A multi-dimensional pore pressure monitoring pressurized consolidation control method, device and medium

Abstract

The application discloses a multi-dimensional hole pressure monitoring pressurization consolidation control method, equipment and medium, and relates to the technical field of intelligent pressure construction of soft foundation. The method comprises the following steps: arranging multiple depth measuring points in the same static pressure operation unit, and synchronously collecting multiple source synchronous data; cutting the multiple source synchronous data according to loading, pressure maintaining, unloading and resting stages, and calculating the state indexes of the soil bodies at the depth measuring points in each stage; selecting a consolidation model, and inverting consolidation parameters to calculate the average consolidation degree, the residual settlement amount and the allowable re-pressing moment of the soil body in the controlled consolidation area; using a time-space prediction model constrained by a consolidation control equation, an effective stress relationship and a drainage boundary to generate the layered reinforcement indexes of the soil bodies at the depth measuring points, the effective reinforcement depth and the prediction uncertainty; when the preset safety gating conditions are met, the hydraulic cylinder is closed-loop controlled, and the consolidation parameters and the time-space prediction model are updated by using new cycle data until the post-pressing detection indexes meet the preset requirements.

Description

Technical Field

[0001] This application relates to the field of intelligent compaction construction technology for soft foundations, and in particular to a multi-dimensional pore pressure monitoring and pressurization consolidation control method, equipment and medium. Background Technology

[0002] Hydraulic static compaction applies static load to the compaction plate using a hydraulic cylinder, compacting and draining shallow soft soil under low vibration conditions. It is suitable for environmentally sensitive scenarios such as proximity to structures and underground pipelines. In the initial stage of loading saturated soil, the external load is partially borne by pore water, forming excess pore pressure. As the pore pressure dissipates, the load gradually transfers to the soil skeleton, increasing effective stress and strength. If compaction continues or the point spacing is shortened before the pore pressure is fully dissipated, it can easily lead to lateral extrusion, compaction plate rebound, or insufficient recovery of deep effective stress. If the rest time is fixed for too long, it will reduce construction efficiency.

[0003] Current construction quality control mainly relies on equipment hydraulic pressure, cumulative settlement of the compaction plate, preset compaction times, and post-compaction sampling. Hydraulic pressure alone only reflects the output of the hydraulic system and cannot distinguish between skeleton compaction and pore pressure transient response. Surface settlement is difficult to differentiate between skeleton compaction, pore pressure response, and lateral flow. Sampling and testing are lagging and lack spatial representativeness, making it difficult to evaluate the effect of deep reinforcement. Existing intelligent compaction technologies are mostly geared towards vibratory rollers or dynamic compaction equipment, using acceleration, spectrum, compaction settlement, or microwave signals as inputs, which are incompatible with the quasi-static loading characteristics of static compaction. While some technologies introduce pore pressure monitoring, they only record the peak pore pressure. As a criterion for hammer discharge, no quantitative relationship between pore pressure dissipation and effective stress recovery rate has been established, nor has the closed-loop optimization of construction parameters been achieved through consolidation theory inversion. In recent years, physical information neural networks have been applied in soil and rock consolidation analysis, but existing studies are mostly focused on vibratory compaction or general consolidation problems, without involving online inversion of consolidation parameters, and without directly linking the output of physical constraint models with the closed-loop control of hydraulic actuators. Pure data-driven models have problems such as poor generalization ability, insufficient interpretability, and dependence on large datasets, making it difficult to maintain consistency with the physical laws of soil and rock when sensors are missing or working conditions change.

[0004] Therefore, how to reduce pore pressure accumulation, ineffective loading, and differential settlement by simultaneously sensing pore pressure and hydraulic displacement at multiple depths, dividing the data into four stages, selecting consolidation models, and inverting parameters, while improving the interpretability and engineering usability of intelligent control, has become an urgent technical problem to be solved. Summary of the Invention

[0005] This application provides a multi-dimensional pore pressure monitoring and pressurized consolidation control method, device, and medium to solve the following technical problem: how to reduce pore pressure accumulation, ineffective loading, and differential settlement by synchronously sensing pore pressure and hydraulic displacement at multiple depths, performing four-stage segmentation, selecting consolidation models, and inverting parameters, while improving the interpretability and engineering usability of intelligent control.

[0006] In a first aspect, embodiments of this application provide a multi-dimensional pore pressure monitoring and pressure consolidation control method. The method includes: setting up multiple depth measuring points within the projection range of the pressure plate and at its outer edge within the same static pressure operation unit, and simultaneously collecting pore water pressure, hydraulic pressure of the hydraulic cylinder, hydraulic cylinder displacement, and pressure plate settlement at each depth measuring point to obtain multi-source synchronous data; based on hydraulic control commands, average contact pressure of the pressure plate, and vertical velocity of the pressure plate, segmenting the multi-source synchronous data according to loading, pressure holding, unloading, and rest stages, and calculating the state indicators of the soil at each depth measuring point in each stage; selecting a consolidation model based on the pressure plate geometry, foundation soil layer distribution, and drainage boundary of the consolidation calculation domain, and jointly inverting consolidation parameters using the layered pore pressure and pressure plate settlement of the soil at each depth measuring point, based on the consolidation... The parameters are calculated to determine the average degree of consolidation, residual settlement, and allowable reloading time of the soil in the controlled consolidation domain. Multi-source synchronous data, soil state indices, consolidation parameters, and spatial relationships between soil layers and points are input into a spatiotemporal prediction model constrained by consolidation control equations, effective stress relationships, and drainage boundary constraints to generate layered reinforcement indices, effective reinforcement depths, and prediction uncertainties for the soil at each depth. When the pore pressure dissipation, effective stress recovery rate, and effective reinforcement depth meet the preset safety threshold conditions, the static pressure, loading rate, holding time, unloading rest time, number of cycles, and point sequence or distance of the hydraulic cylinder in the next cycle are determined to control the hydraulic cylinder in a closed loop. The consolidation parameters and spatiotemporal prediction model are updated using the new cycle data until the post-compression test indicators meet the preset requirements.

[0007] In one implementation of this application, multiple depth measuring points are set up within the projection range of the pressure plate and on the outer edge of the pressure plate in the same static pressure operation unit. The pore water pressure of the soil, the hydraulic pressure of the hydraulic cylinder, the displacement of the hydraulic cylinder, and the settlement of the pressure plate at each depth measuring point are collected simultaneously to obtain multi-source synchronous data. Specifically, this includes: setting up a central pore pressure measuring point within the projection range of the pressure plate based on the depth to be processed and the equivalent diameter of the pressure plate, and setting up radial pore pressure measuring points on the outer edge of the pressure plate; associating the central pore pressure measuring points and radial pore pressure measuring points located in the same depth range into a depth measuring point group, and distributing each depth measuring point group at intervals along the depth direction to form a vertical gradient and a radial gradient of pore pressure; and simultaneously collecting the pore water pressure of the soil at the corresponding depth through each depth measuring point group, as well as the pressure and flow rate of the hydraulic cylinder working chamber and return oil chamber, the hydraulic cylinder displacement, and the settlement of the pressure plate to obtain multi-source synchronous data.

[0008] In one implementation of this application, multi-source synchronous data is segmented according to loading, pressure holding, unloading, and rest stages based on hydraulic control commands, average contact pressure of the pressure plate, and vertical velocity of the pressure plate. Specifically, this includes: calculating the average contact pressure of the pressure plate based on the working chamber pressure of the hydraulic cylinder, the return oil chamber pressure, and the conversion between the effective area of ​​the hydraulic cylinder and the effective area of ​​the pressure plate; and obtaining the vertical velocity of the pressure plate based on the displacement of the hydraulic cylinder. After recognizing the pressurization command in the hydraulic control commands, if the average contact pressure of the pressure plate continues to rise from the baseline, the corresponding time period is marked as the loading stage and the loading start point is recorded. If the average contact pressure of the pressure plate reaches the target pressure... If the pressure remains within the set tolerance range, the corresponding time period is marked as the pressure holding stage and the pressure holding start point is recorded. After the unloading command in the hydraulic control command is detected, if the average contact pressure of the pressure plate drops to the residual pressure threshold, the corresponding time period is marked as the unloading stage and the unloading end point is recorded. When the vertical speed of the pressure plate recovers to stability, the time period from the end of unloading to the next cycle of loading or shifting is marked as the rest stage and the rest start point is recorded. Based on the loading start point, pressure holding start point, unloading end point, and rest start point, the multi-source synchronous data is segmented so that each sampled data corresponds to the loading stage, pressure holding stage, unloading stage, or rest stage, respectively.

[0009] In one implementation of this application, the soil state indices at each depth measuring point in each stage are calculated, specifically including: determining the excess pore pressure in the loading, holding, unloading, and resting stages based on the initial pore water pressure collected at each depth measuring point before static pressure operation and the currently collected pore water pressure; determining the peak pore pressure and the peak pore pressure time at the measuring point in the loading and holding stages; determining the reference stress increment based on the average contact pressure of the pressure plate in the current cyclic holding stage and the stress transfer coefficient at the measuring point in the current depth; and continuously determining the pore pressure ratio and effective stress recovery rate in the loading, holding, unloading, and resting stages based on the current excess pore pressure and the reference stress increment; determining the pore pressure dissipation degree based on the degree of reduction of the current excess pore pressure relative to the peak pore pressure time, and using the pore pressure dissipation degree, pore pressure ratio, and effective stress recovery rate at the end of the resting stage as state indices for re-pressurization or point shifting gating.

[0010] In one implementation of this application, a consolidation model is selected based on the geometry of the pressure plate, the distribution of the foundation soil layers, and the drainage boundary of the consolidation calculation domain. Consolidation parameters are then jointly inverted using the stratified pore pressure of the soil at each depth measuring point and the settlement of the pressure plate. Based on these consolidation parameters, the average degree of consolidation, residual settlement, and allowable re-pressure time of the soil in the controlled consolidation domain are calculated. Specifically, this includes: determining the controlled consolidation domain and its boundary conditions based on the geometry of the pressure plate, the distribution of the foundation soil layers, and the drainage boundary; and, based on the differences in pore pressure response and the degree of soil stratification at each depth measuring point, calculating the average degree of consolidation, residual settlement, and allowable re-pressure time of the soil in the controlled consolidation domain from a pre-set... In the consolidation model, a consolidation model that matches the current drainage conditions and the degree of deformation-seepage coupling is selected. The layered pore pressure and plate settlement of the soil at each depth measuring point are used as observations to construct the joint residual between the theoretical value and the observation of the selected consolidation model. The joint residual is solved under the constraint of consolidation parameters to obtain the consolidation parameters. Based on the consolidation parameters obtained by inversion, the average degree of consolidation and the residual settlement of the soil in the controlled consolidation domain are calculated. The allowable re-pressure time is determined based on the earliest time when the average degree of consolidation, pore pressure ratio and residual settlement meet the preset gate conditions.

[0011] In one implementation of this application, multi-source synchronous data, soil state indices, consolidation parameters, and spatial relationships between soil layers and points at each depth are input into a spatiotemporal prediction model constrained by consolidation control equations, effective stress relationships, and drainage boundaries. This generates layered reinforcement indices, effective reinforcement depths, and prediction uncertainties for the soil at each depth measuring point. Specifically, this includes: constructing a spatial map based on the spatial relationships between measuring points at each depth, static pressure points, soil interfaces, and drainage boundaries; dividing the multi-source synchronous data into dynamic time-series data according to static pressure cycles; and obtaining the soil state indices, consolidation parameters, and static characteristics at each depth measuring point; and inputting the dynamic time-series data, static characteristics, and spatial map into... The temporal encoder, static encoder, and graph encoder of the spatiotemporal prediction model are input, and the outputs of each encoder are fused. In the training or inference of the spatiotemporal prediction model, residual constraints of the consolidation control equation are constructed based on the selected consolidation model, and effective stress consistency constraints and drainage boundary constraints are constructed based on the effective stress relationship and drainage boundary, so that the fused features satisfy the laws of geotechnical physics. The fused features are input into the prediction head of the spatiotemporal prediction model to output the layered reinforcement index and prediction uncertainty of the soil at each depth measuring point. Based on the layered reinforcement index, pore pressure dissipation, effective stress recovery rate, and prediction uncertainty, the depth gate quantity and effective reinforcement depth of each depth measuring point are determined.

[0012] In one implementation of this application, when the pore pressure dissipation, effective stress recovery rate, and effective reinforcement depth meet preset safety thresholding conditions, the static pressure, loading rate, holding time, unloading rest time, number of cycles, and point sequence or distance of the hydraulic cylinder for the next cycle are determined to achieve closed-loop control of the hydraulic cylinder. The consolidation parameters and spatiotemporal prediction model are updated using the new cycle data until the post-pressure detection indicators meet preset requirements. Specifically, this includes comparing the pore pressure dissipation, effective stress recovery rate, and effective reinforcement depth with the corresponding preset safety thresholding conditions. If the safety thresholding conditions are not met, the hydraulic cylinder is controlled to perform at least one safety action among holding pressure, unloading, or extended rest, and then restarted. The newly acquired and updated state indicators and model outputs are used for judgment. If the safety gating conditions are met, the objective function is optimized within the safe and feasible domain determined by the consolidation model and the spatiotemporal prediction model. This optimization includes at least one of the following: reinforcement index deviation, pore pressure exceeding the limit, insufficient consolidation degree, residual settlement, differential settlement, construction time and energy consumption. The static pressure, loading rate, holding time, unloading rest time, number of cycles, and point sequence or point distance for the next cycle are determined to control the hydraulic cylinder in a closed loop. The consolidation parameters and spatiotemporal prediction model are updated using the new cycle data. When the post-compression test indicators meet the preset requirements, the compaction of the current point is stopped and the point is transferred until the post-compression test indicators meet the preset requirements.

[0013] In one implementation of this application, the method further includes: performing anomaly diagnosis on each pore water pressure sensor based on the characteristics of pore water pressure sensor data at each depth measuring point and the interrelationship between the pore water pressure sensor data, in order to determine the reliability of each pore water pressure sensor; when the reliability of the pore water pressure sensor is lower than a preset reliability threshold, restricting the pore water pressure sensor data from participating in the decision-making of the spatiotemporal prediction model and safety gating conditions, and replacing the pore water pressure sensor data with other available data; when the prediction uncertainty of the spatiotemporal prediction model is higher than a preset threshold, the pore water pressure sensor data at the key depth is unavailable, or the calculation module is abnormal, controlling the hydraulic cylinder to perform a safety action and output a verification prompt, and resuming automatic control after the data or calculation module is recovered and re-verified.

[0014] Secondly, this application also provides a multi-dimensional pore pressure monitoring and pressure consolidation control device. The device includes: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores instructions executable by the at least one processor, which, when executed, enable the at least one processor to: deploy multiple depth measuring points within the projection range of the pressure plate and at its outer edge within the same static pressure operation unit, and simultaneously collect pore water pressure, hydraulic pressure, hydraulic cylinder displacement, and pressure plate settlement at each depth measuring point to obtain multi-source synchronous data; segment the multi-source synchronous data according to loading, holding, unloading, and rest stages based on hydraulic control instructions, average contact pressure of the pressure plate, and vertical velocity of the pressure plate, and calculate the state indicators of the soil at each depth measuring point in each stage; and select the drainage boundary of the consolidation calculation domain based on the pressure plate geometry, foundation soil layer distribution, and the... A consolidation model is adopted, and consolidation parameters are jointly inverted using the layered pore pressure and platen settlement of the soil at each depth measuring point. Based on the consolidation parameters, the average degree of consolidation, residual settlement, and allowable re-compression time of the soil in the controlled consolidation domain are calculated. Multi-source synchronous data, state indicators of the soil at each depth measuring point, consolidation parameters, and spatial relationship between soil layers and points are input into a spatiotemporal prediction model constrained by consolidation control equations, effective stress relationships, and drainage boundary constraints to generate layered reinforcement indicators, effective reinforcement depth, and prediction uncertainty of the soil at each depth measuring point. When the pore pressure dissipation, effective stress recovery rate, and effective reinforcement depth meet the preset safety threshold conditions, the static pressure, loading rate, holding time, unloading rest time, number of cycles, and point sequence or distance of the hydraulic cylinder in the next cycle are determined to control the hydraulic cylinder in a closed loop. The consolidation parameters and spatiotemporal prediction model are updated using the new cycle data until the post-compression test indicators meet the preset requirements.

[0015] Thirdly, this application also provides a non-volatile computer storage medium for multi-dimensional pore pressure monitoring and pressure consolidation control, storing computer-executable instructions. These instructions are configured to: deploy multiple depth measuring points within the projection range of the pressure plate and at its outer edge within the same static pressure operation unit; simultaneously collect pore water pressure, hydraulic pressure of the hydraulic cylinder, hydraulic cylinder displacement, and pressure plate settlement at each depth measuring point to obtain multi-source synchronous data; based on hydraulic control instructions, the average contact pressure of the pressure plate, and the vertical velocity of the pressure plate, segment the multi-source synchronous data according to loading, holding, unloading, and rest stages, and calculate the state indicators of the soil at each depth measuring point in each stage; select a consolidation model based on the pressure plate geometry, the distribution of foundation soil layers, and the drainage boundary of the consolidation calculation domain, and use the layered pore pressure and pressure of the soil at each depth measuring point as the basis for the consolidation model; and select a consolidation model based on the layered pore pressure and pressure of the soil at each depth measuring point. The consolidation parameters are obtained through joint inversion of plate settlement. Based on the consolidation parameters, the average degree of consolidation, residual settlement, and allowable re-compression time of the soil in the controlled consolidation domain are calculated. Multi-source synchronous data, soil state indices, consolidation parameters, and spatial relationships between soil layers and points are input into a spatiotemporal prediction model constrained by consolidation control equations, effective stress relationships, and drainage boundaries to generate layered reinforcement indices, effective reinforcement depths, and prediction uncertainties for the soil at each depth measuring point. When the pore pressure dissipation, effective stress recovery rate, and effective reinforcement depth meet the preset safety threshold conditions, the static pressure, loading rate, holding time, unloading rest time, number of cycles, and point sequence or distance of the hydraulic cylinder in the next cycle are determined to control the hydraulic cylinder in a closed loop. The consolidation parameters and spatiotemporal prediction model are updated using the new cycle data until the post-compression test indicators meet the preset requirements.

[0016] This application provides a multi-dimensional pore pressure monitoring and pressurization consolidation control method, equipment, and medium, which has the following beneficial effects: By deploying multiple depth measuring points within the projection range and outer edge of the pressure plate in the static pressure operation unit, multi-source data such as pore water pressure, hydraulic pressure, hydraulic cylinder displacement, and pressure plate settlement are collected simultaneously. This overcomes the limitations of traditional methods that rely on oil pressure, surface settlement, and fixed compaction passes for control. It can simultaneously capture equipment construction information and the stress and drainage state of the deep and shallow soil layers, solving the problem that a single surface index cannot distinguish between soil skeleton compaction, pore pressure transient response, and lateral soil flow. Based on the construction instructions and pressure plate state, loading, pressure holding, unloading, and rest stages are divided, and soil state indices are calculated to accurately match compaction. The cyclical physical time sequence avoids calculation distortion caused by fixed time divisions, enabling quantitative characterization of pore pressure evolution, stress transfer, and deformation rebound processes. A consolidation model is selected based on the plate size, soil layers, and drainage boundaries. Consolidation parameters are obtained by jointly inverting consolidation parameters through layered pore pressure and plate settlement, solving for the average degree of consolidation, residual settlement, and allowable re-pressing time. Re-pressing and rest times are transformed from empirically determined values ​​to theoretical values ​​driven by on-site soil conditions, reducing soil lateral extrusion and rebound, while avoiding ineffective waiting that reduces construction efficiency. A spatiotemporal prediction model constrained by geotechnical physical laws is introduced, outputting layered reinforcement indicators, effective reinforcement depth, and prediction uncertainty, compensating for the shortcomings of delayed and insufficient representative post-pressing testing. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating a multi-dimensional pore pressure monitoring and pressure consolidation control method provided in this application embodiment; Figure 2 This is a schematic diagram of the internal structure of a multi-dimensional pore pressure monitoring and pressurization consolidation control device provided in an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] This application provides a multi-dimensional pore pressure monitoring and pressurized consolidation control method, device, and medium to solve the following technical problem: how to reduce pore pressure accumulation, ineffective loading, and differential settlement by synchronously sensing pore pressure and hydraulic displacement at multiple depths, performing four-stage segmentation, selecting consolidation models, and inverting parameters, while improving the interpretability and engineering usability of intelligent control.

[0020] The technical solutions proposed in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0021] Figure 1 This is a flowchart illustrating a multi-dimensional pore pressure monitoring and pressure consolidation control method provided in an embodiment of this application. Figure 1 As shown in the embodiment of this application, a multi-dimensional pore pressure monitoring and pressurized consolidation control method specifically includes the following steps: Step 10: Within the same static pressure operation unit, set up multiple depth measuring points within the projection range of the pressure plate and on the outer edge of the pressure plate, and simultaneously collect the pore water pressure of the soil, the hydraulic pressure of the hydraulic cylinder, the displacement of the hydraulic cylinder, and the settlement of the pressure plate at each depth measuring point to obtain multi-source synchronous data.

[0022] As an optional embodiment, multiple depth measuring points are set up within the projection range of the pressure plate and on the outer edge of the pressure plate in the same static pressure operation unit, and the pore water pressure of the soil, the hydraulic pressure of the hydraulic cylinder, the displacement of the hydraulic cylinder and the settlement of the pressure plate at each depth measuring point are collected simultaneously to obtain multi-source synchronous data. Specifically, it may include: Step 101: Based on the depth to be processed and the equivalent diameter of the pressure plate, a central hole pressure measuring point is set up within the projection range of the pressure plate, and a radial hole pressure measuring point is set up on the outer edge of the pressure plate.

[0023] In this step, for the foundation reinforcement scenario of hydrostatic pressure loading, the spatial layout design of pore pressure measuring points is carried out based on the intended treatment depth and the equivalent diameter of the pressure plate. A central pore pressure measuring point is set within the projection range of the pressure plate, while radial pore pressure measuring points are arranged on the outer edge of the pressure plate. The central pore pressure measuring point is located within the direct influence area of ​​the pressure plate load, enabling it to collect changes in pore water pressure in the soil directly below the pressure plate throughout the entire static pressure loading process. This reflects the vertical pore pressure generation and dissipation evolution law of the soil below the pressure plate center position, capturing the pore pressure response characteristics under the vertical drainage path. The radial pore pressure measuring points arranged on the outer edge of the pressure plate are used to obtain pore water pressure information of the soil outside the influence range of the pressure plate load, sensing the radial drainage effect of excess pore water pressure spreading outward in the horizontal direction. Through the combined arrangement of the central and radial measuring points, pore pressure data can be collected simultaneously. Vertical and radial gradients can not only grasp the pore pressure dissipation state of the soil within the target reinforcement depth range directly below the pressure plate, but also identify the radial seepage behavior of pore water under load. This provides experimental basis for subsequent selection of suitable consolidation theory models and supports the joint inversion of consolidation parameters. This measuring point layout mode can distinguish the contribution of vertical drainage and radial drainage to pore pressure dissipation, providing a multi-dimensional pore pressure measurement data basis for judging the effective stress recovery degree of deep soil and determining the timing of re-pressure and point relocation. It makes up for the deficiency that setting only a single measuring point cannot fully reflect the seepage consolidation state of the foundation.

[0024] Step 102: Associate the central pore pressure measurement point and the radial pore pressure measurement point located in the same depth range as a depth measurement point group, and distribute each depth measurement point group at intervals along the depth direction to form the vertical gradient and radial gradient of pore pressure.

[0025] In this step, central and radial pore pressure measuring points set up at the same depth interval are interconnected to form depth measuring point groups, which are arranged at intervals along the depth direction. Within each depth measuring point group, the central pore pressure measuring point is within the projection range of the pressure plate, while the radial pore pressure measuring points are arranged at the outer edge of the pressure plate. By simultaneously collecting pore water pressure at two measuring points at different radial positions at the same burial depth, the variation of pore pressure with radial position on the horizontal cross section at the same depth can be reflected, thus constructing the radial gradient of pore pressure and characterizing the difference in diffusion of load-induced excess pore water pressure along the horizontal direction. The measuring point groups at different intervals are arranged in the vertical soil layer. By collecting pore pressure data from measuring point groups at different burial depths, the variation law of pore water pressure with soil depth is captured, thus forming the vertical gradient of pore pressure, reflecting the transmission, accumulation, and dissipation characteristics of excess pore pressure along the vertical direction of the soil layer. Through the vertical and radial gradients of pore pressure, the spatial distribution of the pore pressure field inside the foundation under static loading conditions can be completely reconstructed, which helps to determine whether the foundation is mainly drained vertically or radially. Vertical joint drainage provides experimental data to assist in the selection of consolidation models. At the same time, multi-gradient pore pressure observation data also provides sufficient spatial observation information for the joint inversion of consolidation parameters, making it easier to distinguish the contribution of vertical and radial seepage to pore pressure dissipation. This provides a complete spatial monitoring basis for subsequent assessment of the degree of pore pressure dissipation and effective stress recovery of soil at each layer, and for determining the operational threshold conditions for re-pressure and displacement.

[0026] Step 103: Simultaneously collect pore water pressure of soil at corresponding depths through each depth measuring point group, and simultaneously collect pressure and flow rate of hydraulic cylinder working chamber and return oil chamber, hydraulic cylinder displacement and pressure plate settlement to obtain multi-source synchronous data.

[0027] In this step, soil at corresponding depths is monitored through various depth measurement point groups. Pore water pressure data at different burial depths are collected simultaneously to obtain information on the evolution of excess pore water pressure within the foundation as construction progresses, thus reflecting the development state of drainage consolidation within the soil. Simultaneously, pressure and flow signals from the hydraulic cylinder's working chamber and return chamber are collected to understand the actual working state of the hydraulic circuit and obtain relevant load input information for compaction operations. Simultaneously acquired hydraulic cylinder displacement and pressure plate settlement data are used to characterize the vertical deformation behavior of the pressure plate throughout the construction process, reflecting the compression, creep, and rebound deformation characteristics of the soil under external loads. All monitoring signals are synchronized in time, forming a multi-source synchronous data set. This multi-source synchronous data includes pore pressure field information from different spatial locations within the soil, covering the spatial variation characteristics of pore pressure in the radial and vertical directions, as well as pressure and flow parameters of the hydraulic system and displacement, settlement, and deformation information at the equipment execution end, achieving temporal alignment between the internal consolidation response of the foundation soil and the external construction execution actions.

[0028] Step 20: Based on hydraulic control commands, average contact pressure of the pressure plate and vertical speed of the pressure plate, the multi-source synchronous data is segmented according to the loading, pressure holding, unloading and rest stages, and the state index of the soil at each depth measuring point in each stage is calculated.

[0029] As an optional embodiment, based on hydraulic control commands, average contact pressure of the pressure plate, and vertical speed of the pressure plate, the multi-source synchronous data is segmented according to the loading, pressure holding, unloading, and rest stages, and the state index of the soil at each depth measuring point in each stage is calculated. Specifically, it may include: Step 201: The average contact pressure of the pressure plate is obtained based on the working chamber pressure of the hydraulic cylinder, the return oil chamber pressure, and the conversion between the effective area of ​​the hydraulic cylinder and the effective area of ​​the pressure plate, and the vertical speed of the pressure plate is obtained based on the displacement of the hydraulic cylinder.

[0030] In this step, the collected pressure in the working chamber and return chamber of the hydraulic cylinder are used, combined with the effective area of ​​the hydraulic cylinder and the effective area of ​​the pressure plate, to calculate the average contact pressure of the pressure plate. This conversion process transforms the pressure signal inside the hydraulic system into the actual load level at the interface between the pressure plate and the foundation soil, realizing the conversion from the working parameters of the hydraulic actuator to the external load on the soil. This characterizes the real contact load applied by the pressure plate to the soil surface, avoiding the characterization deviation caused by directly using the hydraulic cylinder oil pressure to replace the actual compressive load on the soil. It can objectively reflect the changes in the external load borne by the soil during static pressure operation. At the same time, the collected hydraulic cylinder displacement time series data is differentiated to derive the vertical velocity of the pressure plate. The vertical velocity of the pressure plate reflects the speed of vertical movement of the pressure plate over time, and can reflect the dynamic characteristics of the pressure plate under different motion behaviors such as pressing down, maintaining pressure, and unloading and lifting.

[0031] Step 202: After recognizing the pressurization command in the hydraulic control command, if the average contact pressure of the pressure plate continues to rise from the baseline, the corresponding time period is marked as the loading stage and the loading start point is recorded.

[0032] Step 203: If the average contact pressure of the pressure plate reaches the target pressure and remains continuously within the set tolerance range, then mark the corresponding time period as the pressure holding stage and record the pressure holding start point.

[0033] In this step, after the pressurization command signal is identified, the change in the average contact pressure of the pressure plate is continuously monitored. Once the average contact pressure of the pressure plate shows a continuous upward trend from the baseline level, the corresponding working period is defined as the loading stage, and the start time of the loading stage is recorded to mark the starting node when the pressure plate begins to apply pressure to the soil. The loading stage represents the process of gradually transferring the load to the foundation soil. The continuous increase of the external load will cause excess pore water pressure to gradually be generated inside the soil. After the loading stage, the average contact pressure of the pressure plate continues to be continuously monitored. When the average contact pressure of the pressure plate rises to the target pressure and can be continuously maintained at the corresponding set value, the pressure is considered to be applied. When the load is within the tolerance range, the time period is defined as the pressure holding stage, and the start time of the pressure holding stage is recorded synchronously. The pressure holding stage represents the operation process in which the pressure plate maintains a stable load output on the soil. Under constant load, the soil undergoes drainage consolidation, and the pore water pressure gradually develops and enters the dissipation process. By combining hydraulic control commands with the contact pressure state of the pressure plate, the start and end points of the loading and pressure holding stages are determined. This allows for the objective differentiation of different construction operation procedures and provides an accurate time boundary basis for subsequent stage segmentation of multi-source synchronous data and stage-by-stage calculation of various soil state indicators. This avoids the disconnect between the stage division based solely on control commands and the actual soil pressure state.

[0034] Step 204: After identifying the unloading command in the hydraulic control command, if the average contact pressure of the pressure plate drops to the residual pressure threshold, mark the corresponding time period as the unloading stage and record the unloading endpoint. When the vertical speed of the pressure plate recovers to a stable state, mark the time period from the end of unloading to the next cycle of loading or moving point as the rest stage and record the rest start point.

[0035] In this step, after the unloading command is detected, the change in the average contact pressure of the pressure plate is continuously tracked. When the average contact pressure of the pressure plate drops to the residual pressure threshold, the operation period is defined as the unloading stage, and the end time of the unloading stage is recorded. The unloading stage corresponds to the process of gradually removing the pressure plate load from the soil. During this stage, the soil will experience stress release and rebound deformation. After the unloading determination is completed, the vertical velocity of the pressure plate continues to be monitored. When the vertical velocity of the pressure plate returns to a stable state, this state node is used as the starting point of the rest stage, which will begin from the end of the unloading until the start or execution point of the next cycle of loading action. The entire time interval before the transfer is marked as the rest phase. During the rest phase, the pressure plate no longer applies an effective working load to the soil, and the foundation soil mainly completes the dissipation of excess pore water pressure and the recovery of effective stress. This method combines hydraulic control commands, contact pressure thresholds, and the movement state of the pressure plate to jointly define the time boundaries between the unloading phase and the rest phase. It can match the actual operating response of the equipment and prevent deviations from the actual stress and deformation state of the soil on site due to relying solely on electrical control commands to divide the time period. It provides a reliable time reference for the phase segmentation of multi-source synchronous data and the calculation of state indicators such as pore pressure dissipation and effective stress recovery rate during the rest period.

[0036] Step 205: Divide the multi-source synchronous data based on the loading start point, pressure holding start point, unloading end point, and rest start point, so that each sampled data corresponds to the loading stage, pressure holding stage, unloading stage, or rest stage respectively.

[0037] In this step, the identified loading start point, pressure holding start point, unloading end point, and rest start point are used as time boundary markers to perform time-series segmentation processing on the entire set of multi-source synchronous data. Each sampled data is assigned to the loading stage, pressure holding stage, unloading stage, or rest stage according to its corresponding timestamp. Through this time boundary division method, a one-to-one correspondence is achieved between various monitoring data such as pore water pressure, hydraulic pressure and flow rate, hydraulic cylinder displacement, and platen settlement and different operational stages of the compaction cycle, distinguishing the evolution of pore pressure inside the soil, hydraulic system conditions, and platen deformation response under different processes. After completing the data stage assignment, the data can be further processed according to the physical characteristics of each stage. The calculation of indices is carried out in a differentiated manner based on process characteristics. The loading stage focuses on capturing the stress and deformation response during the load lifting process. The pressure holding stage focuses on the generation and development of pore pressure under constant load. The unloading stage is used to analyze the soil rebound behavior after the load is removed. The resting stage focuses on the dissipation of excess pore water pressure and the recovery of effective stress when no external load is applied. This data segmentation, which is completed by time boundaries determined by actual operation conditions, avoids the stage mismatch problem caused by using fixed time window division, ensures the physical rationality of the calculation of various soil state indices under different construction stages, and also provides time-ordered basic data for subsequent consolidation parameter inversion, model input, and gating condition determination.

[0038] Step 206: Based on the initial pore water pressure collected at each depth measuring point before the static pressure operation and the currently collected pore water pressure, determine the excess pore pressure during the loading stage, pressure holding stage, unloading stage and rest stage, and determine the peak pore pressure and the peak pore pressure time of the measuring point at that depth during the loading stage and pressure holding stage.

[0039] In this step, before conducting static pressure operations, the initial pore water pressure at each depth measuring point is collected in advance and used as the pressure calculation benchmark. Combined with the pore water pressure data collected in real time at each stage of construction, the excess pore water pressure is calculated in the loading, holding, unloading, and resting stages. This is used to characterize the increase in pore water pressure exceeding the static water state induced by external loads. The dynamic changes of pore water pressure inside the soil are continuously tracked throughout the entire compaction cycle. At the same time, within the time range of the loading and holding stages, the pore water pressure change process at the corresponding depth measuring point is identified and the peak pore pressure at that depth measuring point is determined, and the time corresponding to the peak pore pressure is recorded. This peak pore pressure time will serve as the starting benchmark for subsequent calculations related to pore pressure dissipation, and will be used for the calculation of state indicators such as pore pressure dissipation degree and pore pressure dissipation rate during the subsequent holding, unloading, and resting stages. The excess pore pressure is obtained by comparing the initial benchmark before operation with the real-time monitoring data during construction. The peak pore pressure and its occurrence time are located within the loading and pressure holding intervals. This can closely match the physical process of static compaction load action, avoid misjudging the pressure fluctuation after unloading as the load-induced peak pore pressure, ensure the physical logic and reliability of the subsequent calculation of pore pressure dissipation-related state indicators, and provide an accurate calculation basis for evaluating the soil drainage consolidation process.

[0040] Step 207: Determine the reference stress increment based on the average contact pressure of the pressure plate during the current cyclic pressure holding stage and the stress transfer coefficient at the depth measuring point. Based on the current superstatic pore pressure and the reference stress increment, continuously determine the pore pressure ratio and effective stress recovery rate during the loading stage, pressure holding stage, unloading stage, and rest stage.

[0041] In this step, the average contact pressure of the pressure plate during the current pressure holding stage is extracted. Combined with the stress transfer coefficient at the corresponding depth measurement point, the reference stress increment at that depth is calculated. This reference stress increment represents the theoretical stress level transferred from the external load applied by the pressure plate to the target depth. Using the obtained reference stress increment, and combined with the real-time updated excess pore pressure at each construction stage, the pore pressure ratio and effective stress recovery rate can be continuously calculated during the loading, pressure holding, unloading, and resting stages. The pore pressure ratio reflects the excess pore water pressure at that depth relative to the transferred reference stress increment. The proportion of pore water represents the degree to which external loads are borne by pore water; the effective stress recovery rate reflects the level of transformation of loads from pore water to soil skeleton, reflecting the recovery process of the actual bearing capacity of the soil skeleton. The two state indicators are continuously updated throughout the entire compaction cycle, and can dynamically show the stress redistribution characteristics inside the soil during the entire process of load application, load holding, load removal and static rest. This provides a quantitative basis for real-time evaluation of the changes in the proportion of loads borne by pore water and the recovery state of effective stress in the soil, and also provides continuously changing state input for subsequent re-compaction and displacement point gate condition determination.

[0042] Step 208: Starting from the peak value of pore pressure, determine the pore pressure dissipation degree based on the degree of reduction of the current superstatic pore pressure relative to the peak value of pore pressure, and use the pore pressure dissipation degree, pore pressure ratio and effective stress recovery rate at the end of the resting stage as state indicators for pressure recovery or shift point gating.

[0043] In this step, the peak pore pressure moment is used as the starting time reference for the calculation. Subsequent state parameter calculations are performed from this moment. The pore pressure dissipation degree is calculated based on the degree of decrease in current excess pore pressure compared to the peak pore pressure. The pore pressure dissipation degree characterizes the development of excess pore water pressure dissipation during the drainage process. This calculation process continues throughout the pressure holding, unloading, and rest phases after the peak pore pressure occurs. Instead of directly using instantaneous calculation results at intermediate moments as the decision-making basis, the pore pressure dissipation degree, pore pressure ratio, and effective stress recovery rate corresponding to the end of the rest phase are selected. This set of state parameters is then used to determine the optimal parameters. As the input condition for conducting re-compaction or relocation point gate control judgments, the soil no longer bears the externally applied compaction load during the resting phase, and pore water can fully seep out and drain. Selecting the index results at the end of this phase can more objectively reflect the true consolidation and stress recovery level of the soil after static drainage, avoid the instantaneous state interference caused by construction loading disturbances, prevent misjudgments of premature re-compaction or premature relocation based on intermediate transient data, ensure that the gate control judgment is consistent with the actual consolidation state of the soil, and provide a reliable quantitative evaluation basis for whether to allow the start of the next compaction cycle or the relocation of the work site.

[0044] Step 30: Select a consolidation model based on the geometric dimensions of the pressure plate, the distribution of the foundation soil layers, and the drainage boundary of the consolidation calculation domain. Use the layered pore pressure of the soil at each depth measuring point and the settlement of the pressure plate to jointly invert the consolidation parameters. Calculate the average degree of consolidation, residual settlement, and allowable re-pressure time of the soil in the controlled consolidation domain based on the consolidation parameters.

[0045] As an optional embodiment, a consolidation model is selected based on the geometry of the pressure plate, the distribution of the foundation soil layers, and the drainage boundary of the consolidation calculation domain. The consolidation parameters are then inverted using the stratified pore pressure of the soil at each depth measuring point and the settlement of the pressure plate. Based on the consolidation parameters, the average degree of consolidation, the remaining settlement, and the allowable re-pressure time of the soil in the controlled consolidation domain are calculated. Specifically, this may include: Step 301: Determine the controlled consolidation domain and its boundary conditions based on the geometry of the pressure plate, the distribution of the foundation soil layers, and the drainage boundary. Based on the differences in pore pressure response and the degree of soil stratification at each depth measuring point, select a consolidation model from the preset consolidation models that matches the current drainage conditions and the degree of deformation-seepage coupling.

[0046] In this step, the controlled consolidation domain under static compaction is delineated based on the geometric dimensions of the pressure plate, the actual distribution of the foundation soil layers, and the on-site drainage boundary conditions. Simultaneously, various boundary conditions corresponding to this consolidation domain are determined to limit the spatial scope of the consolidation calculation and the constraint rules for pore pressure and flow rate at the domain boundaries. Based on this, the differences in pore pressure responses collected from various depth measuring points are compared. Simultaneously, considering the degree of soil stratification, a model selection is completed from among several pre-configured consolidation models. Differences in pore pressure responses at measuring points reflect the vertical and radial diffusion characteristics of pore water pressure, while the degree of soil stratification reflects the changes in the physical and mechanical properties of the soil along the depth direction. By comprehensively analyzing the above information, a model suitable for the actual on-site drainage conditions and soil deformation is selected. A consolidation model adapted to the degree of seepage coupling effect is selected. This selection method is based on the field measured response and actual geological conditions, avoiding the calculation deviation caused by applying a single consolidation model. This ensures that the calculation of key physical quantities such as consolidation parameter inversion, average degree of consolidation and residual settlement can closely match the actual seepage consolidation behavior of the foundation, providing a theoretical calculation basis that conforms to the soil mechanism for construction status assessment and re-pressure timing prediction.

[0047] Step 302: Using the stratified pore pressure and platen settlement of the soil at each depth measuring point as observations, construct the joint residual between the theoretical value and the observations of the selected consolidation model, and solve the joint residual under the constraint of consolidation parameters to obtain the consolidation parameters.

[0048] In this step, the stratified pore pressure and pressure plate settlement obtained from each depth measuring point are used as actual observation data. The corresponding theoretical calculation results are solved for the selected consolidation model, constructing a joint residual between the model's theoretical output and the measured observations. This joint residual simultaneously considers both the evolution of pore water pressure within the soil and the deformation of the external pressure plate, incorporating both the internal seepage response and surface settlement deformation into the evaluation system, avoiding the information bias caused by relying solely on a single type of observation data. During the solution of the joint residual, relevant constraints on the consolidation parameters are introduced. These constraints include limitations on the physical properties of the parameters themselves, the a priori range obtained from laboratory tests, and the continuity requirements at the soil interface, ensuring that the parameters to be solved conform to the laws of geotechnical physics. By optimizing the joint residual, the inversion of the consolidation parameters is completed. The consolidation parameters obtained in this way integrate the actual on-site construction response information, reflecting the actual permeability and compressibility characteristics of the soil under in-situ conditions. This provides a parameter basis that fits the on-site working conditions for subsequent calculations of the average degree of consolidation, residual settlement, and the deduction of the allowable re-pressure time.

[0049] Step 303: Calculate the average degree of consolidation and residual settlement of the soil in the controlled consolidation domain based on the consolidation parameters obtained by inversion, and determine the allowable re-pressure time based on the earliest time when the average degree of consolidation, pore pressure ratio and residual settlement meet the preset gate conditions.

[0050] In this step, the consolidation parameters obtained through inversion are substituted into the selected consolidation model to perform calculations, obtaining the average degree of consolidation and residual settlement of the soil within the controlled consolidation domain. The average degree of consolidation can comprehensively characterize the overall dissipation level of excess pore water pressure within the controlled consolidation domain, while the residual settlement reflects the potential settlement deformation of the foundation soil that has not yet been completed. Both describe the current consolidation state of the soil from two dimensions: the degree of consolidation drainage and the deformation development potential. Subsequently, the average degree of consolidation, pore pressure ratio, and residual settlement are combined with the corresponding preset gate conditions. By comparing and selecting all moments that simultaneously meet all gating constraints, the earliest moment is taken as the allowable re-compaction moment. This allowable re-compaction moment is not based on fixed duration experience, but is derived from the in-situ soil consolidation state. This ensures that before the re-compaction action is carried out, the overall consolidation dissipation of the foundation, the pore pressure ratio, and the residual deformation are all within acceptable ranges. It can effectively avoid engineering problems such as lateral extrusion and rebound of the soil caused by starting re-compaction before the pore pressure dissipates sufficiently, and provides a theoretical basis for the timing determination of the compaction cycle.

[0051] Step 40: Input the multi-source synchronous data, the state index of the soil at each depth measuring point, the consolidation parameters, and the spatial relationship between the soil layer and the point into the spatiotemporal prediction model constrained by the consolidation control equation, the effective stress relationship, and the drainage boundary, so as to generate the layered reinforcement index, effective reinforcement depth, and prediction uncertainty of the soil at each depth measuring point.

[0052] As an optional embodiment, multi-source synchronous data, soil state indices, consolidation parameters, and spatial relationships between soil layers and points are input into a spatiotemporal prediction model constrained by consolidation control equations, effective stress relationships, and drainage boundaries to generate layered reinforcement indices, effective reinforcement depths, and prediction uncertainties for soil at each depth measuring point. Specifically, this may include: Step 401: Constructing a spatial map based on the spatial relationships between each depth measuring point, static pressure points, soil layer interfaces, and drainage boundaries; dividing the multi-source synchronous data into dynamic time-series data according to static pressure cycles; and obtaining the soil state indices, consolidation parameters, and static characteristics at each depth measuring point.

[0053] In this step, based on the spatial positions and connectivity between various depth measuring points, static pressure operation points, soil interfaces, and drainage boundaries, a corresponding spatial map structure is constructed. Entities such as measuring points and construction points are set as nodes on the map, and edges are established between nodes based on geometric distance, soil layer boundaries, and drainage connectivity characteristics. This represents the spatial relationships between various objects within the foundation system. Simultaneously, the acquired multi-source synchronous data is sliced ​​according to a complete static pressure cycle to form dynamic time-series data, preserving complete time-series evolution information for each stage of loading, holding pressure, unloading, and rest. Additionally, the acquired data is processed... The soil state indices corresponding to each depth measuring point, the consolidation parameters obtained through inversion, and static features such as equipment geometry and soil conditions that do not change with compaction cycles; dynamic time-series data carry observation information on the evolution of the construction process over time, consolidation parameters and soil state indices reflect the current consolidation and reinforcement state of the soil, static features record the inherent properties of the site and equipment, and spatial maps depict the spatial topological relationships of each element. All of the above types of information together constitute complete model input materials, providing a multi-dimensional basic input of time series, physical parameters, and spatial topology for subsequent spatiotemporal prediction models constrained by geotechnical physics.

[0054] Step 402: Input the dynamic time series data, static features and spatial graph into the time series encoder, static encoder and graph encoder of the spatiotemporal prediction model respectively, and perform feature fusion on the output of each encoder.

[0055] In this step, the dynamic time-series data obtained through static pressure cycle slicing is input into the time-series encoder of the spatiotemporal prediction model. The time-series encoder extracts the time-series features that evolve over time during the entire process of compaction cycle loading, pressure holding, unloading, and rest, uncovering the inherent laws governing the changes in construction conditions, pore pressure, and deformation response with each process. Static features related to equipment and site soil properties are input into the static encoder, performing feature mapping and characterization extraction on inherent attribute information that does not change with the construction process. Simultaneously, a spatial map representing the topological relationships of measuring points, locations, soil interfaces, and drainage boundaries is input into the graph encoder. The graph encoder learns the spatial connectivity and interaction relationships between different nodes, capturing the spatial transmission and correlation characteristics of pore pressure and reinforcement effects. After encoding, the characterization information output by the time-series encoder, static encoder, and graph encoder is fused, integrating information from the time dimension, inherent attribute dimension, and spatial topology dimension into a unified comprehensive feature vector. The fused comprehensive feature vector gathers information from multiple aspects, including construction time-series evolution, site inherent conditions, and foundation spatial structure, providing a complete feature foundation for the model to subsequently extrapolate and output layered pore pressure, reinforcement indicators, and prediction uncertainties.

[0056] Step 403: In the training or inference of the spatiotemporal prediction model, construct the residual constraints of the consolidation control equation based on the selected consolidation model, and construct the effective stress consistency constraints and drainage boundary constraints based on the effective stress relationship and drainage boundary, so that the fused features satisfy the laws of geotechnical physics.

[0057] In this step, during the training and inference process of the spatiotemporal prediction model, residual constraints of the consolidation control equations are constructed in conjunction with the selected consolidation model on site. These constraints impose mathematical restrictions of seepage consolidation theory on the model output results. Simultaneously, effective stress consistency constraints are established using the effective stress principle to ensure that the stress and pore pressure results derived from the model satisfy the load distribution relationship between the soil skeleton and pore water. Drainage boundary constraints are set based on the actual site drainage boundary conditions to ensure that the model output conforms to the seepage flow rules of pore water at the boundary. These various physical constraints act on the integrated characteristics after fusion, standardizing and correcting the model's feature expression and output results. This guides the model's learning and inference process to follow the inherent physical mechanisms of geotechnical engineering, avoiding non-physical interpretations that violate consolidation laws based solely on data fitting. Even in situations where working conditions change or some sensor data is temporarily missing, the multiple physical constraints maintain the rationality of the prediction results, reducing the unreliability risks of purely data-driven models and ensuring that the predicted outputs of layered pore pressure and reinforcement effects conform to the actual consolidation deformation behavior of the foundation soil.

[0058] Step 404: Input the fused features into the prediction head of the spatiotemporal prediction model to output the layered reinforcement index and prediction uncertainty of the soil at each depth measuring point, and determine the depth threshold and effective reinforcement depth of each depth measuring point based on the layered reinforcement index, pore pressure dissipation, effective stress recovery rate and prediction uncertainty.

[0059] In this step, the integrated features after fusion are fed into the prediction heads of the spatiotemporal prediction model. The prediction heads output the layered reinforcement indices corresponding to the soil at each depth measurement point, and simultaneously output the prediction uncertainty of the corresponding prediction results. The prediction uncertainty is used to characterize the reliability of the model's current simulation results. Then, a comprehensive judgment is made by combining the layered reinforcement indices, pore pressure dissipation, effective stress recovery rate, and prediction uncertainty obtained from each depth measurement point. It is determined whether each depth measurement point meets all the corresponding judgment conditions, thereby determining the depth threshold of that depth measurement point. Based on the depth threshold results of each depth measurement point, the location of the deepest measurement point that continuously meets the threshold conditions is retrieved from the ground surface downwards, thereby determining the effective reinforcement depth under the current working conditions. This method incorporates the reinforcement effect, pore pressure dissipation state, effective stress recovery level, and model prediction reliability into the evaluation system, rather than relying solely on the single dimension of reinforcement indices for judgment. This can avoid misjudgments caused by model prediction deviations and objectively reflect the soil layer range where the actual reinforcement effect of the foundation is achieved. It provides a quantitative evaluation basis at the depth level for subsequent re-compaction, continuous compaction, or relocation of work sites.

[0060] Step 50: When the pore pressure dissipation, effective stress recovery rate, and effective reinforcement depth meet the preset safety threshold conditions, determine the static pressure, loading rate, pressure holding time, unloading rest time, number of cycles, and point sequence or distance of the hydraulic cylinder in the next cycle, so as to control the hydraulic cylinder in a closed loop, and update the consolidation parameters and spatiotemporal prediction model using the new cycle data until the post-pressure test indicators meet the preset requirements.

[0061] As an optional embodiment, when the pore pressure dissipation, effective stress recovery rate, and effective reinforcement depth meet the preset safety threshold conditions, the static pressure, loading rate, holding time, unloading rest time, number of cycles, and point sequence or point distance of the hydraulic cylinder in the next cycle are determined to control the hydraulic cylinder in a closed loop. The consolidation parameters and spatiotemporal prediction model are updated using the new cycle data until the post-pressure test indicators meet the preset requirements. Specifically, this may include: Step 501: Compare the pore pressure dissipation, effective stress recovery rate, and effective reinforcement depth with the corresponding preset safety threshold conditions.

[0062] In this step, the calculated pore pressure dissipation, effective stress recovery rate, and effective reinforcement depth are compared and verified with the pre-set corresponding safety threshold conditions. The pore pressure dissipation is used to evaluate the dissipation level of excess pore water pressure inside the soil, the effective stress recovery rate reflects the recovery state of the soil skeleton's bearing capacity, and the effective reinforcement depth characterizes the range of soil layers that can achieve the expected reinforcement effect in this static pressure operation. By comparing each indicator with the preset safety threshold conditions, the system comprehensively judges whether the foundation consolidation and reinforcement effect at the current point meet the operational requirements. This comparison process comprehensively considers the multi-dimensional soil and rock conditions of pore pressure dissipation, stress transformation, and reinforcement depth, and does not rely on a single indicator to make decisions. It can identify situations such as insufficient local soil consolidation or the effective reinforcement depth not reaching the expected level, providing a comprehensive judgment basis for whether to continue the re-pressure operation, end the construction at the current point, and move to the next static pressure point, ensuring that the compaction operation meets the safety and quality requirements of foundation reinforcement.

[0063] Step 502: If the safety gate control conditions are not met, control the hydraulic cylinder to perform at least one of the following safety actions: pressure holding, unloading, or extended rest, and re-acquire the updated status indicators and model output for judgment.

[0064] Step 503: If the safety gating conditions are met, then within the safe feasible region determined by the consolidation model and the spatiotemporal prediction model, optimization is performed using an objective function that includes at least one of the following: reinforcement index deviation, pore pressure exceeding limit, insufficient consolidation degree, residual settlement, differential settlement, construction time and energy consumption. The static pressure, loading rate, pressure holding time, unloading rest time, number of cycles, and point sequence or point distance for the next cycle are determined to control the hydraulic cylinder in a closed loop.

[0065] In this step, if the comparison result determines that the safety threshold conditions are not met, the hydraulic cylinder will be controlled to perform at least one safety control action among pressure holding, unloading, or extended rest. After the action is completed, data is collected again to obtain updated soil state indicators and model output results, and the threshold condition determination is carried out again. The cycle is repeated until the safety constraints are met. If all indicators meet the safety threshold conditions, an objective function is constructed within the safe feasible region jointly defined by the consolidation model and the spatiotemporal prediction model to carry out optimization calculation. The objective function includes at least one optimization objective among the reinforcement index deviation, pore pressure exceeding the limit, insufficient consolidation, residual settlement, differential settlement, construction time, and energy consumption. Through optimization, the static pressure, loading rate, pressure holding time, unloading rest time, number of cycles, and subsequent operation point sequence or point spacing control parameters corresponding to the next compaction cycle are determined. Based on the obtained parameters, the hydraulic cylinder is controlled in a closed loop to perform static pressure operation. This control logic enables the linkage of foundation reinforcement status perception, safety verification, and autonomous optimization of construction parameters. It can dynamically adjust the operation plan based on the real-time consolidation response of the soil, ensuring the quality of foundation reinforcement and construction safety while taking into account deformation control and operational economy, thus forming a complete intelligent closed-loop control system for compaction operations.

[0066] Step 504: Update the consolidation parameters and spatiotemporal prediction model using the new cycle data, and stop compaction at the current point and transfer the point when the post-compaction test indicators meet the preset requirements, until the post-compaction test indicators meet the preset requirements.

[0067] In this step, monitoring data generated from a new round of compaction cycles is collected to iteratively update consolidation parameters and spatiotemporal prediction models, continuously optimizing the model's ability to represent the consolidation response of foundation soil. This allows the model to adapt to soil property changes at the current location after multiple compaction cycles. During continuous cyclic compaction operations, post-compaction testing indicators are evaluated in real time. When the post-compaction testing indicators meet preset requirements, the compaction operation at the current location is terminated, and the process is switched to the next static pressure point. Construction is advanced point by point in this manner until the post-compaction testing indicators for all points meet the preset requirements. This mechanism uses the measured data generated from each round of operations to continuously correct parameters and prediction models, constantly reducing model extrapolation bias. At the same time, the post-compaction testing indicators serve as the final criterion for starting, stopping, and transferring operations at points, taking into account both online model learning and on-site quality acceptance, thus achieving closed-loop control of foundation reinforcement quality throughout the entire construction area.

[0068] Step 505: Based on the characteristics of pore water pressure sensor data at each depth measuring point and the interrelationship between the data of each pore water pressure sensor, perform anomaly diagnosis on each pore water pressure sensor to determine the reliability of each pore water pressure sensor.

[0069] In this step, the data characteristics output by the pore water pressure sensors at each depth measuring point are utilized, along with the inherent correlation between the data collected by different pore water pressure sensors, to conduct anomaly diagnosis of the pore water pressure sensors. This determines whether there are data anomalies in each pore water pressure sensor, and thus determines the reliability of each pore water pressure sensor. Specifically, the data characteristics of the sensor itself are used to identify distortion problems in the time-series signal of a single sensor, while the data correlation between sensors at different measuring points utilizes the spatial evolution consistency of the pore pressure field to identify abnormal signals that deviate from the overall pattern at local measuring points. This joint diagnostic method distinguishes between normal monitoring data and abnormal interference data, quantifies the reliability of each sensor, and allows for differentiated weighting of monitoring data based on sensor reliability in subsequent processes such as multi-source data segmentation, excess pore pressure calculation, consolidation parameter inversion, and spatiotemporal model inference. This reduces the adverse effects of abnormal sensor signals on soil state index calculation, model inference, and gating judgment, ensuring the reliability of the pore pressure observation information upon which the entire intelligent control process depends.

[0070] Step 506: When the reliability of the pore water pressure sensor is lower than the preset reliability threshold, restrict the data of the pore water pressure sensor from participating in the spatiotemporal prediction model and the decision of the safety gating conditions, and replace the data of the pore water pressure sensor with other available data.

[0071] In this step, when the reliability of the pore water pressure sensor is lower than the preset reliability threshold, the data access rights of the sensor will be restricted, prohibiting the data of this group of pore water pressure sensors from participating in the spatiotemporal prediction model calculation and the relevant decision-making process of safety gating conditions, so as to avoid abnormal data interfering with model inference and construction status determination. At the same time, other available monitoring data with the required reliability are selected to replace the data of the low-reliability pore water pressure sensor, and the pore pressure information at the corresponding depth position is supplemented. This processing method can maintain the continuity of the entire control process when the sensor is abnormal, avoid the calculation interruption caused by single-point sensor failure, and ensure that the solution of excess pore pressure, soil condition index calculation, model prediction and gating determination can still be carried out normally, ensuring the stability and reliability of the static compaction intelligent closed-loop control process.

[0072] Step 507: When the prediction uncertainty of the time-space prediction model is higher than the preset threshold, the pore water pressure sensor data at the critical depth is unavailable, or the calculation module is abnormal, the hydraulic cylinder is controlled to perform a safety action and output a verification prompt. Automatic control is restored after the data or calculation module is recovered and re-verified.

[0073] In this step, if the prediction uncertainty output by the spatiotemporal prediction model exceeds the preset threshold, or if the pore water pressure sensor data at key depth locations is unavailable, or if the calculation module malfunctions, the system will control the hydraulic cylinder to execute preset safety actions and simultaneously output a verification prompt message to remind operators to investigate the source of the anomaly. After the relevant monitoring data or calculation module returns to normal, the system will re-perform the data verification and status determination process to confirm that all conditions meet the operational requirements before reactivating the automatic control mode to continue static compaction operations. This anomaly protection mechanism provides unified handling for different risk scenarios such as insufficient model prediction reliability, missing core sensor information, and background calculation failures. It can promptly terminate automatic optimization and control when critical system information is unreliable, avoiding the generation of incorrect compaction control parameters based on unreliable information, and ensuring the equipment safety and controllable construction quality of static compaction operations.

[0074] The above are embodiments of the method proposed in this application. Based on the same inventive concept, embodiments of this application also provide a multi-dimensional pore pressure monitoring and pressurized consolidation control device, the structure of which is as follows: Figure 2 As shown.

[0075] Figure 2 This is a schematic diagram of the internal structure of a multi-dimensional pore pressure monitoring and pressurization consolidation control device provided in an embodiment of this application. Figure 2 As shown, the device includes: At least one processor 201; And a memory 202 that is communicatively connected to at least one processor; The memory 202 stores instructions executable by at least one processor. These instructions are executed by at least one processor 201 to enable the processor 201 to: deploy multiple depth measuring points within the projection range of the pressure plate and along its outer edge within the same static pressure working unit; simultaneously collect pore water pressure, hydraulic cylinder pressure, hydraulic cylinder displacement, and pressure plate settlement at each depth measuring point to obtain multi-source synchronous data; segment the multi-source synchronous data according to loading, holding, unloading, and rest stages based on hydraulic control instructions, average contact pressure of the pressure plate, and vertical velocity of the pressure plate; and calculate the state indicators of the soil at each depth measuring point in each stage; select a consolidation model based on the pressure plate geometry, foundation soil layer distribution, and drainage boundary of the consolidation calculation domain; and combine the layered pore pressure of the soil at each depth measuring point with the pressure plate settlement... Consolidation parameters are inverted, and the average degree of consolidation, residual settlement, and allowable reloading time of the soil in the controlled consolidation domain are calculated based on these parameters. Multi-source synchronous data, soil state indices at each depth measuring point, consolidation parameters, and the spatial relationship between soil layers and points are input into a spatiotemporal prediction model constrained by consolidation control equations, effective stress relationships, and drainage boundaries to generate layered reinforcement indices, effective reinforcement depths, and prediction uncertainties for the soil at each depth measuring point. When pore pressure dissipation, effective stress recovery rate, and effective reinforcement depth meet preset safety threshold conditions, the static pressure, loading rate, holding time, unloading rest time, number of cycles, and point sequence or distance of the hydraulic cylinder for the next cycle are determined to achieve closed-loop control of the hydraulic cylinder. The consolidation parameters and spatiotemporal prediction model are updated using new cycle data until the post-compression test indicators meet preset requirements.

[0076] Some embodiments of this application provide corresponding to Figure 1A non-volatile computer storage medium for multi-dimensional pore pressure monitoring and pressure consolidation control stores computer-executable instructions. These instructions are configured to: deploy multiple depth measuring points within the projection range and outer edge of the pressure plate in the same static pressure operation unit, and simultaneously collect pore water pressure, hydraulic cylinder pressure, hydraulic cylinder displacement, and pressure plate settlement at each depth measuring point to obtain multi-source synchronous data; based on hydraulic control instructions, average contact pressure of the pressure plate, and vertical velocity of the pressure plate, segment the multi-source synchronous data according to loading, holding, unloading, and rest stages, and calculate the state indicators of the soil at each depth measuring point in each stage; select a consolidation model based on the pressure plate geometry, foundation soil layer distribution, and drainage boundary of the consolidation calculation domain, and jointly invert the consolidation model using the layered pore pressure and pressure plate settlement of the soil at each depth measuring point. Based on the consolidation parameters, the average degree of consolidation, residual settlement, and allowable re-compression time of the soil in the controlled consolidation domain are calculated. Multi-source synchronous data, soil state indices at each depth measuring point, consolidation parameters, and spatial relationships between soil layers and points are input into a spatiotemporal prediction model constrained by consolidation control equations, effective stress relationships, and drainage boundary constraints to generate layered reinforcement indices, effective reinforcement depths, and prediction uncertainties for the soil at each depth measuring point. When the pore pressure dissipation, effective stress recovery rate, and effective reinforcement depth meet the preset safety threshold conditions, the static pressure, loading rate, holding time, unloading rest time, number of cycles, and point sequence or distance of the hydraulic cylinder in the next cycle are determined to control the hydraulic cylinder in a closed loop. The consolidation parameters and spatiotemporal prediction model are updated using the new cycle data until the post-compression test indicators meet the preset requirements.

[0077] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments for IoT devices and media are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0078] The systems, media, and methods provided in this application are one-to-one correspondences. Therefore, the systems and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the systems and media will not be repeated here.

[0079] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0080] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0081] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0082] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0083] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0084] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0085] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0086] 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 process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0087] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for multi-dimensional pore pressure monitoring and pressure consolidation control, characterized in that, The method includes: Within the same static pressure operation unit, multiple depth measuring points are set up within the projection range of the pressure plate and on the outer edge of the pressure plate. The pore water pressure of the soil, the hydraulic pressure of the hydraulic cylinder, the displacement of the hydraulic cylinder and the settlement of the pressure plate at each depth measuring point are collected simultaneously to obtain multi-source synchronous data. Based on hydraulic control commands, average contact pressure of the pressure plate, and vertical speed of the pressure plate, the multi-source synchronous data is segmented according to the stages of loading, holding pressure, unloading, and rest, and the state index of the soil at each depth measuring point in each stage is calculated; wherein, the state index includes excess pore pressure, pore pressure dissipation, effective stress recovery rate, and pore pressure ratio. Based on the geometry of the pressure plate, the distribution of the foundation soil layers, and the drainage boundary of the consolidation calculation domain, a consolidation model is selected. The consolidation parameters are then inverted using the layered pore pressure and pressure plate settlement of the soil at each depth measuring point. Based on these consolidation parameters, the average degree of consolidation, residual settlement, and allowable re-pressure time of the soil in the controlled consolidation domain are calculated. The consolidation parameters include the vertical consolidation coefficient and / or the radial consolidation coefficient and / or the volumetric compressibility coefficient and / or the vertical permeability coefficient and / or the horizontal permeability coefficient. The multi-source synchronous data, the state index of the soil at each depth measuring point, the consolidation parameters, and the spatial relationship between the soil layer and the point are input into a spatiotemporal prediction model constrained by the consolidation control equation, the effective stress relationship, and the drainage boundary to generate the layered reinforcement index, effective reinforcement depth, and prediction uncertainty of the soil at each depth measuring point. When the pore pressure dissipation, the effective stress recovery rate, and the effective reinforcement depth meet the preset safety threshold conditions, the static pressure, loading rate, pressure holding time, unloading rest time, number of cycles, and point sequence or point distance of the hydraulic cylinder in the next cycle are determined to control the hydraulic cylinder in a closed loop. The consolidation parameters and the spatiotemporal prediction model are updated using the new cycle data until the post-pressure detection indicators meet the preset requirements.

2. The multi-dimensional pore pressure monitoring and pressure consolidation control method according to claim 1, characterized in that, Within the same static pressure operation unit, multiple depth measuring points are set up within the projection range of the pressure plate and at its outer edge. Simultaneously, pore water pressure, hydraulic cylinder pressure, hydraulic cylinder displacement, and pressure plate settlement are collected at each depth measuring point to obtain multi-source synchronous data. Specifically, this includes: Based on the intended processing depth and the equivalent diameter of the pressure plate, the central hole pressure test points are arranged within the projection range of the pressure plate, and the radial hole pressure test points are arranged on the outer edge of the pressure plate. The central pore pressure measuring point and the radial pore pressure measuring point located in the same depth range are associated as a depth measuring point group, and each depth measuring point group is distributed at intervals along the depth direction to form the vertical gradient and radial gradient of the pore pressure. The pore water pressure of the soil at each depth is collected synchronously by each depth measuring point group. At the same time, the pressure and flow rate of the hydraulic cylinder working chamber and return oil chamber, the displacement of the hydraulic cylinder, and the settlement of the pressure plate are collected to obtain the multi-source synchronous data.

3. The multi-dimensional pore pressure monitoring and pressure consolidation control method according to claim 1, characterized in that, Based on hydraulic control commands, average contact pressure of the pressure plate, and vertical speed of the pressure plate, the multi-source synchronous data is segmented according to the loading, holding, unloading, and rest stages, specifically including: The average contact pressure of the pressure plate is calculated based on the working chamber pressure of the hydraulic cylinder, the return chamber pressure, and the effective area of ​​the hydraulic cylinder and the effective area of ​​the pressure plate. The vertical velocity of the pressure plate is obtained based on the displacement of the hydraulic cylinder. After recognizing the pressurization command in the hydraulic control command, if the average contact pressure of the pressure plate continues to rise from the baseline, the corresponding time period is marked as the loading stage and the loading start point is recorded. If the average contact pressure of the pressure plate reaches the target pressure and remains continuously within the set tolerance range, the corresponding time period is marked as the pressure holding stage and the pressure holding start point is recorded. After the unloading command in the hydraulic control command is detected, if the average contact pressure of the pressure plate drops to the residual pressure threshold, the corresponding time period is marked as the unloading stage and the unloading end point is recorded. When the vertical speed of the pressure plate returns to stability, the time period from the end of unloading to the next cycle of loading or moving point is marked as the rest stage and the rest start point is recorded. The multi-source synchronous data is segmented based on the loading start point, pressure holding start point, unloading end point, and rest start point, so that each sampled data corresponds to a loading stage, pressure holding stage, unloading stage, or rest stage, respectively.

4. The multi-dimensional pore pressure monitoring and pressure consolidation control method according to claim 3, characterized in that, Calculate the soil state indices at each depth measurement point in each stage, specifically including: Based on the initial pore water pressure collected at each depth point before the static pressure operation and the currently collected pore water pressure, the excess static pore pressure is determined in the loading stage, the pressure holding stage, the unloading stage and the resting stage, and the peak pore pressure and the peak pore pressure time of the depth point are determined in the loading stage and the pressure holding stage. The reference stress increment is determined based on the average contact pressure of the pressure plate and the stress transfer coefficient at the depth measuring point during the current cyclic pressure holding stage. Based on the current superstatic pore pressure and the reference stress increment, the pore pressure ratio and effective stress recovery rate are continuously determined during the loading stage, the pressure holding stage, the unloading stage, and the rest stage. Starting from the peak value of the pore pressure, the pore pressure dissipation degree is determined based on the degree of reduction of the current superstatic pore pressure relative to the peak value of the pore pressure. The pore pressure dissipation degree, the pore pressure ratio, and the effective stress recovery rate at the end of the resting phase are used as state indicators for pressure re-pressurization or point shifting gating.

5. The multi-dimensional pore pressure monitoring and pressure consolidation control method according to claim 2, characterized in that, Based on the geometry of the pressure plate, the distribution of the foundation soil layers, and the drainage boundary of the consolidation calculation domain, a consolidation model is selected. Consolidation parameters are then inverted using the layered pore pressure and pressure plate settlement at each depth measuring point. Based on these consolidation parameters, the average degree of consolidation, residual settlement, and allowable re-pressure time of the soil in the controlled consolidation domain are calculated. Specifically, this includes: Based on the geometry of the pressure plate, the distribution of the foundation soil layers, and the drainage boundary, the controlled consolidation domain and its boundary conditions are determined. Based on the differences in pore pressure response and the degree of soil layer stratification at each depth measuring point, a consolidation model that matches the current drainage conditions and the degree of deformation-seepage coupling is selected from the preset consolidation models. Using the layered pore pressure and platen settlement of the soil at each depth measuring point as observations, a joint residual between the theoretical value of the selected consolidation model and the observations is constructed, and the joint residual is solved under the constraint of consolidation parameters to obtain the consolidation parameters. The average degree of consolidation and residual settlement of the soil in the controlled consolidation domain are calculated based on the consolidation parameters obtained from the inversion. The allowable re-pressure time is determined based on the earliest time when the average degree of consolidation, pore pressure ratio, and residual settlement satisfy the preset gating conditions.

6. The multi-dimensional pore pressure monitoring and pressure consolidation control method according to claim 1, characterized in that, The multi-source synchronous data, the state indices of the soil at each depth measuring point, the consolidation parameters, and the spatial relationship between the soil layer and the measuring point are input into a spatiotemporal prediction model constrained by the consolidation control equation, effective stress relationship, and drainage boundary to generate the layered reinforcement index, effective reinforcement depth, and prediction uncertainty of the soil at each depth measuring point, specifically including: A spatial map is constructed based on the spatial relationship between the depth measuring points, static pressure points, soil interfaces and drainage boundaries. The multi-source synchronous data is divided into dynamic time-series data according to static pressure cycles, and the state indicators, consolidation parameters and static characteristics of the soil at each depth measuring point are obtained. The dynamic time-series data, the static features, and the spatial graph are respectively input into the time-series encoder, static encoder, and graph encoder of the spatiotemporal prediction model, and the outputs of each encoder are fused. In the training or inference of the spatiotemporal prediction model, the residual constraints of the consolidation control equation are constructed based on the selected consolidation model, and the effective stress consistency constraints and drainage boundary constraints are constructed based on the effective stress relationship and the drainage boundary, so that the fused features satisfy the laws of geotechnical physics. The fused features are input into the prediction head of the spatiotemporal prediction model to output the layered reinforcement index and prediction uncertainty of the soil at each depth measuring point. Based on the layered reinforcement index, the pore pressure dissipation, the effective stress recovery rate and the prediction uncertainty, the depth gate quantity and effective reinforcement depth of each depth measuring point are determined.

7. The method for multi-dimensional pore pressure monitoring and pressure consolidation control according to claim 1, characterized in that, When the pore pressure dissipation, effective stress recovery rate, and effective reinforcement depth meet the preset safety threshold conditions, the static pressure, loading rate, holding time, unloading rest time, number of cycles, and point sequence or distance of the hydraulic cylinder in the next cycle are determined to control the hydraulic cylinder in a closed loop. The consolidation parameters and the spatiotemporal prediction model are updated using the new cycle data until the post-pressure detection indicators meet the preset requirements, specifically including: The pore pressure dissipation, the effective stress recovery rate, and the effective reinforcement depth are compared with the corresponding preset safety gating conditions. If the safety gate conditions are not met, the hydraulic cylinder is controlled to perform at least one safety action among pressure holding, unloading, or extended rest, and the updated status indicators and model output are re-acquired for judgment. If the safety gating conditions are met, then within the safe and feasible domain determined by the consolidation model and the spatiotemporal prediction model, optimization is performed using an objective function that includes at least one of the following: reinforcement index deviation, pore pressure exceeding limit, insufficient consolidation degree, residual settlement, differential settlement, construction time and energy consumption. The static pressure, loading rate, pressure holding time, unloading rest time, number of cycles, and point sequence or point distance for the next cycle are determined to achieve closed-loop control of the hydraulic cylinder. The consolidation parameters and the spatiotemporal prediction model are updated using new cyclic data. When the post-compaction test indicators meet the preset requirements, the compaction at the current point is stopped and the point is moved until the post-compaction test indicators meet the preset requirements.

8. The multi-dimensional pore pressure monitoring and pressure consolidation control method according to claim 1, characterized in that, The method further includes: Based on the characteristics of the pore water pressure sensor data at each depth measuring point and the interrelationship between the pore water pressure sensor data, anomaly diagnosis is performed on each pore water pressure sensor to determine the reliability of each pore water pressure sensor. When the confidence level of the pore water pressure sensor is lower than a preset confidence level threshold, the data of the pore water pressure sensor is restricted from participating in the decision-making of the spatiotemporal prediction model and the security gating conditions, and the data of the pore water pressure sensor is replaced by other available data. When the prediction uncertainty of the spatiotemporal prediction model is higher than the preset threshold, the pore water pressure sensor data at the key depth is unavailable, or the calculation module is abnormal, the hydraulic cylinder is controlled to perform a safety action and output a verification prompt. Automatic control is restored after the data or calculation module is recovered and re-verified.

9. A multi-dimensional pore pressure monitoring and pressurized consolidation control device, characterized in that, The device includes: At least one processor; And, a memory communicatively connected to the at least one processor; The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform a method as described in any one of claims 1-8.

10. A non-volatile computer storage medium for multi-dimensional pore pressure monitoring and pressure consolidation control, storing computer-executable instructions, characterized in that, When the computer-executable instructions are executed, they implement a method as described in any one of claims 1-8.

Images