Cylinder pressure control method based on complex loose body excavation pressure reflection

Abstract

This invention discloses a hydraulic cylinder pressure control method based on the pressure response during tunneling in complex loose bodies, belonging to the field of swarm intelligence tunneling control technology. The method includes: acquiring real-time tunneling pressure data of the tunneling equipment and constructing a spatial pressure distribution field characterizing the surface stress state; extracting pressure characteristic parameters based on the spatial pressure distribution field, identifying and defining the complex loose body region and its distribution state; establishing thrust decoupling mapping rules according to the distribution state of the complex loose body region, constructing a joint objective function, using a swarm intelligence algorithm for iterative optimization, and calculating the target pressure value of each propulsion cylinder section of the tunneling equipment; outputting the optimal target pressure value for each propulsion cylinder section, and outputting control commands to the hydraulic execution module. The method of this invention, by reconstructing the spatial pressure distribution field and introducing a swarm intelligence algorithm for multi-objective thrust decoupling optimization, achieves active adaptive flexible control of the propulsion cylinder section pressure.

Description

Technical Field

[0001] This invention relates to the field of swarm intelligent tunneling control technology, and in particular to a hydraulic cylinder pressure control method based on the pressure response during tunneling in complex loose materials. Background Technology

[0002] In tunneling operations, the propulsion cylinder system serves as the core power source for the equipment's movement. The precise control of its thrust and pressure directly affects the stability of the tunnel face and the quality of segment assembly. Modern tunneling equipment typically equips the earth pressure chamber or the back of the cutterhead with an array of earth pressure sensors. These sensors are designed to collect data on local stress changes, supplemented by conventional PID feedback regulation or fuzzy logic control.

[0003] When dealing with typical complex loose geological formations such as fault fracture zones and water-rich sand and gravel, existing hydraulic cylinder pressure control technologies mostly rely on discrete single-point pressure feedback, lacking the ability to reconstruct the spatial field state of the overall stress state at the tunnel face. The control system cannot accurately capture the topological boundaries and spatiotemporal evolution of the loose body, easily leading to perception blind spots. Blindly increasing thrust and mechanically rigidly responding can easily trigger further compression and fracturing of the loose body. Traditional analytical algorithms and conventional controllers struggle to achieve globally optimal configuration for multiple objectives under tunneling conditions, resulting in the pressure distribution of each cylinder zone remaining suboptimal for extended periods, with lag in dynamic response and a tendency to overshoot. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a hydraulic cylinder pressure control method based on the pressure response of complex loose bodies to solve the problems of existing tunneling machine hydraulic propulsion technology, such as lack of spatial topological perception of loose bodies at the tunnel face, failure to achieve multi-objective decoupling in thrust control, and insufficient ability to optimize multi-zone pressure distribution.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a hydraulic cylinder pressure control method based on the pressure response of tunneling in complex loose bodies, which includes acquiring real-time tunneling pressure data of the tunneling equipment and constructing a spatial pressure distribution field characterizing the surface stress state;

[0008] Based on the spatial pressure distribution field, pressure characteristic parameters are extracted to identify and define the complex loose body region and its distribution status.

[0009] Based on the distribution of complex loose body regions, thrust decoupling mapping rules are established, a joint objective function is constructed, and a genetic algorithm is used for iterative optimization to calculate the target pressure values ​​of the propulsion cylinder zones of the tunneling equipment.

[0010] Output the optimal target pressure value for each propulsion cylinder zone and output control commands to the hydraulic actuator module.

[0011] As a preferred embodiment of the hydraulic cylinder pressure control method based on the pressure response during tunneling of complex loose materials as described in this invention, the real-time tunneling pressure data includes data collected from an array of components mounted on the stress-bearing surfaces of the tunneling equipment. One pressure sensor; multi-channel data acquisition is employed, and the analog signals output by all sensors are synchronously converted to digital signals at a sampling rate higher than the vibration frequency of the tunneling equipment to obtain a discrete-time series including environmental noise and high-frequency mechanical vibration. ,in , indicating the first The sensor number;

[0012] The sequence is smoothed and then input into a low-pass filter to obtain the cleaned effective tunneling pressure value. .

[0013] As a preferred embodiment of the hydraulic cylinder pressure control method based on the pressure response during tunneling of complex loose bodies as described in this invention, the following steps are included: constructing a spatial pressure distribution field characterizing the surface stress state; mapping the current physical position of the sensor to the absolute coordinate system of the surface; establishing a static two-dimensional Cartesian coordinate system for the tunneling surface with the intersection of the tunneling equipment's central axis and the tunneling surface as the origin; and recording the... The mounting radius of each sensor on the cutter head and initial polar angle ;

[0014] Real-time acquisition via the tool turret spindle encoder Instantaneous rotational angular velocity of the cutter head ; The result is obtained by calculating using the spatial kinematic equations. One sensor in The absolute coordinates projected onto the tunneling surface at any moment ;

[0015] Pressure value The absolute coordinates calculated from the spatial dimensions Perform timestamp binding at any sampling time Encapsulated into a structured data frame .

[0016] As a preferred embodiment of the hydraulic cylinder pressure control method based on the pressure response during tunneling in complex loose materials as described in this invention, wherein: the complex loose material region and its distribution state include, assuming the radius of the cutterhead or excavation face of the tunneling equipment is... Define the effective computation domain ;

[0017] In the domain Within, with the set spatial resolution as Perform two-dimensional equidistant mesh generation to generate a mesh containing Grid coordinate set of unknown nodes ;

[0018] Field state reconstruction is performed using an interpolation algorithm, based on real-time acquired data. Calculate different spatial distances using known sensor data. semivariance of pressure change ;

[0019] Selecting a spherical model By fitting the data, the theoretical variogram is obtained. Spatial correlation rules characterizing current formation pressure;

[0020] The distribution state of the complex loose body region includes, for the grid set For any point to be estimated, the estimated pressure value yes known observations A linear combination; to ensure unbiased estimation and minimize estimation variance, the following system of equations is constructed to solve for the weight coefficients of each known point. ;

[0021] Traversing the mesh set All of them Each node completes full-section interpolation;

[0022] The solution obtained The pressure estimates for each grid point are mapped to a two-dimensional matrix according to their spatial location, generating... Continuous spatial pressure distribution field matrix at time t. For the matrix Masking is performed to output a continuous and smooth spatial pressure distribution field on the tunneling surface;

[0023] Use dual logical thresholds for joint determination:

[0024] Set a safety threshold, and preset a lower limit threshold of the safe pressure required to maintain stability of the tunneling surface. The upper limit threshold of gradient abrupt change, characterizing abrupt changes in formations such as cavitation or extreme looseness. ;

[0025] Perform Boolean logic discrimination on the distribution field matrix. and gradient matrix Double threshold condition discrimination is performed on nodes with the same coordinates in the data;

[0026] The current grid point is determined to be a suspected loose point if and only if the double logic threshold condition is met; generate Binary state matrix of the tunneling surface at time step .

[0027] As a preferred embodiment of the hydraulic cylinder pressure control method based on the pressure response during tunneling in complex loose bodies as described in this invention, wherein: establishing the thrust decoupling mapping rule includes, for the binarized state matrix Perform opening operation; scan the matrix using the eight-neighbor connectivity algorithm. Cluster nodes that are spatially connected and assigned a value of 1 into a connected region; let a total of [number] nodes be extracted. An independent connected region ;

[0028] Calculate the actual physical area of ​​each connected region. Set a threshold for the dangerous area. ,reserve The region is considered a complex loose body region;

[0029] Establish a direct mapping relationship between the feature coordinates of the tunneling surface and the physical partitions of the hydraulic cylinders of the tunneling equipment, and set the search boundary for the heuristic algorithm;

[0030] Assume the tunneling equipment propulsion system is divided into: Each hydraulic cylinder is independently controlled in a zone, and the equivalent force arm coordinates of each zone are known. The target pressure value to be determined is ;

[0031] Based on the centroid coordinates of the loose body Coordinates of each partition The spatial distance determines the control attributes of each partition;

[0032] The decompression follower region of the loose body mapping is defined as the region closest to the centroid of the loose body; a lower and upper bound for the pressure search are set to limit the upper limit of the output;

[0033] The pressurization zone is mapped to the stable strata, and the remaining zones on the opposite side are defined as the pressurization zone.

[0034] The sum of the pressures from all zones must meet the total basic thrust required for the current tunneling rate. .

[0035] As a preferred embodiment of the hydraulic cylinder pressure control method based on the pressure response during tunneling in complex loose bodies as described in this invention, the construction of the joint objective function includes constructing a three-dimensional multi-objective fitness function set. The objective function for minimizing perturbations in the loose body region. The objective function for minimizing device attitude deviation The objective function for minimizing the thrust distribution variance .

[0036] As a preferred embodiment of the hydraulic cylinder pressure control method based on the pressure response of tunneling in complex loose bodies as described in this invention, the step of using a genetic algorithm for iterative optimization includes solving the fitness function set under constraints using a multivariate heuristic optimization algorithm.

[0037] Within the set boundary constraints, randomly generate The initial population consists of 10 particles; the position vector of each particle... This represents the hydraulic cylinder zone pressure distribution scheme;

[0038] Substitute the position vector of each particle into the fitness function set. The evaluation is conducted in the middle; based on the Pareto dominance theory, the individuals in the population are non-dominated and ranked to select the current non-dominated solution set;

[0039] The population is updated according to the specific evolutionary mechanism of the algorithm. In the particle swarm mechanism, the individual extreme value and the global optimal solution set of each particle are calculated, and the particles are guided to fly towards the optimal solution region through the velocity update formula and the position update formula.

[0040] Repeat the iterative update process until the maximum number of iterations is reached. Stop searching.

[0041] As a preferred embodiment of the hydraulic cylinder pressure control method based on the pressure response during tunneling in complex loose bodies as described in this invention, the calculation of the target pressure value for the propulsion cylinder zone of the tunneling equipment includes, after the algorithm iteration is completed, outputting a Pareto front solution set containing multiple feasible solutions; introducing an objective weighting method based on information entropy, assigning an objective function according to the current loose body area. Weights; and adjust the target weights according to the most pressing working conditions currently faced in the tunneling, automatically determining the optimal compromise solution from the frontier solution set. ,in, ;

[0042] The final optimal target pressure values ​​for each zone will be determined. The parameters are converted into electronic control commands and used as target parameters for the next control cycle. Among them, the target values ​​for the loose body zone naturally exhibit low-pressure following characteristics, while the target values ​​for the stable strata zone naturally exhibit high-pressure dominance characteristics.

[0043] In a second aspect, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the hydraulic cylinder pressure control method based on the pressure response of tunneling in complex loose material as described in the first aspect of the present invention.

[0044] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the hydraulic cylinder pressure control method based on the pressure response of tunneling in complex loose material as described in the first aspect of the present invention.

[0045] The beneficial effects of this invention are as follows: By reconstructing the spatial pressure distribution field, it breaks through the perception blind spot of traditional single-point discrete measurements, achieving accurate and global identification of the boundaries and evolution states of complex loose bodies at the tunnel face. A thrust decoupling strategy is established, overturning the rigid logic of traditional blind pressurization and effectively avoiding local collapses and equipment loss of control caused by excessive compression. The introduction of a swarm intelligence algorithm, while ensuring sufficient total thrust and balanced attitude torque, achieves globally optimized dynamic allocation of cylinder pressure in each zone, improving the safety and control accuracy of tunneling in complex strata. Attached Figure Description

[0046] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. 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.

[0047] Figure 1 This is a flowchart of a hydraulic cylinder pressure control method based on the pressure response during tunneling in complex loose materials.

[0048] Figure 2 This is a schematic diagram of a computer device for a hydraulic cylinder pressure control method based on the pressure response during tunneling in complex loose materials. Detailed Implementation

[0049] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0050] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0051] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0052] Reference Figures 1-2This is one embodiment of the present invention, which provides a hydraulic cylinder pressure control method based on the pressure response during tunneling in complex loose materials, comprising the following steps:

[0053] S1: Obtain real-time tunneling pressure data from the tunneling equipment and construct a spatial pressure distribution field characterizing the surface stress state.

[0054] The real-time tunneling pressure data includes data from an array installed on the stress-bearing surface of the tunneling equipment. One pressure sensor; multi-channel data acquisition is employed, and the analog signals output by all sensors are synchronously converted to digital signals at a sampling rate higher than the vibration frequency of the tunneling equipment to obtain a discrete-time series including environmental noise and high-frequency mechanical vibration. ,in , indicating the first The sensor number.

[0055] The sequence is smoothed and then input into a low-pass filter to obtain the cleaned effective tunneling pressure value. .

[0056] Arrayed installation on the stress-bearing surfaces of the tunneling equipment (such as cutterhead panels or earth pressure chamber baffles). One earth pressure sensor. A multi-channel data acquisition card is used, with a sampling rate higher than the highest vibration frequency of the tunneling equipment (e.g., ...). The system performs synchronous analog-to-digital conversion (A / D conversion) on the analog voltage / current signals output from all sensors. It also acquires discrete-time series data including environmental noise and high-frequency mechanical vibrations. ,in, Indicates the first The sensor number.

[0057] Because rock breaking, cutting loose materials, and motor operation generate a large amount of high-frequency noise signals, directly using the raw data will cause malfunctions in the control system. Therefore, digital filtering algorithms are required. (Set the time window length.) The original sequence is smoothed to eliminate sudden spikes in interference:

[0058]

[0059] Smoothed data Input a first-order or second-order Butterworth low-pass filter, with its cutoff frequency set to... (usually set to) (This refers to the low-frequency effective signal reflecting the actual stress changes in the formation), ultimately yielding the effective tunneling pressure value after cleaning. .

[0060] The construction of the spatial pressure distribution field characterizing the surface stress state includes mapping the current physical position of the sensor to the absolute coordinate system of the surface; establishing a static two-dimensional Cartesian coordinate system for the tunneling surface with the intersection of the tunneling equipment's central axis and the tunneling surface as the origin; and recording the first... The mounting radius of each sensor on the cutter head and initial polar angle .

[0061] Real-time acquisition via the tool turret spindle encoder Instantaneous rotational angular velocity of the cutter head ; The result is obtained by calculating using the spatial kinematic equations. One sensor in The absolute coordinates projected onto the tunneling surface at any moment .

[0062] If the sensor is mounted on the rotary cutterhead, its spatial position changes dynamically over time, and its current physical position must be mapped to the absolutely stationary coordinate system of the tunneling surface.

[0063] The origin is the intersection of the tunneling equipment's central axis and the tunneling surface. Establish a static two-dimensional Cartesian coordinate system on the tunneling surface. Record the first... The mounting radius of each sensor on the cutter head and initial polar angle Simultaneously, the real-time data is acquired via the tool turret spindle encoder. Instantaneous rotational angular velocity of the cutter head . No. One sensor in The absolute coordinates projected onto the tunneling surface at any moment Real-time solution is achieved using the following spatial kinematic equations:

[0064]

[0065]

[0066] If the sensor is fixedly mounted on a non-rotating earth pressure chamber bulkhead, then dynamic calculation is unnecessary, and its coordinates are... It is a constant matrix.

[0067] Pressure value The absolute coordinates calculated from the spatial dimensions Perform timestamp binding at any sampling time Encapsulated into a structured data frame .

[0068] S2: Extract pressure characteristic parameters based on the spatial pressure distribution field, identify and define the complex loose body region and its distribution status.

[0069] The complex loose body region and its distribution include, assuming the radius of the cutterhead or excavation face of the tunneling equipment is... Define the effective computation domain .

[0070] In the domain Within, with the set spatial resolution as Perform two-dimensional equidistant mesh generation to generate a mesh containing Grid coordinate set of unknown nodes .

[0071] Field state reconstruction is performed using an interpolation algorithm, based on real-time acquired data. Calculate different spatial distances using known sensor data. semivariance of pressure change .

[0072] Selecting a spherical model By fitting the data, the theoretical variogram is obtained. Spatial correlation rules characterizing current formation pressure.

[0073] In order to digitally represent a continuous spatial field, it is first necessary to virtually mesh the circular (or rectangular) tunneling surface in front of the tunneling equipment.

[0074] Let the radius of the cutterhead or excavation face of the tunneling equipment be... Define the effective computation domain .

[0075] Mesh Discretization: in the domain Within, at the set spatial resolution (For example Perform two-dimensional equidistant mesh generation to generate a mesh containing... Grid coordinate set of unknown nodes .

[0076] Based on spatial autocorrelation, variogram fitting (using ordinary kriging interpolation as an example) shows that the forces acting on geological bodies exhibit spatial autocorrelation (the closer the points are, the closer the pressure values). Ordinary kriging interpolation is used for field state reconstruction.

[0077] Based on real-time acquisition Calculate different spatial distances using known sensor data. semivariance of pressure change :

[0078]

[0079] in, The distance is The number of sensor data point pairs Given a matrix of point coordinates, This represents the real-time pressure value at the corresponding measuring point.

[0080] Fitting the theoretical variogram: Use either a spherical model or a Gaussian model. By fitting the data, the theoretical variogram is obtained. This is used to characterize the spatial correlation of current formation pressure.

[0081] The distribution state of the complex loose body region includes, for the grid set For any point to be estimated, the estimated pressure value yes known observations A linear combination; to ensure unbiased estimation and minimize estimation variance, the following system of equations is constructed to solve for the weight coefficients of each known point. .

[0082] Interpolation weighting and pressure estimation for target grid points. Using a fitted variogram, the pressure values ​​at unknown grid points across the entire cross-section are calculated.

[0083] For grid sets Any point to be estimated in Its pressure estimate yes known observations A linear combination of these equations. To ensure unbiased estimation and minimize the estimation variance, the following system of equations is constructed to solve for the weight coefficients of each known point. :

[0084]

[0085] in For Lagrange multipliers, The values ​​of the variogram between known points. This represents the variogram value between the known point and the point to be estimated.

[0086] Solve for the weights Then, calculate the estimated pressure value for that grid point:

[0087]

[0088] Traversing the mesh set All of them Each node completes the full-section interpolation.

[0089] The solution obtained The pressure estimates for each grid point are mapped to a two-dimensional matrix according to their spatial location, generating... Continuous spatial pressure distribution field matrix at time t. For the matrix Masking is performed to output a continuous and smooth spatial pressure distribution field on the tunneling surface.

[0090] Due to the matrix Includes full-section mesh set middle The system first differentiates the pressure field at each node to capture the spatial abrupt changes in pressure.

[0091] For the effective computational domain Any grid node within The central difference method (or Sobel operator) is used to calculate its value in... direction and Partial derivative of pressure in the direction of change (i.e., rate of change of pressure):

[0092]

[0093]

[0094] in, The grid space resolution set in the previous step, For matrix The corresponding estimated pressure value.

[0095] Calculate the gradient magnitude: synthesize the two-dimensional spatial pressure gradient magnitude vector of this node. :

[0096]

[0097] Traverse all grid points and generate a parallel grid. Consistent pressure gradient magnitude matrix .

[0098] Use dual logical thresholds for joint determination:

[0099] Set a safety threshold, and preset a lower limit threshold of the safe pressure required to maintain stability of the tunneling surface. The upper limit threshold of gradient abrupt change, characterizing abrupt changes in formations such as cavitation or extreme looseness. .

[0100] Perform Boolean logic discrimination on the distribution field matrix. and gradient matrix Double threshold condition discrimination is performed on nodes with the same coordinates.

[0101] The solution obtained The pressure estimates for each grid point are mapped to a two-dimensional matrix according to their spatial location, generating... Continuous spatial pressure distribution field matrix at time t. For the matrix Masking is performed to eliminate the excavation radius. Invalid data other than that is excluded; and a Gaussian smoothing filter is applied to eliminate local distortion noise generated during the interpolation process, ultimately outputting a high-resolution, continuous and smooth spatial pressure distribution field on the tunnel surface.

[0102] The current grid point is determined to be a suspected loose point if and only if the double logic threshold condition is met; generate Binary state matrix of the tunneling surface at time step .

[0103] S3: Based on the distribution of complex loose body regions, establish thrust decoupling mapping rules, construct a joint objective function, use swarm intelligence algorithm for iterative optimization, and calculate the target pressure value of the propulsion cylinder zone of the tunneling equipment.

[0104] The establishment of the thrust decoupling mapping rule includes, for example, the binary state matrix. Perform opening operation; scan the matrix using the eight-neighbor connectivity algorithm. Cluster nodes that are spatially connected and assigned a value of 1 into a connected region; let a total of [number] nodes be extracted. An independent connected region .

[0105] Calculate the actual physical area of ​​each connected region. Set a threshold for the dangerous area. ,reserve The region is considered a complex loose body region.

[0106] Establish a direct mapping relationship between the feature coordinates of the tunneling surface and the physical partitions of the hydraulic cylinders of the tunneling equipment, and set the search boundary for the heuristic algorithm.

[0107] Establish a direct mapping relationship between the feature coordinates of the tunneling surface and the physical partitions of the hydraulic cylinders of the tunneling equipment, and set a safe search boundary for the heuristic algorithm.

[0108] Assume the tunneling equipment propulsion system is divided into: Each hydraulic cylinder is independently controlled in a zone (e.g., four zones: upper, lower, left, and right). The equivalent force arm coordinates of each partition are known as follows: The target pressure value to be determined is Based on the centroid coordinates of the loose body Coordinates of each partition Spatial distance determines the control attributes of each partition:

[0109] Decompression Follower Region (Loose Body Mapping Region): A region is defined as the follower region if it is closest to the centroid of the loose body. Its pressure search lower and upper bounds are set as follows. This forces a limit on its output to prevent it from collapsing due to compression.

[0110] The pressure boosting zone (stable formation mapping zone): The remaining zones on the opposite side are defined as the pressure boosting zone. Its pressure search range is set as follows: This allows it to output high voltage to provide the main power for the equipment to move forward.

[0111] Total thrust constraint: The sum of the pressures of all zones must meet the basic total thrust required for the current tunneling rate. ,Right now

[0112]

[0113] Assume the tunneling equipment propulsion system is divided into: Each hydraulic cylinder is independently controlled in a zone, and the equivalent force arm coordinates of each zone are known. The target pressure value to be determined is .

[0114] Based on the centroid coordinates of the loose body Coordinates of each partition The spatial distance determines the control attributes of each partition.

[0115] The decompression follower region of the loose body mapping is defined as the region closest to the centroid of the loose body; a lower and upper bound for the pressure search are set to limit the upper limit of the output.

[0116] The pressurization zone is mapped to the stable strata, and the remaining zones on the opposite side are defined as the pressurization zones.

[0117] The sum of the pressures from all zones must meet the total basic thrust required for the current tunneling rate. .

[0118] The construction of the joint objective function includes constructing a three-dimensional multi-objective fitness function set. The objective function for minimizing perturbations in the loose body region. The objective function for minimizing device attitude deviation The objective function for minimizing the thrust distribution variance .

[0119] Furthermore, the control logic of decompression following and boosting is transformed into a computable mathematical objective function. A multi-objective fitness function set containing the following three dimensions is constructed. :

[0120] Objective function 1 (Minimizing disturbance in the loose region): Ensure that the cylinder pressure in the loose body mapping region is as small as possible to achieve flexible following, expressed by the formula:

[0121]

[0122] in, Based on loose volume area Dynamically adjusted sensitivity weights.

[0123] Objective function two (minimizing device attitude deviation): Ensure that the resultant torque generated by each zone can offset the current attitude deviation (yaw angle deviation). pitch angle deviation The formula is expressed as:

[0124]

[0125] in , The combined torque generated by the hydraulic cylinders in each zone; , is the attitude stiffness coefficient.

[0126] The iterative optimization using swarm intelligence algorithms includes solving for the fitness function set under constraints using a multivariate heuristic optimization algorithm.

[0127] Within the defined search boundary, randomly generate The initial population consists of 10 particles; the position vector of each particle... This represents the hydraulic cylinder zone pressure distribution scheme.

[0128] Substitute the position vector of each particle into the fitness function set. The evaluation is conducted in the middle; based on the Pareto dominance theory, the individuals in the population are non-dominated and ranked to select the current non-dominated solution set.

[0129] The population is updated according to the specific evolutionary mechanism of the algorithm. In the particle swarm optimization mechanism, the individual extreme value and the global optimal solution set of each particle are calculated, and the particles are guided to fly towards the optimal solution region through velocity update formula and position update formula.

[0130] Repeat the iterative update process until the maximum number of iterations is reached. Stop searching.

[0131] S4: Outputs the optimal target pressure value for each propulsion cylinder zone and outputs control commands to the hydraulic actuator module.

[0132] The calculation of the target pressure value of the propulsion cylinder zone of the tunneling equipment includes, after the algorithm iteration is completed, outputting a Pareto front solution set containing multiple feasible solutions; introducing an objective weighting method based on information entropy, and assigning an objective function according to the current loose body area. Weights; and adjust the target weights according to the most pressing working conditions currently faced in the tunneling, automatically determining the optimal compromise solution from the frontier solution set. ,in, .

[0133] The final optimal target pressure values ​​for each zone will be determined. The parameters are converted into electronic control commands and used as target parameters for the next control cycle. Among them, the target values ​​for the loose body zone naturally exhibit low-pressure following characteristics, while the target values ​​for the stable strata zone naturally exhibit high-pressure dominance characteristics.

[0134] The hydraulic valve group independently adjusts the oil inlet flow state of each zone according to the received electrical signal, thereby establishing a differential pressure field in space that satisfies the decoupling strategy.

[0135] The electro-hydraulic proportional valves in each zone change the valve core opening degree according to the magnitude of the control current. For the decompression following zone mapped to a complex loose body, the corresponding proportional valve quickly reduces the opening degree or opens the overflow, so that the hydraulic pressure in the cylinder group drops rapidly, and the piston rod exhibits a low-stiffness compliant state, avoiding squeezing and damage to the loose formation.

[0136] For the pressurized main thrust zone mapped to the stable stratum, the corresponding proportional valve increases its opening to guide high-pressure hydraulic oil into the rodless chamber, enabling the set of cylinders to quickly build up pressure and provide the main torque required for the tunneling machine to advance.

[0137] This embodiment also provides a computer device, such as... Figure 2 As shown, the method applicable to the hydraulic cylinder pressure control method based on the pressure response of tunneling in complex loose materials includes: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the hydraulic cylinder pressure control method based on the pressure response of tunneling in complex loose materials as proposed in the above embodiments.

[0138] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0139] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the hydraulic cylinder pressure control method based on the pressure response during tunneling in complex loose bodies, as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0140] In summary, this invention achieves the following: acquiring real-time tunneling pressure data of the tunneling equipment and constructing a spatial pressure distribution field characterizing the surface stress state; extracting pressure characteristic parameters based on the spatial pressure distribution field to identify and define the complex loose body region and its distribution state; establishing thrust decoupling mapping rules based on the distribution state of the complex loose body region, constructing a joint objective function, using a genetic algorithm for iterative optimization, and calculating the target pressure value of the tunneling equipment's propulsion cylinder partition; outputting the optimal target pressure value of each propulsion cylinder partition, and outputting control commands to the hydraulic execution module.

[0141] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A hydraulic cylinder pressure control method based on the pressure response during tunneling in complex loose materials, characterized in that: This includes acquiring real-time tunneling pressure data from tunneling equipment and constructing a spatial pressure distribution field characterizing the surface stress state; Based on the spatial pressure distribution field, pressure characteristic parameters are extracted to identify and define the complex loose body region and its distribution status. Based on the distribution of complex loose body regions, thrust decoupling mapping rules are established, a joint objective function is constructed, and a swarm intelligence algorithm is used for iterative optimization to calculate the target pressure value of the propulsion cylinder zone of the tunneling equipment. Output the optimal target pressure value for each propulsion cylinder zone and output control commands to the hydraulic actuator module.

2. The hydraulic cylinder pressure control method based on the pressure response during tunneling in complex loose materials as described in claim 1, characterized in that: The real-time tunneling pressure data includes data from an array installed on the stress-bearing surface of the tunneling equipment. One pressure sensor; multi-channel data acquisition is employed, and the analog signals output by all sensors are synchronously converted to digital signals at a sampling rate higher than the vibration frequency of the tunneling equipment to obtain a discrete-time series including environmental noise and high-frequency mechanical vibration. ,in , indicating the first The sensor number; The sequence is smoothed and then input into a low-pass filter to obtain the cleaned effective tunneling pressure value. .

3. The hydraulic cylinder pressure control method based on the pressure response during tunneling in complex loose materials as described in claim 2, characterized in that: The construction of the spatial pressure distribution field characterizing the surface stress state includes mapping the current physical position of the sensor to the absolute coordinate system of the surface; A static two-dimensional Cartesian coordinate system for the tunneling surface is established with the intersection of the tunneling equipment's central axis and the tunneling surface as the origin; the first... The mounting radius of the sensor on the cutter head and initial polar angle ; Real-time acquisition via the tool turret spindle encoder Instantaneous rotational angular velocity of the cutter head ; The result is obtained by calculating using the spatial kinematic equations. One sensor in The absolute coordinates projected onto the tunneling surface at any moment ; Pressure value The absolute coordinates calculated from the spatial dimensions Perform timestamp binding at any sampling time Encapsulated into a structured data frame .

4. The hydraulic cylinder pressure control method based on the pressure response during tunneling in complex loose materials as described in claim 3, characterized in that: The complex loose body region and its distribution include, assuming the radius of the cutterhead or excavation face of the tunneling equipment is... Define the effective computation domain ; In the domain Within, with the set spatial resolution as Perform two-dimensional equidistant mesh generation to generate a mesh containing Grid coordinate set of unknown nodes ; Field state reconstruction is performed using an interpolation algorithm, based on real-time acquired data. Calculate different spatial distances using known sensor data. Squaring of pressure changes ; Selecting a spherical model By fitting the data, the theoretical variogram is obtained. Spatial correlation rules characterizing current formation pressure; The distribution state of the complex loose body region includes, for the grid set For any point to be estimated, the estimated pressure value yes known observations A linear combination; to ensure unbiased estimation and minimize estimation variance, the following system of equations is constructed to solve for the weight coefficients of each known point. ; Traversing the mesh set All of them Each node completes full-section interpolation; The solution obtained The pressure estimates for each grid point are mapped to a two-dimensional matrix according to their spatial location, generating... Continuous spatial pressure distribution field matrix at time t. For the matrix Masking is performed to output a continuous and smooth spatial pressure distribution field on the tunneling surface; Use dual logical thresholds for joint determination: Set a safety threshold, and preset a lower limit threshold of the safe pressure required to maintain stability of the tunneling surface. The upper limit threshold of gradient abrupt change, characterizing abrupt changes in formations such as cavitation or extreme looseness. ; Perform Boolean logic discrimination on the distribution field matrix. and gradient matrix Double threshold condition discrimination is performed on nodes with the same coordinates in the data; The current grid point is determined to be a suspected loose point if and only if the double logic threshold condition is met; generate Binary state matrix of the tunneling surface at time step .

5. The hydraulic cylinder pressure control method based on the pressure response during tunneling in complex loose materials as described in claim 4, characterized in that: The establishment of the thrust decoupling mapping rule includes, for example, the binary state matrix. Perform opening operation; scan the matrix using the eight-neighbor connectivity algorithm. Cluster nodes that are spatially connected and assigned a value of 1 into a connected region; let a total of [number] nodes be extracted. An independent connected region ; Calculate the actual physical area of ​​each connected region. Set a threshold for the dangerous area. ,reserve The region is considered a complex loose body region; Establish a direct mapping relationship between the feature coordinates of the tunneling surface and the physical partitions of the hydraulic cylinders of the tunneling equipment, and set the search boundary for the heuristic algorithm; Assume the tunneling equipment propulsion system is divided into: Each hydraulic cylinder is independently controlled in a zone, and the equivalent force arm coordinates of each zone are known. The target pressure value to be determined is ; Based on the centroid coordinates of the loose body Coordinates of each partition The spatial distance determines the control attributes of each partition; The decompression follower region of the loose body mapping is defined as the region closest to the centroid of the loose body; a lower and upper bound for the pressure search are set to limit the upper limit of the output; The pressurization zone is mapped to the stable strata, and the remaining zones on the opposite side are defined as the pressurization zone. The sum of the pressures from all zones must meet the total basic thrust required for the current tunneling rate. .

6. The hydraulic cylinder pressure control method based on the pressure response during tunneling in complex loose materials as described in claim 5, characterized in that: The construction of the joint objective function includes constructing a three-dimensional multi-objective fitness function set. The objective function for minimizing perturbations in the loose body region. The objective function for minimizing device attitude deviation The objective function for minimizing the thrust distribution variance .

7. The hydraulic cylinder pressure control method based on the pressure response during tunneling in complex loose materials as described in claim 6, characterized in that: The iterative optimization using swarm intelligence algorithms includes solving the fitness function set under constraints using a multivariate heuristic optimization algorithm. Within the defined search boundary, randomly generate The initial population consists of 10 particles; the position vector of each particle... This represents the hydraulic cylinder zone pressure distribution scheme; Substitute the position vector of each particle into the fitness function set. The evaluation is conducted in the middle; based on the Pareto dominance theory, the individuals in the population are non-dominated and ranked to select the current non-dominated solution set; The population is updated according to the specific evolutionary mechanism of the algorithm. In the particle swarm mechanism, the individual extreme value and the global optimal solution set of each particle are calculated, and the particles are guided to fly towards the optimal solution region through the velocity update formula and the position update formula. Repeat the iterative update process until the maximum number of iterations is reached. Stop searching.

8. The hydraulic cylinder pressure control method based on the pressure response during tunneling in complex loose materials as described in claim 7, characterized in that: The calculation of the target pressure value of the propulsion cylinder zone of the tunneling equipment includes, after the algorithm iteration is completed, outputting a Pareto front solution set containing multiple feasible solutions; introducing an objective weighting method based on information entropy, and assigning an objective function according to the current loose body area. Weight; It adjusts the target weights based on the most pressing working conditions currently faced in tunneling, and automatically determines the optimal compromise solution from the front-line solution set. ,in, ; The final optimal target pressure values ​​for each zone will be determined. The parameters are converted into electronic control commands and used as target parameters for the next control cycle. Among them, the target values ​​for the loose body zone show low-pressure following characteristics, while the target values ​​for the stable strata zone show high-pressure dominance.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the hydraulic cylinder pressure control method based on the tunneling pressure response of complex loose material as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the hydraulic cylinder pressure control method based on the pressure response of tunneling in complex loose material as described in any one of claims 1 to 8.

Images