Computer-aided optimization method for mix proportion design of compaction-free solid waste roadbed filler

Abstract

The invention relates to the technical field of mix proportion optimization, and discloses a computer-aided optimization method for mix proportion design of compaction-free solid waste roadbed filler, which comprises the following steps: constructing a corresponding material model based on a target initial proportion, obtaining target detection data of the material model, inputting the target detection data into a pre-constructed first strength model, and constructing a compaction-free solid waste roadbed filler mix proportion design model. Determining a durability value based on the target initial ratio, optimizing the target initial ratio according to the first compressive strength value, the durability value and a first optimization algorithm to obtain a target optimization ratio, and optimizing the target initial ratio according to the first compressive strength value, the durability value and the first optimization algorithm to obtain a target optimization ratio; according to the method, when various solid wastes are applied to the roadbed, a plurality of cost, durability values and roadbed strength factors are considered at the same time, so that the ratio of various solid wastes is comprehensively optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of mix ratio optimization, and more particularly to a computer-aided optimization method for mix ratio design of compaction-free solid waste roadbed filler. Background Art

[0002] Industrial solid waste materials refer to general industrial waste other than toxic and hazardous solid wastes. With the process of industrialization, the output of these solid wastes has continued to increase, occupying a large amount of land and posing safety hazards. At the same time, with the rapid development of my country's transportation construction, traditional non-renewable resources such as sand, stone, and soil are becoming increasingly scarce. Effectively utilizing the material properties of industrial solid waste to replace traditional road construction materials has become an important way to solve the problems of resource shortage and environmental pollution. Metallurgy, thermal power, and construction solid waste are typical examples. By using them in the construction of transportation infrastructure such as roads and railways, the transformation of transportation infrastructure towards green, low-carbon and economic development can be promoted. However, due to the different material properties of construction solid waste, how to optimize its ratio to ensure the quality of subsequent roadbed has become an urgent problem to be solved. Most existing technologies are limited to cost considerations and lack comprehensive consideration of quality optimization.

[0003] For example, Chinese patent publication number CN116776643A discloses a sintering batch optimization method based on the fmincon function. This patent collects raw material demand and unit cost, establishes a mathematical model of the sintering process, sets relevant constraints, optimizes the raw material ratio, and finally uses the fmincon function to solve and output the optimal batching scheme to improve the economy and efficiency of the sintering process. Chinese patent publication number CN110502781A discloses a ferroalloy production batch optimization method based on prior knowledge. By establishing an optimization objective function for smelting cost and performing piecewise linearization on the change in manganese grade in the raw material, a piecewise linear objective function is obtained. Then, the least squares method and simplex method with prior knowledge are used to solve the optimal ferroalloy raw material ratio for each segment to obtain the global optimal ratio scheme that meets the constraints.

[0004] Existing technologies mostly focus on optimizing the ratio of raw materials from a cost perspective. However, when applying metallurgical, thermal power, and construction solid waste to roadbeds, multiple factors must be considered comprehensively. In addition to cost, the strength and durability of the roadbed are also crucial. Currently, there are few technologies that can comprehensively optimize the ratio of construction solid waste from these multiple perspectives.

[0005] In view of this, the present invention proposes a computer-aided optimization method for the mix ratio design of compaction-free solid waste roadbed filler to solve the above problems. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a computer-aided optimization method for designing the mix ratio of compaction-free solid waste roadbed filler.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] First, a computer-aided optimization method for the mix design of compaction-free solid waste roadbed fillers is provided, including:

[0009] S10: Obtaining a target initial mix ratio, constructing a corresponding material model based on the target initial mix ratio, obtaining target detection data of the material model, inputting the target detection data into a pre-constructed first strength model to obtain a first compressive strength value, and determining a durability value based on the target initial mix ratio;

[0010] S20: Optimizing the target initial mix ratio according to the first compressive strength value, the durability value, and the first optimization algorithm to obtain a target optimized mix ratio;

[0011] S30: Determine the cost impact value based on the target optimization ratio. If the cost impact value is greater than the preset impact threshold, delete the current target optimization ratio and return to S20 to regenerate; if not, output the target optimization ratio.

[0012] Furthermore, the method for determining the target initial ratio includes:

[0013] The weight of construction solid waste and the weight of solid waste-based cementitious materials are obtained, the actual water weight is determined according to the weight of solid waste-based cementitious materials, and the weight of construction solid waste, the weight of solid waste-based cementitious materials and the actual water weight are input into a preset proportion classification model to obtain an initial proportion set, wherein the initial proportion set includes R target initial proportions.

[0014] Furthermore, the method for constructing the first strength model includes:

[0015] Acquire a first sample data set, where the first sample data set includes historical target detection data and historical first compressive strength values;

[0016] Divide the first sample data set into a sample training set and a sample test set, and construct a regression network;

[0017] The historical target detection data in the sample training set is used as the input data of the regression network, and the historical first compressive strength value in the sample training set is used as the output data of the regression network. The regression network is trained to obtain an initial regression network for predicting the real-time first compressive strength value.

[0018] The initial regression network is tested using a sample test set, and the initial regression network that satisfies a preset error value is output as the first strength model.

[0019] Furthermore, the first optimization algorithm is a sparrow search algorithm. The target initial ratio is optimized based on the sparrow search algorithm. The method for obtaining the target optimized ratio includes:

[0020] S201: Randomly generate a group of sparrow individuals, each sparrow individual represents a target initial ratio, and randomly generate an initial position for each sparrow individual That is, the target initial ratio is to satisfy:

[0021]

[0022] in, is the first compressive strength value corresponding to the target initial ratio, FPV min A first intensity threshold is preset;

[0023] S202: Construct the fitness function value of each sparrow individual

[0024]

[0025] Where, is the durability value corresponding to the target initial ratio;

[0026] S203: Perform exploration operations on some sparrow individuals and update their target initial ratio

[0027] S204: Check the updated Is it greater than FPV? min , if not greater than FPV min , then perform boundary processing;

[0028] S205: Perform following operations on the remaining sparrow individuals and update their target initial ratios

[0029] S206: Calculate the fitness function value of each sparrow individual after the update Update the current optimal solution;

[0030] S207: When the preset maximum number of iterations T is reached max Stop searching when , and output the target initial ratio corresponding to the current optimal solution, which is the target optimized ratio.

[0031] Furthermore, the method for performing boundary processing includes:

[0032]

[0033] Where, Refers to the first compressive strength value of the i-th sparrow individual after being updated in the t+1 generation.

[0034] Furthermore, the method of performing the exploration operation on some sparrow individuals includes:

[0035]

[0036] Where, is the position of the i-th sparrow in the t-th generation, is the position of the i-th sparrow in the t+1 generation, T max is the maximum number of iterations, θ is the random angle, exp(·) is the exponential function with e as the base, and e is a natural constant.

[0037] Further, update its target initial ratio The methods include:

[0038]

[0039] Where S is a random number, x best is the location of the current optimal solution.

[0040] In a second aspect, a computer-aided optimization system for designing a mix ratio of a non-compacted solid waste roadbed filler is provided, which is used to implement the computer-aided optimization method for designing a mix ratio of a non-compacted solid waste roadbed filler, comprising:

[0041] Data processing module: used to obtain a target initial mix ratio, build a corresponding material model based on the target initial mix ratio, obtain target detection data of the material model, input the target detection data into a pre-built first strength model to obtain a first compressive strength value, and determine a durability value based on the target initial mix ratio;

[0042] Optimization module: used to optimize the target initial ratio according to the first compressive strength value, the durability value and the first optimization algorithm to obtain the target optimized ratio;

[0043] Judgment output module: used to determine the cost impact value based on the target optimization ratio. If the cost impact value is greater than the preset impact threshold, the current target optimization ratio is deleted and returned to the optimization module for regeneration; if not, the target optimization ratio is output.

[0044] In a third aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the computer-aided optimization method for the mix ratio design of compaction-free solid waste roadbed filler is implemented.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] The present invention first constructs a corresponding material model based on the target initial ratio, obtains target detection data of the material model, inputs the target detection data into a pre-constructed first strength model, obtains a first compressive strength value, determines a durability value based on the target initial ratio, optimizes the target initial ratio according to the first compressive strength value, the durability value and the first optimization algorithm, and obtains a target optimized ratio. The present invention optimizes the target initial ratio according to the first compressive strength value, the durability value and the first optimization algorithm, and obtains a target optimized ratio. When applying construction solid waste to roadbed, the present invention simultaneously considers multiple costs, durability values ​​and roadbed strength factors, thereby comprehensively optimizing the ratio of construction solid waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A flow chart of the computer-aided optimization method for designing the mix ratio of compaction-free solid waste roadbed filler in the present invention;

[0048] Figure 2 Schematic diagram of the structure of the computer-aided optimization system for designing the mix ratio of compaction-free solid waste roadbed filler in the present invention;

[0049] Figure 3 Flowchart of the method for determining the target initial ratio in the present invention;

[0050] Figure 4 This is a flow chart of the first strength model construction method in the present invention. DETAILED DESCRIPTION

[0051] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0052] Example 1

[0053] See also Figure 1 As shown, this embodiment discloses a computer-aided optimization method for designing a mix ratio of a compaction-free solid waste roadbed filler, comprising:

[0054] S10: Obtaining a target initial mix ratio, constructing a corresponding material model based on the target initial mix ratio, obtaining target detection data of the material model, inputting the target detection data into a pre-constructed first strength model to obtain a first compressive strength value, and determining a durability value based on the target initial mix ratio;

[0055] In this embodiment, the target initial ratio refers to the ratio between solid waste-based cementitious materials, construction solid waste and water. The construction solid waste can be concrete, mortar blocks, gravel, red brick blocks, ceramic tiles, etc., and the solid waste-based cementitious materials are made by mixing fly ash, slag powder, etc. The production process of solid waste-based cementitious materials is an existing technology, and this embodiment will not go into details about it.

[0056] like Figure 3 As shown, the method for determining the target initial ratio includes:

[0057] The weight of construction solid waste and the weight of solid waste-based cementitious materials are obtained, the actual water weight is determined according to the weight of solid waste-based cementitious materials, and the weight of construction solid waste, the weight of solid waste-based cementitious materials and the actual water weight are input into a preset proportion classification model to obtain an initial proportion set, wherein the initial proportion set includes R target initial proportions.

[0058] It should be noted that determining the actual water weight based on the weight of solid waste-based cementitious materials means that solid waste-based cementitious materials and water are mixed and stirred in a preset proportion to obtain compaction-free solid waste soil. The fluidized solid waste soil is used for subsequent roadbed pouring. After the pouring is completed, construction waste needs to be thrown into the poured fluidized solid waste soil in turn. The significant advantages of fluidized solid waste soil are good fluidity and self-compacting without vibration. It is very suitable for backfill projects in narrow spaces. The processing and construction of the materials are simple, which can shorten the construction period and improve construction efficiency. Construction solid waste includes concrete, mortar blocks, gravel, red bricks, ceramic tiles, etc.

[0059] like Figure 4 As shown in FIG, the construction method of the ratio classification model includes:

[0060] Obtain Q sets of training data, where Q is a positive integer greater than 1, and the training data includes the weight of historical building solid waste, the weight of historical solid waste-based cementitious materials, the weight of historical water, and a set of historical mix ratios;

[0061] The weight of historical building solid waste, the weight of historical solid waste-based cementitious materials, the historical water weight and the historical mix ratio set are used as the sample set, and the sample set is divided into a training set and a test set to construct a classifier;

[0062] The weight of historical building solid waste, historical solid waste-based cementitious materials, and historical water weight in the training set are used as input data, and the historical mix ratio set in the training set is used as output data to train the classifier and obtain an initial classifier.

[0063] The initial classifier is tested using the test set, and a classifier that meets the preset accuracy is output as the matching classification model. The classifier is preferably a naive Bayes model or a support vector machine model.

[0064] In this embodiment, the above training data is obtained by people skilled in the art based on experiments.

[0065] Methods for constructing corresponding material models include:

[0066] The target initial mix ratio and the corresponding weight of construction solid waste, weight of solid waste-based cementitious materials and actual water weight are input into the three-dimensional modeling software to obtain the material model output by the three-dimensional modeling software.

[0067] It is understandable that the above-mentioned three-dimensional modeling software can be Civil 3D, PLAXIS, GeoStudio, etc. In addition to the target initial ratio and the corresponding construction solid waste weight, solid waste-based cementitious material weight and actual water weight, there are other parameters in the modeling process, which can be set in advance. Because the core of this embodiment is to optimize the roadbed structure according to the ratio between solid waste-based cementitious material, construction solid waste and water, rather than frequently adjusting the basic geological conditions, the basic parameters can be preset or use default values.

[0068] Methods for obtaining target detection data of material models include:

[0069] A simulated cyclic triaxial test is performed on the material model to obtain target detection data of the material model during the simulated cyclic triaxial test.

[0070] It should be noted that the cyclic triaxial test refers to an experimental method commonly used in geotechnical engineering and material mechanics. Its purpose is to simulate the deformation and strength characteristics of soil or other fillers under cyclic loading. This experiment is mainly used to study the fatigue characteristics and ultimate failure behavior of materials under repeated loads (such as traffic loads or earthquake loads). In this implementation, the cyclic triaxial test is realized by simulating the stress, strain, and deformation of the material under load through finite element analysis software (such as PLAXIS, ABAQUS, ANSYS, etc.).

[0071] Target detection data includes but is not limited to deformation, anti-fracture time and dynamic stiffness value. Deformation refers to the change in geometric shape or size under the action of external force. Dynamic stiffness refers to the stiffness value under dynamic load (such as cyclic load or vibration). Since the material model is a brittle material, the anti-fracture time refers to the time that the material model can remain unbroken under the action of external force. The smaller the deformation, the less likely the material model is to deform under the same external force, indicating that the strength of the material model is higher. Lower deformation means that the material can better resist deformation force, which is crucial for maintaining structural stability; the longer the anti-fracture time, the longer the material model can maintain its integrity under external force, indicating that the material model has higher anti-destruction ability and strength; the higher the dynamic stiffness value, the stronger the material model's anti-deformation ability under dynamic conditions, and the higher the strength. A high dynamic stiffness value means that the material model can effectively maintain structural stability when subjected to vibration or cyclic loads.

[0072] It should be added that the deformation, anti-rupture time and dynamic stiffness values ​​mentioned above are all related to the target initial ratio. Once the target initial ratio changes, the deformation, anti-rupture time and dynamic stiffness values ​​will also change.

[0073] The construction method of the first strength model includes:

[0074] Acquire a first sample data set, where the first sample data set includes historical target detection data and historical first compressive strength values;

[0075] Divide the first sample data set into a sample training set and a sample test set, and construct a regression network;

[0076] The historical target detection data in the sample training set is used as the input data of the regression network, and the historical first compressive strength value in the sample training set is used as the output data of the regression network. The regression network is trained to obtain an initial regression network for predicting the real-time first compressive strength value.

[0077] The initial regression network is tested using a sample test set, and the output of the initial regression network that satisfies a preset error value is used as the first strength model. The initial regression network is preferably a deep neural network model.

[0078] It should be noted that the first compressive strength value represents the material model's ability to resist rupture under dynamic or static loads. Since brittle materials do not undergo obvious plastic deformation, when the stress exceeds its compressive strength, the material will suddenly rupture or break. Therefore, the first compressive strength value reflects the maximum stress limit that the material can withstand. Before reaching this limit, the material will remain intact, but once it exceeds this limit, it will quickly destroy. When evaluating the strength of brittle materials, the compressive strength value is an important indicator for judging the material's stability and rupture risk. A higher compressive strength value means that the material can withstand a larger load during use without rupture, thereby exhibiting higher strength and reliability.

[0079] Methods for determining durability values ​​based on target initial mix ratios include:

[0080]

[0081] Where, EIV is the durability value, SCM is the weight of solid waste-based cementitious materials, CSW is the weight of construction solid waste, and WTR is rt is the actual water weight, WTR sd is the standard water weight, log3(·) is the logarithmic function with base 3, tan -1 (·) is the inverse tangent function, cosh(·) is the hyperbolic cosine function, and f1, f2, and f3 are the proportions of each component in the target initial ratio.

[0082] It should be noted that the durability value represents the material's ability to maintain its structural stability and integrity during long-term use. It reflects the material's ability to resist performance degradation and cracking under various external environmental conditions (such as repeated loads, humidity changes, temperature fluctuations, etc.).

[0083] S20: Optimizing the target initial mix ratio according to the first compressive strength value, the durability value, and the first optimization algorithm to obtain a target optimized mix ratio;

[0084] In this embodiment, the first optimization algorithm may be a sparrow search algorithm. The target initial ratio is optimized based on the sparrow search algorithm. The method for obtaining the target optimized ratio includes:

[0085] S201: Randomly generate a group of sparrow individuals, each sparrow individual represents a target initial ratio, and randomly generate an initial position for each sparrow individual That is, the target initial ratio is to satisfy:

[0086]

[0087] in, is the first compressive strength value corresponding to the target initial ratio, FPV min A first intensity threshold is preset.

[0088] It should be noted that the purpose of this embodiment is to optimize the target initial ratio to obtain the optimal target initial ratio, that is, the target optimized ratio. The subsequent roadbed is constructed according to the target optimized ratio, which can ensure both strength and durability. However, in this embodiment, the larger the first compressive strength value, the stronger the structural stability of the roadbed. Therefore, this embodiment must pre-set the first strength threshold. Setting the first strength threshold can ensure that during the optimization process, the selected material combination can maintain the stability of the roadbed and prevent the roadbed from failing or becoming unstable due to an excessively small first compressive strength value. At the same time, during the optimization process, setting the first strength threshold can narrow the search space, thereby accelerating the convergence of the algorithm. When searching for the optimal ratio, the sparrow search algorithm will automatically exclude combinations whose first compressive strength values ​​exceed the first strength threshold, thereby avoiding invalid calculations and improving optimization efficiency.

[0089] S202: Construct the fitness function value of each sparrow individual

[0090]

[0091] Where, is the durability value corresponding to the target initial ratio.

[0092] It should be noted that the fitness function is the criterion for evaluating the quality of each solution during the optimization process. Here, the fitness function evaluates the quality of each sparrow individual (solution) by adding the negative of the first compressive strength value to the durability value.

[0093] S203: Perform exploration operations on some sparrow individuals and update their target initial ratio

[0094]

[0095] Where, is the position of the i-th sparrow in the t-th generation, is the position of the i-th sparrow in the t+1 generation, T max is the maximum number of iterations, θ is the random angle, exp(·) is the exponential function with e as the base, and e is a natural constant.

[0096] In this embodiment, the exploration operation updates the position of individual sparrows through exponential decay and angle random factors. As the number of iterations increases, the movement range of the individual gradually decreases, so that the algorithm has a greater exploration ability in the early stage and gradually concentrates on the possible optimal solution area.

[0097] S204: Check the updated Is it greater than FPV? min , if not greater than FPVmin , then perform boundary processing;

[0098] The above steps are to ensure that the first compressive strength value of the sparrow individual after updating will not exceed the preset FPV min ,Boundary processing ensures that every solution in the optimization process is valid by correcting the ,solutions that exceed the minimum threshold back to the maximum allowed value.

[0099] S205: Perform following operations on the remaining sparrow individuals and update their target initial ratios

[0100] The above-mentioned following operation means that the remaining sparrow individuals will follow the direction of the current optimal solution for update. By continuously following the optimal solution, the follower individuals have the opportunity to gradually approach the optimal solution, thereby improving the overall fitness of the population.

[0101] S206: Calculate the fitness function value of each sparrow individual after the update Update the current optimal solution;

[0102] After updating the ratio of individual sparrows, the fitness of each individual sparrow is recalculated to determine its pros and cons under the new ratio scheme. Through this operation, the algorithm can evaluate the effect of each update and select the optimal ratio scheme.

[0103] S207: When the preset maximum number of iterations T is reached max Stop searching when , and output the target initial ratio corresponding to the current optimal solution, which is the target optimized ratio.

[0104] If not greater than FPV min , the methods for boundary processing include:

[0105]

[0106] Where, Refers to the first compressive strength value of the i-th sparrow individual after being updated in the t+1 generation.

[0107] It should be added that the above steps are With FPV min This ensures that the ratio scheme that exceeds the preset first intensity threshold is forced to be corrected to the feasible range, ensuring that all solutions in the optimization process can be actually applied and avoiding the generation of infeasible solutions.

[0108] Update its target initial ratio The methods include:

[0109]

[0110] Where S is a random number, xbest is the location of the current optimal solution.

[0111] In this embodiment, the above steps indicate that the individual sparrows follow and update based on the current optimal solution. In this way, the individual sparrows will gradually move closer to the optimal solution and converge to a better solution.

[0112] S30: Determine the cost impact value based on the target optimization ratio. If the cost impact value is greater than the preset impact threshold, delete the current target optimization ratio and return to S20 to regenerate; if not, output the target optimization ratio.

[0113] It should be noted that deleting the current target optimization ratio mentioned above means removing the currently generated target optimization ratio from the calculation process, and no longer retaining the relevant data or parameters of the ratio, to ensure that the ratio will not be used or referenced again in the subsequent optimization process, so as to generate a completely different new target optimization ratio.

[0114] Methods for determining cost impact values ​​based on target optimization ratios include:

[0115]

[0116] Where CIV is the cost impact value, exp[·] is the exponential function with e as the base, sinh(·) is the hyperbolic sine function, and sin -1 (·) is the inverse sine function, e is a natural constant, and s1, s2, and s3 are the proportions of each component in the target optimized ratio.

[0117] It should be noted that in step S20, based on the first compressive strength value and durability value, the material ratio is adjusted using an optimization algorithm (such as a sparrow search algorithm) to ensure that the target optimized ratio obtained performs best in terms of strength and durability. Then, in step S30, the cost impact of the target optimized ratio is evaluated. If the cost impact value is too high, the target optimized ratio will be deleted and returned to S20 for regeneration. This combination ensures that only the target optimized ratio with cost-effectiveness controlled under the premise of meeting the strength and durability standards will be finally selected.

[0118] In this embodiment, a corresponding material model is constructed based on the target initial ratio, target detection data of the material model is obtained, and the target detection data is input into a pre-constructed first strength model to obtain a first compressive strength value. The durability value is determined based on the target initial ratio, and the target initial ratio is optimized according to the first compressive strength value, the durability value and the first optimization algorithm to obtain a target optimized ratio. The target initial ratio is optimized according to the first compressive strength value, the durability value and the first optimization algorithm to obtain a target optimized ratio. When applying construction solid waste to the roadbed, this embodiment simultaneously considers multiple costs, durability values ​​and roadbed strength factors, thereby comprehensively optimizing the ratio of construction solid waste.

[0119] Example 2

[0120] See also Figure 2 As shown, based on the same inventive concept, this embodiment discloses a computer-aided optimization system for designing the mix ratio of compaction-free solid waste roadbed fillers. For details not provided in this embodiment, please refer to the description of the relevant parts in Example 1. The system includes:

[0121] Data processing module: used to obtain a target initial mix ratio, build a corresponding material model based on the target initial mix ratio, obtain target detection data of the material model, input the target detection data into a pre-built first strength model to obtain a first compressive strength value, and determine a durability value based on the target initial mix ratio;

[0122] Methods for determining the target initial mix ratio include:

[0123] The weight of construction solid waste and the weight of solid waste-based cementitious materials are obtained, the actual water weight is determined according to the weight of solid waste-based cementitious materials, and the weight of construction solid waste, the weight of solid waste-based cementitious materials and the actual water weight are input into a preset proportion classification model to obtain an initial proportion set, wherein the initial proportion set includes R target initial proportions.

[0124] The construction method of the ratio classification model includes:

[0125] Obtain Q sets of training data, where Q is a positive integer greater than 1, and the training data includes the weight of historical building solid waste, the weight of historical solid waste-based cementitious materials, the weight of historical water, and a set of historical mix ratios;

[0126] The weight of historical building solid waste, the weight of historical solid waste-based cementitious materials, the historical water weight and the historical mix ratio set are used as the sample set, and the sample set is divided into a training set and a test set to construct a classifier;

[0127] The weight of historical building solid waste, historical solid waste-based cementitious materials, and historical water weight in the training set are used as input data, and the historical mix ratio set in the training set is used as output data to train the classifier and obtain an initial classifier.

[0128] The initial classifier is tested using the test set, and a classifier that meets the preset accuracy is output as the matching classification model. The classifier is preferably a naive Bayes model or a support vector machine model.

[0129] In this embodiment, the above training data is obtained by people skilled in the art based on experiments.

[0130] Methods for constructing corresponding material models include:

[0131] The target initial mix ratio and the corresponding weight of construction solid waste, weight of solid waste-based cementitious materials and actual water weight are input into the three-dimensional modeling software to obtain the material model output by the three-dimensional modeling software.

[0132] Methods for obtaining target detection data of material models include:

[0133] A simulated cyclic triaxial test is performed on the material model to obtain target detection data of the material model during the simulated cyclic triaxial test.

[0134] The construction method of the first strength model includes:

[0135] Acquire a first sample data set, where the first sample data set includes historical target detection data and historical first compressive strength values;

[0136] Divide the first sample data set into a sample training set and a sample test set, and construct a regression network;

[0137] The historical target detection data in the sample training set is used as the input data of the regression network, and the historical first compressive strength value in the sample training set is used as the output data of the regression network. The regression network is trained to obtain an initial regression network for predicting the real-time first compressive strength value.

[0138] The initial regression network is tested using a sample test set, and the output of the initial regression network that satisfies a preset error value is used as the first strength model. The initial regression network is preferably a deep neural network model.

[0139] Methods for determining durability values ​​based on target initial mix ratios include:

[0140]

[0141] Where, EIV is the durability value, SCM is the weight of solid waste-based cementitious materials, CSW is the weight of construction solid waste, and WTR is rt is the actual water weight, WTR sd is the standard water weight, log3(·) is the logarithmic function with base 3, tan -1(·) is the inverse tangent function, cosh(·) is the hyperbolic cosine function, and f1, f2, and f3 are the proportions of each component in the target initial ratio.

[0142] Optimization module: used to optimize the target initial ratio according to the first compressive strength value, the durability value and the first optimization algorithm to obtain the target optimized ratio;

[0143] Judgment output module: used to determine the cost impact value based on the target optimization ratio. If the cost impact value is greater than the preset impact threshold, the current target optimization ratio is deleted and returned to S20 to regenerate; if not, the target optimization ratio is output.

[0144] It should be noted that deleting the current target optimization ratio mentioned above means removing the currently generated target optimization ratio from the calculation process, and no longer retaining the relevant data or parameters of the ratio, to ensure that the ratio will not be used or referenced again in the subsequent optimization process, so as to generate a completely different new target optimization ratio.

[0145] Methods for determining cost impact values ​​based on target optimization ratios include:

[0146]

[0147] Where CIV is the cost impact value, exp[·] is the exponential function with e as the base, sinh(·) is the hyperbolic sine function, and sin -1 (·) is the inverse sine function, e is a natural constant, and s1, s2, and s3 are the proportions of each component in the target optimized ratio.

[0148] Example 3

[0149] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the computer-aided optimization method for designing the mix ratio of compaction-free solid waste roadbed fillers provided by the above-mentioned methods is implemented.

[0150] Since the electronic device introduced in this embodiment is an electronic device used to implement the computer-aided optimization method for the mix ratio design of non-compacted solid waste roadbed filler in the embodiment of this application, based on the computer-aided optimization method for the mix ratio design of non-compacted solid waste roadbed filler introduced in the embodiment of this application, those skilled in the art can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application will not be described in detail here. As long as those skilled in the art implement the electronic device used by the computer-aided optimization method for the mix ratio design of non-compacted solid waste roadbed filler in the embodiment of this application, they all fall within the scope of protection of this application.

[0151] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters, weights and thresholds in the formulas are set by technicians in this field according to actual conditions.

[0152] The above embodiments can be implemented in whole or in part through software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired or wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, or a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0153] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0154] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0155] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only one type. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0156] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0157] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0158] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

[0159] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A computer-aided optimization method for designing the mix ratio of compaction-free solid waste roadbed filler, characterized in that: include: S10: obtaining a target initial mix ratio, constructing a corresponding material model based on the target initial mix ratio, obtaining target detection data of the material model, inputting the target detection data into a pre-constructed first strength model, obtaining a first compressive strength value, and determining a durability value based on the target initial mix ratio; S20: Optimizing the target initial ratio according to the first compressive strength value, the durability value and the first optimization algorithm to obtain a target optimized ratio; S30: Determine the cost impact value based on the target optimization ratio. If the cost impact value is greater than the preset impact threshold, delete the current target optimization ratio and return to S20 to regenerate; if not, output the target optimization ratio.

2. The computer-aided optimization method for designing the mix ratio of compaction-free solid waste roadbed filler according to claim 1 is characterized in that: The method for determining the target initial ratio includes: The weight of construction solid waste and the weight of solid waste-based cementitious materials are obtained, the actual water weight is determined according to the weight of solid waste-based cementitious materials, the weight of construction solid waste, the weight of solid waste-based cementitious materials and the actual water weight are input into a preset proportion classification model to obtain an initial proportion set, wherein the initial proportion set includes R target initial proportions.

3. The computer-aided optimization method for designing the mix ratio of compaction-free solid waste roadbed filler according to claim 2 is characterized in that: The method for constructing the first strength model includes: Acquire a first sample data set, wherein the first sample data set includes historical target detection data and historical first compressive strength values; Divide the first sample data set into a sample training set and a sample test set, and construct a regression network; The historical target detection data in the sample training set is used as the input data of the regression network, and the historical first compressive strength value in the sample training set is used as the output data of the regression network, and the regression network is trained to obtain an initial regression network for predicting the real-time first compressive strength value; The initial regression network is tested using a sample test set, and the output of the initial regression network that satisfies a preset error value is used as the first strength model.

4. The computer-aided optimization method for designing the mix ratio of compaction-free solid waste roadbed filler according to claim 3 is characterized in that: The first optimization algorithm is a sparrow search algorithm. The target initial ratio is optimized based on the sparrow search algorithm. The method for obtaining the target optimized ratio includes: S201: Randomly generate a group of sparrow individuals, each sparrow individual represents a target initial ratio, and randomly generate an initial position for each sparrow individual That is, the target initial ratio is to satisfy: in, is the first compressive strength value corresponding to the target initial ratio, FPV min A first intensity threshold is preset; S202: Construct the fitness function value of each sparrow individual In the formula, is the durability value corresponding to the target initial ratio; S203: Perform exploration operations on some sparrow individuals and update their target initial ratio S204: Check for updated Is it greater than FPV? min , if not greater than FPV min , then perform boundary processing; S205: Perform a follow-up operation on the remaining sparrow individuals to update their target initial ratio S206: Calculate the fitness function value of each sparrow individual after the update Update the current optimal solution; S207: When the preset maximum number of iterations T is reached max Stop searching when , and output the target initial ratio corresponding to the current optimal solution, which is the target optimization ratio.

5. The computer-aided optimization method for designing the mix ratio of compaction-free solid waste roadbed filler according to claim 4 is characterized in that: The method for performing boundary processing comprises: In the formula, Refers to the first compressive strength value of the i-th sparrow individual after being updated in the t+1 generation.

6. The computer-aided optimization method for designing the mix ratio of compaction-free solid waste roadbed filler according to claim 5, characterized in that: The method for performing an exploration operation on some sparrow individuals comprises: In the formula, is the position of the i-th sparrow in the t-th generation, is the position of the i-th sparrow in the t+1 generation, T max is the maximum number of iterations, θ is the random angle, exp(·) is the exponential function with e as the base, and e is a natural constant.

7. The computer-aided optimization method for designing the mix ratio of compaction-free solid waste roadbed filler according to claim 6, characterized in that: The target initial ratio is updated The methods include: In the formula, S is a random number, x best is the location of the current optimal solution.

8. A computer-aided optimization system for designing a mix ratio of a non-compacted solid waste roadbed filler, which is used to implement a computer-aided optimization method for designing a mix ratio of a non-compacted solid waste roadbed filler according to any one of claims 1 to 7, characterized in that: include: Data processing module: used to obtain the target initial ratio, build a corresponding material model based on the target initial ratio, obtain target detection data of the material model, input the target detection data into a pre-built first strength model, obtain a first compressive strength value, and determine a durability value based on the target initial ratio; Optimization module: used to optimize the target initial ratio according to the first compressive strength value, the durability value and the first optimization algorithm to obtain the target optimized ratio; Judgment output module: used to determine the cost impact value based on the target optimization ratio. If the cost impact value is greater than the preset impact threshold, the current target optimization ratio is deleted and returned to the optimization module for regeneration; if not, the target optimization ratio is output.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the computer-aided optimization method for designing the mix ratio of compaction-free solid waste roadbed filler as described in any one of claims 1 to 7 is implemented.

Images