

[0055] The parameter adjustment formula is:

[0056] P 调整 =P 当前 +K p ·Δθ

[0057] ω 调整 =ω 当前 +K ω ·Δθ

[0058] where P 调整 is the adjusted thrust cylinder pressure, P 当前 is the current thrust cylinder pressure, K p is the proportional coefficient; ω 调整 is the adjusted cutterhead speed, ω 当前 is the current cutterhead speed, K ω is the proportional coefficient;

[0059] The tunneling direction deviation is represented by a quaternion:

[0060]

[0061] where Δq is the bias quaternion, q actual is the actual attitude quaternion, q design is the design axis attitude quaternion;

[0062] converted into Euler angle bias:

[0063]

[0064] Δφ is the roll angle bias, Δθ is the pitch angle bias, Δψ is the yaw angle bias, and f(Δq) is the bias quaternion function;

[0065] Dynamic adaptive PID adjustment according to feedback data:

[0066] Propulsion system control quantity calculation:

[0067]

[0068] where u(t) is the control output, e(t) is the error signal, K p is the proportional gain, K i is the integral gain, K d is the derivative gain, and τ is the integral time variable;

[0069] K p = K p0 + α · ||e(t) ||

[0070] where K p0 is the basic value of the proportional gain, and α is the adjustable parameter;

[0071] Cylinder thrust distribution:

[0072]

[0073] where F i is the actual thrust of the i-th cylinder, F i,desired is the ideal thrust of the i-th cylinder, and z is the total number of cylinders;

[0074] Constraint condition:

[0075]

[0076] r i is the position vector of the i-th cylinder, and M desired is the desired resultant moment vector.

[0077] Preferably, in step S3:

[0078] Data visualization:

[0079] Smooth curve with cubic spline interpolation:

[0080]

[0081] where, is the interpolation curve function, a i , b i , c i , d i are spline coefficients, is the node position;

[0082] Dynamic alarm threshold:

[0083] T alarm = μ ± k·σ

[0084] where, T alarm is the alarm threshold, μ is the mean, σ is the standard deviation, k is the adjustable coefficient;

[0085] Manual intervention instruction verification:

[0086]

[0087] u valid is the effective instruction after verification, u cmd is the operator input instruction, u auto is the instruction generated by the control system, and δ is the maximum allowable deviation range.

[0088] The beneficial effects in the present application are:

[0089] (1) Improve the excavation accuracy: through multi-sensor fusion, the accurate control of the shield excavation axis direction is realized, and the excavation accuracy is significantly improved;

[0090] (2) Improve the excavation efficiency: automatic control reduces the misoperation and adjustment problems of manual operation, and improves the excavation efficiency;

[0091] (3) Reduce the engineering risk: accurate axis control reduces the risk of shield machine deviating from the designed axis, and guarantees the construction safety;

[0092] (4) Facilitate construction management: the man-machine interaction module provides an intuitive operation interface, which facilitates the construction personnel to monitor and intervene in the excavation process of the shield machine. BRIEF DESCRIPTION OF DRAWINGS

[0093] In the drawings:

[0094] Figure 1 is the shield excavation axis direction control system block diagram based on multi-sensor fusion proposed by the present application;

[0095] Figure 2 A flow chart of a shield tunneling axis direction control system based on multi-sensor fusion is proposed for the present application.

[0096] Figure 3 A man-machine interface diagram is proposed for the present application.

[0097] In the figure: 1-Real-time data display area, 2-Alarm prompt area, 3-Manual operation area, 4-Remote monitoring area. DETAILED DESCRIPTION

[0098] Reference Figure 1 A shield tunneling axis direction control system based on multi-sensor fusion, comprising a sensor module, a data processing module, a control module and a man-machine interaction module;

[0099] The sensor module is used to collect various state information of the shield machine in real time.

[0100] Specifically, the sensor module comprises:

[0101] Laser total station: used for measuring the absolute position and attitude of the shield machine, high precision, suitable for long distance measurement;

[0102] Installation position: installed at the tail of the shield machine, the measurement reference point is set at a fixed position in the tunnel.

[0103] Function: Provide high-precision absolute position and attitude information as an important reference data for tunneling direction control.

[0104] Gyroscope: used for measuring the real-time attitude of the shield machine, including pitch angle, yaw angle and roll angle;

[0105] Installation position: installed at the center position of the shield body of the shield machine;

[0106] Function: Real-time measurement of the attitude change of the shield machine, providing immediate feedback for the adjustment of the tunneling direction.

[0107] Accelerometer: used for measuring the acceleration of the shield machine, assisting in judging the motion state of the shield machine;

[0108] Installation position: installed at the center position of the cutterhead of the shield machine;

[0109] Function: Measure the acceleration change of the shield machine to assist in judging the motion state of the shield machine.

[0110] Displacement sensor: used for measuring the displacement change of the shield machine to ensure the accuracy of the tunneling direction;

[0111] Installation position: installed on the thrust cylinder of the shield machine;

[0112] Function: To measure the displacement changes of the tunnel boring machine in real time, providing accurate displacement data for adjusting the tunneling direction. Pressure sensor: Used to measure the pressure of the tunnel boring machine's propulsion cylinders, assisting in determining the thrust status of the tunnel boring machine;

[0113] Installation location: Installed in the hydraulic circuit of the tunnel boring machine's propulsion cylinder;

[0114] Function: To measure the pressure of the propulsion cylinder in real time, providing reference data on thrust status for adjusting the tunneling direction.

[0115] Sensor installation and calibration:

[0116] Laser total station: Fixed to the tail of the tunnel boring machine (TBM) via a bracket, ensuring its measurement range covers the entire tunneling area. The bracket should have sufficient rigidity and stability to minimize the impact of vibration on measurement accuracy. Calibration is required after installation to ensure the accuracy of the measurement reference points.

[0117] Gyroscope: Installed on the center line of symmetry of the shield body to reduce measurement errors. During installation, ensure that the measurement axis of the gyroscope is aligned with the motion axis of the tunnel boring machine. After installation, calibration is required to ensure the accuracy of the measurement data.

[0118] Accelerometer: Mounted on the symmetrical center line of the cutter head to reduce measurement errors. During installation, ensure the accelerometer's measurement axis is aligned with the cutter head's motion axis. Calibration is required after installation to ensure the accuracy of the measurement data.

[0119] Displacement sensors: Installed on the piston rod of each propulsion cylinder to ensure accurate and real-time measurements. During installation, ensure a secure connection between the sensor and the cylinder to prevent loosening due to vibration or impact. Calibration is required after installation to ensure the accuracy of the measurement data.

[0120] Pressure sensors: Installed in the hydraulic circuit of each propulsion cylinder to ensure accurate and real-time measurements. During installation, ensure a secure connection between the sensor and the hydraulic system to prevent measurement errors due to leaks or blockages. Calibration is required after installation to ensure the accuracy of the measurement data.

[0121] The data processing module is used to preprocess the data collected by the sensor module;

[0122] The control module performs calculations based on the data output by the data processing module, and combines this with a real-time feedback mechanism to control the tunnel boring machine's advance direction while simultaneously performing fault diagnosis calculations.

[0123] The human-machine interaction module is used to provide an operating interface for the tunnel boring machine, allowing construction personnel to monitor and intervene in the tunneling process, display real-time data collected by the sensor module, and issue alarms for fault signals fed back by the control module.

[0124] As another embodiment of this application, this embodiment proposes a shield tunneling axis orientation control method based on multi-sensor fusion, which includes any of the above-mentioned shield tunneling axis orientation control systems based on multi-sensor fusion. The method steps are as follows:

[0125] S1. Data Acquisition and Preprocessing:

[0126] Data acquisition: Acquire the real-time status information data of the tunnel boring machine collected by the sensor module and transmit the data to the data processing module;

[0127] The position measurement using a laser total station can be expressed as:

[0128] P t =R t ·P0+T t

[0129] Where: P t Let R be the position vector of the tunnel boring machine at time t. t Let P0 be the rotation matrix, representing the tunnel boring machine's attitude, and T be the initial position vector. t It is a translation vector.

[0130] Attitude measurement uses quaternion representation:

[0131] q = [q0, q1, q2, q3] T

[0132] Where q0 is the scalar part and [q1,q2,q3] is the vector part.

[0133] The relationship between angular velocity and attitude change measured by gyroscope:

[0134]

[0135] in, This is the quaternion multiplication operator, ω = [ω x ,ω y ,ω z ] T The angular velocity measured by the gyroscope. The derivative of the quaternion with respect to time represents the rate of attitude change;

[0136] Accelerometer measurements include both gravitational components and acceleration due to motion.

[0137] a meas =R T (q)·g+a motion +n a

[0138] Among them, a measR is the accelerometer measurement value. T (q) is the transpose of the rotation matrix derived from the quaternion, g: the gravitational acceleration vector [0,0,g], a motion n is the acceleration generated by the movement of the tunnel boring machine. a Accelerometer measurement noise is typically modeled as Gaussian white noise.

[0139] Displacement sensor model, relationship between propulsion cylinder displacement and tunnel boring machine forward distance:

[0140]

[0141] Where, k i The contribution coefficient of each hydraulic cylinder, Δy i This represents the change in displacement of each hydraulic cylinder;

[0142] Dynamic model of pressure sensor, relationship between cylinder pressure and thrust:

[0143]

[0144] Among them, A i For the effective area, b i c is the damping coefficient. i For friction compensation, F i Let P be the thrust of the i-th cylinder. i The pressure of the i-th cylinder (or oil chamber);

[0145] Synchronization of data from sensors with different sampling rates:

[0146]

[0147] Where, x sync For the synchronized data, w i Let τ be the weight of the i-th sensor. i Let t be the time delay compensation amount for the i-th sensor. k For synchronization time points.

[0148] Data preprocessing: The data processing module performs preprocessing operations on the collected data, including the following steps:

[0149] (1) Filtering: A low-pass filter is used to remove high-frequency noise and smooth the data. The cutoff frequency of the low-pass filter is set according to actual needs to ensure that high-frequency noise can be effectively removed while retaining useful signals.

[0150] (2) Noise Reduction: Random noise in the data is removed through algorithms such as Kalman filtering to improve data reliability. Kalman filters can estimate the system state in real time, remove measurement noise and process noise, and improve data accuracy.

[0151] (3) Data fusion: Data from multiple sensors is fused using data fusion algorithms (such as Kalman filtering and particle filtering) to improve the accuracy and reliability of the data. Data fusion algorithms can comprehensively consider data from multiple sensors, thereby improving the overall performance of the system.

[0152] Data fusion is performed using an extended Kalman filter (EKF).

[0153] Equations of state:

[0154] x k =f(x) k-1 ,u k )+w k

[0155] Where, x k This is a state vector containing parameters such as position and orientation, u k Let w be the control input vector at time k. k Process noise represents model uncertainty;

[0156] Observation equation:

[0157] z k =h(x k )+v k

[0158] Among them, z k Let v be the observation vector. k The observation noise represents the measurement error;

[0159] Kalman gain calculation:

[0160]

[0161] Among them, K k Let P be the Kalman gain matrix, representing the degree of confidence in the observations. k∣k-1 To estimate the covariance matrix a priori, H k The observation matrix maps the state space to the observation space, R. k To observe the noise covariance matrix;

[0162] Adaptive wavelet denoising:

[0163]

[0164] in, For the denoised signal, c j0,k d is the scaling factor, representing the low-frequency components of the signal. j,k For wavelet coefficients, φ represents the high-frequency details of the signal. j0,k (t) is the scaling function, ψ j,k(t) is the wavelet function, j0 is the initial decomposition scale, and J is the maximum decomposition scale;

[0165] Robust weighted average fusion:

[0166]

[0167] x is the fused estimate (optimal estimate). i Let w be the measurement value of the i-th sensor. i Let i be the weight of the i-th sensor. Let be the measurement variance of the i-th sensor (reflecting measurement accuracy), and n be the number of sensors participating in the fusion.

[0168] Regular calibration: The data collected by the sensor is calibrated regularly to ensure long-term accuracy. The calibration cycle is determined based on the sensor's characteristics and the actual usage environment, typically weekly or monthly.

[0169] Dynamic calibration: During the tunnel boring machine's excavation process, sensors are dynamically calibrated based on real-time data to ensure data accuracy. Dynamic calibration can promptly correct sensor drift and errors, improving system reliability.

[0170] Local storage: The processed data is stored on the system's local storage device for subsequent analysis and comparison with historical data. Local storage devices can be hard drives, solid-state drives, etc., ensuring data security and reliability.

[0171] Remote storage: Supports uploading data to a remote server, allowing construction personnel to remotely monitor the tunneling status of the tunnel boring machine via the network. Remote storage devices can be cloud servers, data centers, etc., ensuring data real-time performance and accessibility.

[0172] S2. Tunnel Boring Machine Operation Control:

[0173] Direction Adjustment: The control module uses the preprocessed data from step S1 to calculate the deviation between the actual tunneling direction of the tunnel boring machine and the design axis. The deviation calculation formula is as follows:

[0174] Δθ=θ 实际 -θ 设计

[0175] Where Δθ is the deviation angle, θ 实际 θ represents the actual tunneling direction of the tunnel boring machine. 设计 To design the axis direction;

[0176] Parameter Adjustment: The control module adjusts the pressure of the tunnel boring machine's propulsion cylinders and the speed of the cutterhead to achieve precise control of the tunneling direction. The adjustment formula is as follows:

[0177] P调整 =P 当前 +K p ·Δθ

[0178] ω 调整 =ω 当前 +K ω ·Δθ

[0179] Among them, P 调整 To adjust the pressure of the propulsion cylinder, P 当前 To maintain the current hydraulic cylinder pressure, K p ω is the proportionality constant. 调整 ω is the adjusted cutter head speed. 当前 K represents the current spindle speed. ω This is the proportionality coefficient;

[0180] Real-time feedback: The control module monitors the tunneling status of the tunnel boring machine in real time and makes dynamic adjustments based on feedback data to ensure the accuracy of the tunneling direction. The real-time feedback mechanism can promptly correct deviations, improving the system's response speed and control accuracy.

[0181] The deviation in the tunneling direction is represented by quaternions:

[0182]

[0183] Where Δq is the deviation quaternion, q actual Let q be the actual attitude quaternion. design To design the quaternion of axis attitude;

[0184] Convert to Euler angle deviation:

[0185]

[0186] Δφ is the roll angle deviation, Δθ is the pitch angle deviation, Δψ is the yaw angle deviation, and f(Δq) is the deviation quaternion function;

[0187] Dynamically adaptively adjust the PID based on feedback data:

[0188] Propulsion system control quantity calculation:

[0189]

[0190] Where u(t) is the control output, e(t) is the deviation signal (actual value - setpoint), and K p For proportional gain, K i For integral gain, K d Let τ be the differential gain, and τ be the integral time variable;

[0191] K p =K p0+α·||e(t)||

[0192] Among them, K p0 Let α be the base value (initial value or default value) of the proportional gain, and let α be an adjustable parameter or coefficient that determines the magnitude of the deviation signal ||e(t)|| relative to the proportional gain K. p The degree of impact;

[0193] Hydraulic cylinder thrust distribution:

[0194]

[0195] Among them, F i F represents the actual thrust of the i-th cylinder. i,desired Let z be the ideal thrust of the i-th cylinder, and z be the total number of cylinders.

[0196] Constraints:

[0197]

[0198] r i Let M be the position vector of the i-th cylinder. desired Let be the desired resultant moment vector;

[0199] Real-time monitoring: Monitor the operating status of the tunnel boring machine in real time, including sensor data, equipment operating parameters, etc., and promptly detect potential faults;

[0200] Fault Alarm: When a potential fault is detected, the system issues an alarm to remind construction personnel to inspect and handle it. Alarm methods can include audible and visual alarms, SMS notifications, etc., ensuring that construction personnel receive alarm information promptly.

[0201] Fault Log: Records the time, location, and cause of a fault, facilitating fault analysis and handling by construction personnel. Fault logs can be stored locally or uploaded to a remote server for subsequent analysis.

[0202] S3, Artificial Intervention:

[0203] Real-time monitoring: Construction personnel can monitor the tunneling status of the tunnel boring machine in real time through the human-machine interaction module;

[0204] Data visualization: Real-time data such as the tunnel boring machine's attitude, position, speed, and pressure are displayed on the operating interface, allowing construction personnel to intuitively understand the tunneling status of the machine. Data visualization can use charts, graphs, dashboards, etc., to improve data readability.

[0205] Smoothing curve using cubic spline interpolation:

[0206]

[0207] in, Let a be the interpolation curve function. i b i c i d i For spline coefficients, For node position;

[0208] Data update frequency: Set the data update frequency according to actual needs, usually once per second, to ensure that construction personnel can monitor the tunneling status of the tunnel boring machine in real time;

[0209] Abnormal Alarm: When the tunnel boring machine (TBM) exhibits abnormal tunneling behavior, the system issues an alarm to alert construction personnel to intervene. Abnormal alarms include excessive deviation in tunneling direction, abnormal equipment operating parameters, and abnormal environmental parameters.

[0210] Dynamic alarm threshold:

[0211] T alarm =μ±k·σ

[0212] Among them, T alarm Where μ is the alarm threshold, σ is the mean, k is the standard deviation, and k is the adjustable coefficient.

[0213] Alarm methods: Alarm methods can include audible and visual alarms, SMS notifications, email notifications, etc., to ensure that construction personnel can receive alarm information in a timely manner.

[0214] Manual Adjustment: Construction personnel can manually adjust the tunneling direction of the tunnel boring machine through the operating interface to ensure construction safety. Manual adjustment functions include adjusting parameters such as propulsion cylinder pressure and cutterhead rotation speed.

[0215] Verification of manual intervention instructions:

[0216]

[0217] u valid For verified valid instructions, u cmd Enter commands for the operator, u auto The command is generated by the control system, and δ is the maximum permissible deviation range.

[0218] Emergency Stop: In emergency situations, construction personnel can use the operating interface to urgently stop the tunnel boring machine's excavation, ensuring construction safety. The emergency stop function can immediately cut off the power to the tunnel boring machine and stop all operations.

[0219] Remote monitoring:

[0220] Network connectivity: Supports remote monitoring of the tunnel boring machine's excavation status via network. Construction personnel can view the real-time data of the tunnel boring machine anytime, anywhere using mobile phones, tablets, computers, and other devices.

[0221] Data synchronization: The remote monitoring equipment keeps data synchronized with the local system to ensure that construction personnel can obtain the latest tunneling status information in real time.

[0222] Historical data query:

[0223] Data storage: The tunneling data of the tunnel boring machine is stored in the system, including data such as attitude, position, speed, and pressure, so that construction personnel can easily query historical data.

[0224] Data Query: Construction personnel can query historical data through the user interface to analyze the tunneling process of the tunnel boring machine and optimize the construction plan. The historical data query function can be filtered by time, date, tunneling mileage, and other conditions, making it easy for construction personnel to quickly find the data they need.

[0225] System availability calculation:

[0226]

[0227] Where A represents system availability (between 0 and 1), MTBF represents mean time between failures, and MTTR represents mean time to repair.

[0228] Minimize system energy consumption:

[0229]

[0230] Among them, P i Let β be the power of each component, β be the adjustment coefficient, β be the trade-off coefficient between control energy consumption and performance, and u be the control input vector.

[0231] System installation and debugging:

[0232] Sensor installation: A laser total station is installed at the tail of the tunnel boring machine, a gyroscope is installed at the center of the shield body, an accelerometer is installed at the center of the cutterhead, displacement and pressure sensors are installed on the propulsion cylinders, temperature sensors are installed on key components, and humidity and gas sensors are installed inside the tunnel.

[0233] Data processing module debugging: Debug the filters, denoising algorithms, data fusion algorithms, etc. to ensure that the data processing module can work properly.

[0234] Control module debugging: Debug the direction adjustment algorithm, real-time feedback mechanism, fault diagnosis algorithm, etc. to ensure that the control module can work normally.

[0235] Human-computer interaction module debugging: Debug the functions such as real-time data display, alarm prompts, manual operation, remote monitoring, and historical data query to ensure that the human-computer interaction module can work normally.

[0236] System Operation and Monitoring

[0237] System startup: When the system starts, all sensors are initialized to ensure that they are in normal working condition.

[0238] Data Acquisition and Processing: The sensor module collects real-time information on the tunnel boring machine's attitude, position, speed, pressure, etc., and transmits the data to the data processing module. The data processing module performs preprocessing operations such as filtering, noise reduction, and data fusion on the collected data to improve the accuracy and reliability of the data.

[0239] Automatic control: The control module automatically adjusts the tunnel boring machine's advance direction based on the processed data to ensure that the tunneling axis meets the design requirements.

[0240] Manual intervention: Construction personnel can monitor the tunneling status of the tunnel boring machine in real time through the human-machine interaction module and intervene manually when necessary.

[0241] System Testing and Optimization: System testing involves testing the system in actual engineering projects, collecting test data, and analyzing system performance. System optimization involves optimizing the system based on the test results to improve its stability and reliability.

Claims

1. A shield tunneling axis direction control system based on multi-sensor fusion, characterized in that: It comprises a sensor module, a data processing module, a control module and a human-computer interaction module. The sensor module is used for real-time acquisition of various state information of the shield machine, and comprises: A laser total station is used for measuring the absolute position and attitude of the shield machine; A gyroscope is used for measuring the real-time attitude of the shield machine, including the pitch angle, yaw angle and roll angle; An accelerometer is used for measuring the acceleration of the shield machine, assisting in judging the motion state of the shield machine; A displacement sensor is used for measuring the displacement change of the shield machine, ensuring the accuracy of the tunneling direction; A pressure sensor is used for measuring the pressure of the shield machine's propulsion cylinder, assisting in judging the thrust state of the shield machine; The data processing module is used for pre-processing the data collected by the sensor module; The control module performs operation based on the data output by the data processing module, controls the propulsion direction of the shield machine in combination with a real-time feedback mechanism, and performs fault judgment operation; The human-computer interaction module is used for providing a shield machine operation interface for construction personnel to monitor and intervene in the tunneling process of the shield machine, displaying the real-time data collected by the sensor module, and alarming the fault signals fed back by the control module.

2. A shield tunneling axis direction control method based on multi-sensor fusion, characterized in that: The method comprises the steps of: S1, data acquisition and preprocessing: Data acquisition: acquiring the shield machine state information data collected by the sensor module in real time, and transmitting the data to the data processing module; Data preprocessing: the data processing module performs preprocessing operation on the collected data; S2, shield machine operation control: Direction adjustment: the control module applies the data preprocessed in step S1 to calculate the deviation of the actual tunneling direction of the shield machine from the design axis; Parameter adjustment: the control module adjusts the propulsion cylinder pressure and cutterhead speed parameters of the shield machine to realize accurate control of the tunneling direction; Real-time feedback: the control module monitors the tunneling state of the shield machine in real time and dynamically adjusts according to the feedback data; Real-time monitoring: real-time monitoring of the running state of the shield machine to monitor whether there is a potential fault in the shield machine; Fault alarm: when a potential fault is judged, an alarm signal is triggered; Fault record: recording the time, position and cause information of the fault; S3, manual intervention: Real-time monitoring: the construction personnel monitor the tunneling state of the shield machine in real time through the human-computer interaction module; Manual adjustment: the construction personnel manually adjust the tunneling direction of the shield machine through the operation interface; Emergency stop: the construction personnel trigger an emergency stop command through the operation interface to stop the tunneling of the shield machine.

3. The shield tunneling axis direction control method based on multi-sensor fusion according to claim 2, characterized in that, In step S1: EKF is used for data fusion: State equation: x k = f(x k-1 , u k ) + w k where x k is the state vector, u k is the control input vector at time k, w k is the process noise; Observation equation: z k = h(x k ) + v k where z k is the observation vector, v k is the observation noise; Kalman gain calculation: where K k is the Kalman gain matrix, P k∣k-1 is the a priori estimate covariance matrix, H k is the observation matrix mapping the state space to the observation space, R k is the observation noise covariance matrix; Adaptive wavelet denoising: wherein, is the denoised signal, c j0,k is the scale coefficient, d j,k is the wavelet coefficient, φ j0,k (t) is the scale function, ψ j,k (t) is the wavelet function, j0 is the initial decomposition scale, and J is the maximum decomposition scale. Robust weighted average fusion: x is the fused estimate i wi is the measurement of the ith sensor, w i wi is the weight of the ith sensor, σi2is the measurement variance of the ith sensor, n is the number of sensors participating in the fusion.

4. The shield tunneling axis direction control method based on multi-sensor fusion according to claim 3, characterized in that, In step S1: Synchronization of different sampling rate sensor data: wherein x sync is the synchronized data, w i is the weight of the i th sensor, τ i is the time delay compensation of the i th sensor, t k is the synchronization time point.

5. The shield tunneling axis direction control method based on multi-sensor fusion according to claim 2, characterized in that, In step S2: The deviation formula of the actual tunneling direction from the design axis is: Δθ = θ 实际 -θ 设计 Wherein, Δθ is the deviation angle, θ 实际 is the actual tunneling direction of the shield machine, θ 设计 is the design axis direction; The parameter adjustment formula is: P 调整 = P 当前 + K p · Δθ ω 调整 = ω 当前 + K ω · Δθ P 调整 is the adjusted propelling cylinder pressure, P 当前 is the current propelling cylinder pressure, K p is the proportional coefficient; ω 调整 is the adjusted cutterhead rotational speed, ω 当前 is the current cutterhead rotational speed, K ω is the proportional coefficient; The tunneling direction deviation is expressed by a quaternion: where Δq is the bias quaternion, q actual is the actual attitude quaternion, q design is the design axis attitude quaternion; Converted into Euler angle deviation: Δφ is the roll angle deviation, Δθ is the pitch angle deviation, Δψ is the yaw angle deviation, and f(Δq) is the deviation quaternion function; Dynamic adaptive PID adjustment is performed according to the feedback data: Propulsion system control quantity calculation: where u(t) is the control output, e(t) is the deviation signal, K p is the proportional gain, K i is the integral gain, K d is the differential gain, and τ is the integral time variable. K p = K p0 + a · || e(t) || where K p0 is a basic value of the proportional gain, and a is an adjustable parameter; Cylinder thrust distribution: wherein F i is the actual thrust of the i-th oil cylinder, F i,desired is the ideal thrust of the i-th oil cylinder, and z is the total number of oil cylinders. Constraints: r i is the position vector of the ith cylinder, M desired is the desired resultant moment vector.

6. The shield tunneling axis direction control method based on multi-sensor fusion according to claim 2, characterized in that, In step S3: Data visualization: Smooth curve using cubic spline interpolation: wherein is an interpolating curve function, a i , b i , c i , d i are spline coefficients, is a node position; Dynamic alarm threshold: T alarm = μ ± k · σ where T alarm is the alarm threshold, μ is the mean, σ is the standard deviation, and k is an adjustable coefficient. Manual intervention command verification: u valid u cmd u auto u

Images