A method and system for predicting and improving the strength of silt-stabilized soil based on physical and chemical properties

By establishing a correlation database and prediction model for sludge solidified soil strength and building an evaluation system, the time-consuming and labor-intensive problem in the prediction and improvement of sludge solidified soil strength in the existing technology is solved, and efficient prediction and improvement of sludge solidified soil strength is achieved.

CN118888063BActive Publication Date: 2024-11-29CHINA COMM CONSTR FIRST HARBOR CONSULTANTS +1
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411345215.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-26
Publication Date
2024-11-29
Estimated Expiration
2044-09-26

AI Technical Summary

Technical Problem

In the prior art, for sludge in different areas, a large number of tests are required to explore the suitability of sludge and different types of curing agents, which leads to time-consuming and labor-intensive engineering and is easily restricted by the sample maintenance age.

Method used

By summarizing the influencing factors of the sludge solidified soil strength, establishing a correlation database between the influencing factors and the sludge solidified soil strength, a specific algorithm is used to establish a strength prediction model, and a sludge solidified soil strength evaluation system is established to form a sludge solidified soil strength improvement plan.

Benefits of technology

Effectively predict the strength of sludge solidified soil, reduce the amount of tests required in actual projects, reduce the consumption of manpower, material resources and time, and improve the efficiency of improving the strength of sludge solidified soil.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118888063B_ABST
    Figure CN118888063B_ABST
Patent Text Reader

Abstract

The present application discloses a method and system for predicting and improving the strength of silt-solidified soil based on physical and chemical properties, which relates to the field of engineering materials. The method includes: summarizing the influencing factors of the strength of silt-solidified soil, and establishing a correlation database between the influencing factors and the strength of silt-solidified soil; classifying the influencing factors to obtain the curing agent parameters and the physical and chemical parameters of the silt; based on the correlation database, using a specific algorithm to establish a strength prediction model, and determine the parameter boundary range of the strength prediction model; obtaining the measured values ​​of the physical and chemical parameters of the silt to be evaluated; building a silt-solidified soil strength evaluation system; dividing the evaluation path based on the measured values ​​of the physical and chemical parameters, the parameter boundary range and the silt-solidified soil strength evaluation system, and forming a silt-solidified soil strength improvement plan. While realizing the prediction of the strength of silt-solidified soil, the present application forms a silt-solidified soil strength improvement plan, and the whole process is more time-saving and labor-saving.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of engineering materials, and in particular to a method and system for predicting and improving the strength of silt-solidified soil based on physical and chemical properties. Background Art

[0002] In the actual construction process of civil engineering, port and waterway engineering, land reclamation engineering, etc., the effective treatment and utilization of dredged sludge is of vital importance. Using dredged sludge as engineering material after solidification is currently the most common treatment method, which is also of great significance to the protection of the environment and resources.

[0003] The solidification treatment of sludge refers to mixing sludge with a solidifying agent so that the mixture produces a "skeleton effect" under the action of a hydration reaction, thereby forming a certain strength. Among them, the hydration reaction includes physical and chemical reactions, so the physical and chemical properties of the sludge itself are also key factors affecting the reaction process.

[0004] In the prior art, for silt in different regions, a large number of tests are usually required to explore the applicability of silt and different types of curing agents in order to determine the silt solidification soil preparation plan with the strength required for the project. This method of using a large number of tests requires the preparation of different test samples and is easily restricted by the curing age of the samples. The whole process is time-consuming and labor-intensive. Summary of the invention

[0005] The purpose of this application is to provide a method and system for predicting and improving the strength of silt-solidified soil based on physical and chemical properties. While realizing the strength prediction of silt-solidified soil, a silt-solidified soil strength improvement plan is formed, making the whole process more time-saving and labor-saving.

[0006] To achieve the above objectives, this application provides the following solutions.

[0007] In the first aspect, the present application provides a method for predicting and improving the strength of silt-stabilized soil based on physical and chemical properties, and the method for predicting and improving the strength of silt-stabilized soil based on physical and chemical properties includes: summarizing the influencing factors of the strength of silt-stabilized soil, and establishing a correlation database between the influencing factors and the strength of silt-stabilized soil; classifying the influencing factors to obtain curing agent parameters and silt physical and chemical parameters; the curing agent parameters at least include the curing agent dosage; the physical and chemical parameters include unimprovable parameters and improveable parameters; the unimprovable parameters at least include the median particle size; the improveable parameters at least include the organic matter content; based on the correlation database, a strength prediction model is established using a specific algorithm, and the parameter boundary range of the strength prediction model is determined; the parameter boundary range includes: an unimprovable parameter boundary range and an improveable parameter boundary range; obtaining the measured values ​​of the physical and chemical parameters of the silt to be evaluated; the measured values ​​of the physical and chemical parameters include: the measured values ​​of the unimprovable parameters and the improveable parameters The method comprises the following steps: first, inputting the measured values ​​of the unimprovable parameters and the measured values ​​of the improveable parameters directly into the strength prediction model; second, inputting the measured values ​​of the unimprovable parameters directly into the strength prediction model, determining the first optimal parameter value of the improveable parameters, and inputting the first optimal parameter value into the strength prediction model; third, inputting the method comprises the following steps: determining the limit parameter value of the unimprovable parameters exceeding the boundary range of the unimprovable parameters, determining the second optimal parameter value of the improveable parameters, and inputting the limit parameter value and the second optimal parameter value into the strength prediction model; and dividing the evaluation paths based on the measured values ​​of the physical and chemical parameters, the boundary range of the parameters, and the strength evaluation system of the silt solidified soil to form a silt solidified soil strength improvement plan.

[0008] Optionally, the third evaluation path also includes: conducting a sludge solidification test based on the second optimal parameters to obtain a test solidification strength; when the test solidification strength is greater than or equal to the output result of the strength prediction model, determining the output result of the strength prediction model as a solidification strength guarantee value; when the test solidification strength is less than the output result of the strength prediction model, changing the curing agent parameters input into the strength prediction model until the output result of the strength prediction model is equal to the test solidification strength, and determining the curing agent parameters input into the strength prediction model when the output result of the strength prediction model is equal to the test solidification strength as model curing agent parameters, and calculating the parameter amplification factor based on the model curing agent parameters and the curing agent parameters in the sludge solidification test.

[0009] Optionally, the calculation formula of the parameter amplification factor is: ; In the formula, is the parameter magnification factor, is the model curing agent parameter, It is the curing agent parameter in the sludge solidification test.

[0010] Optionally, based on the measured values ​​of the physical and chemical parameters, the parameter boundary ranges and the silt-solidified soil strength evaluation system, an evaluation path is divided to form a silt-solidified soil strength improvement plan, which specifically includes: comparing the measured values ​​of the physical and chemical parameters with the parameter boundary ranges; when all the measured values ​​of the physical and chemical parameters are within the parameter boundary ranges, executing the first evaluation path, and determining the output result of the strength prediction model as the solidification strength prediction value; the solidification strength prediction value is used to guide the improvement of the silt-solidified soil strength; when all the measured values ​​of the unimprovable parameters are within the unimprovable parameter boundary ranges, Moreover, when some or all of the measured values ​​of the improveable parameters are outside the boundary range of the improveable parameters, the second evaluation path is executed, the output result of the strength prediction model is determined as the expected value of the curing strength, and the strength of the silt-solidified soil is improved by curing agent improvement; when some or all of the measured values ​​of the unimprovable parameters are outside the boundary range of the unimprovable parameters, the third evaluation path is executed, and when the test curing strength is less than the output result of the strength prediction model, the curing agent parameter in the subsequent silt-solidified soil strength improvement should be the curing agent parameter input into the strength prediction model divided by the parameter amplification factor.

[0011] Optionally, determining the first optimal parameter value of the improvable parameter specifically includes: selecting multiple groups of test parameters within the boundary range of the improvable parameter using the orthogonal method or the complete method; inputting the measured values ​​of the unimprovable parameter and each group of test parameters into the strength prediction model to obtain different output results; comparing all the output results, and determining a group of test parameters corresponding to the largest output result as the first optimal parameter.

[0012] Optionally, determining a boundary parameter value of an unimprovable parameter that exceeds the boundary range of the unimprovable parameter specifically includes: determining different boundary values ​​of the boundary range of the unimprovable parameter; when the measured value of the unimprovable parameter is outside the boundary range of the unimprovable parameter, selecting a boundary value closest to the measured value of the unimprovable parameter as the boundary parameter value of the unimprovable parameter.

[0013] Optionally, determining the second optimal parameter value of the improvable parameter specifically includes: selecting multiple groups of test parameters using the orthogonal method or the complete method within the boundary range of the improvable parameter; inputting the boundary parameter values ​​of the unimprovable parameter that exceed the boundary range of the unimprovable parameter, and each group of test parameters into the intensity prediction model to obtain different output results; comparing all the output results, and determining a group of test parameters corresponding to the largest output result as the second optimal parameters.

[0014] Optionally, the specific algorithm is a BP neural network algorithm, a decision tree algorithm, a random forest algorithm or a gradient boosting algorithm.

[0015] Optionally, the non-improvable parameters also include: plasticity index, the ratio of quartz to plagioclase content, and the ratio of quartz to clay mineral content; the improvable parameters also include: the ratio of water content to liquid limit, the ratio of silicon to calcium content, and the ratio of aluminum to calcium content.

[0016] In a second aspect, the present application also provides a computer system, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for predicting and improving the strength of silt-solidified soil based on physical and chemical properties.

[0017] According to the specific embodiments provided in this application, this application discloses the following technical effects.

[0018] This application takes full account of the influence of physical and chemical parameters on the strength of silt solidified soil, and establishes a strength prediction model based on an associated database. At the same time, a silt solidified soil strength evaluation system including different evaluation paths is also built, and the strength prediction model is used to predict the strength of silt solidified soil, and the reliability of the strength prediction model is evaluated using different evaluation paths. In addition, this application also plans different evaluation paths according to the measured values ​​of physical and chemical parameters and the parameter boundary range of the strength prediction model, and adjusts the physical and chemical parameters or curing agent parameters of silt under different evaluation paths, so as to form a silt solidified soil strength improvement plan. Therefore, this application can effectively predict the strength of silt solidified soil, and generate a strength improvement plan, which effectively reduces the consumption of manpower, material resources and time while reducing the amount of experiments required to be carried out in actual engineering. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0020] Figure 1 A flow chart of a method for predicting and improving the strength of silt-stabilized soil based on physical and chemical properties provided in an embodiment of the present application.

[0021] Figure 2 This is a diagram of the experimental verification results of the unconfined compressive strength test provided in the embodiment of the present application.

[0022] Figure 3 This is a diagram of the internal structure of a computer system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0024] The purpose of this application is to provide a method and system for predicting and improving the strength of silt-solidified soil based on physical and chemical properties. While realizing the strength prediction of silt-solidified soil, a silt-solidified soil strength improvement plan is formed, making the whole process more time-saving and labor-saving.

[0025] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0026] Example 1

[0027] This embodiment provides a method for predicting and improving the strength of silt-solidified soil based on physical and chemical properties. Figure 1 As shown, the method for predicting and improving the strength of silt-stabilized soil based on physical and chemical properties is as follows.

[0028] Step S1: Summarize the influencing factors of the strength of silt-stabilized soil, and establish a correlation database between the influencing factors and the strength of silt-stabilized soil.

[0029] In this embodiment, the influencing factors of the strength of silt-solidified soil include: median particle size, organic matter content, plasticity index, ratio of water content to liquid limit, ratio of silicon to calcium content, etc.; multiple groups of historical data of influencing factors are stored in the associated database, each group of historical data corresponds to a silt-solidified soil strength, and different groups of historical data and their corresponding silt-solidified soil strengths together constitute the associated database. Among them, the associated database is established based on the numpy module of python.

[0030] Step S2: classify the influencing factors to obtain the curing agent parameters and the physicochemical parameters of the sludge; the physicochemical parameters include unimprovable parameters and improveable parameters.

[0031] In this embodiment, the curing agent parameters include: curing agent dosage, curing agent type, etc.; the unimprovable parameters include: median particle size, plasticity index, quartz to plagioclase content ratio, quartz to clay mineral content ratio, etc.; the improveable parameters include: organic matter content, water content to liquid limit ratio, silicon (Si) to calcium (Ca) element content ratio, aluminum (Al) to calcium (Ca) element content ratio, etc.

[0032] In addition, the physical and chemical parameters in step S2 refer to the physical parameters and chemical parameters of the sludge, such as the median particle size as a physical parameter and Si / Ca as a chemical parameter. The physical parameters and chemical parameters affect the progress of the hydration reaction between the sludge and the curing agent to a certain extent.

[0033] Step S3: Based on the associated database, a strength prediction model is established using a specific algorithm, and a parameter boundary range of the strength prediction model is determined; the parameter boundary range includes: an unimprovable parameter boundary range and an improveable parameter boundary range.

[0034] In this embodiment, the associated database is divided into training set, validation set and test set based on step S1, and the historical data of different groups of influencing factors are used as input, and the silt solidification soil strength corresponding to the historical data of different groups is used as output, and the strength prediction model is established based on the BP (Back Propagation) neural network algorithm in python. Among them, there are three types of input parameters of the strength prediction model, namely, curing agent parameters, non-improvable parameters and improveable parameters. The curing agent parameters do not need to set the parameter boundary range, but the non-improvable parameters and improveable parameters need to set the parameter boundary range. The specific parameter boundary ranges are shown in Table 1.

[0035] Table 1 Parameter boundary range table

[0036]

[0037] As a preferred implementation mode, a decision tree algorithm (Extreme Gradient Boosting, XGBoost), a random forest algorithm or a gradient boosting algorithm may also be used to establish a strength prediction model.

[0038] Step S4: obtaining measured values ​​of the physical and chemical parameters of the sludge to be evaluated; the measured values ​​of the physical and chemical parameters include: measured values ​​of non-improvable parameters and measured values ​​of improveable parameters.

[0039] In this embodiment, the physical and chemical parameters of the sludge to be evaluated need to be determined by means of experiments. The moisture content, liquid limit and median particle size of the sludge to be evaluated can be determined by standardized operations according to the "Geotechnical Test Procedures"; the mineral composition of the sludge to be evaluated (quartz, plagioclase, clay minerals, etc.) can be determined by using a D8 Advance X-ray diffractometer; the chemical composition of the sludge to be evaluated (Si, Ca, Al, etc.) can be determined by using a PW2400 / 40 X-fluorescence spectrometer.

[0040] In addition, in order to ensure the validity of the measured values ​​of physical and chemical parameters, the test results will be processed, that is, the maximum and minimum values ​​of multiple data of each test parameter will be removed and the average value will be taken, and finally this average value will be used as the measured value of the parameter.

[0041] Step S5: Establish a silt-solidified soil strength evaluation system; the silt-solidified soil strength evaluation system includes: a first evaluation path, a second evaluation path and a third evaluation path; the first evaluation path includes: directly inputting the measured values ​​of the unimprovable parameters and the measured values ​​of the improvable parameters into the strength prediction model; the second evaluation path includes: directly inputting the measured values ​​of the unimprovable parameters into the strength prediction model, determining the first optimal parameter value of the improvable parameters, and inputting the first optimal parameter value into the strength prediction model; the third evaluation path includes: determining the limit parameter value of the unimprovable parameter that exceeds the boundary range of the unimprovable parameter, determining the second optimal parameter value of the improvable parameter, and inputting the limit parameter value and the second optimal parameter value into the strength prediction model.

[0042] In this embodiment, the third evaluation path also includes: conducting a sludge solidification test (i.e., unconfined compressive strength test) based on the second optimal parameters to obtain the test solidification strength; when the test solidification strength is greater than or equal to the output result of the strength prediction model, the output result of the strength prediction model is determined as the solidification strength guarantee value; when the test solidification strength is less than the output result of the strength prediction model, the curing agent parameter input to the strength prediction model is changed until the output result of the strength prediction model is equal to the test solidification strength, and the curing agent parameter input to the strength prediction model when the output result of the strength prediction model is equal to the test solidification strength is determined as the model curing agent parameter, and the parameter amplification factor is calculated based on the model curing agent parameter and the curing agent parameter in the sludge solidification test. The calculation formula of the parameter amplification factor is as follows.

[0043] .

[0044] In the formula, is the parameter magnification factor, is the model curing agent parameter, It is the curing agent parameter in the sludge solidification test.

[0045] Furthermore, the first optimal parameter value of the improvable parameter is determined, specifically including: selecting multiple groups of test parameters within the boundary range of the improvable parameter using the orthogonal method or the complete method; inputting the measured values ​​of the unimprovable parameter and each group of test parameters into the strength prediction model to obtain different output results; comparing all the output results, and determining a group of test parameters corresponding to the maximum output result as the first optimal parameter.

[0046] Furthermore, determining the boundary parameter value of the unimprovable parameter that exceeds the boundary range of the unimprovable parameter specifically includes: determining different boundary values ​​of the boundary range of the unimprovable parameter; when the measured value of the unimprovable parameter is outside the boundary range of the unimprovable parameter, selecting a boundary value closest to the measured value of the unimprovable parameter as the boundary parameter value of the unimprovable parameter.

[0047] For example: it is known that the parameter boundary range of the median particle size is 9-11μm, and the boundary values ​​of this parameter boundary range are 9μm and 11μm respectively. If the median particle size measured by the experiment is 8μm, it is obviously not within the parameter boundary range, so the boundary value of 9μm closest to 8μm is taken as the boundary parameter value of the median particle size.

[0048] Furthermore, the second optimal parameter value of the improvable parameter is determined, specifically including: selecting multiple groups of test parameters within the boundary range of the improvable parameter using the orthogonal method or the complete method; inputting the boundary parameter values ​​of the unimprovable parameters that exceed the boundary range of the unimprovable parameter, and each group of test parameters into the strength prediction model to obtain different output results; comparing all the output results, and determining a group of test parameters corresponding to the largest output result as the second optimal parameters.

[0049] Step S6: Based on the measured values ​​of physical and chemical parameters, the boundary range of parameters and the silt-stabilized soil strength evaluation system, the evaluation paths are divided to form a silt-stabilized soil strength improvement plan.

[0050] In this embodiment, step S6 is specifically as follows.

[0051] Step S61: Compare the measured value of the physical and chemical parameter with the parameter boundary range.

[0052] Step S62: When all the measured values ​​of the physical and chemical parameters are within the parameter boundary range, the first evaluation path is executed, and the output result of the strength prediction model is determined as the solidification strength prediction value; the solidification strength prediction value is used to guide the improvement of the strength of silt solidified soil.

[0053] Among them, the execution of the first evaluation path shows that the strength prediction model established in step S3 is completely suitable for the prediction of the solidification strength of the sludge to be evaluated. The improvement of the strength of the sludge solidified soil only needs to input different parameter values ​​into the strength prediction model, and adjust the corresponding parameter values ​​by comparing the output results of the strength prediction model. The optimal output result (i.e., the maximum output result) of the strength prediction model can be used as the optimal solidification strength value of the sludge to be evaluated. Different parameter values ​​are selected by using the orthogonal method or the complete method within the boundary range of the non-improvable parameter / the boundary range of the improveable parameter.

[0054] Step S63: When all the measured values ​​of the unimprovable parameters are within the boundary range of the unimprovable parameters, and some or all of the measured values ​​of the improvable parameters are outside the boundary range of the improvable parameters, the second evaluation path is executed, the output result of the strength prediction model is determined as the expected value of the solidification strength, and the strength of the silt solidified soil is improved by improving the solidifying agent.

[0055] Among them, the execution of the second evaluation path shows that although the strength prediction model established in step S3 is suitable for predicting the solidification strength of the sludge to be evaluated, its prediction result is only used as an expected value. In addition to executing the unimprovable parameters and the improveable parameters according to the second evaluation path, the improvement of the strength of the sludge solidified soil also needs to be achieved through the improvement of the curing agent to achieve the expected solidification strength.

[0056] Step S64: When some or all of the measured values ​​of the unimprovable parameters are outside the boundary range of the unimprovable parameters, the third evaluation path is executed, and when the test curing strength is less than the output result of the strength prediction model, the curing agent parameter in the subsequent silt-solidified soil strength improvement should be the curing agent parameter of the input strength prediction model divided by the parameter amplification factor.

[0057] Among them, the third evaluation path is executed. When the test curing strength is greater than or equal to the output result of the strength prediction model, the output result of the strength prediction model established in step S3 is conservative but still valid, and can be used as the curing strength guarantee value in the strength improvement of silt solidified soil; when the test curing strength is less than the output result of the strength prediction model, the output result of the strength prediction model established in step S3 is not accurate. In order to achieve the improvement of the strength of silt solidified soil, the amount of curing agent added in the subsequent silt solidification test should be the amount of curing agent added into the strength prediction model divided by the parameter amplification factor.

[0058] Based on the above analysis, the scheme for improving the strength of silt-solidified soil is mainly reflected in the optimal parameter combination. Among them, the scheme formed according to the first and second evaluation paths is mainly to optimize the improveable parameters and improve the adaptability between silt and curing agent, supplemented by replacing the curing agent or replacing part of the curing agent components; and the scheme formed according to the third evaluation path is an experimental design scheme formed to meet the strength requirements of silt-solidified soil. Therefore, no matter which method is used, it effectively reduces the consumption of manpower, material resources and time, and can improve the adaptability between silt and curing agent, which has extremely high theoretical value and engineering practice significance.

[0059] Example 2

[0060] This embodiment provides a practical application scenario of a method for predicting and improving the strength of silt-stabilized soil based on physical and chemical properties, as follows.

[0061] Taking coastal silt in Dalian, Lianyungang, Qingdao and other places as the object, the strength data of solidified soil prepared by cement-based curing agent in actual projects were collected, and the correlation database between the influencing factors and curing strength of silt solidified soil was established based on the numpy module of python. The cumulative number of data links in the correlation database is 1508, and the influencing factors include: median particle size d 50 , organic matter content, plasticity index, water content / liquid limit, Si / Ca, Al / Ca, quartz / plagioclase, quartz / clay minerals and curing agent dosage. Among them, the curing agent dosage is 3.75%~6.25% (mass ratio to sludge).

[0062] The influencing factors were classified to obtain the curing agent parameters and the physical and chemical parameters of the sludge. Among them, the physical and chemical parameters are divided into improveable parameters and unimprovable parameters; the curing agent parameters are mainly the curing agent dosage; the improveable parameters include: organic matter content, moisture content / liquid limit, Si / Ca and Al / Ca; the unimprovable parameters include: median particle size d 50 , plasticity index, quartz / plagioclase, quartz / clay minerals.

[0063] Through the associated database, a silt-stabilized soil strength prediction model was established based on the BP neural network algorithm in python, and the data in the associated database were randomly divided into 70% as training data and 30% as verification data.

[0064] A silt-stabilized soil strength evaluation system is established as shown in Table 2, and the parameter boundary range of each influencing factor is clarified in the system.

[0065] Table 2 Silt-stabilized soil strength evaluation system

[0066]

[0067] The silt in the coastal area of ​​Tianjin was used as the silt to be solidified. The basic values ​​of different parameters were obtained through experiments. After subsequent data processing, the measured values ​​of different parameters were obtained, including: curing agent dosage = 5%, median particle size = 9um, organic matter content = 6%, plasticity index = 17kpa, water content / liquid limit = 1.33, Si / Ca = 6.44, Al / Ca = 1.61, quartz / plagioclase = 30.1, quartz / clay mineral = 12.1.

[0068] The measured values ​​of different parameters of the sludge to be solidified were compared with Table 2, and the second evaluation path was selected for prediction and analysis. For the unimprovable parameters, the measured values ​​were used as the input of the model; for the improveable parameters, in view of the relatively low organic matter content of the sludge in the coastal area of ​​Tianjin and the characteristics of the pipeline casting mode adopted in the actual project, the organic matter content and water content / liquid limit were kept unchanged, and the complete method was used to gradually reduce Si / Ca and Al / Ca (i.e., increase the Ca element content in the curing agent), form multiple groups of parameters and input them into the model, and use the optimal output result of the model as the expected value of the expected curing effect, that is, the expected curing strength can be achieved by improving the curing agent.

[0069] Based on the above-mentioned solidified sludge strength improvement plan, the corresponding test (unconfined compressive strength test) was designed for verification. Figure 2 The experimental verification result of this embodiment shows that the above-mentioned solidified sludge strength improvement scheme can greatly improve the applicability between sludge and the curing agent. Under the premise that the amount of curing agent added remains unchanged, the strength of the solidified soil can be increased by up to 23.8%.

[0070] Example 3

[0071] This embodiment provides a computer system, which may be a server or a terminal, and its internal structure diagram may be as follows: Figure 3As shown. The computer system includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer system is used to provide computing and control capabilities. The memory of the computer system includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer system is used to store video tag processing data. The input / output interface of the computer system is used to exchange information between the processor and an external device. The communication interface of the computer system is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for predicting and improving the strength of silt-solidified soil based on physical and chemical properties is implemented.

[0072] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer system to which the scheme of the present application is applied. The specific computer system may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0073] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0074] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0075] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0076] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for predicting and improving the strength of silt-stabilized soil based on physical and chemical properties, characterized in that: The method for predicting and improving the strength of silt-stabilized soil based on physical and chemical properties includes: Summarize the influencing factors of the strength of silt-stabilized soil, and establish a correlation database between the influencing factors and the strength of silt-stabilized soil; The influencing factors are classified to obtain curing agent parameters and physicochemical parameters of sludge; the curing agent parameters at least include the curing agent dosage; the physicochemical parameters include unimprovable parameters and improveable parameters; the unimprovable parameters at least include the median particle size; the improveable parameters at least include the organic matter content; Based on the associated database, a strength prediction model is established by using a specific algorithm, and a parameter boundary range of the strength prediction model is determined; the parameter boundary range includes: an unimprovable parameter boundary range and an improveable parameter boundary range; Obtaining measured values ​​of physical and chemical parameters of the sludge to be evaluated; the measured values ​​of the physical and chemical parameters include: measured values ​​of non-improvable parameters and measured values ​​of improveable parameters; Establish a silt solidified soil strength evaluation system; the silt solidified soil strength evaluation system includes: a first evaluation path, a second evaluation path and a third evaluation path; the first evaluation path includes: directly inputting the measured value of the unimprovable parameter and the measured value of the improveable parameter into the strength prediction model; the second evaluation path includes: directly inputting the measured value of the unimprovable parameter into the strength prediction model, determining the first optimal parameter value of the improveable parameter, and inputting the first optimal parameter value into the strength prediction model; the third evaluation path includes: determining the limit parameter value of the unimprovable parameter that exceeds the boundary range of the unimprovable parameter, determining the second optimal parameter value of the improveable parameter, and inputting the limit parameter value and the second optimal parameter value into the strength prediction model; Based on the measured values ​​of the physical and chemical parameters, the boundary ranges of the parameters and the silt-solidified soil strength evaluation system, evaluation paths are divided to form a silt-solidified soil strength improvement plan.

2. The method for predicting and improving the strength of silt-stabilized soil based on physical and chemical properties according to claim 1 is characterized in that: The third evaluation path also includes: Performing a sludge solidification test based on the second optimal parameter to obtain a test solidification strength; When the test curing strength is greater than or equal to the output result of the strength prediction model, determining the output result of the strength prediction model as the curing strength guarantee value; When the test curing strength is less than the output result of the strength prediction model, the curing agent parameters input into the strength prediction model are changed until the output result of the strength prediction model is equal to the test curing strength, and the curing agent parameters input into the strength prediction model when the output result of the strength prediction model is equal to the test curing strength are determined as model curing agent parameters, and the parameter amplification coefficient is calculated based on the model curing agent parameters and the curing agent parameters in the sludge solidification test.

3. The method for predicting and improving the strength of silt-stabilized soil based on physical and chemical properties according to claim 2 is characterized in that: The calculation formula of the parameter amplification factor is: ; In the formula, is the parameter magnification factor, is the model curing agent parameter, It is the curing agent parameter in the sludge solidification test.

4. The method for predicting and improving the strength of silt-stabilized soil based on physical and chemical properties according to claim 2 is characterized in that: Based on the measured values ​​of the physical and chemical parameters, the boundary range of the parameters and the silt-stabilized soil strength evaluation system, the evaluation paths are divided to form a silt-stabilized soil strength improvement plan, which specifically includes: Comparing the measured value of the physical and chemical parameter with the parameter boundary range; When all the measured values ​​of the physical and chemical parameters are within the parameter boundary range, the first evaluation path is executed, and the output result of the strength prediction model is determined as the solidification strength prediction value; the solidification strength prediction value is used to guide the improvement of the strength of the silt solidified soil; When all the measured values ​​of the unimprovable parameters are within the boundary range of the unimprovable parameters, and part or all of the measured values ​​of the improvable parameters are outside the boundary range of the improvable parameters, the second evaluation path is executed, the output result of the strength prediction model is determined as the expected value of the solidification strength, and the strength of the silt solidified soil is improved by improving the solidifying agent; When some or all of the measured values ​​of the unimprovable parameters are outside the boundary range of the unimprovable parameters, the third evaluation path is executed, and when the test curing strength is less than the output result of the strength prediction model, the curing agent parameters in the subsequent silt-solidified soil strength improvement should be the curing agent parameters input into the strength prediction model divided by the parameter amplification factor.

5. The method for predicting and improving the strength of silt-stabilized soil based on physical and chemical properties according to claim 1 is characterized in that: Determining a first optimal parameter value of an improveable parameter specifically includes: Selecting multiple groups of test parameters within the boundary range of the improvable parameters by using an orthogonal method or a complete method; Input the measured values ​​of the non-improvable parameters and each group of test parameters into the strength prediction model to obtain different output results; All output results are compared, and a set of test parameters corresponding to the maximum output result is determined as the first optimal parameters.

6. The method for predicting and improving the strength of silt-stabilized soil based on physical and chemical properties according to claim 1 is characterized in that: Determining the limit parameter value of the non-improvable parameter that exceeds the boundary range of the non-improvable parameter specifically includes: Determining different limit values ​​of the boundary range of the non-improvable parameter; When the actual measured value of the unimprovable parameter is outside the boundary range of the unimprovable parameter, a limit value closest to the actual measured value of the unimprovable parameter is selected as the limit parameter value of the unimprovable parameter.

7. The method for predicting and improving the strength of silt-stabilized soil based on physical and chemical properties according to claim 1 is characterized in that: Determining a second optimal parameter value of the improveable parameter specifically includes: Selecting multiple groups of test parameters within the boundary range of the improvable parameters by using an orthogonal method or a complete method; Inputting the limit parameter values ​​of the non-improvable parameters that exceed the boundary range of the non-improvable parameters and each group of test parameters into the strength prediction model respectively to obtain different output results; All output results are compared, and a set of test parameters corresponding to the maximum output result is determined as the second optimal parameters.

8. The method for predicting and improving the strength of silt-stabilized soil based on physical and chemical properties according to claim 1 is characterized in that: The specific algorithm is a BP neural network algorithm, a decision tree algorithm, a random forest algorithm or a gradient boosting algorithm.

9. The method for predicting and improving the strength of silt-stabilized soil based on physical and chemical properties according to claim 1, characterized in that: The non-improvable parameters also include: plasticity index, ratio of quartz to plagioclase content, and ratio of quartz to clay mineral content; the improveable parameters also include: ratio of water content to liquid limit, ratio of silicon to calcium content, and ratio of aluminum to calcium content.

10. A computer system comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for predicting and improving the strength of silt-solidified soil based on physical and chemical properties as described in any one of claims 1 to 9.

Citation Information

Patent Citations

  • Rheological stratum foundation pit excavation long-time displacement prediction and evaluation method

    CN103699774A

  • Strength prediction method and system for sludge solidified soil

    CN115081067A