An AI-based engineering cost big data intelligent analysis system and method

Abstract

The application belongs to the technical field of engineering cost, and relates to an AI-based engineering cost big data intelligent analysis system and method, wherein a ground pile coupling model is constructed, precipitation prediction parameters in a construction period are input as time-varying boundary conditions, transient seepage changes of foundation soil under the action of precipitation are analyzed, the distribution of pore water pressure increment in the influence domain of each supporting pile is quantified, the pile body inclination probability, embedded failure probability and soil loss probability between piles of the supporting pile are predicted based on the reduction relationship of the pore water pressure increment and the effective stress of the soil body, directional parameter adjustment is triggered according to the probability threshold value condition, a supporting pile design parameter adjustment scheme and a corresponding supporting structure incremental cost are formulated, high precipitation risk working conditions are identified in advance to output risk control supporting cost, the possibility of supporting structure failure is effectively reduced, the safety and stability of the engineering structure are enhanced, and the economic loss caused by potential accidents is reduced.

Description

Technical Field

[0001] This invention belongs to the field of engineering cost technology, and more specifically, relates to an AI-based intelligent analysis system and method for engineering cost big data. Background Technology

[0002] With the acceleration of urbanization and the continuous expansion of underground space development, deep foundation pit engineering is developing towards ultra-deep and complex trends. Among them, the support pile structure has become the core support form for high-rise buildings, subway hubs and underground utility tunnels due to its advantages such as strong lateral pressure resistance and wide construction adaptability. However, due to factors such as complex geological conditions, diverse design schemes and large fluctuations in material prices, cost control of support pile engineering has become a key and difficult point in project cost management.

[0003] However, existing cost-related solutions for retaining pile engineering still have significant limitations in addressing the aforementioned challenges, mainly in the following aspects: Current methods rely primarily on design drawings and static geological survey reports, failing to fully consider the time-varying impact of dynamic precipitation on soil permeability during the construction period. Consequently, they lack dynamic prediction of the probability of retaining pile failure caused by precipitation and a mechanism for quantifying the additional repair costs resulting from seepage damage. This technological gap easily leads to severe cost overruns in retaining pile engineering when precipitation control is inadequate. Summary of the Invention

[0004] In view of this, in order to solve the problems mentioned in the background technology, an AI-based intelligent analysis system and method for engineering cost big data is proposed.

[0005] The technical solution adopted by the present invention to solve its technical problem is as follows: Firstly, the present invention provides an AI-based intelligent analysis system for engineering cost big data, including: a model building module, a penetration analysis module, a failure probability prediction module, a parameter optimization module, a cost control output module, and a raw cost output module.

[0006] The model building module is connected to the penetration simulation module, the penetration simulation module is connected to the failure probability prediction module, the failure probability prediction module is connected to the parameter optimization module and the original cost output module, and the parameter optimization module is connected to the cost control output module.

[0007] The model building module constructs a ground-pile coupled model based on the geological survey parameters of the foundation engineering and the design parameters of the support piles.

[0008] The permeability simulation module inputs the predicted precipitation parameters during the construction period as the surface boundary conditions into the model, analyzes the transient seepage changes of the foundation soil under the action of precipitation, and quantifies the distribution of pore water pressure increments within the influence zone around each support pile.

[0009] A failure probability prediction module predicts a failure probability distribution of each supporting pile according to a reduction relationship of the pore water pressure increment relative to the effective stress of the soil body, and the failure probability distribution includes a pile body inclination probability, an embedded failure probability, and a soil loss probability between piles.

[0010] A parameter optimization module formulates a supporting pile design parameter adjustment scheme when any sub-item probability in the failure probability distribution of any supporting pile exceeds a preset warning threshold, and the adjustment scheme includes one or more combinations of increasing a pile diameter, deepening an embedded depth, or reducing a pile spacing.

[0011] A cost regulation output module calculates an incremental cost of the supporting structure generated by implementing the adjustment scheme, integrates the incremental cost with an original supporting cost of the foundation engineering, and outputs a risk-regulated supporting cost.

[0012] An original cost output module outputs an original supporting cost of the foundation engineering when all sub-item probabilities in the failure probability distributions of all supporting piles do not exceed the threshold.

[0013] In a second aspect, the present application provides an AI-based engineering cost big data intelligent analysis method, which includes: constructing a ground-pile coupling model according to geological survey parameters and supporting pile design parameters of the foundation engineering.

[0014] A pore water pressure increment prediction parameter in a construction period is input as a ground surface boundary condition into the model, the transient seepage change of the foundation soil under the action of dewatering is analyzed, and the pore water pressure increment distribution in the influence domain of each supporting pile is quantified.

[0015] A failure probability distribution of each supporting pile is predicted according to a reduction relationship of the pore water pressure increment relative to the effective stress of the soil body, and the failure probability distribution includes a pile body inclination probability, an embedded failure probability, and a soil loss probability between piles.

[0016] When any sub-item probability in the failure probability distribution of any supporting pile exceeds a preset warning threshold, a supporting pile design parameter adjustment scheme is formulated, and the adjustment scheme includes one or more combinations of increasing a pile diameter, deepening an embedded depth, or reducing a pile spacing.

[0017] An incremental cost of the supporting structure generated by implementing the adjustment scheme is calculated, the incremental cost is integrated with an original supporting cost of the foundation engineering, and a risk-regulated supporting cost is output.

[0018] When all sub-item probabilities in the failure probability distributions of all supporting piles do not exceed the threshold, an original supporting cost of the foundation engineering is output.

[0019] Compared with the prior art, the embodiments of the present application have at least the following advantages or beneficial effects: (1) The present application constructs a pile-soil coupling model, inputs the precipitation prediction parameters as time-varying boundary conditions, and analyzes the transient seepage field evolution caused by precipitation infiltration by taking the pore water pressure increment as the starting point, thereby providing a scientific and systematic analysis method for deeply understanding the stress mechanism of the supporting structure under the precipitation working condition, and helping to more comprehensively grasp the engineering risk.

[0020] (2) The present application predicts the pile body inclination probability, embedded failure probability and soil loss probability between piles based on the reduction relationship of the pore water pressure increment relative to the effective stress of the soil, and triggers directional parameter adjustment based on the probability threshold value, thereby identifying high precipitation risk working conditions in advance to output risk control supporting cost, effectively reducing the possibility of supporting structure failure, enhancing the safety and stability of the engineering structure, and thereby reducing the economic loss caused by potential accidents. BRIEF DESCRIPTION OF DRAWINGS

[0021] The present application will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present application. For ordinary skilled persons in the art, other drawings can be obtained without creative labor on the basis of the following drawings.

[0022] Figure 1 The system structure block diagram provided for the first embodiment of the present application.

[0023] Figure 2 The construction logic diagram of the pile-soil coupling model in the first embodiment of the present application.

[0024] Figure 3 The method flowchart provided for the second embodiment of the present application. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary skilled persons in the art without creative labor are within the scope of protection of the present application.

[0026] Embodiment one, please refer to Figure 1 As shown in the first embodiment of the present application, an AI-based engineering cost big data intelligent analysis system is provided, which comprises a model construction module, a penetration deduction module, a failure probability prediction module, a parameter optimization module, a control cost output module and an original cost output module.

[0027] The model construction module is connected with a penetration deduction module, the penetration deduction module is connected with a failure probability prediction module, the failure probability prediction module is connected with a parameter optimization module and an original cost output module respectively, and the parameter optimization module is connected with a regulated cost output module.

[0028] The model construction module constructs a pile-soil coupling model according to the geological survey parameters and the support pile design parameters of the foundation engineering.

[0029] Please refer to Figure 2 As shown in the figure, in a preferred embodiment of the present application, the construction process of the pile-soil coupling model includes the following steps: A1. Extracting the spatial distribution data of each soil layer in the geological survey parameters and the groundwater level depth, constructing a three-dimensional initial foundation profile, and associating each soil layer with its soil type to preset the saturated permeability index.

[0030] It should be noted that the soil type includes but is not limited to clay, sand, silt, etc., and the preset saturated permeability index can be calibrated by the variable head permeability test for each soil type at the initial stage of system development and pre-stored in the cloud database for direct extraction and application.

[0031] A2. Extracting the distribution position coordinates, pile diameter and pile end elevation of each support pile in the support pile design parameters, positioning the support pile body in the initial foundation profile and setting its geometric shape as a cylindrical structure, and establishing a material property transition zone for the cross-layer section of the support pile passing through different soil layers.

[0032] A3. Grid division is performed on the initial foundation profile, a radius value is adaptively set according to the pile diameter value to define the spherical pile peripheral influence domain, i.e. the encryption area, grid refinement is implemented on the influence domain, and the grid density is required to be higher than the reference density of the non-encryption area (i.e. other areas in the initial foundation profile except the spherical pile peripheral influence domain).

[0033] It should be noted that the radius value of the pile peripheral influence domain needs to cover the stress disturbance range of the interaction between the support pile and the soil layer, and the adaptive setting standard is the product of the pile diameter value and the soil quality dependent coefficient, wherein the soil quality dependent coefficient is calibrated according to the soil permeability standard of the soil layer soil type.

[0034] A4. According to the initial groundwater level depth, the initial state identification of the saturated zone and the unsaturated zone is divided in the foundation profile, the pore water pressure reference value is configured for the saturated zone, and the matrix suction reference value is configured for the unsaturated zone.

[0035] It should be noted that the saturated zone division standard is the area in the foundation profile with an elevation lower than or equal to the initial groundwater level depth, and the part of the soil layer that reaches the preset saturated permeability index of the corresponding soil type.

[0036] The permeation deduction module inputs the dewatering prediction parameters in the construction period as the ground surface boundary condition into the model, analyzes the transient seepage change of the ground soil under the dewatering action, and quantifies the pore water pressure increment distribution in the influence domain of each supporting pile.

[0037] In a preferred embodiment of the present application, the quantification of the pore water pressure increment distribution in the influence domain of each supporting pile includes: converting the peak strength and duration of single dewatering in the dewatering prediction parameters into a time-varying ground surface infiltration flux boundary curve according to a preset rule, and loading it to the model ground surface area according to the time sequence.

[0038] It should be noted that the specific content of the above-mentioned preset rule includes: setting the preset saturated permeation index of the soil layer at the top layer in the vertical direction of the three-dimensional profile of the foundation as the upper limit threshold of the infiltration flux, when the peak strength of dewatering does not exceed the saturated permeation index, defining the time-varying ground surface infiltration flux boundary curve as a constant value curve, and the flux value is equal to the peak strength of dewatering, otherwise when the peak strength of dewatering exceeds the saturated permeation index, performing segmented conversion, including taking the upper limit value of the saturated permeation index as the flux value of the peak duration segment and the flux value of the post-dewatering segment being zero.

[0039] The time span of the ground surface infiltration flux boundary curve is strictly aligned with the duration of dewatering, and continues for a preset drainage duration after dewatering.

[0040] The saturation state identifier and the pore water pressure value of each grid cell in the foundation profile are re-assigned step by step in time, and the re-assignment operation includes: i. triggering saturation state identifier update when the water content of the grid cell reaches the preset saturated permeation index of the associated soil layer.

[0041] ii. The new saturated grid cell deletes its matrix suction reference value, updates the elevation deviation between the cell center elevation and the real-time groundwater level, and quantifies the pore water pressure value of the new saturated grid cell.

[0042] iii. The saturated grid cell superimposes the pore water pressure supplement value quantified by the water level elevation amount on the pore water pressure reference value configured for it.

[0043] It should be noted that the pore water pressure value of the new saturated grid cell is specifically quantified as the product of the absolute deviation between the cell center elevation and the real-time elevation of the groundwater level and the preset water bulk density.

[0044] The pore water pressure supplement value quantified by the water level elevation amount is specifically quantified as the product of the water level elevation amount and the preset water bulk density.

[0045] The pore water pressure values of each grid cell of the pile-soil coupling model at each time step during the dewatering process are collected to analyze the transient seepage change of the ground soil under the dewatering action.

[0046] The pore water pressure difference before and after the precipitation of each grid unit in the influence domain of each supporting pile is calculated, and the pore water pressure increment distribution in the influence domain of each supporting pile is quantified.

[0047] In a preferred embodiment of the present application, the process of obtaining the pore water pressure difference before and after the precipitation of each grid unit includes: if the initial state of the grid unit before precipitation is a non-saturated area, then the difference between the pore water pressure value after precipitation and the matrix suction reference value is taken as the pore water pressure difference before and after precipitation, wherein the matrix suction reference value is negative.

[0048] If the initial state of the grid unit before precipitation is a saturated area, then the difference between the pore water pressure after precipitation and the pore water pressure reference value is taken as the pore water pressure difference before and after precipitation.

[0049] The embodiment of the present application analyzes the transient seepage field evolution caused by precipitation infiltration by constructing a pile-coupling model, inputting precipitation prediction parameters as time-varying boundary conditions, and taking pore water pressure increment as the starting point, which provides a scientific and systematic analysis method for deeply understanding the stress mechanism of supporting structures under precipitation conditions, and helps to more comprehensively grasp the engineering risks.

[0050] The failure probability prediction module predicts the failure probability distribution of each supporting pile according to the reduction relationship between the pore water pressure increment and the effective stress of the soil body, and the failure probability distribution includes the pile body inclination probability, the embedded failure probability, and the soil loss probability between piles.

[0051] In a preferred embodiment of the present application, predicting the pile body inclination probability of each supporting pile includes: dividing the left region and the right region of the influence domain around the pile with the supporting pile axis as the boundary.

[0052] A fitting function representing the reduction relationship between the pore water pressure increment and the effective stress of the soil body is constructed through regression analysis, and the average effective stress reduction index of the left region and the right region is calculated respectively by combining the pore water pressure increments of each grid unit in the left region and the right region.

[0053] It should be noted that the specific process of constructing the fitting function representing the reduction relationship between the pore water pressure increment and the effective stress of the soil body through regression analysis includes: defining the physical correlation constraint between the pore water pressure increment and the soil body effective stress reduction according to the stress balance principle of the soil unit, setting a mathematical model for representing the nonlinear reduction relationship between the two, and in the present application, an exponential decay model function can be exemplarily used.

[0054] A preset number of observation groups containing pore water pressure increments and their corresponding soil body effective stress reduction indexes are obtained, and the mathematical model parameters are iteratively optimized using the nonlinear least squares method to minimize the sum of squares of observation group residuals, thereby determining the final fitting function.

[0055] Convert the absolute difference value of the average effective stress reduction index of the left and right sides into a bilateral imbalance degree, and substitute it into a preset failure probability evaluation function to quantify the pile body inclination probability prediction value.

[0056] It should be noted that the specific conversion process of the above bilateral imbalance degree is that the absolute difference value of the average effective stress reduction index of the left and right sides is the numerator, and the maximum value of the average effective stress reduction index of the left and right sides is the denominator, and the ratio operation is expanded to convert the bilateral imbalance degree.

[0057] It should also be noted that the above preset failure probability evaluation function can be exemplified as a sigmoid function, which is based on the fact that the sigmoid function can strictly follow the critical mutation theory of soil instability.

[0058] In a preferred embodiment of the present application, the prediction of the embedded failure probability of each support pile comprises: taking the bottom surface of the support pile as the reference surface, expanding and extending downward vertically along the cross-sectional direction of the pile body to a preset embedded depth to define the pile end bearing area in the pile surrounding influence domain.

[0059] Extract the pore water pressure increment of each grid element in the pile end bearing area, and calculate the gradient component of the pore water pressure increment in the vertical direction of the pile end bearing area using the central difference method.

[0060] Refer to the effective stress reduction index corresponding to the maximum pore water pressure increment of the grid element in the pile end bearing area, substitute the ratio of the effective stress reduction index and the preset permissible reduction index threshold value into the preset failure probability evaluation function, and determine the correction factor in combination with the positive and negative logical relationship of the gradient component to quantify the embedded failure probability prediction value of the support pile.

[0061] It should be noted that the specific process of determining the correction factor in combination with the positive and negative logical relationship of the gradient component is as follows: if the gradient component is positive, it means that the pore water pressure increases along the depth direction, that is, the pressure of the soil layer below the pile end is higher than the pressure of the pile end interface, indicating that the water head effect occurs in the pile end bearing layer, which weakens the adhesion of the pile-soil interface, and thus triggers the risk amplification correction, and the value range of the correction factor is set to .

[0062] If the gradient component is negative, it means that the pore water pressure decreases along the depth direction, that is, the pressure of the soil layer below the pile end is lower than the pressure of the pile end interface, forming a favorable pressure gradient, which enhances the embedded stability of the pile end, triggers the risk reduction correction, and the value range of the correction factor is set to .

[0063] The content of the present application can exemplarily take the median value in the value range of the correction factor.

[0064] In a preferred embodiment of the present application, the method for predicting the soil loss probability between the supporting piles comprises: positioning a pair of adjacent supporting piles and taking the center line of the two piles as the reference axis, and expanding to both sides to form an interactive area between the piles with a set distance, and the set distance is dynamically calculated according to the proportional relationship between the pile diameter and the pile spacing.

[0065] It should be noted that the above-mentioned dynamic calculation method of the set distance is: obtaining the sum of the pile radii of the pair of adjacent supporting piles, the pile radius being half of the pile diameter value, and the difference between the pile spacing and the sum of the pile radii, and taking the preset proportion of the difference value as the set distance, wherein the preset proportion can be exemplarily taken in the value range of .

[0066] Traverse the pore water pressure increment of each grid unit in the interactive area between the piles, mark the units with an increment value higher than the average level as high-pressure units, and the units lower than the average level as low-pressure units.

[0067] Statistical direction data of the seepage path generated by the high-pressure units to the adjacent low-pressure units, when the included angle between the extension direction of the seepage path and the normal direction of the reference axis is less than a preset angle, it is determined that the soil loss risk path is towards the inter-pile gap.

[0068] Calculate the proportion of the risk path in all seepage paths and substitute it into the preset failure probability evaluation function to quantify the soil loss probability between the piles.

[0069] The parameter optimization module, when any sub-item probability in the failure probability distribution of any supporting pile exceeds a preset warning threshold, formulates a supporting pile design parameter adjustment scheme, which includes one or a combination of increasing the pile diameter, deepening the embedded depth, or reducing the pile spacing.

[0070] In a preferred embodiment of the present application, the method for formulating a supporting pile design parameter adjustment scheme comprises: marking the supporting piles with sub-item probabilities exceeding the preset warning threshold in the failure probability distribution as risk supporting piles, and taking the distribution coordinates of the risk supporting piles as the adjustment coordinates.

[0071] Organize the failure mode types triggered by each risk supporting pile and the corresponding adjustment measures, if a single risk supporting pile triggers multiple failure mode types, then generate a combined measure chain according to a preset priority adjustment order, wherein the preset priority adjustment order is in order of increasing the pile diameter, deepening the embedded depth, and reducing the pile spacing.

[0072] It should be noted that the sorting basis of the above-mentioned preset priority adjustment order is that increasing the pile diameter has the smallest construction disturbance, and simultaneously improves the bending and shear resistance, and the material increment cost is linearly controllable, which is suitable for being the first choice for priority adjustment.

[0073] Deepening the embedded depth needs additional excavation, and it is used for treating embedded failure and limited by the depth of bearing layer, but compared with reducing the pile spacing, the whole pile arrangement needs to be adjusted and the situation of chain design change is caused, the engineering is easier to control, and it is suitable as the priority adjustment of the secondary selection.

[0074] Accessing the risk level table of each failure mode type stored in the cloud database, determining the risk level mapped by the probability prediction value corresponding to the triggered failure mode type, and synchronously extracting the risk level preset adjustment parameter.

[0075] The regulation cost output module calculates the incremental cost of the supporting structure generated by implementing the adjustment scheme, integrates with the original supporting cost of the foundation engineering, and outputs the risk regulation supporting cost.

[0076] In a preferred embodiment of the present application, the calculation of the incremental cost of the supporting structure generated by implementing the adjustment scheme comprises: analyzing the adjustment parameter items in the adjustment scheme, extracting the corresponding cumulative adjustment amount of the pile diameter increase value, the embedded deepening value and the pile spacing reduction value.

[0077] Accessing the unit cost parameter table stored in the cloud database, determining the incremental cost corresponding to the cumulative adjustment amount of each adjustment parameter item type in the adjustment scheme.

[0078] The adjustment parameter item types are summarized to obtain the incremental cost of the supporting structure generated by the adjustment scheme.

[0079] The original cost output module outputs the original supporting cost of the foundation engineering when all sub-item probabilities in the failure probability distribution of all supporting piles do not exceed the threshold value.

[0080] The embodiment of the present application predicts the pile body inclination probability, embedded failure probability and soil loss probability between piles based on the reduction relationship of the increment of pore water pressure relative to the effective stress of the soil body, and triggers directional parameter adjustment based on the probability exceeding the threshold value, identifies high dewatering risk working conditions in advance to output the risk regulation supporting cost, effectively reduces the possibility of supporting structure failure, enhances the safety and stability of the engineering structure, and further reduces the economic loss caused by potential accidents.

[0081] It should be further supplemented that the cloud database is applied in the execution process of the present application, and all parameters in the cloud database are obtained by system development implantation.

[0082] Embodiment two, please refer to Figure 3 As shown in the second embodiment of the present application, an AI-based engineering cost big data intelligent analysis method is provided, which comprises: constructing a ground-pile coupling model according to the geological survey parameters and supporting pile design parameters of the foundation engineering.

[0083] The construction period precipitation prediction parameter is taken as the ground boundary condition input into the model, the ground soil transient seepage change under the action of precipitation is analyzed, and the pore water pressure increment distribution in the influence domain of each supporting pile is quantified.

[0084] According to the reduction relationship of the pore water pressure increment and the effective stress of the soil body, the failure probability distribution of each supporting pile is predicted, and the failure probability distribution includes the pile body inclination probability, the embedded failure probability, and the soil loss probability between piles.

[0085] When any sub-item probability in the failure probability distribution of any supporting pile exceeds a preset warning threshold, a supporting pile design parameter adjustment scheme is formulated, and the adjustment scheme includes one or a combination of increasing the pile diameter, deepening the embedded depth, or reducing the pile spacing.

[0086] The incremental cost of the supporting structure generated by calculating and implementing the adjustment scheme is integrated with the original supporting cost of the foundation engineering, and the risk control supporting cost is output.

[0087] When all sub-item probabilities in the failure probability distribution of all supporting piles do not exceed the threshold, the original supporting cost of the foundation engineering is output.

[0088] The implementation principle and the technical effects of the AI-based engineering cost big data intelligent analysis method provided by the embodiment of the application are the same as those of the foregoing system embodiment. For brevity of description, the part not mentioned in the method embodiment can refer to the corresponding content in the foregoing system embodiment.

[0089] The above content is only an example and description of the structure of the application. Those skilled in the art of the technical field to which the application belongs can make various modifications or supplements or adopt similar ways to replace the described specific embodiments, as long as the modifications or supplements or replacements do not deviate from the structure of the application or exceed the scope defined by the application, and all of them should belong to the protection scope of the application.

Claims

1. An AI-based engineering cost big data intelligent analysis system, characterized in that, Comprise: According to the geological survey parameters of foundation engineering and the design parameters of supporting pile, a pile-soil coupling model is constructed; The predicted parameters of construction period are inputted into the model as the surface boundary conditions to analyze the transient seepage changes of foundation soil under the action of dewatering and to quantify the pore water pressure increment distribution in the influence domain of each supporting pile; According to the reduction relationship between the pore water pressure increment and the effective stress of soil, the failure probability distribution of each supporting pile is predicted, which includes the pile body inclination probability, the embedded failure probability and the soil loss probability between piles; When any sub-item probability in the failure probability distribution of any supporting pile exceeds the preset warning threshold, a design parameter adjustment scheme for the supporting pile is formulated, which includes one or more combinations of increasing the pile diameter, deepening the embedded depth or reducing the pile spacing; The incremental cost of the supporting structure generated by the adjustment scheme is calculated and integrated with the original supporting cost of the foundation engineering, and the risk control supporting cost is outputted; When all sub-item probabilities in the failure probability distribution of all supporting piles do not exceed the threshold, the original supporting cost of the foundation engineering is outputted. The calculation of the incremental cost of the supporting structure generated by the adjustment scheme comprises: Analyzing the adjustment parameter items in the adjustment scheme, extracting the cumulative adjustment amount corresponding to the increase of pile diameter, the deepening of embedded depth and the reduction of pile spacing; Accessing the unit cost parameter table stored in the cloud database to determine the incremental cost corresponding to the cumulative adjustment amount of each adjustment parameter item type in the adjustment scheme; The adjustment parameter items are summarized to obtain the incremental cost of the supporting structure generated by the adjustment scheme.

2. The AI-based engineering cost big data intelligent analysis system according to claim 1, characterized in that: The construction process of the pile-soil coupling model comprises the following steps: A1. Extracting the spatial distribution data of each soil layer in the geological survey parameters and the groundwater level depth, constructing a three-dimensional initial profile of the foundation, and associating each soil layer with its soil type to preset the saturated permeability index; A2. Extracting the distribution position coordinates, pile diameter and pile end elevation of each supporting pile in the design parameters of supporting pile, positioning the supporting pile body in the initial profile of the foundation and setting its geometric shape as a cylindrical structure, and establishing a material property transition zone for the cross-layer section of the supporting pile passing through different soil layers; A3. Grid division is performed on the initial profile of the foundation, and the radius value is adaptively set according to the pile diameter value to define a spherical pile influence domain, i.e. an encryption area, and the grid refinement is performed on the influence domain, which requires the grid density to be higher than the reference density of the non-encryption area; A4. According to the initial groundwater level depth, the initial state identification of saturated and unsaturated areas is divided in the foundation profile, the pore water pressure reference value is configured for the saturated area, and the matrix suction reference value is configured for the unsaturated area.

3. The AI-based engineering cost big data intelligent analysis system according to claim 2, characterized in that: The quantification of the pore water pressure increment distribution in the influence domain of each supporting pile comprises: The peak intensity and duration of single dewatering in the predicted parameters of dewatering are converted into time-varying surface infiltration flux boundary curves according to the preset rules, and are loaded into the model surface area according to the time sequence; The saturation state identification and pore water pressure value of each grid element in the foundation profile are re-assigned at each time step, which includes: i. When the water content of the grid element reaches the preset saturated permeability index of the associated soil layer, the saturation state identification is updated; ii. The new saturated grid cell deletes its matrix suction reference value, updates the elevation deviation according to the cell center elevation and the real-time groundwater level, and quantifies the new saturated grid cell pore water pressure value; iii. The saturated grid cell superimposes the pore water pressure supplement value quantified by the water level uplift elevation on the pore water pressure reference value configured by it; Collect the pore water pressure values of each grid cell of the pile-soil coupling model at each time step during the precipitation process to analyze the transient seepage changes of the foundation soil under the action of precipitation; Organize the pore water pressure difference values of each grid cell in the influence domain of each support pile before and after the precipitation to quantify the pore water pressure increment distribution in the influence domain of each support pile.

4. The AI-based engineering cost big data intelligent analysis system according to claim 3, characterized in that: The process of obtaining the pore water pressure difference values of the grid cells before and after the precipitation includes: If the initial state of the grid cell before precipitation is a non-saturated area, the difference between the pore water pressure value after precipitation and the matrix suction reference value is taken as the pore water pressure difference value before and after precipitation, wherein the matrix suction reference value is negative; If the initial state of the grid cell before precipitation is a saturated area, the difference between the pore water pressure after precipitation and the pore water pressure reference value is taken as the pore water pressure difference value before and after precipitation.

5. The AI-based engineering cost big data intelligent analysis system according to claim 3, characterized in that: The process of predicting the pile body inclination probability of each support pile includes: Divide the left and right regions of the influence domain with the support pile axis as the boundary; Construct a fitting function representing the reduction relationship between the pore water pressure increment and the effective stress of the soil through regression analysis, and calculate the average effective stress reduction index of the left and right regions respectively by combining the pore water pressure increments of each grid cell in the left and right regions; Convert the absolute difference between the left and right average effective stress reduction indexes into a bilateral imbalance degree, and substitute it into a preset failure probability evaluation function to quantify the pile body inclination probability prediction value.

6. The AI-based engineering cost big data intelligent analysis system according to claim 4, characterized in that: The process of predicting the embedded failure probability of each support pile includes: Take the bottom surface of the support pile as the reference surface, symmetrically expand along the cross-sectional direction of the pile body and vertically downward to a preset embedded depth to define the pile end bearing area in the influence domain; Extract the pore water pressure increment of each grid cell in the pile end bearing area, and calculate the gradient component of the pore water pressure increment in the vertical direction of the pile end bearing area using the central difference method; Refer to the effective stress reduction index corresponding to the maximum pore water pressure increment of the grid cell in the pile end bearing area, substitute the ratio of the index and the preset permissible reduction index threshold into the preset failure probability evaluation function, and determine the correction factor by combining the positive and negative logical relationship of the gradient component to quantify the embedded failure probability prediction value of the support pile.

7. The AI-based engineering cost big data intelligent analysis system according to claim 4, characterized in that: The process of predicting the soil loss probability between piles includes: Position the adjacent support piles and expand a set distance to the left and right of the center line connecting the two piles to form an inter-pile interaction area, and the set distance is dynamically calculated according to the proportional relationship between the pile diameter and the pile spacing; Traverse the pore water pressure increments of each grid cell in the inter-pile interaction area, mark the cells with increments higher than the average level as high-pressure cells and the cells with increments lower than the average level as low-pressure cells; The statistical high-pressure unit generates direction data of a seepage path to an adjacent low-pressure unit, and when an included angle between an extension direction of the seepage path and a normal direction of a reference axis is less than a preset angle, the seepage path is determined as a soil loss risk path towards an inter-pile gap; A proportion value of the risk path in all seepage paths is calculated and substituted into a preset failure probability evaluation function to quantify a soil loss probability of the inter-pile gap. 8.The AI-based engineering cost big data intelligent analysis system according to claim 1, characterized in that: The support pile design parameter adjustment scheme includes: Marking a support pile with a sub-item probability exceeding a preset warning threshold in the failure probability distribution as a risk support pile, and taking the distribution position coordinates of the risk support pile as adjustment position coordinates; Organizing the failure mode types triggered by each risk support pile and the corresponding adjustment measures, and if a single risk support pile triggers multiple failure mode types, generating a combined measure chain according to a preset priority adjustment order, wherein the preset priority adjustment order is in order of increasing pile diameter, deepening the embedded depth, and reducing the pile spacing; Accessing a risk level table of each failure mode type stored in the cloud database to determine the risk level mapped by the probability prediction value corresponding to the failure mode type, and synchronously extracting the preset adjustment parameters of the risk level.

9. An AI-based engineering cost big data intelligent analysis method, the following steps are executed by an AI-based engineering cost big data intelligent analysis system according to any one of claims 1-8, characterized in that, It includes: Constructing a ground-pile coupling model according to the geological exploration parameters of the foundation engineering and the support pile design parameters; Inputting the dewatering prediction parameters in the construction period as the ground surface boundary conditions into the model, analyzing the transient seepage changes of the foundation soil under the action of dewatering, and quantifying the pore water pressure increment distribution in the influence domain of each support pile; According to the reduction relationship between the pore water pressure increment and the effective stress of the soil body, the failure probability distribution of each support pile is predicted, which includes the pile body inclination probability, the embedded failure probability and the inter-pile soil loss probability; When any sub-item probability in the failure probability distribution of any support pile exceeds a preset warning threshold, a support pile design parameter adjustment scheme is developed, which includes one or more combinations of increasing the pile diameter, deepening the embedded depth, or reducing the pile spacing; Calculate the incremental cost of the support structure generated by implementing the adjustment scheme, and integrate it with the original support cost of the foundation engineering, and output the risk control support cost; When all sub-item probabilities in the failure probability distribution of all support piles do not exceed the threshold, output the original support cost of the foundation engineering.

Images