Pipe gallery fertilizer groove three-dimensional backfilling system and method based on earthworm bionical peristalsis shear-axial compaction coupling and artificial intelligence closed loop control

Abstract

This invention discloses a three-dimensional backfilling system and method for pipe gallery trenches based on earthworm-inspired peristaltic shear-axial compaction coupling and artificial intelligence closed-loop control. The system includes an earthworm-inspired peristaltic shear vibration compaction unit, an axial compaction pulse unit, boundary fitting and guiding constraint components, a multimodal sensing unit, and a digital twin and artificial intelligence control unit. The peristaltic unit adopts a segmented sleeve structure, generating a directional horizontal shear wave field for initial compaction within the narrow trench through a peristaltic sequence of "anchoring phase-shear phase-propulsion phase"; the axial unit applies adjustable compaction pulses vertically for intensified compaction. The multimodal sensing unit collects soil state data in real time, and the AI ​​control unit constructs a digital twin model, employing a reinforcement learning and graphical model collaborative control strategy to optimize compaction parameters online. This invention achieves directional energy transfer and adaptive pore pressure control within a narrow space, significantly improving backfill density and uniformity, and is suitable for high groundwater conditions.

Description

Technical Field

[0001] This invention relates to the intersection of underground space engineering backfilling construction technology, soil and rock compaction control technology and artificial intelligence intelligent construction technology, and in particular to a three-dimensional backfilling system and method for pipe gallery trenches based on earthworm biomimetic peristaltic shear-axial compaction coupling and artificial intelligence closed-loop control. Background Technology

[0002] In the construction of integrated utility tunnels and underground passages, trench backfilling is often affected by factors such as narrow space, high groundwater level, and large fluctuations in the moisture content of backfill soil. Traditional single compaction methods have unstable energy transfer in narrow trenches, which can easily lead to problems such as "dense surface and loose deep layers", "local over-vibration disturbance" or "rebound and subsequent settlement", making it difficult to simultaneously meet the requirements of backfill density, uniformity, and controllable disturbance to surrounding structures.

[0003] In existing engineering practices, the vibratory compaction method of "first horizontal vibration compaction, then vertical tamping" is usually adopted to improve the compaction effect. However, under high groundwater conditions, the following shortcomings still exist: (1) Horizontal vibration energy is difficult to focus inside the narrow trench and is prone to escape to the side wall structure, resulting in energy waste and disturbance to the surrounding structure; (2) During the vertical compaction process, the pore water pressure rises significantly, which can easily trigger a chain reaction of "over-vibration-pore pressure rise-rebound"; (3) The compaction parameters rely on manual experience for adjustment, which is difficult to adapt to the complex working conditions of soil heterogeneity and dynamic changes in groundwater level; (4) There is a lack of real-time perception and closed-loop control of compaction quality and risk status, and it is difficult to trace the settlement and uniformity problems in the later stage.

[0004] Therefore, there is an urgent need for a three-dimensional intelligent backfilling compaction system and method that can achieve directional energy transfer, controllable pore pressure, and adaptive adjustment under narrow, fertile trenches and high groundwater conditions. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the prior art and provide a three-dimensional backfilling system and method for pipe gallery trenches based on earthworm biomimetic peristaltic shearing-axial compaction coupling and artificial intelligence closed-loop control. This solves the problems of unstable compaction energy transfer, uncontrollable disturbance, and reliance on manual experience for parameter adjustment in the prior art under conditions of high groundwater level and narrow trench space.

[0006] The present invention adopts the following technical solution: On one hand, this invention provides a three-dimensional backfilling system for pipe gallery trenches based on earthworm-inspired peristaltic shearing-axial compaction coupling and artificial intelligence closed-loop control, comprising: The earthworm-inspired peristaltic shear vibration compaction unit is used to form a directional horizontal shear wave field in the narrow space of the fertilizer trench, and to perform initial compaction and lateral stabilization treatment on the backfill soil. An axial compaction pulse unit is located at the rear end of the earthworm-inspired peristaltic shear vibration compaction unit. It is used to apply compaction pulses with adjustable laws and energy spectra vertically to further compact the initially compacted backfill soil. The boundary fitting and guiding constraint component is sleeved on the outer periphery of the earthworm biomimetic peristaltic shear vibration compaction unit and the axial compaction pulse unit, which is used to make the system fit against the side wall of the fertilizer tank and to provide guidance and constraint for the movement of the system in the fertilizer tank; Multimodal sensing units are distributed on the earthworm biomimetic peristaltic shear vibration compaction unit, the axial compaction pulse unit, and the boundary fitting and guiding constraint component, and are used to collect various sensing data reflecting the backfilling status of the fertilizer trench in real time. The digital twin and artificial intelligence control unit is connected to the multimodal sensing unit and controlled by the earthworm-inspired peristaltic shear vibration compaction unit and the axial compaction pulse unit. It is used to receive the sensing data, construct and update the digital twin model of the backfilling process of the fertilizer trench, estimate the soil state and compaction quality index online based on the model, and generate and output compaction control parameters in real time through reinforcement learning and graph model collaborative control strategy.

[0007] In addition to any of the possible implementations described above, another implementation is provided in which the earthworm biomimetic peristaltic shear vibration compaction unit is a segmented flexible sleeve structure, including at least three peristaltic segments arranged sequentially along the axial direction; Each of the said peristaltic segments includes: It fits the cyst body and is placed on the outer periphery of the peristaltic segment. Through controllable radial expansion and contraction, the peristaltic segment switches between an expanded state and a contracted state. A shear vibration generator, located inside the segment, is used to output directional horizontal shear vibration; The digital twin and artificial intelligence control unit controls the expansion state of the cyst in each peristaltic segment and the start / stop of the shear vibration generator, causing the at least three peristaltic segments to sequentially execute the following phases, forming a peristaltic sequence: Anchoring phase: The bladder of the current creeping segment is in an expanded state, anchoring the segment to the side wall of the trough, and the shear vibration generator is turned off; Shear phase: The adhering capsule of the current creeping segment remains in an expanded state, and at the same time, the shear vibration generator is activated to output directional horizontal shear vibration, forming a shear wave field in the surrounding soil; Propulsion phase: The appositional sac of the current peristaltic segment switches to a contracted state, releases the anchorage, and achieves the overall forward propulsion of the system through the phase coordination of adjacent segments.

[0008] In addition to any of the possible implementations described above, a further implementation is provided in which the outer surface of the conforming capsule is provided with micro-anchors or textures to simulate the gripping effect of earthworm bristles, so as to enhance the anchoring force in backfill soil with high moisture content and reduce energy leakage.

[0009] In addition to any of the possible implementations described above, another implementation is provided in which the axial compaction pulse unit includes: Axial pulse driver, used to output adjustable axial compaction pulses with adjustable law and energy spectrum; An energy-releasing vibration isolation layer, disposed around the outer periphery of the axial pulse driver, is used to absorb and dissipate lateral vibration energy, reducing disturbance to the sidewalls of the fertilizer tank; and, The replaceable compaction end is connected to the power output end of the axial pulse driver to contact the backfill soil and transmit compaction energy.

[0010] In addition to any of the possible implementations described above, another implementation is provided in which the multimodal sensing unit includes at least one of the following sensors: Deep displacement sensing array inside the borehole is used to monitor the displacement of deep soil in the trench. Layered settlement sensors are used to monitor the settlement of soil layers at different depths. Groundwater level or pore water pressure sensors are used to monitor dynamic changes in groundwater. Soil vibration sensors are used to monitor the vibration response of backfill soil during compaction; and, Equipment condition sensors are used to monitor the power, spectrum, acceleration, and displacement of the earthworm-inspired peristaltic shear vibration compaction unit and the axial compaction pulse unit.

[0011] In addition to any of the possible implementations described above, another implementation is provided in which the digital twin and artificial intelligence control unit includes: The state estimation module estimates the equivalent stiffness, water content-pore pressure state, and compaction quality index of the soil online based on the real-time data and physical constraint learning model of the multimodal sensing unit. The physical constraint learning module stores and updates physical or empirical models that reflect the soil compaction process, providing constraints for state estimation and decision-making. The collaborative decision-making module uses a graph structure to discretize the fertilizer trench space and, based on a reinforcement learning policy network, optimizes and outputs compaction control parameters, including creep rhythm, shear vibration direction / frequency / amplitude, axial compaction energy, and path arrangement, under constraints not exceeding a preset safety threshold; and, The safety constraint module is used to monitor real-time data and trigger a degradation strategy or shutdown command when vibration or displacement parameters are abnormal.

[0012] In addition to any of the possible implementations described above, a further implementation is provided in which the system further includes: a platform docking and early warning management unit, connected to the digital twin and artificial intelligence control unit, for receiving compaction quality indicators and risk status information, pushing the information to an external management platform, and triggering multi-level early warnings when the compaction quality indicators or risk status exceed a preset threshold, thereby realizing digital management and quality traceability of the construction process.

[0013] On the other hand, the present invention also provides a three-dimensional backfilling method for pipe gallery trenches based on earthworm-inspired peristaltic shearing-axial compaction coupling and artificial intelligence closed-loop control. The method is implemented through the above-mentioned system and includes: S1: Establish a digital twin model of the geometries and the initial state of the soil. S2: Execute the earthworm-inspired peristaltic shear vibration compaction unit to generate a horizontal shear wave field in the fertilizer trough, perform initial compaction on the backfill soil, and form a laterally stable soil structure. S3: Execute the axial compaction pulse unit to apply axial compaction pulses to the initially compacted soil and perform vertical compaction. S4: Based on the real-time sensing data collected by the multimodal sensing unit, update the digital twin model, estimate the soil state and compaction quality online, and adjust the compaction control parameters in steps S2 and S3 in a closed loop based on this; and, S5: Output the compaction quality indicators and risk status to achieve quality traceability during the construction process.

[0014] In addition to any of the possible implementations described above, another implementation is provided in which the horizontal initial compaction described in step S2 includes a peristaltic sequence consisting of an anchoring phase, a shearing phase, and a propulsion phase. In the anchoring phase, the segment is anchored to the sidewall of the fat trench by radially expanding the fitting bladder of the current creeping segment; In the shear phase, the shear vibration generator of this segment outputs directional horizontal vibration, forming a shear wave field in the surrounding soil. In the propulsion phase, the overall forward propulsion of the system is achieved by controlling the phase difference between adjacent peristaltic segments.

[0015] In addition to any of the possible implementations described above, another implementation is provided in which the closed-loop adjustment of the compaction control parameters in step S4 includes: When the multimodal sensing unit detects a rise in groundwater level or abnormal pore water pressure, the digital twin and artificial intelligence control unit automatically executes at least one of the following strategies: Reduce the compaction energy of the axial compaction pulse unit; Increase the shear vibration frequency of the earthworm-inspired peristaltic shear vibration compaction unit; or, Switch to a low-amplitude, high-frequency steady-state operating mode; This helps to dissipate pore water pressure and reduce disturbance to the soil.

[0016] The beneficial effects of this invention are as follows: 1. Directional force transmission and energy focusing: Through a biomimetic creeping anchoring-shearing-propulsion sequence, the horizontal shear wave field is generated and focused, significantly improving the effective depth and uniformity of action in narrow trenches, and solving the problem that energy tends to escape to the sidewalls in traditional vibration compaction.

[0017] 2. Pore pressure adaptive control: Real-time monitoring of groundwater level and pore water pressure changes through multi-modal sensing units, combined with AI control strategies to automatically adjust compaction parameters (reduce axial energy, increase shear frequency, switch steady-state mode), effectively suppressing the chain reaction of "over-vibration-pore pressure rise-rebound", which is particularly suitable for high groundwater conditions.

[0018] 3. AI closed-loop adaptive construction: Based on the digital twin model, soil parameters (equivalent stiffness, water content and pore pressure state) are calibrated in real time. The graph structure space modeling and reinforcement learning strategy are adopted to optimize compaction parameters under safety constraints, which greatly reduces the dependence on manual parameter adjustment and improves quality consistency.

[0019] 4. Multi-level early warning and quality traceability: Through platform integration and early warning management units, multi-level early warnings are achieved for multiple indicators such as compaction efficiency, energy transfer efficiency, and comprehensive compaction quality index, forming a full-process "quality fingerprint" of parameters-state-results, which facilitates platform-based management and closed-loop risk handling.

[0020] 5. Structural Adaptability: The replaceable compaction end design can adapt to different backfill soil gradations and moisture conditions; the micro-anchor / texture design significantly improves the anchoring force in high moisture content backfill soil, ensuring the reliable execution of the creep sequence. Attached Figure Description

[0021] Figure 1 This is a schematic diagram of the overall structure of the system of the present invention.

[0022] Figure 2 This is a schematic diagram of the earthworm-inspired peristaltic shearing vibration compaction unit of the present invention.

[0023] Figure 3 This is a schematic diagram of the axial compaction pulse unit of the present invention.

[0024] Figure 4 This is a flowchart of the online calibration and state estimation process for digital twins according to the present invention.

[0025] Figure 5This is a flowchart of the intelligent vibratory compaction method of the present invention.

[0026] In the diagram: 1. Earthworm-inspired peristaltic shear vibration compaction unit; 1-1. Peristaltic segment; 1-2. Adhering sac; 1-3. Shear vibration generator; 1-4. Micro-anchor / texture; 2. Axial compaction pulse unit; 2-1. Axial pulse driver; 2-2. Energy-releasing vibration isolation layer; 2-3. Replaceable compaction end; 3. Boundary adhesion and guidance constraint assembly; 4. Multimodal sensing unit; 5. Digital twin and artificial intelligence control unit; 5-1. State estimation module; 5-2. Physical constraint learning module; 5-3. Collaborative decision-making module; 5-4. Safety constraint module; 6. Platform docking and early warning management unit. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments and the accompanying drawings. It should be understood that these descriptions are merely exemplary and not intended to limit the scope of the invention. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concept of the invention.

[0028] The accompanying drawings illustrate a layer structure according to an embodiment of the present invention. These drawings are not to scale, and some details have been enlarged for clarity, and some details may have been omitted. The shapes of the various regions and layers shown in the drawings, as well as their relative sizes and positional relationships, are merely exemplary and may deviate from reality due to manufacturing tolerances or technical limitations. Furthermore, those skilled in the art can design regions / layers with different shapes, sizes, and relative positions as needed.

[0029] Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0030] In the description of this invention, it should be noted that the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0031] Furthermore, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0032] This invention provides a three-dimensional backfilling system for pipe gallery trenches based on earthworm-inspired peristaltic shearing-axial compaction coupling and artificial intelligence closed-loop control, comprising: Earthworm-inspired peristaltic shear vibration compaction unit 1 is used to form a directional horizontal shear wave field in the narrow space of the fertilizer trench to perform initial compaction and lateral stabilization treatment on the backfill soil; Axial compaction pulse unit 2 is located at the rear end of the earthworm biomimetic peristaltic shear vibration compaction unit 1, and is used to apply compaction pulses with adjustable law and energy spectrum vertically to further compact the initially compacted backfill soil. The boundary fitting and guiding constraint component 3 is sleeved on the outer periphery of the earthworm biomimetic peristaltic shear vibration compaction unit 1 and the axial compaction pulse unit 2, and is used to make the system fit against the side wall of the fertilizer tank, and to provide guidance and constraint for the movement of the system in the fertilizer tank. Multimodal sensing units 4 are distributed on the earthworm biomimetic peristaltic shear vibration compaction unit 1, the axial compaction pulse unit 2 and the boundary fitting and guiding constraint component 3, and are used to collect various sensing data reflecting the backfilling status of the fertilizer trench in real time. The digital twin and artificial intelligence control unit 5 is connected to the multimodal sensing unit 4 and is controlled by the earthworm biomimetic peristaltic shear vibration compaction unit 1 and the axial compaction pulse unit 2. It is used to receive the sensing data, construct and update the digital twin model of the backfilling process of the fertilizer trench, estimate the soil state and compaction quality index online based on the model, and generate and output compaction control parameters in real time through reinforcement learning and graph model collaborative control strategy.

[0033] This invention discloses a three-dimensional backfilling method for pipe gallery trenches based on earthworm-inspired peristaltic shearing-axial compaction coupling and artificial intelligence closed-loop control. The method is implemented through the aforementioned system and includes: S1: Establish a digital twin model of the geometries and the initial state of the soil. S2: The earthworm-inspired peristaltic shearing vibration compaction unit 1 is executed to generate a horizontal shear wave field in the fertilizer trough, which initially compacts the backfill soil and forms a laterally stable soil structure. S3: Execute the axial compaction pulse unit 2 to apply axial compaction pulses to the initially compacted soil and perform vertical compaction. S4: Based on the real-time sensing data collected by the multimodal sensing unit 4, update the digital twin model, estimate the soil state and compaction quality online, and adjust the compaction control parameters in steps S2 and S3 in a closed loop based on this; and, S5: Output the compaction quality indicators and risk status to achieve quality traceability during the construction process.

[0034] Example 1 System overall architecture: like Figure 1As shown, the system of the present invention consists of an earthworm biomimetic peristaltic shear vibration compaction unit 1, an axial compaction pulse unit 2, a boundary fitting and guiding constraint component 3, a multimodal sensing unit 4, a digital twin and artificial intelligence control unit 5, and a platform docking and early warning management unit 6.

[0035] The system is designed for the conditions of high groundwater levels and narrow spaces in utility tunnels. It improves backfill quality through a three-dimensional compaction mechanism of "horizontal creep shear wave initial compaction + vertical axial pulse compaction".

[0036] The axial compaction pulse unit 2 is located at the rear end of the earthworm-inspired peristaltic shear vibration compaction unit 1. The two are connected by a flexible connection structure, and their motion and vibration parameters can be controlled independently. The boundary fitting and guiding constraint component 3 is sleeved on the outer periphery of the two units. It is made of a low-friction coefficient polymer material, with a guide rail on the inner side and an adjustable fitting plate on the outer side. The fitting degree can be adjusted according to the width of the fertilizer tank, providing guidance and constraint for the system's movement within the fertilizer tank.

[0037] Earthworm-inspired peristaltic shearing vibration compaction unit: like Figure 2 As shown, the earthworm-inspired peristaltic shear vibration compaction unit 1 is a segmented flexible sleeve structure, comprising three peristaltic segments 1-1 (front, middle, and rear sections) arranged sequentially along the axial direction. In practical applications, more segments can be added according to the depth of the fertilizer trough. Each peristaltic segment 1-1 includes: The fitting bladder 1-2 is set on the outer periphery of the segment and radial expansion and contraction are controlled by hydraulic or pneumatic pressure. In the expansion state, the segment can be anchored to the side wall of the trough, and in the contraction state, the anchoring is released. Shear vibration generators 1-3 are installed inside the segment and use eccentric motors or electromagnetic exciters to output directional horizontal shear vibrations with a frequency of 20-80Hz and an amplitude of 0-5mm. Micro-anchors / textures 1-4 are set on the outer surface of the fitting capsule 12 and are distributed in a barb-like or grid-like pattern to simulate the gripping effect of earthworm bristles. They can significantly improve the anchoring force and reduce energy loss in backfill soil with high moisture content.

[0038] The digital twin and artificial intelligence control unit 5 controls the expansion state of the apical sac 1-2 of each peristaltic segment 1-1 and the start and stop of the shear vibration generator 1-3, so that the three peristaltic segments sequentially execute the following phases, forming a peristaltic sequence similar to that of an earthworm: Anchoring phase: The front section expands and anchors to the bladder body, while the middle and rear sections contract, and the shear vibration generator is turned off; Shear phase: The front section remains anchored, the middle section expands and anchors, and the shear vibration generator is activated to output directional horizontal shear vibration, forming a shear wave field in the surrounding soil. Propulsion phase: The front section contracts to release the anchor, the middle section remains anchored, and the rear section expands to anchor. The overall forward propulsion of the system is achieved through the phase difference between the front section and the middle and rear sections.

[0039] This peristaltic sequence achieves directional force transmission similar to that of an earthworm within the narrow space of the trough, focusing horizontal shear energy into the soil and significantly increasing the effective depth of action.

[0040] Axial compaction pulse unit: like Figure 3 As shown, the axial compaction pulse unit 2 includes: The axial pulse driver 2-1, using an electro-hydraulic servo or electromagnetic pulse mechanism, can output adjustable axial compaction pulses with a frequency of 0.5-10Hz and an energy of 0-50kJ. The energy-releasing vibration isolation layer 2-2 is set on the outer periphery of the axial pulse driver 2-1. It adopts a multi-layer damping rubber and shape memory alloy composite structure, which can absorb and dissipate more than 80% of the lateral vibration energy, greatly reducing the disturbance to the side wall of the fertilizer tank. The replaceable compaction end 2-3 is connected to the power output end of the axial pulse driver 2-1. The end contact surface can be designed as a flat surface, a convex surface, or a grid pattern, and can be replaced according to the backfill soil gradation and moisture content to optimize energy transfer efficiency.

[0041] Multimodal sensing unit: The multimodal sensing units 4 are distributed throughout the system components and inside the fertilizer tank, specifically including: A deep displacement sensing array inside the borehole is deployed every 1m along the depth of the trench, using MEMS accelerometers or fiber optic grating sensors to monitor the displacement of deep soil. The stratified settlement sensor, using a magnetic ring settlement gauge, monitors the settlement of soil layers at different depths with an accuracy of 0.1 mm. The groundwater level / pore water pressure sensor uses a vibrating wire pore pressure gauge to monitor changes in groundwater level and dynamic pore water pressure in real time. The soil vibration sensor, which uses a triaxial accelerometer, is deployed on the side wall and surrounding structure of the compaction trench to monitor the vibration response during the compaction process. Equipment operating condition sensors, including power meters, spectrum analyzers, laser displacement sensors, etc., monitor in real time the power consumption, vibration spectrum, acceleration and displacement stroke of the earthworm biomimetic peristaltic shear vibration compaction unit 1 and the axial compaction pulse unit 2.

[0042] Digital twin and artificial intelligence control unit: like Figure 4 As shown, the digital twin and artificial intelligence control unit 5 includes the following modules: State estimation module 5-1: Based on real-time data from multimodal sensing unit 4 and combined with the soil constitutive model in physical constraint learning module 5-2, the extended Kalman filter algorithm is used to estimate the equivalent stiffness Keq, water content-pore pressure state pu, and compaction quality index Qc of the soil online. The equivalent stiffness Keq reflects the compaction degree of the soil, with a value ranging from 0 to 100 MPa; the compaction quality index Qc comprehensively reflects indicators such as relative density, void ratio, and settlement rate, with the target design value Qtarget set at 0.90-0.98 according to engineering requirements.

[0043] Physical Constraint Learning Module 5-2: Stores and updates physical models (such as Terzaghi consolidation theory and Hardin-Drnevich dynamic constitutive model) and empirical models (such as compaction degree-moisture content-energy consumption curve) that reflect the soil compaction process, providing constraint boundaries for state estimation and decision-making.

[0044] Collaborative Decision Module 5-3: A graph structure is used to perform three-dimensional discretization modeling of the soil trench space, dividing the trench into several voxel units, each of which is assigned current soil parameters; a policy network based on reinforcement learning (using DQN or PPO algorithm) optimizes and outputs compaction control parameters at = [fh, Ah, dirh, Ev, rpath] under the constraint of not exceeding a preset safety threshold, with the goal of maximizing the compaction quality index and minimizing energy consumption and sidewall disturbance, representing the horizontal vibration frequency / amplitude / direction and the axial pulse energy and path radius / order, respectively.

[0045] Safety constraint module 5-4: Real-time monitoring of data from multimodal sensing unit 4. When the vibration velocity exceeds 5 mm / s or the lateral displacement exceeds 2 mm, a degradation strategy (reducing Ev by 30% or switching to low-amplitude high-frequency mode) or a shutdown command is triggered, and the abnormal information is reported to the platform docking and early warning management unit 6.

[0046] Example 2: Intelligent Vibratory Compaction Method like Figure 5 As shown, the method for backfilling and compacting pipe gallery trenches using the system of the present invention includes the following steps: S1: Establish a digital twin model of the fertilizer trench geometry and the initial state of the soil. Obtain the geometric dimensions of the fertilizer trench through 3D laser scanning, and obtain parameters such as the initial moisture content, density, and gradation of the soil through field exploration. Input these parameters into the digital twin and artificial intelligence control unit 5 to construct the initial digital twin model.

[0047] S2: Execute the earthworm-inspired peristaltic shear vibration compaction unit 1 to generate a horizontal shear wave field within the fertilizer trench, initially compacting the backfill soil and forming a laterally stable soil structure. Initial parameter settings: vibration frequency 30Hz, amplitude 3mm, peristalsis cycle 30s / cycle.

[0048] S3: Execute axial compaction pulse unit 2 to apply axial compaction pulses to the initially compacted soil for vertical densification compaction. Initial parameter settings: pulse frequency 2Hz, energy 20kJ / pulse, number of compaction passes 3.

[0049] S4: Based on the real-time sensing data collected by the multimodal sensing unit 4, the digital twin model is updated every 10 seconds to estimate the soil state and compaction quality online, and the compaction control parameters in steps S2 and S3 are adjusted in a closed loop based on this. When the pore water pressure is detected to rise above the threshold (e.g., 1.5 times the initial value), the axial compaction energy is automatically reduced to 10 kJ / cycle, the shear vibration frequency is increased to 50 Hz, and the system switches to a low-amplitude, high-frequency steady-state mode to promote pore pressure dissipation.

[0050] S5: The compaction quality indicators and risk status are output to the external management platform through the platform interface and early warning management unit 6 to realize early warning push and quality traceability. When the compaction quality index Qc reaches more than 95% of the design target value Qtarget, the compaction operation is completed.

[0051] Multi-level early warning mechanism: The system platform integration and early warning management unit 6 is equipped with a comprehensive multi-level early warning mechanism, and the threshold settings for key monitoring parameters are as follows: (1) Early warning of creep shear compaction efficiency ηs: When ηs is below 0.85, a yellow first-level early warning is triggered; when it is below 0.70, an orange second-level early warning is triggered, and the creep frequency is automatically adjusted; when it is below 0.55, a red third-level early warning is triggered, and the emergency mode switching is started; when ηs is below 0.60 for 3 consecutive creep cycles, an emergency mode switching early warning is triggered.

[0052] (2) Axial compaction energy transfer efficiency ηv warning: When ηv is lower than 0.80, a first-level warning is triggered; when it is lower than 0.65, a second-level warning is triggered; when it is lower than 0.50, a third-level warning is triggered and the pulse energy Ev is automatically reduced to a safe value; when the ηv decay rate exceeds 0.05 / min, an energy decay warning is triggered.

[0053] (3) Comprehensive compaction quality index Qc warning: When Qc is lower than 95% of the design target value Qtarget, a first-level warning is triggered; when it is lower than 90%, a second-level warning is triggered; when it is lower than 85%, a third-level warning is triggered and the supplementary compaction procedure is started; when the Qc growth rate is lower than 0.02 / pass, an efficiency insufficient warning is triggered; when the Qc local difference coefficient exceeds 0.15, a uniformity warning is triggered.

[0054] (4) Soil moisture content ω warning: When ω deviates from the optimum moisture content ωopt by more than ±2%, a first-level warning is triggered; when it exceeds ±4%, a second-level warning is triggered and the creep frequency is adjusted; when it exceeds ±6%, a third-level warning is triggered and construction is suspended; when the moisture content gradient exceeds 1.5% / m, a stratification unevenness warning is triggered.

[0055] (5) Equivalent stiffness Keq warning: When the Keq growth rate is less than 80% of the expected value, a first-level warning is triggered; when it is less than 60%, a second-level warning is triggered and the number of compaction passes is increased; when it is less than 40%, a third-level warning is triggered and process adjustment is initiated; when the local dispersion coefficient of Keq exceeds 0.20, a homogeneity warning is triggered.

[0056] Engineering application results: The system of this invention was applied to the backfill section of a utility tunnel project in a certain city. The trench was 0.8m wide and 6m deep, with a groundwater level of 2.5m. The backfill soil was silty clay with an optimum moisture content of 16.5%. After compaction using the system of this invention, the following results were achieved: (1) Significantly improved compaction quality: According to the test, the average compaction degree of the backfill soil reached 96.8%, the coefficient of variation was 0.08, and the uniformity was improved by more than 40% compared with the traditional construction method; (2) Improved construction efficiency: Compared with the traditional "vibratory roller + impact rammer" combination process, the construction time is shortened by 35%; (3) Pore pressure control is good: the maximum pore pressure rise during compaction is only 1.3 times the initial value, and the level 3 warning is not triggered; (4) Minimal disturbance to surrounding structures: The maximum vibration velocity of the sidewall of the fertilizer tank is 2.8 mm / s, which is far below the standard limit (10 mm / s). (5) Complete quality traceability: The platform records the compaction parameters and quality indicators throughout the entire process, forming a complete "quality fingerprint" file.

[0057] This invention provides a three-dimensional backfilling system and method for utility tunnel trenches based on earthworm-inspired peristaltic shearing-axial compaction coupling and artificial intelligence closed-loop control. It can be widely applied to trench backfilling construction in underground space engineering projects such as integrated utility tunnels, underground passages, and sections adjacent to railway structures. The system has a compact structure and strong adaptability, and is particularly suitable for complex working conditions such as narrow spaces and high groundwater levels, demonstrating good industrial practicality and application value.

[0058] The above description of the embodiments is only for the purpose of helping to understand the method and core idea of ​​this application; at the same time, for those skilled in the art, there will be changes in the specific implementation and application scope based on the idea of ​​this application. Therefore, the content of this specification should not be construed as a limitation of this application.

[0059] Certain terms are used in the specification and claims to refer to specific components. Those skilled in the art will understand that hardware manufacturers may use different names to refer to the same component. This specification and claims do not distinguish components based on differences in name, but rather on differences in function. The terms "comprising" and "including" used throughout the specification and claims are open-ended and should be interpreted as "comprising / including but not limited to". "Approximately" means that within an acceptable margin of error, those skilled in the art can solve the technical problem and substantially achieve the technical effect within a certain margin of error. The following descriptions in the specification are preferred embodiments for carrying out this application; however, these descriptions are for the purpose of illustrating the general principles of this application and are not intended to limit the scope of this application. The scope of protection of this application shall be determined by the appended claims.

[0060] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a product or system comprising a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a product or system. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the product or system that includes said element.

[0061] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0062] The foregoing description illustrates and describes several preferred embodiments of this application. However, as previously stated, it should be understood that this application is not limited to the forms disclosed herein and should not be construed as excluding other embodiments. It can be used in various other combinations, modifications, and environments, and can be altered within the scope of the application concept described herein through the foregoing teachings or techniques or knowledge in related fields. Any modifications and variations made by those skilled in the art that do not depart from the spirit and scope of this application should be within the protection scope of the appended claims.

Claims

1. A three-dimensional backfilling system for pipe gallery trenches based on earthworm-inspired peristaltic shearing-axial compaction coupling and artificial intelligence closed-loop control, characterized in that, include: The earthworm-inspired peristaltic shear vibration compaction unit is used to form a directional horizontal shear wave field in the narrow space of the fertilizer trench, and to perform initial compaction and lateral stabilization treatment on the backfill soil. An axial compaction pulse unit is located at the rear end of the earthworm-inspired peristaltic shear vibration compaction unit. It is used to apply compaction pulses with adjustable laws and energy spectra vertically to further compact the initially compacted backfill soil. The boundary fitting and guiding constraint component is sleeved on the outer periphery of the earthworm biomimetic peristaltic shear vibration compaction unit and the axial compaction pulse unit, which is used to make the system fit against the side wall of the fertilizer tank and to provide guidance and constraint for the movement of the system in the fertilizer tank; Multimodal sensing units are distributed on the earthworm biomimetic peristaltic shear vibration compaction unit, the axial compaction pulse unit, and the boundary fitting and guiding constraint component, and are used to collect various sensing data reflecting the backfilling status of the fertilizer trench in real time. The digital twin and artificial intelligence control unit is connected to the multimodal sensing unit and controlled by the earthworm biomimetic peristaltic shear vibration compaction unit and the axial compaction pulse unit. It is used to receive the sensing data, construct and update the digital twin model of the backfilling process of the fertilizer trench, estimate the soil state and compaction quality index online based on the model, and generate and output compaction control parameters in real time through a collaborative control strategy.

2. The three-dimensional backfilling system for pipe gallery trenches based on earthworm-inspired peristaltic shearing-axial compaction coupling and artificial intelligence closed-loop control as described in claim 1, characterized in that, The earthworm-inspired peristaltic shear vibration compaction unit is a segmented flexible sleeve structure, comprising at least three peristaltic segments arranged sequentially along the axial direction; Each of the said peristaltic segments includes: It fits the cyst body and is placed on the outer periphery of the peristaltic segment. Through controllable radial expansion and contraction, the peristaltic segment switches between an expanded state and a contracted state. A shear vibration generator is installed inside the creeping segment to output directional horizontal shear vibration; The digital twin and artificial intelligence control unit controls the expansion state of the cyst in each peristaltic segment and the start / stop of the shear vibration generator, causing the at least three peristaltic segments to sequentially execute the following phases, forming a peristaltic sequence: Anchoring phase: The bladder of the current creeping segment is in an expanded state, anchoring the segment to the side wall of the trough, and the shear vibration generator is turned off; Shear phase: The adhering capsule of the current creeping segment remains in an expanded state, and at the same time, the shear vibration generator is activated to output directional horizontal shear vibration, forming a shear wave field in the surrounding soil; Propulsion phase: The appositional sac of the current peristaltic segment switches to a contracted state, releases the anchorage, and achieves the overall forward propulsion of the system through the phase coordination of adjacent segments.

3. The three-dimensional backfilling system for pipe gallery trenches based on earthworm-inspired peristaltic shearing-axial compaction coupling and artificial intelligence closed-loop control as described in claim 2, is characterized in that... The outer surface of the fitted capsule is provided with micro-anchors or textures to simulate the gripping effect of earthworm bristles, thereby enhancing the anchoring force in backfill soil with high moisture content and reducing energy loss.

4. The three-dimensional backfilling system for pipe gallery trenches based on earthworm-inspired peristaltic shearing-axial compaction coupling and artificial intelligence closed-loop control as described in claim 1, characterized in that, The axial compaction pulse unit includes: Axial pulse driver, used to output adjustable axial compaction pulses with adjustable law and energy spectrum; An energy-releasing vibration isolation layer, disposed around the outer periphery of the axial pulse driver, is used to absorb and dissipate lateral vibration energy, reducing disturbance to the sidewalls of the fertilizer tank; and, The replaceable compaction end is connected to the power output end of the axial pulse driver to contact the backfill soil and transmit compaction energy.

5. The three-dimensional backfilling system for pipe gallery trenches based on earthworm-inspired peristaltic shearing-axial compaction coupling and artificial intelligence closed-loop control as described in claim 1, characterized in that, The multimodal sensing unit includes at least one of the following sensors: Deep displacement sensing array inside the borehole is used to monitor the displacement of deep soil in the trench. Layered settlement sensors are used to monitor the settlement of soil layers at different depths. Groundwater level or pore water pressure sensors are used to monitor dynamic changes in groundwater. Soil vibration sensors are used to monitor the vibration response of backfill soil during compaction; and, Equipment condition sensors are used to monitor the power, spectrum, acceleration, and displacement of the earthworm-inspired peristaltic shear vibration compaction unit and the axial compaction pulse unit.

6. The three-dimensional backfilling system for pipe gallery trenches based on earthworm-inspired peristaltic shearing-axial compaction coupling and artificial intelligence closed-loop control as described in claim 1, characterized in that, The digital twin and artificial intelligence control unit includes: The state estimation module estimates the equivalent stiffness, water content-pore pressure state, and compaction quality index of the soil online based on the real-time data and physical constraint learning model of the multimodal sensing unit. The physical constraint learning module stores and updates physical or empirical models that reflect the soil compaction process, providing constraints for state estimation and decision-making. The collaborative decision-making module uses a graph structure to discretize the fertilizer trench space and, based on a reinforcement learning policy network, optimizes and outputs compaction control parameters, including creep rhythm, shear vibration direction / frequency / amplitude, axial compaction energy, and path arrangement, under constraints not exceeding a preset safety threshold; and, The safety constraint module is used to monitor real-time data and trigger a degradation strategy or shutdown command when vibration or displacement parameters are abnormal.

7. The three-dimensional backfilling system for pipe gallery trenches based on earthworm-inspired peristaltic shearing-axial compaction coupling and artificial intelligence closed-loop control as described in claim 1, characterized in that, Also includes: The platform docking and early warning management unit is connected to the digital twin and artificial intelligence control unit. It is used to receive compaction quality indicators and risk status information, push the information to the external management platform, and trigger multi-level early warnings when the compaction quality indicators or risk status exceed preset thresholds, so as to realize digital management and quality traceability of the construction process.

8. A method for three-dimensional backfilling of pipe gallery trenches based on earthworm-inspired peristaltic shearing-axial compaction coupling and artificial intelligence closed-loop control, characterized in that, The method is implemented using the system as described in any one of claims 1-7, and the method includes: S1: Establish a digital twin model of the geometries and the initial state of the soil. S2: Execute the earthworm-inspired peristaltic shear vibration compaction unit to generate a horizontal shear wave field in the fertilizer trough, perform initial compaction on the backfill soil, and form a laterally stable soil structure. S3: Execute the axial compaction pulse unit to apply axial compaction pulses to the initially compacted soil and perform vertical compaction. S4: Based on the real-time sensing data collected by the multimodal sensing unit, update the digital twin model, estimate the soil state and compaction quality online, and adjust the compaction control parameters in steps S2 and S3 in a closed loop based on this; and, S5: Output the compaction quality indicators and risk status to achieve quality traceability during the construction process.

9. The method for three-dimensional backfilling of pipe gallery trenches based on earthworm-inspired peristaltic shearing-axial compaction coupling and artificial intelligence closed-loop control as described in claim 8, characterized in that, The horizontal initial compaction described in step S2 includes a creeping sequence consisting of an anchoring phase, a shearing phase, and a propulsion phase. In the anchoring phase, the segment is anchored to the sidewall of the fat trench by radially expanding the fitting bladder of the current creeping segment; In the shear phase, the shear vibration generator of this segment outputs directional horizontal vibration, forming a shear wave field in the surrounding soil. In the propulsion phase, the overall forward propulsion of the system is achieved by controlling the phase difference between adjacent peristaltic segments.

10. The method for three-dimensional backfilling of pipe gallery trenches based on earthworm-inspired peristaltic shearing-axial compaction coupling and artificial intelligence closed-loop control as described in claim 8, characterized in that, The closed-loop adjustment of compaction control parameters in step S4 includes: When the multimodal sensing unit detects a rise in groundwater level or abnormal pore water pressure, the digital twin and artificial intelligence control unit automatically executes at least one of the following strategies: Reduce the compaction energy of the axial compaction pulse unit; Increase the shear vibration frequency of the earthworm-inspired peristaltic shear vibration compaction unit; or, Switch to a low-amplitude, high-frequency steady-state operating mode; This helps to dissipate pore water pressure and reduce disturbance to the soil.

Images