Methods, apparatus, equipment and storage medium for predicting the dynamic strength of lightweight soil using air bubbles

Abstract

This application discloses a method, apparatus, device, and storage medium for predicting the dynamic strength of lightweight soil using bubble-based methods. The method includes: determining lightweight soil sample information; inputting the lightweight soil sample information into a preset dynamic strength prediction model; and performing dynamic strength prediction processing on the lightweight soil sample information based on the dynamic strength prediction model to obtain lightweight soil dynamic strength data. The dynamic strength prediction model is trained using a preset number of dynamic strength corrosion resistance coefficient prediction formulas under different environmental factors. This application relates to the field of concrete strength prediction technology. By using a dynamic strength prediction model trained with a preset number of dynamic strength corrosion resistance coefficient prediction formulas under different environmental factors to predict the dynamic strength of lightweight soil samples, the accuracy of the dynamic strength prediction data for lightweight soil samples is improved by considering different environmental factors.

Description

Technical Field

[0001] This application relates to the field of concrete strength prediction technology, and in particular to a method, apparatus, equipment and storage medium for predicting the dynamic strength of lightweight soil with air bubbles. Background Technology

[0002] Aerated lightweight soil is a lightweight geosynthetic material containing a large number of closed pores, formed by uniformly mixing pre-made foam with cement slurry, and optionally adding other aggregates (such as clay and sand), followed by pouring and curing. Due to its adjustable density and strength, superior engineering performance, convenient construction, and good economy, aerated lightweight soil has broad application prospects in roadbed filling, bridge abutment filling, slope treatment, retaining wall backfill, and pipeline backfilling projects.

[0003] Dynamic strength testing refers to the test that determines the strength and deformation capacity of soil under dynamic load. It is the basis for solving the dynamic stability of soil. During the operation phase of transportation infrastructure, the service environment of aerated lightweight soil is extremely complex. It will be subjected to millions of traffic loads (cars, trains, airplanes). Therefore, it is necessary to accurately predict the strength of lightweight soil to improve the reliability of the project.

[0004] Existing technologies predict concrete strength using model prediction methods. However, in actual engineering applications, lightweight soil is not only subject to loads but also to various environmental factors, resulting in low accuracy of strength prediction. Summary of the Invention

[0005] The main objective of this application is to provide a method, apparatus, equipment, and storage medium for predicting the dynamic strength of lightweight soil using bubbles, aiming to solve the technical problem of difficulty in predicting the strength of lightweight soil considering environmental durability factors in the prior art.

[0006] To achieve the above objectives, this application provides a method for predicting the dynamic strength of lightweight soil using air bubbles, the method comprising:

[0007] Determine information about lightweight soil samples;

[0008] The information of the lightweight soil sample is input into a preset dynamic strength prediction model. Based on the dynamic strength prediction model, the dynamic strength prediction of the lightweight soil sample is processed to obtain dynamic strength data of lightweight soil. The dynamic strength prediction model is trained based on a preset number of dynamic strength corrosion resistance coefficient prediction formulas under different environmental factors.

[0009] Optionally, the step of determining the information of the lightweight soil sample includes:

[0010] Obtain lightweight soil samples;

[0011] The lightweight soil sample was subjected to sample analysis to obtain lightweight soil sample information.

[0012] Optionally, the step of performing sample analysis on the lightweight soil sample to obtain lightweight soil sample information includes:

[0013] The lightweight soil samples were subjected to environmental analysis and property analysis respectively to obtain the environmental information and property data of the lightweight soil.

[0014] Based on the environmental information and the attribute data, the information of the lightweight soil sample is determined.

[0015] Optionally, the step of performing dynamic strength prediction processing on the lightweight soil sample information based on the dynamic strength prediction model to obtain lightweight soil dynamic strength data includes:

[0016] Based on the dynamic strength prediction model and the environmental information, the corresponding dynamic strength corrosion resistance coefficient prediction formula is determined;

[0017] Based on the dynamic strength corrosion resistance coefficient prediction formula and the attribute data, the dynamic strength data of lightweight soil is calculated.

[0018] Optionally, the environmental information includes chemical immersion environment and wet-dry cycle environment, and the attribute data includes concentration data, density data, chemical medium information data, time data, and cycle number data. The step of calculating the dynamic strength data of lightweight soil based on the dynamic strength corrosion resistance coefficient prediction formula and the attribute data includes:

[0019] Based on the dynamic strength prediction model, the following preset formula for predicting the dynamic strength corrosion resistance coefficient is determined:

[0020]

[0021]

[0022] Wherein, y1 is the prediction formula for the dynamic strength corrosion resistance coefficient under chemical immersion environment, y2 is the prediction formula for the dynamic strength corrosion resistance coefficient under the dry-wet cycle environment, c is the concentration coefficient, ρ is the density coefficient, λ is the chemical medium coefficient, t is the immersion time coefficient, and N is the dry-wet cycle number coefficient.

[0023] Based on the environmental information, a corresponding prediction formula for the dynamic strength corrosion resistance coefficient is determined.

[0024] The steps for calculating the dynamic strength data of lightweight soil based on the dynamic strength corrosion resistance coefficient prediction formula and the attribute data include:

[0025] Substituting the attribute data into the corresponding dynamic strength corrosion resistance coefficient prediction formula yields the dynamic strength data of lightweight soil.

[0026] Optionally, before the step of obtaining lightweight soil sample information, the method includes:

[0027] Obtain lightweight soil training samples and their dynamic strength data labels;

[0028] Based on the aforementioned lightweight soil training samples, a formula for predicting the dynamic strength corrosion resistance coefficient was determined.

[0029] Based on the lightweight soil training samples, the dynamic strength corrosion resistance coefficient prediction formula, and the dynamic strength data labels of the lightweight soil training samples, the preset training model is iteratively trained to obtain a dynamic strength prediction model that meets the accuracy requirements.

[0030] Optionally, the step of iteratively training a preset model to be trained based on the lightweight soil training samples, the dynamic strength corrosion resistance coefficient prediction formula, and the dynamic strength data labels of the lightweight soil training samples to obtain a dynamic strength prediction model that meets the accuracy requirements includes:

[0031] The lightweight soil training sample is input into the model to be trained, and the predicted dynamic strength data is obtained based on the dynamic strength corrosion resistance coefficient prediction formula.

[0032] The difference between the predicted dynamic strength data and the dynamic strength data labels of the lightweight soil training samples is calculated to obtain the error result;

[0033] Based on the error result, determine whether the error result meets the error standard indicated by the preset error threshold range;

[0034] If the error result does not meet the error standard indicated by the preset error threshold range, return to the step of inputting the lightweight soil training sample into the model to be trained, and obtaining the predicted dynamic strength data based on the dynamic strength corrosion resistance coefficient prediction formula, until the training error result meets the error standard indicated by the preset error threshold range, and then stop training to obtain the dynamic strength prediction model.

[0035] This application also provides a bubble-based lightweight soil dynamic strength prediction device, the bubble-based lightweight soil dynamic strength prediction device comprising:

[0036] The determination module is used to determine information about lightweight soil samples;

[0037] The prediction module is used to input the information of the lightweight soil sample into a preset dynamic strength prediction model, and perform dynamic strength prediction processing on the information of the lightweight soil sample based on the dynamic strength prediction model to obtain dynamic strength data of lightweight soil. The dynamic strength prediction model is composed of a preset number of dynamic strength corrosion resistance coefficient prediction formulas under different environmental factors.

[0038] This application also provides a bubble-based lightweight soil dynamic strength prediction device, which includes: a memory, a processor, and a program stored in the memory for implementing the bubble-based lightweight soil dynamic strength prediction method.

[0039] The memory is used to store the program for implementing the method for predicting the dynamic strength of lightweight soil with bubbles;

[0040] The processor is used to execute a program that implements the bubble-based lightweight soil dynamic strength prediction method, thereby implementing the steps of the bubble-based lightweight soil dynamic strength prediction method.

[0041] This application also provides a storage medium storing a program for implementing a bubble-based lightweight soil dynamic strength prediction method, wherein the program for implementing the bubble-based lightweight soil dynamic strength prediction method is executed by a processor to implement the steps of the bubble-based lightweight soil dynamic strength prediction method.

[0042] This application provides a method, apparatus, equipment, and storage medium for predicting the dynamic strength of lightweight soil using bubble-based methods. Compared to existing technologies where lightweight soil is affected not only by loads but also by various environmental factors, leading to low accuracy in strength prediction, this application determines lightweight soil sample information; inputs this information into a preset dynamic strength prediction model; and performs dynamic strength prediction processing on the lightweight soil sample information based on the dynamic strength prediction model to obtain dynamic strength data. The dynamic strength prediction model is trained using a preset number of dynamic strength corrosion resistance coefficient prediction formulas under different environmental factors. In other words, this application uses a dynamic strength prediction model trained with a preset number of dynamic strength corrosion resistance coefficient prediction formulas under different environmental factors to predict the dynamic strength of lightweight soil samples, thus improving the accuracy of the predicted dynamic strength data. Attached Figure Description

[0043] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without any creative effort.

[0044] Figure 1 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of this application;

[0045] Figure 2 This is a flowchart illustrating the first embodiment of the bubble-based lightweight soil dynamic strength prediction method of this application;

[0046] Figure 3 This is a schematic diagram of the module of the bubble-based lightweight soil dynamic strength prediction device of this application.

[0047] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0048] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0049] like Figure 1 As shown, Figure 1 This is a schematic diagram of the terminal structure of the hardware operating environment involved in the embodiments of this application.

[0050] The terminal in this application embodiment can be a PC, or a smartphone, tablet computer, e-book reader, MP3 (Moving Picture Experts Group Audio Layer III) player, MP4 (Moving Picture Experts Group Audio Layer IV) player, portable computer, or other portable terminal devices with display functions.

[0051] like Figure 1 As shown, the terminal may include: a processor 1001, such as a CPU; a network interface 1004; a user interface 1003; a memory 1005; and a communication bus 1002. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and an input unit such as a keyboard. Optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0052] Optionally, the terminal may also include a camera, RF (Radio Frequency) circuitry, sensors, audio circuitry, a WiFi module, and so on. Sensors may include light sensors, motion sensors, and other sensors. Specifically, light sensors may include ambient light sensors and proximity sensors. The ambient light sensor can adjust the display brightness according to the ambient light level, while the proximity sensor can turn off the display and / or backlight when the mobile terminal is moved to the ear. As a type of motion sensor, a gravity accelerometer can detect the magnitude of acceleration in various directions (generally three axes). When stationary, it can detect the magnitude and direction of gravity, and can be used for applications that identify the mobile terminal's posture (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition functions (such as pedometers, taps), etc. Of course, the mobile terminal may also be equipped with other sensors such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, which will not be elaborated here.

[0053] Those skilled in the art will understand that Figure 1 The terminal structure shown does not constitute a limitation on the terminal and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0054] like Figure 1 As shown, the memory 1005, which serves as a computer storage medium, may include an operating device, a network communication module, a user interface module, and a bubble lightweight soil dynamic strength prediction program.

[0055] exist Figure 1 In the terminal shown, the network interface 1004 is mainly used to connect to the backend server and communicate with the backend server; the user interface 1003 is mainly used to connect to the client (user terminal) and communicate with the client; and the processor 1001 can be used to call the bubble lightweight soil dynamic strength prediction program stored in the memory 1005.

[0056] Reference Figure 2 This application provides a method for predicting the dynamic strength of bubble-filled lightweight soil, the method comprising:

[0057] Step S100: Determine the information of the lightweight soil sample;

[0058] Step S200: Input the information of the lightweight soil sample into the preset dynamic strength prediction model. Based on the dynamic strength prediction model, perform dynamic strength prediction processing on the information of the lightweight soil sample to obtain the dynamic strength data of lightweight soil. The dynamic strength prediction model is trained based on the dynamic strength corrosion resistance coefficient prediction formula of a preset number of different environmental factors.

[0059] In this embodiment, a specific application scenario may be:

[0060] Existing technologies predict concrete strength using model prediction methods. However, in actual engineering applications, lightweight soil is not only subject to loads but also to various environmental factors, resulting in low accuracy of strength prediction.

[0061] The specific steps are as follows:

[0062] Step S100: Determine the information of the lightweight soil sample;

[0063] In this embodiment, the bubble lightweight soil dynamic strength prediction method is applied to the bubble lightweight soil dynamic strength prediction device.

[0064] In this embodiment, lightweight soil refers to aerated lightweight soil, which is a lightweight geosynthetic material containing a large number of closed pores formed by uniformly mixing pre-made foam with cement slurry and then pouring and curing it. Because aerated lightweight soil has adjustable density and strength, excellent engineering performance, convenient construction, and good economy, it is commonly used in roadbed filling, bridge abutment filling, slope treatment, retaining wall backfill, and pipeline backfilling projects.

[0065] In this embodiment, the lightweight soil sample information includes environmental information and attribute information of the lightweight soil sample. The environmental information includes chemical soaking environment, such as the environment under sodium sulfate soaking or magnesium sulfate soaking, and wet-dry cycle environment, for example, the environment in which the lightweight soil is repeatedly dried and moistened. The attribute information includes the density of the lightweight soil, the sulfate concentration of the chemical medium, and the type of chemical medium.

[0066] In this embodiment, the device can determine the information of the lightweight soil sample by testing the lightweight soil sample with a laboratory device, or by having the user upload the lightweight soil sample information to the device.

[0067] Specifically, step S100 includes the following steps S110-S120:

[0068] Step S110: Obtain a lightweight soil sample;

[0069] In this embodiment, the lightweight soil sample is a lightweight soil material whose dynamic strength is to be predicted. It can be lightweight soil material to be filled in the project, or lightweight soil material after being filled for a period of time.

[0070] In this embodiment, the device can acquire lightweight soil samples either through a sample grabbing device or by having the user place the sample into the device themselves.

[0071] Step S120: Perform sample analysis on the lightweight soil sample to obtain lightweight soil sample information.

[0072] In this embodiment, the device performs sample analysis on the lightweight soil sample to obtain lightweight soil sample information. The sample analysis can be performed by testing the lightweight soil sample using lightweight soil testing equipment.

[0073] Specifically, step S120 includes the following steps S121-S122:

[0074] Step S121: Perform environmental analysis and attribute analysis on the lightweight soil sample to obtain the environmental information and attribute data of the lightweight soil.

[0075] In this embodiment, the device performs environmental analysis and property analysis on the lightweight soil sample to obtain environmental information and property data of the lightweight soil. The environmental information of the lightweight soil includes chemical soaking environment and wet-dry cycle environment, and the property data of the lightweight soil includes the density of the lightweight soil, the sulfate concentration of the chemical medium, the type of chemical medium, etc.

[0076] Step S122: Determine the lightweight soil sample information based on the environmental information and the attribute data.

[0077] In this embodiment, the lightweight soil sample information consists of the environmental information and the attribute data. The device determines the lightweight soil sample information based on the environmental information and the attribute data.

[0078] Step S200: Input the information of the lightweight soil sample into the preset dynamic strength prediction model. Based on the dynamic strength prediction model, perform dynamic strength prediction processing on the information of the lightweight soil sample to obtain the dynamic strength data of lightweight soil. The dynamic strength prediction model is trained based on the dynamic strength corrosion resistance coefficient prediction formula of a preset number of different environmental factors.

[0079] In this embodiment, the device inputs the lightweight soil sample information into a preset dynamic strength prediction model. Based on the dynamic strength prediction model, the device performs dynamic strength prediction processing on the lightweight soil sample information to obtain lightweight soil dynamic strength data. The dynamic strength prediction model is a neural network model, which is obtained by iteratively training a preset model to be trained based on a preset number of dynamic strength corrosion coefficient prediction formulas under different environmental factors, lightweight soil training samples, and the dynamic strength data labels of the lightweight soil training samples.

[0080] In this application, a dynamic strength prediction model is trained using a preset number of dynamic strength corrosion coefficient prediction formulas under different environmental factors to predict the dynamic strength of lightweight soil samples. This model takes into account different environmental factors, thus improving the accuracy of the dynamic strength prediction data for lightweight soil samples.

[0081] Specifically, step S200 includes the following steps S210-S220:

[0082] Step S210: Based on the dynamic strength prediction model and the environmental information, determine the corresponding dynamic strength corrosion resistance coefficient prediction formula;

[0083] In this embodiment, the device determines the corresponding dynamic strength corrosion resistance coefficient prediction formula based on the dynamic strength prediction model and the environmental information. The dynamic strength prediction model includes dynamic strength corrosion resistance coefficient prediction formulas under different environmental factors. For example, there is a dynamic strength corrosion resistance coefficient prediction formula under chemical immersion environment and a dynamic strength corrosion resistance coefficient prediction formula under wet-dry cycle environment. The device determines the corresponding dynamic strength corrosion resistance coefficient prediction formula based on the environmental information of the lightweight soil sample.

[0084] Specifically, step S210 includes the following steps S211-S212:

[0085] Step S211: Based on the dynamic strength prediction model, determine the following preset dynamic strength corrosion resistance coefficient prediction formula:

[0086]

[0087]

[0088] Where y1 is the prediction formula for the dynamic strength corrosion resistance coefficient under chemical immersion environment, y2 is the prediction formula for the dynamic strength corrosion resistance coefficient under the dry-wet cycle environment, c is the concentration coefficient (%), and ρ is the density coefficient (g / cm³). 3 ), λ is the chemical medium coefficient, t is the soaking time coefficient (days), and N is the wet-dry cycle number coefficient (with 24 hours of chemical soaking followed by 24 hours of drying as one cycle);

[0089] In this embodiment, the dynamic strength prediction model includes the two dynamic strength corrosion resistance coefficient prediction formulas mentioned above. These two formulas are derived from experimental data and derivation formulas. Specifically, referring to Table 1 below, the experimental data of bubble-bubble lightweight soil under chemical immersion conditions are presented. The chemical immersion types include immersion without chemical substances, sodium sulfate immersion environment, and magnesium sulfate immersion environment. The dynamic strength corrosion resistance coefficient of the bubble-bubble lightweight soil is calculated based on the final measured ultimate strength of the soil.

[0090]

[0091] Table 1 shows the formula for predicting the dynamic strength corrosion resistance coefficient based on the data above:

[0092]

[0093] Furthermore, the chemical environment coefficient λ for Na2SO4 was determined to be 1, and the chemical environment coefficient λ for MgSO4 was determined to be 1.05. Therefore, the prediction formula for the dynamic strength corrosion resistance coefficient under the Na2SO4 chemical immersion environment is as follows:

[0094]

[0095] Formula for predicting dynamic strength corrosion resistance coefficient under MgSO4 chemical immersion environment:

[0096]

[0097] Referring to Table 2 below, which shows the experimental data of bubble-bubbled lightweight soil under wet-dry cycle conditions, the dynamic strength corrosion resistance coefficient of bubble-bubbled lightweight soil was calculated based on the final measured ultimate strength of the soil.

[0098]

[0099]

[0100] Table 2 shows the formula for predicting the dynamic strength corrosion resistance coefficient based on the data above:

[0101]

[0102] Furthermore, the chemical environment coefficient λ for Na2SO4 was determined to be 1, and the chemical environment coefficient λ for MgSO4 was determined to be 1.05. Therefore, the prediction formula for the dynamic strength corrosion resistance coefficient under the Na2SO4 chemical immersion environment is as follows:

[0103]

[0104] Formula for predicting dynamic strength corrosion resistance coefficient under MgSO4 chemical immersion environment:

[0105]

[0106] Step S212: Based on the environmental information, determine the corresponding dynamic strength corrosion resistance coefficient prediction formula;

[0107] In this embodiment, the device determines the corresponding dynamic strength corrosion resistance coefficient prediction formula based on the environmental information. For example, if the environmental information of the lightweight soil is a chemical immersion environment and it is sodium sulfate, then the corresponding dynamic strength corrosion resistance coefficient prediction formula is determined as follows:

[0108] Step S220: Based on the dynamic strength corrosion resistance coefficient prediction formula and the attribute data, the dynamic strength data of lightweight soil is calculated.

[0109] In this embodiment, the device calculates the dynamic strength data of lightweight soil based on the dynamic strength corrosion resistance coefficient prediction formula and the attribute data.

[0110] Specifically, step S220 includes the following step S221:

[0111] The steps for calculating the dynamic strength data of lightweight soil based on the dynamic strength corrosion resistance coefficient prediction formula and the attribute data include:

[0112] Step S221: Substitute the attribute data into the corresponding dynamic strength corrosion resistance coefficient prediction formula to obtain the dynamic strength data of lightweight soil.

[0113] In this embodiment, the device substitutes the attribute data into the corresponding dynamic strength corrosion resistance coefficient prediction formula to obtain the dynamic strength data of lightweight soil, wherein the attribute data includes concentration, density and time coefficient.

[0114] Prior to step S100, the step of determining the information of the lightweight soil sample, the method includes the following steps A100-A300:

[0115] Step A100: Obtain the lightweight soil training sample and the dynamic strength data label of the lightweight soil training sample;

[0116] In this embodiment, the lightweight soil training sample is a lightweight soil sample used for model training, and the dynamic strength data label of the lightweight soil training sample is the label of the corresponding dynamic strength data of the lightweight soil training sample. The device can obtain the lightweight soil training sample and the dynamic strength data label of the lightweight soil training sample by uploading it by the user.

[0117] Step A200: Based on the lightweight soil training samples, determine the prediction formula for the dynamic strength corrosion resistance coefficient;

[0118] In this embodiment, the device determines the prediction formula for the dynamic strength corrosion resistance coefficient based on the lightweight soil training sample, referring to the above step S211, which will not be repeated here.

[0119] Step A300: Based on the lightweight soil training samples, the dynamic strength corrosion resistance coefficient prediction formula, and the dynamic strength data labels of the lightweight soil training samples, the preset training model is iteratively trained to obtain a dynamic strength prediction model that meets the accuracy requirements.

[0120] In this embodiment, the device iteratively trains a preset training model based on the lightweight soil training sample, the dynamic strength corrosion resistance coefficient prediction formula, and the dynamic strength data label of the lightweight soil training sample to obtain a dynamic strength prediction model that meets the accuracy requirements.

[0121] Specifically, step A300 includes the following steps A310-A340:

[0122] Step A310: Input the lightweight soil training sample into the model to be trained, and obtain the predicted dynamic strength data based on the dynamic strength corrosion resistance coefficient prediction formula;

[0123] In this embodiment, the lightweight soil training sample is input into the model to be trained, and the predicted dynamic strength data is obtained based on the dynamic strength corrosion resistance coefficient prediction formula in the model to be trained.

[0124] Step A320: Calculate the difference between the predicted dynamic strength data and the dynamic strength data label of the lightweight soil training sample to obtain the error result;

[0125] In this embodiment, the device calculates the difference between the predicted dynamic strength data and the dynamic strength data label of the lightweight soil training sample to obtain the error result. Since there is a difference in the predicted dynamic strength data in the model to be trained, the error result is used to determine whether the model to be trained has been trained.

[0126] Step A330: Based on the error result, determine whether the error result meets the error standard indicated by the preset error threshold range;

[0127] In this embodiment, the device determines whether the error result meets the error standard indicated by the preset error threshold range based on the error result. The preset error threshold range is a self-set threshold used to determine whether the error result is too large. If the error is too large, the model needs to continue iterative training until the model training meets the accuracy condition.

[0128] Step A340: If the error result does not meet the error standard indicated by the preset error threshold range, return to the step of inputting the lightweight soil training sample into the model to be trained, and obtaining the predicted dynamic strength data based on the dynamic strength corrosion resistance coefficient prediction formula, until the training error result meets the error standard indicated by the preset error threshold range, and then stop training to obtain the dynamic strength prediction model.

[0129] In this embodiment, if the error result does not meet the error standard indicated by the preset error threshold range, the process returns to inputting the lightweight soil training sample into the model to be trained, and obtaining the predicted dynamic strength data based on the dynamic strength corrosion resistance coefficient prediction formula. Training stops when the training error result meets the error standard indicated by the preset error threshold range, and a dynamic strength prediction model is obtained. That is, if the error is too large, the model needs to continue iterative training until the model training meets the accuracy conditions.

[0130] This application provides a method for predicting the dynamic strength of lightweight soil using bubble-based methods. Compared to existing technologies where lightweight soil is affected not only by loads but also by various environmental factors, leading to low accuracy in strength prediction, this application determines lightweight soil sample information; inputs this information into a preset dynamic strength prediction model; and performs dynamic strength prediction processing on the lightweight soil sample information based on the dynamic strength prediction model to obtain dynamic strength data. The dynamic strength prediction model is trained using a preset number of dynamic strength corrosion resistance coefficient prediction formulas under different environmental factors. In other words, this application uses a dynamic strength prediction model trained with a preset number of dynamic strength corrosion resistance coefficient prediction formulas under different environmental factors to predict the dynamic strength of lightweight soil samples, thus improving the accuracy of the predicted dynamic strength data.

[0131] This application also provides a bubble-based lightweight soil dynamic strength prediction device, referring to... Figure 3 The bubble-based lightweight soil dynamic strength prediction device includes:

[0132] Module 10 is used to determine the information of lightweight soil samples;

[0133] The prediction module 20 is used to input the information of the lightweight soil sample into a preset dynamic strength prediction model, and perform dynamic strength prediction processing on the information of the lightweight soil sample based on the dynamic strength prediction model to obtain dynamic strength data of lightweight soil. The dynamic strength prediction model is composed of a preset number of dynamic strength corrosion resistance coefficient prediction formulas under different environmental factors.

[0134] Optionally, the determining module includes:

[0135] The acquisition module is used to acquire lightweight soil samples;

[0136] The sample analysis module is used to perform sample analysis on the lightweight soil sample to obtain lightweight soil sample information.

[0137] Optionally, the sample analysis module includes:

[0138] The environmental and property analysis module is used to perform environmental analysis and property analysis on the lightweight soil sample respectively to obtain the environmental information and property data of the lightweight soil.

[0139] The sample information determination module is used to determine the lightweight soil sample information based on the environmental information and the attribute data.

[0140] Optionally, the prediction module 20 includes:

[0141] The prediction formula determination module is used to determine the corresponding dynamic strength corrosion resistance coefficient prediction formula based on the dynamic strength prediction model and the environmental information.

[0142] The calculation module is used to calculate the dynamic strength data of lightweight soil based on the dynamic strength corrosion resistance coefficient prediction formula and the attribute data.

[0143] Optionally, the prediction formula determination module includes:

[0144] The dynamic strength corrosion resistance coefficient prediction formula determination module, based on the dynamic strength prediction model, determines the following preset dynamic strength corrosion resistance coefficient prediction formula:

[0145]

[0146]

[0147] Where y1 is the prediction formula for the dynamic strength corrosion resistance coefficient under chemical immersion environment, y2 is the prediction formula for the dynamic strength corrosion resistance coefficient under the dry-wet cycle environment, c is the concentration coefficient, ρ is the density coefficient, λ is the chemical medium coefficient, t is the immersion time coefficient, and N is the dry-wet cycle number coefficient.

[0148] The corresponding formula determination module determines the corresponding dynamic strength corrosion resistance coefficient prediction formula based on the environmental information.

[0149] Optionally, the computing module includes:

[0150] The calculation module is used to substitute the attribute data into the corresponding dynamic strength corrosion resistance coefficient prediction formula to obtain the dynamic strength data of lightweight soil.

[0151] Optionally, the bubble-based lightweight soil dynamic strength prediction device further includes:

[0152] The sample acquisition module is used to acquire lightweight soil training samples and the dynamic strength data labels of the lightweight soil training samples;

[0153] The model's dynamic strength corrosion resistance coefficient prediction formula is determined and used to determine the dynamic strength corrosion resistance coefficient prediction formula based on the lightweight soil training samples.

[0154] The training module is used to iteratively train the preset model to be trained based on the lightweight soil training samples, the determined dynamic strength corrosion resistance coefficient prediction formula, and the dynamic strength data labels of the lightweight soil training samples, so as to obtain a dynamic strength prediction model that meets the accuracy conditions.

[0155] Optionally, the training module includes:

[0156] The predicted dynamic strength data determination module is used to input the lightweight soil training sample into the model to be trained, and obtain the predicted dynamic strength data based on the dynamic strength corrosion resistance coefficient prediction formula.

[0157] The difference calculation module is used to calculate the difference between the predicted dynamic strength data and the dynamic strength data label of the lightweight soil training sample to obtain the error result;

[0158] The judgment module is used to determine, based on the error result, whether the error result meets the error standard indicated by the preset error threshold range;

[0159] The iterative training module is used to return to the step of inputting the lightweight soil training sample into the model to be trained and obtaining the predicted dynamic strength data based on the dynamic strength corrosion resistance coefficient prediction formula if the error result does not meet the error standard indicated by the preset error threshold range. Training is stopped when the training error result meets the error standard indicated by the preset error threshold range, and the dynamic strength prediction model is obtained.

[0160] The specific implementation of the bubble lightweight soil dynamic strength prediction device in this application is basically the same as the embodiments of the bubble lightweight soil dynamic strength prediction method described above, and will not be repeated here.

[0161] Reference Figure 1 , Figure 1 This is a schematic diagram of the terminal structure of the hardware operating environment involved in the embodiments of this application.

[0162] like Figure 1 As shown, the terminal may include: a processor 1001, such as a CPU; a network interface 1004; a user interface 1003; a memory 1005; and a communication bus 1002. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and an input unit such as a keyboard. Optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0163] Optionally, the bubble-based lightweight soil dynamic strength prediction device may also include a rectangular user interface, a network interface, a camera, RF (Radio Frequency) circuitry, sensors, audio circuitry, a WiFi module, etc. The rectangular user interface may include a display screen and an input submodule such as a keyboard. Optionally, the rectangular user interface may also include a standard wired interface or a wireless interface. The network interface may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0164] Those skilled in the art will understand that Figure 1 The structure of the bubble lightweight soil dynamic strength prediction device shown does not constitute a limitation on the bubble lightweight soil dynamic strength prediction device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0165] like Figure 1 As shown, the memory 1005, serving as a storage medium, may include an operating system, a network communication module, and a bubble lightweight soil dynamic strength prediction program. The operating system is a program that manages and controls the hardware and software resources of the bubble lightweight soil dynamic strength prediction device, supporting the operation of the bubble lightweight soil dynamic strength prediction program and other software and / or programs. The network communication module is used to enable communication between the various components within the memory 1005, as well as communication with other hardware and software in the bubble lightweight soil dynamic strength prediction system.

[0166] exist Figure 1 In the bubble lightweight soil dynamic strength prediction device shown, the processor 1001 is used to execute the bubble lightweight soil dynamic strength prediction program stored in the memory 1005 to implement the steps of the bubble lightweight soil dynamic strength prediction method described above.

[0167] The specific implementation of the bubble lightweight soil dynamic strength prediction device in this application is basically the same as the embodiments of the bubble lightweight soil dynamic strength prediction method described above, and will not be repeated here.

[0168] This application also provides a storage medium storing a program for predicting the dynamic strength of lightweight soil using bubbles. The program for predicting the dynamic strength of lightweight soil using bubbles is executed by a processor to implement the method as described below:

[0169] Determine information about lightweight soil samples;

[0170] The information of the lightweight soil sample is input into a preset dynamic strength prediction model. Based on the dynamic strength prediction model, the dynamic strength prediction of the lightweight soil sample is processed to obtain dynamic strength data of lightweight soil. The dynamic strength prediction model is trained based on a preset number of dynamic strength corrosion resistance coefficient prediction formulas under different environmental factors.

[0171] Optionally, the step of determining the information of the lightweight soil sample includes:

[0172] Obtain lightweight soil samples;

[0173] The lightweight soil sample was subjected to sample analysis to obtain lightweight soil sample information.

[0174] Optionally, the step of performing sample analysis on the lightweight soil sample to obtain lightweight soil sample information includes:

[0175] The lightweight soil samples were subjected to environmental analysis and property analysis respectively to obtain the environmental information and property data of the lightweight soil.

[0176] Based on the environmental information and the attribute data, the information of the lightweight soil sample is determined.

[0177] Optionally, the step of performing dynamic strength prediction processing on the lightweight soil sample information based on the dynamic strength prediction model to obtain lightweight soil dynamic strength data includes:

[0178] Based on the dynamic strength prediction model and the environmental information, the corresponding dynamic strength corrosion resistance coefficient prediction formula is determined;

[0179] Based on the dynamic strength corrosion resistance coefficient prediction formula and the attribute data, the dynamic strength data of lightweight soil is calculated.

[0180] Optionally, the environmental information includes chemical immersion environment and wet-dry cycle environment, and the attribute data includes concentration data, density data, chemical medium information data, time data, and cycle number data. The step of calculating the dynamic strength data of lightweight soil based on the dynamic strength corrosion resistance coefficient prediction formula and the attribute data includes:

[0181] Based on the dynamic strength prediction model, the following preset formula for predicting the dynamic strength corrosion resistance coefficient is determined:

[0182]

[0183]

[0184] Wherein, y1 is the prediction formula for the dynamic strength corrosion resistance coefficient under chemical immersion environment, y2 is the prediction formula for the dynamic strength corrosion resistance coefficient under the dry-wet cycle environment, c is the concentration coefficient, ρ is the density coefficient, λ is the chemical medium coefficient, t is the immersion time coefficient, and N is the dry-wet cycle number coefficient.

[0185] Based on the environmental information, a corresponding prediction formula for the dynamic strength corrosion resistance coefficient is determined.

[0186] The steps for calculating the dynamic strength data of lightweight soil based on the dynamic strength corrosion resistance coefficient prediction formula and the attribute data include:

[0187] Substituting the attribute data into the corresponding dynamic strength corrosion resistance coefficient prediction formula yields the dynamic strength data of lightweight soil.

[0188] Optionally, before the step of obtaining lightweight soil sample information, the method includes:

[0189] Obtain lightweight soil training samples and their dynamic strength data labels;

[0190] Based on the aforementioned lightweight soil training samples, a formula for predicting the dynamic strength corrosion resistance coefficient was determined.

[0191] Based on the lightweight soil training samples, the dynamic strength corrosion resistance coefficient prediction formula, and the dynamic strength data labels of the lightweight soil training samples, the preset training model is iteratively trained to obtain a dynamic strength prediction model that meets the accuracy requirements.

[0192] Optionally, the step of iteratively training a preset model to be trained based on the lightweight soil training samples, the dynamic strength corrosion resistance coefficient prediction formula, and the dynamic strength data labels of the lightweight soil training samples to obtain a dynamic strength prediction model that meets the accuracy requirements includes:

[0193] The lightweight soil training sample is input into the model to be trained, and the predicted dynamic strength data is obtained based on the dynamic strength corrosion resistance coefficient prediction formula.

[0194] The difference between the predicted dynamic strength data and the dynamic strength data labels of the lightweight soil training samples is calculated to obtain the error result;

[0195] Based on the error result, determine whether the error result meets the error standard indicated by the preset error threshold range;

[0196] If the error result does not meet the error standard indicated by the preset error threshold range, return to the step of inputting the lightweight soil training sample into the model to be trained, and obtaining the predicted dynamic strength data based on the dynamic strength corrosion resistance coefficient prediction formula, until the training error result meets the error standard indicated by the preset error threshold range, and then stop training to obtain the dynamic strength prediction model.

[0197] The specific implementation of the storage medium in this application is basically the same as the embodiments of the above-described bubble lightweight soil dynamic strength prediction method, and will not be repeated here.

[0198] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described method for predicting the dynamic strength of lightweight soil using bubbles.

[0199] The specific implementation of the computer program product in this application is basically the same as the embodiments of the above-mentioned bubble lightweight soil dynamic strength prediction method, and will not be repeated here.

[0200] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0201] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0202] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0203] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method of predicting the dynamic strength of an aerated lightweight soil, characterized by, The bubble lightweight soil dynamic strength prediction method comprises: determining lightweight soil sample information; inputting the lightweight soil sample information into a preset dynamic strength prediction model, performing dynamic strength prediction processing on the lightweight soil sample information based on the dynamic strength prediction model, and obtaining lightweight soil dynamic strength data, wherein the dynamic strength prediction model is obtained based on a preset number of dynamic strength corrosion resistance coefficient prediction formulas under different environmental factors; The step of determining the lightweight soil sample information comprises: obtaining a lightweight soil sample; performing sample analysis processing on the lightweight soil sample to obtain lightweight soil sample information; The step of performing sample analysis processing on the lightweight soil sample to obtain lightweight soil sample information comprises: respectively performing environmental analysis processing and attribute analysis processing on the lightweight soil sample to obtain environmental information and attribute data of the lightweight soil; determining lightweight soil sample information based on the environmental information and the attribute data; The step of performing dynamic strength prediction processing on the lightweight soil sample information based on the dynamic strength prediction model to obtain lightweight soil dynamic strength data comprises: determining a corresponding dynamic strength corrosion resistance coefficient prediction formula based on the dynamic strength prediction model and the environmental information; calculating lightweight soil dynamic strength data based on the dynamic strength corrosion resistance coefficient prediction formula and the attribute data; The environmental information comprises a chemical immersion environment and a dry-wet cycle environment, and the attribute data comprises concentration data, density data, chemical medium information data, time data, and cycle number data. The step of calculating lightweight soil dynamic strength data based on the dynamic strength corrosion resistance coefficient prediction formula and the attribute data comprises: determining the following preset dynamic strength corrosion resistance coefficient prediction formula based on the dynamic strength prediction model: wherein, is a dynamic strength corrosion resistance coefficient prediction formula under a chemical immersion environment, is a dynamic strength corrosion resistance coefficient prediction formula under a dry-wet cycle environment, c is a concentration coefficient, based on the environmental information, determining a corresponding dynamic strength corrosion resistance coefficient prediction formula; is a density coefficient, is a chemical medium coefficient, t is an immersion time coefficient, N is a dry-wet cycle number coefficient; The step of calculating lightweight soil dynamic strength data based on the dynamic strength corrosion resistance coefficient prediction formula and the attribute data comprises: substituting the attribute data into the corresponding dynamic strength corrosion resistance coefficient prediction formula to obtain lightweight soil dynamic strength data. Before the step of determining the lightweight soil sample information, the method comprises:

2. The method of claim 1, wherein obtaining a lightweight soil training sample and dynamic strength data labels of the lightweight soil training sample; determining a dynamic strength corrosion resistance coefficient prediction formula based on the lightweight soil training sample; iteratively training a preset to-be-trained model based on the lightweight soil training sample, the dynamic strength corrosion resistance coefficient prediction formula, and the dynamic strength data labels of the lightweight soil training sample to obtain a dynamic strength prediction model that meets the accuracy condition. The step of iteratively training a preset to-be-trained model based on the lightweight soil training sample, the dynamic strength corrosion resistance coefficient prediction formula, and the dynamic strength data labels of the lightweight soil training sample to obtain a dynamic strength prediction model that meets the accuracy condition comprises:

3. The method for predicting the dynamic strength of lightweight soil with air bubbles as described in claim 2, characterized in that, inputting the lightweight soil training sample into the to-be-trained model to obtain predicted dynamic strength data based on the dynamic strength corrosion resistance coefficient prediction formula; performing difference calculation on the predicted dynamic strength data and the dynamic strength data labels of the lightweight soil training sample to obtain an error result; and ​ Based on the error result, it is judged whether the error result meets the error standard indicated by the preset error threshold range; If the error result does not meet the error standard indicated by the preset error threshold range, the step of inputting the lightweight soil training sample into the to-be-trained model and obtaining predicted dynamic strength data based on the dynamic strength corrosion resistance coefficient prediction formula is returned until the training is stopped after the training error result meets the error standard indicated by the preset error threshold range, and a dynamic strength prediction model is obtained.

4. An apparatus for predicting dynamic strength of a bubble lightweight soil, characterized by, The bubble lightweight soil dynamic strength prediction device comprises: A determination module is configured to determine lightweight soil sample information; A prediction module is configured to input the lightweight soil sample information into a preset dynamic strength prediction model, perform dynamic strength prediction processing on the lightweight soil sample information based on the dynamic strength prediction model, and obtain lightweight soil dynamic strength data, wherein the dynamic strength prediction model is composed of a preset number of dynamic strength corrosion resistance coefficient prediction formulas under different environmental factors; The determination module comprises: An acquisition module is configured to acquire a lightweight soil sample; A sample analysis module is configured to perform sample analysis processing on the lightweight soil sample to obtain lightweight soil sample information; The sample analysis module comprises: An environmental and attribute analysis module is configured to perform environmental analysis processing and attribute analysis processing on the lightweight soil sample respectively to obtain environmental information and attribute data of the lightweight soil; A sample information determination module is configured to determine lightweight soil sample information based on the environmental information and the attribute data; The prediction module comprises: A prediction formula determination module is configured to determine a corresponding dynamic strength corrosion resistance coefficient prediction formula based on the dynamic strength prediction model and the environmental information; A calculation module is configured to calculate lightweight soil dynamic strength data based on the dynamic strength corrosion resistance coefficient prediction formula and the attribute data; The prediction formula determination module comprises: A dynamic strength corrosion resistance coefficient prediction formula determination module is configured to determine the following preset dynamic strength corrosion resistance coefficient prediction formula based on the dynamic strength prediction model: wherein, is a dynamic strength corrosion resistance coefficient prediction formula under a chemical immersion environment, is a dynamic strength corrosion resistance coefficient prediction formula under a dry-wet cycle environment, c is a concentration coefficient ρ is a density coefficient, is a chemical medium coefficient, t is an immersion time coefficient, N is a dry-wet cycle number coefficient; A corresponding formula determination module is configured to determine a corresponding dynamic strength corrosion resistance coefficient prediction formula based on the environmental information; The calculation module comprises: A substitution calculation module is configured to substitute the attribute data into the corresponding dynamic strength corrosion resistance coefficient prediction formula to obtain lightweight soil dynamic strength data.

5. An apparatus for predicting dynamic strength of a bubble lightweight soil, characterized by, The bubble lightweight soil dynamic strength prediction device comprises a memory, a processor, and a program stored on the memory for implementing the bubble lightweight soil dynamic strength prediction method, The memory is configured to store the program for implementing the bubble lightweight soil dynamic strength prediction method; The processor is configured to execute the program for implementing the bubble lightweight soil dynamic strength prediction method to implement the steps of the bubble lightweight soil dynamic strength prediction method according to any one of claims 1 to 3.

6. A storage medium, characterized by The storage medium has a program for implementing the bubble lightweight soil dynamic strength prediction method stored thereon, and the program for implementing the bubble lightweight soil dynamic strength prediction method is executed by the processor to implement the steps of the bubble lightweight soil dynamic strength prediction method according to any one of claims 1 to 3.

Images