Method and system for evaluating reinforcement effect of dredger fill foundation based on monitoring data inversion

Abstract

The invention provides a dredger fill foundation reinforcement effect evaluation method and system based on monitoring data inversion, and relates to the technical field of dredger fill foundations, and the method comprises the steps: carrying out the multi-level monitoring deployment of a dredger fill foundation construction area according to a dredger fill foundation reinforcement scheme; according to the dredger fill foundation monitoring grid, construction synchronous monitoring of the dredger fill foundation construction area is executed, and multi-degree-of-freedom foundation performance parameter inversion is carried out; performing multi-index reinforcement effect evaluation on the foundation performance parameter inversion layer according to the reinforcement effect evaluation event set; performing abnormal causal tracing on the reinforcement effect evaluation characteristic layer according to reinforcement operation monitoring data; and a dredger fill foundation reinforcement scheme is fed back and adjusted according to the reinforcement effect evaluation graph model. According to the method and the device, the problem of monitoring disjunction in dredger fill foundation reinforcement effect evaluation in the prior art can be solved, data-driven real-time inversion and multi-dimensional comprehensive evaluation are realized, and the technical effect of establishing a comprehensive evaluation system is achieved.

Description

Technical Field

[0001] This application relates to the field of hydraulic reclamation foundation technology, and in particular to a method and system for evaluating the reinforcement effect of hydraulic reclamation foundation based on monitoring data inversion. Background Technology

[0002] With the rapid economic development of coastal areas and the increasing scarcity of land resources, land reclamation using dredged materials has become an important means of expanding construction land. Reclaimed soil typically possesses undesirable engineering characteristics such as high water content, high compressibility, low strength, and loose structure, requiring effective foundation reinforcement to meet construction requirements. Therefore, scientifically and accurately assessing the reinforcement effect and ensuring the long-term stability and safety of the foundation are crucial to the success of such projects.

[0003] Currently, existing technologies for evaluating the effectiveness of dredged and filled soil foundation reinforcement mainly rely on monitoring during construction and inspection after construction, which has a series of systemic defects. First, in the monitoring deployment phase, existing technologies mostly rely on specifications or experience to set up monitoring points, lacking deep integration with specific reinforcement schemes and geological prediction models. This results in the monitoring network failing to accurately capture the most critical deformation and stress areas, leading to monitoring blind spots or wasted resources. Second, at the data analysis level, existing methods typically remain at the level of direct statistics and simple comparison of monitoring data, failing to delve into the key performance parameters within the soil. The evaluation remains at the surface level, making it difficult to reveal the true state of the foundation's inherent reinforcement mechanism. Third, in the effectiveness evaluation stage, existing technologies often use single indicators or isolated thresholds for judgment, lacking a comprehensive and coordinated evaluation system with multiple dimensions and indicators. The evaluation results are one-sided and lack overall perspective; for example, they may only focus on achieving settlement standards while ignoring the potential risks of lateral displacement.

[0004] In summary, existing technologies suffer from several technical problems. These include a disconnect between monitoring deployment and the plan, insufficient depth of data analysis, a one-sided and isolated evaluation system, a lack of intelligent traceability in anomaly diagnosis, and fragmented information across different stages. Consequently, the evaluation of the reinforcement effect of dredged and filled soil foundations is inefficient, has limited accuracy, is difficult to trace, and results in delayed decision-making. This further impacts the real-time management of engineering risks, the dynamic optimization of reinforcement plans, and the overall quality of engineering projects. Summary of the Invention

[0005] The purpose of this application is to provide a method and system for evaluating the reinforcement effect of dredged soil foundations based on monitoring data inversion. This is to solve the technical problems in the existing technology, which are caused by the disconnect between monitoring deployment and scheme, insufficient depth of data analysis, one-sided and isolated evaluation system, lack of intelligent traceability for anomaly diagnosis, and information fragmentation in various links. These problems result in low efficiency, limited accuracy, difficulty in tracing the source, and delayed decision-making in evaluating the reinforcement effect of dredged soil foundations, which further affect the real-time management of engineering risks, the dynamic optimization of reinforcement schemes, and the overall quality of engineering projects.

[0006] In view of the above problems, this application provides a method and system for evaluating the reinforcement effect of dredged soil foundation based on monitoring data inversion.

[0007] Firstly, this application provides a method for evaluating the reinforcement effect of dredged soil foundations based on monitoring data inversion. This method is implemented through a system for evaluating the reinforcement effect of dredged soil foundations based on monitoring data inversion. The method includes: deploying multi-level monitoring in the dredged soil foundation construction area according to the dredged soil foundation reinforcement scheme to construct a dredged soil foundation monitoring grid; performing synchronous construction monitoring of the dredged soil foundation construction area according to the monitoring grid to obtain multi-dimensional monitoring sequences, and performing multi-degree-of-freedom foundation performance parameter inversion based on the multi-dimensional monitoring sequences to construct a foundation performance parameter inversion layer; evaluating the reinforcement effect of the foundation performance parameter inversion layer based on a set of reinforcement effect evaluation events to generate a reinforcement effect evaluation characteristic layer; performing anomaly causal tracing on the reinforcement effect evaluation characteristic layer based on reinforcement operation monitoring data to obtain a reinforcement effect anomaly tracing layer; organizing the foundation performance parameter inversion layer, the reinforcement effect evaluation characteristic layer, and the reinforcement effect anomaly tracing layer to generate a reinforcement effect evaluation diagram model, and adjusting the dredged soil foundation reinforcement scheme based on the reinforcement effect evaluation diagram model.

[0008] Preferably, the method for evaluating the reinforcement effect of dredged soil foundation based on monitoring data inversion further includes: performing multi-characteristic prediction on the dredged soil foundation construction area according to the dredged soil foundation reinforcement scheme to obtain the predicted settlement distribution, predicted displacement distribution, and predicted pore water pressure distribution; deploying settlement monitoring in the dredged soil foundation construction area according to the predicted settlement distribution to generate a settlement monitoring deployment grid; deploying displacement monitoring in the dredged soil foundation construction area according to the predicted displacement distribution to generate a displacement monitoring deployment grid; deploying pore water pressure monitoring in the dredged soil foundation construction area according to the predicted pore water pressure distribution to generate a pore water pressure monitoring deployment grid; and fusing the settlement monitoring deployment grid, the displacement monitoring deployment grid, and the pore water pressure monitoring deployment grid to generate the dredged soil foundation monitoring grid.

[0009] Preferably, the method for evaluating the reinforcement effect of dredged soil foundation based on monitoring data inversion further includes: performing compression characteristic inversion on the dredged soil foundation construction area based on each settlement monitoring parameter in the settlement monitoring sequence to obtain inversion results of each settlement characteristic; performing bearing capacity characteristic inversion on the dredged soil foundation construction area based on each displacement monitoring parameter in the displacement monitoring sequence to obtain inversion results of each displacement characteristic; performing consolidation characteristic inversion on the dredged soil foundation construction area based on each pore water pressure monitoring parameter in the pore water pressure monitoring sequence to obtain inversion results of each pressure characteristic; and encapsulating the inversion results of each settlement characteristic, each displacement characteristic, and each pressure characteristic as the foundation performance parameter inversion layer.

[0010] Preferably, the method for evaluating the reinforcement effect of dredged and filled soil foundations based on monitoring data inversion further includes: classifying the reinforcement effect evaluation into multiple indicators according to the reinforcement effect evaluation event set to obtain a settlement quality evaluation event set, a bearing capacity evaluation event set, and a consolidation quality evaluation event set; evaluating the settlement quality of each settlement characteristic inversion result according to the settlement quality evaluation event set to generate a settlement quality evaluation sequence; evaluating the bearing capacity of each displacement characteristic inversion result according to the bearing capacity evaluation event set to generate a bearing capacity evaluation sequence; evaluating the consolidation quality of each pressure characteristic inversion result according to the consolidation quality evaluation event set to generate a consolidation quality evaluation sequence; and encapsulating the settlement quality evaluation sequence, the bearing capacity evaluation sequence, and the consolidation quality evaluation sequence into the reinforcement effect evaluation characteristic layer.

[0011] Preferably, the method for evaluating the reinforcement effect of dredged and filled soil foundations based on monitoring data inversion further includes: performing multi-scale perturbation based on the settlement quality assessment event set to obtain multiple settlement quality assessment spaces; performing iterative supervised training on neural network models based on the multiple settlement quality assessment spaces to obtain multiple settlement quality assessment models that satisfy the convergence condition of assessment loss; performing output feature fusion training based on the multiple settlement quality assessment models to obtain a settlement quality fusion model; constructing a settlement quality evaluator using the multiple settlement quality assessment models as first-level nodes of settlement quality assessment and the settlement quality fusion model as a second-level node of settlement quality assessment; and inputting the inversion results of each settlement characteristic into the settlement quality evaluator to obtain the settlement quality assessment sequence.

[0012] Preferably, the method for evaluating the reinforcement effect of dredged and filled soil foundation based on monitoring data inversion further includes: performing multi-dimensional anomaly detection on the reinforcement effect evaluation characteristic layer according to the expected reinforcement effect conditions to obtain a settlement quality anomaly feature set, a bearing capacity anomaly feature set, and a consolidation quality anomaly feature set; performing multi-level causal tracing on the settlement quality anomaly feature set according to the reinforcement operation monitoring data to establish a settlement quality anomaly tracing layer; performing multi-level causal tracing on the bearing capacity anomaly feature set according to the reinforcement operation monitoring data to establish a bearing capacity anomaly tracing layer; performing multi-level causal tracing on the consolidation quality anomaly feature set according to the reinforcement operation monitoring data to establish a consolidation quality anomaly tracing layer; and encapsulating the settlement quality anomaly tracing layer, the bearing capacity anomaly tracing layer, and the consolidation quality anomaly tracing layer into the reinforcement effect anomaly tracing layer.

[0013] Preferably, the method for evaluating the reinforcement effect of dredged and filled soil foundation based on monitoring data inversion further includes: performing multi-parameter correlation analysis on each settlement quality anomaly feature in the settlement quality anomaly feature set according to the reinforcement operation monitoring data to obtain a correlation sequence of each anomaly operation; tracing intermediate factors for each settlement quality anomaly feature based on the correlation sequence of each anomaly operation according to the reinforcement operation monitoring data to obtain a group of intermediate factors for each anomaly; tracing basic factors for each group of intermediate factors based on the correlation sequence of each anomaly operation according to the reinforcement operation monitoring data to obtain a group of basic factors for each anomaly; and organizing causal paths according to the settlement quality anomaly feature set, the group of intermediate factors for each anomaly, and the group of basic factors for each anomaly to generate the settlement quality anomaly tracing layer.

[0014] Preferably, the method for evaluating the reinforcement effect of dredged and filled soil foundation based on monitoring data inversion further includes: the multidimensional monitoring sequence includes a settlement monitoring sequence, a displacement monitoring sequence, and a pore water pressure monitoring sequence.

[0015] Preferably, the method for evaluating the reinforcement effect of dredged and filled soil foundation based on monitoring data inversion further includes: the expected conditions for reinforcement effect include expected settlement quality, expected bearing capacity, and expected consolidation quality.

[0016] Secondly, this application also provides a system for evaluating the reinforcement effect of dredged soil foundations based on monitoring data inversion, used to execute the method for evaluating the reinforcement effect of dredged soil foundations based on monitoring data inversion as described in the first aspect, including: a dredged soil foundation monitoring grid construction module, used to deploy multi-level monitoring of the dredged soil foundation construction area according to the dredged soil foundation reinforcement scheme, and construct a dredged soil foundation monitoring grid; and a foundation performance parameter inversion layer construction module, used to perform synchronous monitoring of the construction area of ​​the dredged soil foundation according to the dredged soil foundation monitoring grid, obtain multi-dimensional monitoring sequences, and perform multi-degree-of-freedom foundation performance parameter inversion based on the multi-dimensional monitoring sequences, and construct a foundation performance parameter inversion layer. The system comprises: a data inversion layer; a reinforcement effect evaluation characteristic layer generation module, used to perform multi-index reinforcement effect evaluation on the foundation performance parameter inversion layer based on the reinforcement effect evaluation event set, and generate a reinforcement effect evaluation characteristic layer; a reinforcement effect anomaly tracing layer acquisition module, used to perform anomaly causal tracing on the reinforcement effect evaluation characteristic layer based on reinforcement operation monitoring data, and obtain a reinforcement effect anomaly tracing layer; and a reinforcement effect evaluation diagram model generation module, used to organize the foundation performance parameter inversion layer, the reinforcement effect evaluation characteristic layer, and the reinforcement effect anomaly tracing layer, generate a reinforcement effect evaluation diagram model, and adjust the hydraulic fill foundation reinforcement scheme based on the reinforcement effect evaluation diagram model.

[0017] The technical solution provided in this application has at least the following technical effects or advantages: by achieving the technical goals of data-driven, real-time inversion, multi-dimensional comprehensive evaluation, intelligent root cause diagnosis and dynamic closed-loop feedback optimization of the reinforcement effect of dredged and filled soil foundations, it achieves the technical effects of improving the scientific nature and data representativeness of monitoring deployment, deepening the understanding and quantitative evaluation of the inherent engineering state of the foundation, constructing a comprehensive evaluation system with multi-indicator synergy, and realizing rapid and accurate tracing of abnormal problems.

[0018] The above description is merely an overview of the technical solution of this application. To enable a clearer understanding of the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the evaluation method for the reinforcement effect of dredged soil foundation based on monitoring data inversion in this application.

[0021] Figure 2 This is a schematic diagram of the structure of the dredged soil foundation reinforcement effect evaluation system based on monitoring data inversion in this application.

[0022] Figure labeling: Module 1 for monitoring grid construction of dredged and filled soil foundation, Module 2 for construction of foundation performance parameter inversion layer, Module 3 for generation of reinforcement effect evaluation characteristic layer, Module 4 for acquisition of reinforcement effect anomaly tracing layer, and Module 5 for generation of reinforcement effect evaluation map model. Detailed Implementation

[0023] This application provides a method and system for evaluating the effectiveness of dredged soil foundation reinforcement based on monitoring data inversion. It addresses the technical problems in existing technologies, such as the disconnect between monitoring deployment and implementation plans, insufficient depth of data analysis, a fragmented and isolated evaluation system, lack of intelligent traceability for anomaly diagnosis, and information fragmentation across different stages. These issues lead to low efficiency, limited accuracy, difficulty in tracing the source of problems, and delayed decision-making, further impacting real-time risk management, dynamic optimization of reinforcement plans, and the overall quality of engineering projects. The application achieves the technical goals of data-driven, real-time inversion, multi-dimensional comprehensive evaluation, intelligent root cause diagnosis, and dynamic closed-loop feedback optimization of dredged soil foundation reinforcement effectiveness. This results in improved scientific rigor and data representativeness of monitoring deployment, deepened understanding and quantitative assessment of the inherent engineering state of the foundation, the construction of a comprehensive evaluation system with multi-indicator synergy, and rapid and accurate tracing of anomalies.

[0024] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0025] Example 1, please refer to the appendix. Figure 1 This application provides a method for evaluating the reinforcement effect of dredged soil foundations based on monitoring data inversion, which is applied to a system for evaluating the reinforcement effect of dredged soil foundations based on monitoring data inversion. The method specifically includes the following steps: Based on the reinforcement plan for the dredged soil foundation, a multi-level monitoring deployment was carried out in the construction area of ​​the dredged soil foundation, and a monitoring grid for the dredged soil foundation was constructed.

[0026] Furthermore, this application also includes: performing multi-characteristic prediction on the construction area of ​​the dredged soil foundation according to the dredged soil foundation reinforcement scheme to obtain the predicted settlement distribution, the predicted displacement distribution, and the predicted pore water pressure distribution; deploying settlement monitoring in the construction area of ​​the dredged soil foundation according to the predicted settlement distribution to generate a settlement monitoring deployment grid; deploying displacement monitoring in the construction area of ​​the dredged soil foundation according to the predicted displacement distribution to generate a displacement monitoring deployment grid; deploying pore water pressure monitoring in the construction area of ​​the dredged soil foundation according to the predicted pore water pressure distribution to generate a pore water pressure monitoring deployment grid; and fusing the settlement monitoring deployment grid, the displacement monitoring deployment grid, and the pore water pressure monitoring deployment grid to generate the dredged soil foundation monitoring grid.

[0027] Specifically, based on the dredged fill foundation reinforcement scheme—that is, the engineering reinforcement plan designed for weak dredged fill foundations, including construction methods, parameters, and steps—multi-characteristic predictions are performed on the dredged fill foundation construction area, i.e., the geographical area where the reinforcement project will be implemented. Multi-characteristic prediction refers to estimating the possible settlement, horizontal displacement, and pore water pressure changes in the construction area during the reinforcement process through numerical simulation or empirical formulas, thereby obtaining the predicted distributions of settlement, displacement, and pore water pressure. The predicted settlement distribution represents the spatial variation of the vertical settlement of the foundation at different locations; the predicted displacement distribution represents the spatial variation of the horizontal movement of the foundation; and the predicted pore water pressure distribution represents the spatial variation of the water pressure value within the soil.

[0028] Secondly, based on the predicted settlement distribution, settlement monitoring is deployed in the construction area of ​​the dredged soil foundation. Settlement monitoring deployment refers to the process of planning and arranging settlement measuring instruments such as settlement plates or leveling points, aiming to generate a settlement monitoring deployment grid, that is, a monitoring point structure optimized according to the predicted settlement characteristics, to ensure dense deployment of points in areas with large or significant predicted settlement, so as to efficiently capture the settlement data of the foundation.

[0029] Then, based on the predicted displacement distribution, displacement monitoring is deployed in the construction area of ​​the dredged soil foundation. Displacement monitoring deployment refers to arranging the positions of displacement measuring equipment such as inclinometers or total stations to generate a displacement monitoring deployment grid. That is, based on the spatial characteristics of the predicted displacement, monitoring points are set in key areas to comprehensively record the horizontal deformation of the foundation during the construction process.

[0030] Next, based on the predicted distribution of pore water pressure, pore water pressure monitoring was deployed in the construction area of ​​the dredged soil foundation. Pore water pressure monitoring deployment refers to the process of setting up sensors such as pore water pressure gauges to form a pore water pressure monitoring deployment grid. That is, monitoring points are set up in areas where the predicted water pressure changes are significant, such as near the drainage boundary or loading center, to track the dynamic dissipation of water pressure during the consolidation process.

[0031] Finally, by integrating the settlement monitoring deployment grid, displacement monitoring deployment grid, and pore water pressure monitoring deployment grid, that is, by spatially integrating and coordinating the three monitoring point networks, a monitoring grid for the dredged soil foundation is generated to cover the entire construction area. This grid can simultaneously collect multi-dimensional monitoring data, avoid duplication or omission of points, and provide a comprehensive and efficient data collection foundation for subsequent foundation performance inversion.

[0032] Based on the monitoring grid of the dredged soil foundation, synchronous monitoring of the construction area of ​​the dredged soil foundation is performed to obtain a multi-dimensional monitoring sequence. Based on the multi-dimensional monitoring sequence, multi-degree-of-freedom foundation performance parameters are inverted to construct a foundation performance parameter inversion layer.

[0033] Furthermore, this application also includes: performing compression characteristic inversion on the construction area of ​​the dredged soil foundation based on each settlement monitoring parameter in the settlement monitoring sequence to obtain inversion results of each settlement characteristic; performing bearing capacity characteristic inversion on the construction area of ​​the dredged soil foundation based on each displacement monitoring parameter in the displacement monitoring sequence to obtain inversion results of each displacement characteristic; performing consolidation characteristic inversion on the construction area of ​​the dredged soil foundation based on each pore water pressure monitoring parameter in the pore water pressure monitoring sequence to obtain inversion results of each pressure characteristic; and encapsulating the inversion results of each settlement characteristic, the inversion results of each displacement characteristic, and the inversion results of each pressure characteristic into the foundation performance parameter inversion layer.

[0034] Furthermore, this application also includes: the multidimensional monitoring sequence includes a settlement monitoring sequence, a displacement monitoring sequence, and a pore water pressure monitoring sequence.

[0035] Specifically, based on the monitoring grid for dredged soil foundations, synchronous monitoring is conducted in the construction area of ​​the dredged soil foundation, i.e., the geographical area where the reinforcement project is implemented. Synchronous construction monitoring refers to the process of collecting various types of data in real time during the reinforcement operation, thereby obtaining a multi-dimensional monitoring sequence. The multi-dimensional monitoring sequence is a systematic record, in chronological order, of various types of field data collected through the deployed monitoring network during the dredged soil foundation reinforcement construction. Specifically, it includes settlement monitoring sequences, displacement monitoring sequences, and pore water pressure monitoring sequences. The settlement monitoring sequence is a time-series data series composed of vertical deformation data continuously measured and recorded at a certain time frequency by settlement monitoring points arranged on the foundation surface. The settlement monitoring parameters in the settlement monitoring sequence directly reflect the compression and settlement process of the foundation soil under load. The displacement monitoring sequence is a time-series data series composed of horizontal movement data measured and recorded at predetermined intervals by displacement monitoring points arranged inside or on the surface of the foundation using equipment such as inclinometers or total stations. Displacement monitoring parameters in a displacement monitoring sequence are used to reveal the potential lateral deformation or slippage trends of the foundation soil under the influence of construction. A pore water pressure monitoring sequence refers to a time-series data series composed of pore water pressure sensors embedded in the foundation soil, continuously or intermittently measuring and recording the water pressure values ​​in the soil. Pore water pressure monitoring parameters in the pore water pressure monitoring sequence are used to characterize the dynamic state of pore water pressure dissipation and soil consolidation development during the foundation reinforcement process.

[0036] Based on the settlement monitoring parameters of each monitoring point in the settlement monitoring sequence, the compression characteristics of the dredged soil foundation construction area are inverted. Settlement monitoring parameters refer to the measured values ​​of the vertical deformation of the foundation. Compression characteristic inversion is to calculate the compressibility index of the foundation soil, such as the compression modulus or compression coefficient, by analyzing the settlement data, and then obtain the inversion results of each settlement characteristic to reflect the compressibility performance of the foundation.

[0037] Next, based on the displacement monitoring parameters of each monitoring point in the displacement monitoring sequence, the bearing capacity characteristics of the dredged soil foundation construction area are inverted. The displacement monitoring parameters refer to the measured values ​​of the horizontal movement of the foundation. The bearing capacity characteristic inversion is to evaluate the stability and bearing capacity of the foundation by analyzing the displacement data, such as inverting the ultimate bearing capacity or safety factor of the foundation, thereby obtaining the inversion results of each displacement characteristic to characterize the bearing capacity of the foundation.

[0038] Then, based on the pore water pressure monitoring parameters at each monitoring point in the pore water pressure monitoring sequence, the consolidation characteristics of the dredged soil foundation construction area are inverted. Pore water pressure monitoring parameters refer to the measured values ​​of water pressure in the soil. Consolidation characteristic inversion involves analyzing pore water pressure data to deduce consolidation process indices of the foundation, such as the consolidation coefficient or drainage rate, and then obtaining the inversion results of various pressure characteristics to describe the consolidation characteristics of the foundation.

[0039] Finally, the inversion results of each settlement characteristic, displacement characteristic, and pressure characteristic are encapsulated and integrated into a unified structured dataset to form a foundation performance parameter inversion layer. This integrates the key foundation performance parameters obtained from monitoring data, providing fundamental data support for subsequent reinforcement effect evaluation.

[0040] Based on the set of reinforcement effect evaluation events, the foundation performance parameter inversion layer is evaluated using multiple indicators to generate a reinforcement effect evaluation characteristic layer.

[0041] Furthermore, this application also includes: classifying the reinforcement effect assessment into multiple indicators based on the reinforcement effect assessment event set to obtain a settlement quality assessment event set, a bearing capacity assessment event set, and a consolidation quality assessment event set; performing settlement quality assessment on the inversion results of each settlement characteristic based on the settlement quality assessment event set to generate a settlement quality assessment sequence; performing bearing capacity assessment on the inversion results of each displacement characteristic based on the bearing capacity assessment event set to generate a bearing capacity assessment sequence; performing consolidation quality assessment on the inversion results of each pressure characteristic based on the consolidation quality assessment event set to generate a consolidation quality assessment sequence; and encapsulating the settlement quality assessment sequence, the bearing capacity assessment sequence, and the consolidation quality assessment sequence into the reinforcement effect assessment characteristic layer.

[0042] Furthermore, this application also includes: performing multi-scale perturbation based on the settlement quality assessment event set to obtain multiple settlement quality assessment spaces; performing iterative supervised training on neural network models based on the multiple settlement quality assessment spaces to obtain multiple settlement quality assessment models that satisfy the assessment loss convergence condition; performing output feature fusion training based on the multiple settlement quality assessment models to obtain a settlement quality fusion model; constructing a settlement quality evaluator using the multiple settlement quality assessment models as first-level nodes of settlement quality assessment and the settlement quality fusion model as a second-level node of settlement quality assessment; and inputting the inversion results of each settlement characteristic into the settlement quality evaluator to obtain the settlement quality assessment sequence.

[0043] Specifically, the reinforcement effect evaluation event set consists of pre-defined criteria and thresholds used to quantify the effectiveness of foundation reinforcement. A multi-index reinforcement effect evaluation classification is then performed based on this event set. This classification systematically divides the overall evaluation task into different subcategories according to the nature and purpose of the evaluation indicators, thereby obtaining settlement quality evaluation event sets, bearing capacity evaluation event sets, and consolidation quality evaluation event sets. The settlement quality evaluation event set is a set of evaluation criteria defined for the control effect of vertical deformation of the foundation; the bearing capacity evaluation event set is a set of evaluation criteria defined for the stability and load-bearing capacity of the foundation; and the consolidation quality evaluation event set is a set of evaluation criteria defined for the drainage and consolidation process of the foundation.

[0044] Next, multi-scale perturbation is implemented based on the settlement quality assessment event set. Multi-scale perturbation refers to generating multiple independent yet related assessment perspectives by changing the scale parameters of the assessment criteria or introducing variable transformations at different levels. Each scale perturbation forms a settlement quality assessment space, which is the data feature domain or parameter environment used to train and validate the assessment model, determined by specific perturbation parameters.

[0045] Then, for the multiple settlement quality assessment spaces obtained, iterative supervised training of neural network models is performed. A neural network model is a computational architecture composed of multiple interconnected nodes, capable of learning complex mapping relationships between inputs and outputs. Iterative supervised training refers to continuously adjusting the model's internal parameters using labeled training data through multiple iterations of forward and backward propagation. The evaluation loss convergence condition refers to the threshold at which training stops when the loss function value, used to measure the model's prediction error, decreases to a stable and small state. Through iterative supervised training, multiple settlement quality assessment models are obtained, each adapted to its corresponding settlement quality assessment space.

[0046] Furthermore, multiple settlement quality assessment models are used for output feature fusion training. Output feature fusion training refers to using the output results or intermediate layer features of each basic model as new inputs to train a high-level model to achieve information integration and decision optimization. The resulting settlement quality fusion model can comprehensively weigh the judgments of multiple basic models, improving the accuracy and robustness of the assessment.

[0047] Subsequently, multiple settlement quality assessment models were used as primary nodes for settlement quality assessment. Primary nodes are model units that directly receive the raw inversion data and perform preliminary assessments. A fusion settlement quality model was used as a secondary node for settlement quality assessment. Secondary nodes are model units that receive the outputs of the primary nodes and perform the final comprehensive judgment. By hierarchically connecting the primary and secondary nodes, a settlement quality evaluator was constructed, creating an automated assessment device with a hierarchical structure.

[0048] Subsequently, the settlement characteristic inversion results—that is, the specific parameter values ​​reflecting the foundation compressibility derived from the settlement monitoring data—are input into the constructed settlement quality evaluator. The settlement quality evaluator processes and calculates each input parameter to ultimately obtain a settlement quality evaluation sequence, which is a data column composed of a quantitative evaluation value corresponding to each settlement characteristic inversion result, arranged in sequence.

[0049] Multi-scale perturbations are applied to the event set for carrying capacity assessment, introducing variable transformations at different levels to obtain multiple carrying capacity assessment spaces. Then, neural network models are iteratively trained under supervised supervision using these multiple assessment spaces. Labeled training data is used to continuously adjust the model's internal parameters through multiple iterations of forward and backward propagation, resulting in multiple settlement quality assessment models. These models are then used for output feature fusion training. The outputs of each base model or intermediate layer features are used as new inputs to train a high-level model for information integration and decision optimization, resulting in a carrying capacity fusion model. Finally, using the multiple carrying capacity assessment models as first-level nodes and the fusion model as second-level nodes, a hierarchical connection between the first and second-level nodes is established to construct a carrying capacity evaluator—that is, an automated assessment device with a hierarchical structure. Subsequently, the inversion results of each bearing characteristic, that is, the specific parameter values ​​reflecting the foundation compression performance derived from the bearing monitoring data, are input into the constructed bearing quality evaluator to process and calculate each input parameter, and finally obtain the bearing quality evaluation sequence, that is, a data column composed of a quantitative evaluation value corresponding to each bearing characteristic inversion result arranged in sequence.

[0050] Simultaneously, multi-scale perturbations are applied to the consolidation quality assessment event set, introducing variable transformations at different levels to obtain multiple consolidation quality assessment spaces. Then, neural network models are iteratively trained under supervised supervision using these multiple consolidation quality assessment spaces. Using labeled training data, the internal parameters of the models are continuously adjusted through multiple iterations of forward and backward propagation, resulting in multiple consolidation quality assessment models. Next, output feature fusion training is performed using these multiple consolidation quality assessment models. The output results of each basic model or intermediate layer features are used as new inputs to train a high-level model to achieve information integration and decision optimization, resulting in a consolidation quality fusion model. Finally, using the multiple consolidation quality assessment models as first-level nodes and the consolidation quality fusion model as second-level nodes, a consolidation quality evaluator is constructed by hierarchically connecting the first-level and second-level nodes, thus building an automated assessment device with a hierarchical structure. Subsequently, the inversion results of each consolidation characteristic, that is, the specific parameter values ​​reflecting the foundation compression performance derived from the consolidation monitoring data, are input into the constructed consolidation quality evaluator to process and calculate each input parameter, and finally obtain the consolidation quality evaluation sequence, that is, obtain a data column composed of a quantitative evaluation value corresponding to each consolidation characteristic inversion result arranged in sequence.

[0051] Finally, the settlement quality assessment sequence, bearing capacity assessment sequence, and consolidation quality assessment sequence are encapsulated, integrated and stored according to a predetermined data structure, and a reinforcement effect assessment characteristic layer is generated. This layer integrates multi-dimensional and multi-index quantitative assessment results, characterizing the quality status of the foundation reinforcement project in terms of settlement control, bearing capacity improvement, and consolidation process.

[0052] Based on the reinforcement operation monitoring data, anomaly causal tracing is performed on the reinforcement effect evaluation characteristic layer to obtain the reinforcement effect anomaly tracing layer.

[0053] Furthermore, this application also includes: performing multi-dimensional anomaly detection on the reinforcement effect evaluation characteristic layer according to the expected reinforcement effect conditions to obtain a settlement quality anomaly feature set, a bearing capacity anomaly feature set, and a consolidation quality anomaly feature set; performing multi-level causal tracing on the settlement quality anomaly feature set according to the reinforcement operation monitoring data to establish a settlement quality anomaly tracing layer; performing multi-level causal tracing on the bearing capacity anomaly feature set according to the reinforcement operation monitoring data to establish a bearing capacity anomaly tracing layer; performing multi-level causal tracing on the consolidation quality anomaly feature set according to the reinforcement operation monitoring data to establish a consolidation quality anomaly tracing layer; and encapsulating the settlement quality anomaly tracing layer, the bearing capacity anomaly tracing layer, and the consolidation quality anomaly tracing layer into the reinforcement effect anomaly tracing layer.

[0054] Furthermore, this application also includes: the expected conditions for the reinforcement effect include the expected settlement quality assessment, the expected bearing capacity assessment, and the expected consolidation quality assessment.

[0055] Furthermore, this application also includes: performing multi-parameter correlation analysis on each settlement quality anomaly feature in the settlement quality anomaly feature set based on the reinforcement operation monitoring data to obtain a correlation sequence for each anomaly operation; tracing intermediate factors for each settlement quality anomaly feature based on the correlation sequence for each anomaly operation and the reinforcement operation monitoring data to obtain a group of intermediate factors for each anomaly; tracing basic factors for each group of intermediate factors based on the correlation sequence for each anomaly operation and the reinforcement operation monitoring data to obtain a group of basic factors for each anomaly; and organizing causal paths based on the settlement quality anomaly feature set, the group of intermediate factors for each anomaly, and the group of basic factors for each anomaly to generate the settlement quality anomaly tracing layer.

[0056] Specifically, the expected conditions for reinforcement effects are pre-set quantitative standards and target thresholds used as benchmarks for evaluating the final effectiveness of reinforced reclamation foundation projects. These conditions encompass settlement quality assessment expectations, bearing capacity assessment expectations, and consolidation quality assessment expectations. Settlement quality assessment expectations are targets set for controlling the vertical deformation of the foundation, specifying the allowable range or stability standard for settlement or differential settlement in various areas of the foundation after reinforcement. When the actual settlement quality assessment value obtained from the evaluation fails to meet this pre-set expectation, the assessment point is deemed abnormal, and the corresponding characteristic information is added to the settlement quality anomaly feature set for further analysis. Simultaneously, bearing capacity assessment expectations are targets set for foundation stability and load-bearing capacity, specifying the required bearing capacity safety factor or deformation resistance capacity after reinforcement. If the actual obtained bearing capacity assessment value is lower than this expected value, it indicates an anomaly in the bearing performance at that location, and this anomaly will be included in the bearing capacity anomaly feature set. Furthermore, the consolidation quality assessment expectation is a target set for the process and effect of foundation drainage consolidation, specifying the design requirements that parameters such as soil consolidation degree, pore water pressure dissipation degree, or consolidation completion time must meet. In actual assessment, if the calculated consolidation quality assessment value does not meet this expectation, it indicates that there is an anomaly in the consolidation process, and this anomaly will be collected into the consolidation quality anomaly feature set.

[0057] Based on the expected conditions of the reinforcement effect, multidimensional anomaly detection is performed on the reinforcement effect evaluation characteristic layer to identify abnormal values ​​or abnormal patterns in the evaluation results that deviate from the expected conditions. Settlement quality anomaly feature set, bearing capacity anomaly feature set, and consolidation quality anomaly feature set are obtained respectively. These are the sets of evaluation features marked as abnormal in their respective dimensions, which are used to indicate the problem areas or indicators in the reinforcement effect.

[0058] Next, the reinforcement operation monitoring data are data records collected in real time during the foundation reinforcement construction process, reflecting various construction operation parameters and statuses. Based on the reinforcement operation monitoring data, a multi-level causal tracing of the settlement quality anomaly feature set is performed to establish a settlement quality anomaly tracing layer. Specifically, this includes performing multi-parameter correlation analysis on each settlement quality anomaly feature within the settlement quality anomaly feature set, i.e., each identified settlement assessment anomaly point, based on the reinforcement operation monitoring data. Multi-parameter correlation analysis refers to calculating the statistical correlation between anomaly features and multiple construction monitoring parameters, thereby obtaining a correlation sequence for each anomaly operation, i.e., a list of operation parameters related to a specific anomaly feature, sorted by correlation strength.

[0059] Then, based on the correlation sequence of each abnormal operation, intermediate factors are traced for each settlement quality anomaly characteristic according to the monitoring data of the reinforcement operation. Tracing intermediate factors refers to analyzing intermediate variables or engineering conditions that are directly related to the strongly correlated operation parameters and affect the foundation state, such as the effectiveness of drainage paths or the range of soil disturbance, so as to obtain the intermediate factor group of each anomaly, that is, the set of intermediate influencing factors corresponding to each anomaly characteristic.

[0060] Furthermore, based on the correlation sequence of each abnormal operation, the basic factors of each abnormal intermediate factor group are traced according to the monitoring data of the reinforcement operation. The basic factor tracing refers to the in-depth exploration of the fundamental construction reasons that lead to the changes in intermediate factors, such as inaccurate setting of construction equipment parameters, non-compliance of material specifications, or deviation in process execution, so as to obtain the basic factor group of each abnormality, that is, the set of original construction factors to which each abnormal feature is traced.

[0061] Subsequently, causal paths were organized based on the set of settlement quality anomaly characteristics, the intermediate factor groups of each anomaly, and the basic factor groups of each anomaly. Causal path organization refers to linking and organizing the anomaly characteristics, intermediate factors, and basic factors according to their logical causal relationships to form a clear fault chain, thereby generating a settlement quality anomaly tracing layer that records the complete tracing path from the manifestation of settlement anomalies to the underlying construction causes.

[0062] Simultaneously, based on the reinforcement operation monitoring data, multi-parameter correlation analysis is performed on each load-bearing quality anomaly feature within the load-bearing quality anomaly feature set—that is, each identified load-bearing assessment anomaly point—to calculate the statistical correlation degree between the anomaly feature and multiple construction monitoring parameters, thereby obtaining the correlation sequence of each anomaly operation. Then, based on the correlation sequence of each anomaly operation, intermediate factors are traced for each load-bearing quality anomaly feature according to the reinforcement operation monitoring data. This involves analyzing intermediate variables or engineering conditions directly related to strongly correlated operation parameters and affecting the foundation state, thereby obtaining the intermediate factor groups of each anomaly. Further, based on the correlation sequence of each anomaly operation, basic factors are traced for each intermediate factor group according to the reinforcement operation monitoring data, thereby obtaining the basic factor groups of each anomaly—that is, the set of original construction factors traced back to each anomaly feature. Subsequently, causal paths are organized based on the load-bearing quality anomaly feature set, the intermediate factor groups of each anomaly, and the basic factor groups of each anomaly. These paths are linked and organized according to logical causal relationships to form a clear fault chain, thereby generating a load-bearing quality anomaly tracing layer that records the complete tracing path from the manifestation of load-bearing anomalies to the underlying construction causes.

[0063] Accordingly, based on the reinforcement operation monitoring data, multi-parameter correlation analysis is performed on each consolidation quality anomaly feature within the consolidation quality anomaly feature set, i.e., each identified consolidation assessment anomaly point. The statistical correlation between the anomaly feature and multiple construction monitoring parameters is calculated to obtain the correlation sequence of each anomaly operation. Then, based on the correlation sequence of each anomaly operation, intermediate factors are traced for each consolidation quality anomaly feature according to the reinforcement operation monitoring data. This involves analyzing intermediate variables or engineering conditions directly related to strongly correlated operation parameters and affecting the foundation state, thereby obtaining the intermediate factor groups for each anomaly. Further, based on the correlation sequence of each anomaly operation, basic factors are traced for each intermediate factor group according to the reinforcement operation monitoring data, thereby obtaining the basic factor groups for each anomaly, i.e., the original set of construction factors traced back to each anomaly feature. Afterwards, causal paths are organized based on the consolidation quality anomaly feature set, the intermediate factor groups, and the basic factor groups. These are linked and organized according to logical causal relationships to form a clear fault chain, thus generating a consolidation quality anomaly tracing layer that records the complete tracing path from the manifestation of consolidation anomalies to the underlying construction causes.

[0064] Finally, the settlement quality anomaly tracing layer, bearing capacity anomaly tracing layer, and consolidation quality anomaly tracing layer are encapsulated, merged and integrated according to a unified format to generate a reinforcement effect anomaly tracing layer. This layer fully contains detailed causal tracing information on anomalies in settlement, bearing capacity, and consolidation, providing a clear diagnostic basis for feedback adjustment of reinforcement schemes.

[0065] The foundation performance parameter inversion layer, the reinforcement effect evaluation characteristic layer, and the reinforcement effect anomaly tracing layer are organized to generate a reinforcement effect evaluation map model, and the reinforcement scheme of the dredged soil foundation is adjusted based on the reinforcement effect evaluation map model.

[0066] Specifically, the foundation performance parameter inversion layer, reinforcement effect evaluation characteristic layer, and reinforcement effect anomaly tracing layer are systematically organized and arranged, and merged, linked, and integrated according to their inherent logical relationships and data structures. A reinforcement effect evaluation graphical model is generated based on the results of this organization and integration. This model is a graph-based data model where nodes represent various entities and states, from original monitoring data and inversion parameters to evaluation results and anomaly causes, while edges express various logical relationships such as data derivation, evaluation judgment, and causal tracing. This allows for a global and visual representation of the overall foundation reinforcement effect and its underlying causal chain.

[0067] Subsequently, based on the generated reinforcement effect evaluation model, feedback adjustments are made to the reinforcement scheme for the dredged soil foundation. Feedback adjustment refers to the targeted and scientific adjustment and optimization of construction parameters, procedures, or local measures in the original reinforcement scheme based on the distribution of reinforcement effectiveness, abnormal locations, and their root causes revealed by the reinforcement effect evaluation model. For example, if the reinforcement effect evaluation model identifies areas with insufficient bearing capacity and their corresponding excessively large drainage board spacing, this parameter can be adjusted in subsequent construction or similar designs.

[0068] In summary, the method for evaluating the reinforcement effect of dredged soil foundation based on monitoring data inversion provided in this application has the following technical effects: by achieving the technical goals of data-driven, real-time inversion, multi-dimensional comprehensive evaluation, intelligent root cause diagnosis, and dynamic closed-loop feedback optimization of the reinforcement effect of dredged soil foundation, it achieves the technical effects of improving the scientific nature and data representativeness of monitoring deployment, deepening the understanding and quantitative evaluation of the inherent engineering state of the foundation, constructing a comprehensive evaluation system with multi-indicator synergy, and realizing rapid and accurate tracing of abnormal problems.

[0069] Example 2: Based on the same inventive concept as the method for evaluating the reinforcement effect of dredged fill foundations based on monitoring data inversion in the foregoing examples, this application also provides a system for evaluating the reinforcement effect of dredged fill foundations based on monitoring data inversion. Please refer to the appendix. Figure 2 The system includes: a monitoring grid construction module 1 for dredged soil foundation, used to deploy multi-level monitoring of the dredged soil foundation construction area according to the dredged soil foundation reinforcement scheme, and construct a dredged soil foundation monitoring grid; a foundation performance parameter inversion layer construction module 2, used to perform synchronous monitoring of the dredged soil foundation construction area according to the monitoring grid, obtain multi-dimensional monitoring sequences, and perform multi-degree-of-freedom foundation performance parameter inversion according to the multi-dimensional monitoring sequences, and construct a foundation performance parameter inversion layer; and a reinforcement effect evaluation characteristic layer generation module 3, used to generate a reinforcement effect evaluation characteristic layer based on the reinforcement effect evaluation event set. The foundation performance parameter inversion layer is used to evaluate the reinforcement effect of multiple indices and generate a reinforcement effect evaluation characteristic layer; the reinforcement effect anomaly tracing layer acquisition module 4 is used to perform anomaly causal tracing of the reinforcement effect evaluation characteristic layer based on reinforcement operation monitoring data and obtain the reinforcement effect anomaly tracing layer; the reinforcement effect evaluation diagram model generation module 5 is used to organize the foundation performance parameter inversion layer, the reinforcement effect evaluation characteristic layer and the reinforcement effect anomaly tracing layer, generate a reinforcement effect evaluation diagram model, and adjust the dredged soil foundation reinforcement scheme based on the reinforcement effect evaluation diagram model.

[0070] Furthermore, the system for evaluating the reinforcement effect of dredged soil foundation based on monitoring data inversion is also used for: performing multi-characteristic prediction on the dredged soil foundation construction area according to the dredged soil foundation reinforcement scheme, and obtaining the predicted distribution of settlement, displacement, and pore water pressure; deploying settlement monitoring in the dredged soil foundation construction area according to the predicted settlement distribution, and generating a settlement monitoring deployment grid; deploying displacement monitoring in the dredged soil foundation construction area according to the predicted displacement distribution, and generating a displacement monitoring deployment grid; deploying pore water pressure monitoring in the dredged soil foundation construction area according to the predicted pore water pressure distribution, and generating a pore water pressure monitoring deployment grid; and fusing the settlement monitoring deployment grid, the displacement monitoring deployment grid, and the pore water pressure monitoring deployment grid to generate the dredged soil foundation monitoring grid.

[0071] Furthermore, the system for evaluating the reinforcement effect of dredged soil foundation based on monitoring data inversion is also used for: performing compression characteristic inversion on the dredged soil foundation construction area based on each settlement monitoring parameter in the settlement monitoring sequence to obtain inversion results of each settlement characteristic; performing bearing capacity characteristic inversion on the dredged soil foundation construction area based on each displacement monitoring parameter in the displacement monitoring sequence to obtain inversion results of each displacement characteristic; performing consolidation characteristic inversion on the dredged soil foundation construction area based on each pore water pressure monitoring parameter in the pore water pressure monitoring sequence to obtain inversion results of each pressure characteristic; and encapsulating the inversion results of each settlement characteristic, each displacement characteristic, and each pressure characteristic into the foundation performance parameter inversion layer.

[0072] Furthermore, the system for evaluating the reinforcement effect of dredged and filled soil foundations based on monitoring data inversion is also used for: classifying multi-index reinforcement effect evaluations according to the reinforcement effect evaluation event set, and obtaining a settlement quality evaluation event set, a bearing capacity evaluation event set, and a consolidation quality evaluation event set; evaluating the settlement quality of each settlement characteristic inversion result based on the settlement quality evaluation event set, and generating a settlement quality evaluation sequence; evaluating the bearing capacity of each displacement characteristic inversion result based on the bearing capacity evaluation event set, and generating a bearing capacity evaluation sequence; evaluating the consolidation quality of each pressure characteristic inversion result based on the consolidation quality evaluation event set, and generating a consolidation quality evaluation sequence; and encapsulating the settlement quality evaluation sequence, the bearing capacity evaluation sequence, and the consolidation quality evaluation sequence into the reinforcement effect evaluation characteristic layer.

[0073] Furthermore, the system for evaluating the reinforcement effect of dredged and filled soil foundations based on monitoring data inversion is also used for: performing multi-scale perturbation based on the settlement quality assessment event set to obtain multiple settlement quality assessment spaces; performing iterative supervised training on neural network models based on the multiple settlement quality assessment spaces to obtain multiple settlement quality assessment models that meet the convergence conditions of assessment loss; performing output feature fusion training based on the multiple settlement quality assessment models to obtain a settlement quality fusion model; constructing a settlement quality evaluator using the multiple settlement quality assessment models as first-level nodes of settlement quality assessment and the settlement quality fusion model as a second-level node of settlement quality assessment; and inputting the inversion results of each settlement characteristic into the settlement quality evaluator to obtain the settlement quality assessment sequence.

[0074] Furthermore, the system for evaluating the reinforcement effect of dredged and filled soil foundations based on monitoring data inversion is also used for: performing multi-dimensional anomaly detection on the reinforcement effect evaluation characteristic layer according to the expected reinforcement effect conditions, and obtaining a set of settlement quality anomaly features, a set of bearing capacity anomaly features, and a set of consolidation quality anomaly features; performing multi-level causal tracing on the settlement quality anomaly feature set according to the reinforcement operation monitoring data, and establishing a settlement quality anomaly tracing layer; performing multi-level causal tracing on the bearing capacity anomaly feature set according to the reinforcement operation monitoring data, and establishing a bearing capacity anomaly tracing layer; performing multi-level causal tracing on the consolidation quality anomaly feature set according to the reinforcement operation monitoring data, and establishing a consolidation quality anomaly tracing layer; and encapsulating the settlement quality anomaly tracing layer, the bearing capacity anomaly tracing layer, and the consolidation quality anomaly tracing layer into the reinforcement effect anomaly tracing layer.

[0075] Furthermore, the system for evaluating the reinforcement effect of dredged and filled soil foundations based on monitoring data inversion is also used for: performing multi-parameter correlation analysis on each settlement quality anomaly feature in the settlement quality anomaly feature set according to the reinforcement operation monitoring data to obtain the correlation sequence of each anomaly operation; tracing intermediate factors for each settlement quality anomaly feature based on the correlation sequence of each anomaly operation according to the reinforcement operation monitoring data to obtain each anomaly intermediate factor group; tracing basic factors for each anomaly intermediate factor group based on the correlation sequence of each anomaly operation according to the reinforcement operation monitoring data to obtain each anomaly basic factor group; and organizing causal paths according to the settlement quality anomaly feature set, the anomaly intermediate factor groups, and the anomaly basic factor groups to generate the settlement quality anomaly tracing layer.

[0076] Furthermore, the evaluation system for the reinforcement effect of dredged and filled soil foundation based on monitoring data inversion is also used for: the multidimensional monitoring sequence includes a settlement monitoring sequence, a displacement monitoring sequence, and a pore water pressure monitoring sequence.

[0077] Furthermore, the system for evaluating the reinforcement effect of dredged and filled soil foundations based on monitoring data inversion is also used for: the expected conditions for the reinforcement effect include expected settlement quality, expected bearing capacity, and expected consolidation quality.

[0078] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The method and specific examples for evaluating the reinforcement effect of dredged and filled soil foundations based on monitoring data inversion in the foregoing embodiment 1 are also applicable to the system for evaluating the reinforcement effect of dredged and filled soil foundations based on monitoring data inversion in this embodiment. Through the foregoing detailed description of the method for evaluating the reinforcement effect of dredged and filled soil foundations based on monitoring data inversion, those skilled in the art can clearly understand the system for evaluating the reinforcement effect of dredged and filled soil foundations based on monitoring data inversion in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0079] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0080] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for evaluating the reinforcement effect of dredged and filled soil foundations based on monitoring data inversion, characterized in that, The method includes: Based on the reinforcement plan for the dredged soil foundation, a multi-level monitoring deployment was carried out in the construction area of ​​the dredged soil foundation, and a monitoring grid for the dredged soil foundation was constructed. Based on the monitoring grid of the dredged soil foundation, synchronous monitoring of the construction area of ​​the dredged soil foundation is performed to obtain a multi-dimensional monitoring sequence. Based on the multi-dimensional monitoring sequence, multi-degree-of-freedom foundation performance parameters are inverted to construct a foundation performance parameter inversion layer. Based on the set of reinforcement effect evaluation events, the foundation performance parameter inversion layer is evaluated for multi-index reinforcement effect, and a reinforcement effect evaluation characteristic layer is generated. Based on the reinforcement operation monitoring data, anomaly causal tracing is performed on the reinforcement effect evaluation characteristic layer to obtain the reinforcement effect anomaly tracing layer. The foundation performance parameter inversion layer, the reinforcement effect evaluation characteristic layer, and the reinforcement effect anomaly tracing layer are organized to generate a reinforcement effect evaluation map model, and the reinforcement scheme of the dredged soil foundation is adjusted based on the reinforcement effect evaluation map model.

2. The method for evaluating the reinforcement effect of dredged soil foundation based on monitoring data inversion as described in claim 1, characterized in that, Based on the dredged soil foundation reinforcement plan, a multi-level monitoring deployment was implemented in the dredged soil foundation construction area, constructing a dredged soil foundation monitoring grid, including: Based on the aforementioned dredged soil foundation reinforcement scheme, multi-characteristic predictions are performed on the dredged soil foundation construction area to obtain the predicted distribution of settlement, displacement, and pore water pressure. Settlement monitoring is deployed in the construction area of ​​the dredged soil foundation based on the predicted settlement distribution, and a settlement monitoring deployment grid is generated; Based on the predicted displacement distribution, displacement monitoring is deployed in the construction area of ​​the dredged soil foundation, and a displacement monitoring deployment grid is generated. Based on the predicted pore water pressure distribution, a pore water pressure monitoring deployment is carried out in the construction area of ​​the dredged and filled soil foundation, and a pore water pressure monitoring deployment grid is generated. The settlement monitoring deployment grid, the displacement monitoring deployment grid, and the pore water pressure monitoring deployment grid are integrated to generate the dredged soil foundation monitoring grid.

3. The method for evaluating the reinforcement effect of dredged and filled soil foundations based on monitoring data inversion as described in claim 1, characterized in that, Based on the multidimensional monitoring sequence, multi-degree-of-freedom foundation performance parameters are inverted to construct a foundation performance parameter inversion layer, including: Compression characteristics were inverted for each settlement monitoring parameter in the settlement monitoring sequence to obtain the settlement characteristic inversion results for the construction area of ​​the dredged soil foundation. Based on each displacement monitoring parameter in the displacement monitoring sequence, the bearing capacity characteristics of the dredged soil foundation construction area are inverted to obtain the inversion results of each displacement characteristic. Based on each pore water pressure monitoring parameter in the pore water pressure monitoring sequence, the consolidation characteristics of the dredged soil foundation construction area are inverted to obtain the inversion results of each pressure characteristic. The inversion results of each settlement characteristic, each displacement characteristic, and each pressure characteristic are encapsulated into the foundation performance parameter inversion layer.

4. The method for evaluating the reinforcement effect of dredged and filled soil foundations based on monitoring data inversion as described in claim 1, characterized in that, Based on the reinforcement effect evaluation event set, a multi-index reinforcement effect evaluation is performed on the foundation performance parameter inversion layer to generate a reinforcement effect evaluation characteristic layer, including: Based on the set of reinforcement effect evaluation events, the reinforcement effect evaluation is classified into multiple indicators to obtain the set of settlement quality evaluation events, the set of bearing capacity evaluation events, and the set of consolidation quality evaluation events. Based on the aforementioned set of settlement quality assessment events, the settlement quality is assessed using the inversion results of each settlement characteristic, and a settlement quality assessment sequence is generated. Based on the load-bearing quality assessment event set, the load-bearing quality assessment results of each displacement characteristic inversion are performed to generate a load-bearing quality assessment sequence. Consolidation quality is assessed based on the consolidation quality assessment event set and the inversion results of each pressure characteristic are used to generate a consolidation quality assessment sequence. The settlement quality assessment sequence, the bearing capacity assessment sequence, and the consolidation quality assessment sequence are encapsulated into the reinforcement effect assessment characteristic layer.

5. The method for evaluating the reinforcement effect of dredged and filled soil foundations based on monitoring data inversion as described in claim 4, characterized in that, Based on the aforementioned settlement quality assessment event set, settlement quality assessment is performed on the inversion results of each settlement characteristic to generate a settlement quality assessment sequence, including: Multi-scale perturbation is performed based on the settlement quality assessment event set to obtain multiple settlement quality assessment spaces; Based on the multiple settlement quality assessment spaces, the neural network model is iteratively supervised and trained to obtain multiple settlement quality assessment models that satisfy the convergence condition of assessment loss. Based on the multiple settlement quality assessment models, the output features are fused and trained to obtain a settlement quality fusion model; A settlement quality evaluator is constructed using the multiple settlement quality assessment models as primary nodes for settlement quality assessment and the fusion settlement quality model as a secondary node for settlement quality assessment. The inversion results of each settlement characteristic are input into the settlement quality evaluator to obtain the settlement quality evaluation sequence.

6. The method for evaluating the reinforcement effect of dredged soil foundation based on monitoring data inversion as described in claim 1, characterized in that, Based on the reinforcement operation monitoring data, anomaly causal tracing is performed on the reinforcement effect evaluation characteristic layer to obtain the reinforcement effect anomaly tracing layer, including: Based on the expected conditions of the reinforcement effect, multidimensional anomaly detection is performed on the reinforcement effect evaluation characteristic layer to obtain the settlement quality anomaly feature set, the bearing quality anomaly feature set, and the consolidation quality anomaly feature set. Based on the reinforcement operation monitoring data, a multi-level causal tracing of the settlement quality anomaly feature set is performed to establish a settlement quality anomaly tracing layer. Based on the reinforcement operation monitoring data, a multi-level causal tracing of the load-bearing quality anomaly feature set is performed to establish a load-bearing quality anomaly tracing layer. Based on the reinforcement operation monitoring data, a multi-level causal tracing of the consolidation quality anomaly feature set is performed to establish a consolidation quality anomaly tracing layer; The settlement quality anomaly tracing layer, the bearing capacity anomaly tracing layer, and the consolidation quality anomaly tracing layer are encapsulated into the reinforcement effect anomaly tracing layer.

7. The method for evaluating the reinforcement effect of dredged and filled soil foundations based on monitoring data inversion as described in claim 6, characterized in that, Based on the reinforcement operation monitoring data, a multi-level causal tracing of the settlement quality anomaly feature set is performed to establish a settlement quality anomaly tracing layer, including: Based on the reinforcement operation monitoring data, a multi-parameter correlation analysis is performed on each settlement quality anomaly feature in the settlement quality anomaly feature set to obtain the correlation sequence of each anomaly operation. Based on the correlation sequence of each abnormal operation, the intermediate factors of each abnormal settlement quality feature are traced according to the monitoring data of the reinforcement operation to obtain the intermediate factor group of each abnormality. Based on the correlation sequence of each abnormal operation, the basic factors of each abnormal intermediate factor group are traced according to the reinforcement operation monitoring data to obtain the basic factor group of each abnormality. The causal path is organized based on the set of settlement quality anomalies, the intermediate factor groups of each anomaly, and the basic factor groups of each anomaly to generate the settlement quality anomaly tracing layer.

8. The method for evaluating the reinforcement effect of dredged soil foundation based on monitoring data inversion as described in claim 1, characterized in that, The multidimensional monitoring sequence includes a settlement monitoring sequence, a displacement monitoring sequence, and a pore water pressure monitoring sequence.

9. The method for evaluating the reinforcement effect of dredged and filled soil foundations based on monitoring data inversion as described in claim 6, characterized in that, The expected conditions for the reinforcement effect include the expected settlement quality assessment, the expected bearing capacity assessment, and the expected consolidation quality assessment.

10. A system for evaluating the reinforcement effect of dredged and filled soil foundations based on monitoring data inversion, characterized in that, The steps for implementing the method for evaluating the reinforcement effect of dredged soil foundation based on monitoring data inversion as described in any one of claims 1 to 9 include: The dredged soil foundation monitoring grid construction module is used to deploy multi-level monitoring in the dredged soil foundation construction area according to the dredged soil foundation reinforcement scheme and construct the dredged soil foundation monitoring grid. The foundation performance parameter inversion layer construction module is used to perform synchronous construction monitoring of the construction area of ​​the dredged soil foundation according to the monitoring grid of the dredged soil foundation, obtain multi-dimensional monitoring sequences, and perform multi-degree-of-freedom foundation performance parameter inversion according to the multi-dimensional monitoring sequences to construct the foundation performance parameter inversion layer. The reinforcement effect evaluation characteristic layer generation module is used to perform multi-index reinforcement effect evaluation on the foundation performance parameter inversion layer based on the reinforcement effect evaluation event set, and generate the reinforcement effect evaluation characteristic layer. The reinforcement effect anomaly tracing layer acquisition module is used to perform anomaly causal tracing on the reinforcement effect evaluation characteristic layer based on reinforcement operation monitoring data, and acquire the reinforcement effect anomaly tracing layer. The reinforcement effect evaluation map model generation module is used to organize the foundation performance parameter inversion layer, the reinforcement effect evaluation characteristic layer, and the reinforcement effect anomaly tracing layer to generate a reinforcement effect evaluation map model, and adjust the dredged soil foundation reinforcement scheme based on the reinforcement effect evaluation map model.

Images