Method, device and equipment for optimizing mix proportion of dredged sediment geopolymer and medium

Abstract

The invention discloses a dredged sediment geopolymer mix proportion optimization method, device and equipment and a medium. The method comprises the following steps: acquiring dredging sediment geopolymer mix proportion key parameters and corresponding compressive strength data, and constructing a to-be-processed sample set; constructing and training a compressive strength prediction model based on the to-be-processed sample set, and determining a nonlinear mapping relation function of the dredged sediment geopolymer mix proportion key parameters and compressive strength data; constructing a target fitness function according to the nonlinear mapping relation function, the dredged sediment geopolymer production material cost and the production carbon emission; constructing constraint conditions according to the matching ratio key parameter range of the dredged sediment geopolymer, the use amount range of production materials and the volume of the dredged sediment geopolymer per cubic meter; and based on the target fitness function and the constraint condition, carrying out dredging sediment geopolymer mix proportion key parameter multi-target optimization through a genetic algorithm, and determining a dredging sediment geopolymer target mix proportion. And multi-objective optimization of the mixture ratio of the dredged sediment geopolymer is realized.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of dredging, and in particular, to a method, device, equipment and medium for optimizing the mix proportion of dredged sediment geopolymers. Background Art

[0002] A large amount of dredged sediment generated in port waterway dredging, reservoir silt removal and marine engineering construction, with an annual output of hundreds of millions of cubic meters, its efficient resource utilization has become an urgent issue in the field of dredging technology. Geopolymer is a polymer formed by the polymerization reaction of aluminosilicate materials under the action of an alkaline activator. And dredged sediment usually contains a certain amount of elements such as silicon and aluminum, having the material basis for preparing geopolymers. Therefore, preparing dredged sediment into geopolymers is an effective way of resource utilization.

[0003] Due to the complex composition of dredged sediment, which contains organic matter, heavy metals and inert particles, directly using dredged sediment to replace the silicon-aluminum source for geopolymer preparation may lead to problems such as large fluctuations in the compressive strength of geopolymers and a sharp increase in material costs, and it is necessary to prepare geopolymers through a reasonable mix proportion of dredged sediment geopolymers.

[0004] At present, orthogonal experiments and response surface analysis methods are mostly used to explore the mix proportion of geopolymers. However, the strength formation mechanism of the dredged sediment - geopolymer system involves complex alkali activation reactions, silicon-aluminum network reconstruction and impurity interference effects, and traditional methods have obvious limitations: First, the experimental method requires a large amount of time and resources and is difficult to cover the multi-dimensional parameter space; Second, statistical methods based on linear regression or polynomial models cannot accurately describe the non-linear relationship between the variables involved in preparing geopolymers from dredged sediment, resulting in an unreasonable mix proportion determined. Machine learning techniques can also be used to explore the mix proportion of geopolymers, but most focus on single-objective optimization and have insufficient engineering usability in practical applications. Summary of the Invention

[0005] The present invention provides a method, device, equipment and medium for optimizing the mix proportion of dredged sediment geopolymers, which can break through the bottleneck of "low precision, long time consumption, and multi-objective imbalance" in traditional technologies and provide effective support for the large-scale resource utilization of dredged sediment.

[0006] In a first aspect, the embodiments of the present invention provide a method for optimizing the mix proportion of dredged sediment geopolymers, including:

[0007] Obtain the key parameters of the mix proportion of dredged sediment geopolymers and the corresponding compressive strength data, and construct a sample set to be processed, where the key parameters of the mix proportion of dredged sediment geopolymers at least include the content of dredged sediment, the concentration of the alkaline activator, and the modulus of the alkaline activator;

[0008] Construct and train a compressive strength prediction model based on the to-be-processed sample set, and determine the non-linear mapping relationship function between the key parameters of the dredged sediment geopolymer mix proportion and the compressive strength data;

[0009] Construct an objective fitness function according to the non-linear mapping relationship function, the production material cost of the dredged sediment geopolymer, and the production carbon emission;

[0010] Construct constraint conditions according to the key parameter range of the dredged sediment geopolymer mix proportion, the production material usage range, and the volume of the dredged sediment geopolymer per cubic meter;

[0011] Based on the objective fitness function and the constraint conditions, perform multi-objective optimization of the key parameters of the dredged sediment geopolymer mix proportion through a genetic algorithm to determine the target mix proportion of the dredged sediment geopolymer.

[0012] In a second aspect, an embodiment of the present invention provides a device for optimizing the mix proportion of dredged sediment geopolymer, including:

[0013] A to-be-processed sample set construction module, configured to obtain the key parameters of the dredged sediment geopolymer mix proportion and the corresponding compressive strength data, and construct a to-be-processed sample set, where the key parameters of the dredged sediment geopolymer mix proportion at least include the dredged sediment content, the alkali activator concentration, and the alkali activator modulus;

[0014] A non-linear mapping relationship function determination module, configured to construct and train a compressive strength prediction model based on the to-be-processed sample set, and determine the non-linear mapping relationship function between the key parameters of the dredged sediment geopolymer mix proportion and the compressive strength data;

[0015] An objective fitness function construction module, configured to construct an objective fitness function according to the non-linear mapping relationship function, the production material cost of the dredged sediment geopolymer, and the production carbon emission;

[0016] A constraint condition construction module, configured to construct constraint conditions according to the key parameter range of the dredged sediment geopolymer mix proportion, the production material usage range, and the volume of the dredged sediment geopolymer per cubic meter;

[0017] A multi-objective optimization module, configured to perform multi-objective optimization of the key parameters of the dredged sediment geopolymer mix proportion through a genetic algorithm based on the objective fitness function and the constraint conditions to determine the target mix proportion of the dredged sediment geopolymer.

[0018] In a third aspect, an embodiment of the present invention provides an electronic device, including:

[0019] At least one processor; and

[0020] A memory communicatively connected to the at least one processor; wherein,

[0021] The memory stores a computer program that can be executed by the at least one processor. When the computer program is executed by the at least one processor, the at least one processor is enabled to execute the method described in the first aspect.

[0022] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the method described in the first aspect is implemented.

[0023] In the technical solution of the embodiment of the present invention, key parameters of the dredged sediment geopolymer mix ratio and corresponding compressive strength data are obtained and a sample set to be processed is constructed; a compressive strength prediction model is constructed and trained through the sample set to be processed, and a non-linear mapping relationship function between the key parameters of the dredged sediment geopolymer mix ratio and the compressive strength data is established; an objective fitness function is constructed according to the non-linear mapping relationship function, the production material cost of the dredged sediment geopolymer, and the production carbon emission; constraint conditions are constructed according to the range of the key parameters of the dredged sediment geopolymer mix ratio, the range of the production material dosage, and the volume of the dredged sediment geopolymer per cubic meter; based on the objective fitness function and the constraint conditions, multi-objective optimization of the key parameters of the dredged sediment geopolymer mix ratio is carried out through a genetic algorithm to determine the target mix ratio of the dredged sediment geopolymer. This solution breaks through the bottlenecks of "low accuracy, long time consumption, and multi-objective imbalance" in the traditional technology through the high-precision prediction of the compressive strength prediction model and the multi-objective optimization of the dredged sediment geopolymer mix ratio in multiple aspects of compressive strength, production cost, and carbon emission, providing effective support for the large-scale resource utilization of dredged sediment.

[0024] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0026] Figure 1 is a flowchart of a method for optimizing the mix ratio of a dredged sediment geopolymer according to Embodiment 1 of the present invention;

[0027] Figure 2 is a flowchart of a method for optimizing the mix ratio of a dredged sediment geopolymer according to Embodiment 2 of the present invention;

[0028] Figure 3Schematic diagram of optimizing model parameters of a compressive strength prediction model provided in Embodiment 2 of the present invention;

[0029] Figure 4 Schematic diagram of performing regression fitting on a training sample set based on a compressive strength prediction model provided in Embodiment 2 of the present invention;

[0030] Figure 5 Schematic diagram of performing regression fitting on a test sample set based on a compressive strength prediction model provided in Embodiment 2 of the present invention;

[0031] Figure 6 Flowchart of a method for optimizing the mix proportion of dredged bottom mud geopolymers provided in Embodiment 3 of the present invention;

[0032] Figure 7 Schematic diagram of performing global optimization using a genetic algorithm provided in Embodiment 3 of the present invention;

[0033] Figure 8 Schematic diagram of the structure of a device for optimizing the mix proportion of dredged bottom mud geopolymers provided in Embodiment 4 of the present invention;

[0034] Figure 9 Schematic diagram of the structure of an electronic device implementing the embodiments of the present invention. Detailed implementation manners

[0035] In order to enable those skilled in the art of the present technology to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0036] It should be noted that the terms "first", "second", etc. in the present invention are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0037] Embodiment 1

[0038] Figure 1 FIG. Figure 1 is a flowchart of a method for optimizing the mix ratio of dredged sediment geopolymers according to Embodiment 1 of the present invention. This embodiment is applicable to the situation of optimizing the mix ratio of dredged sediment geopolymers. This method can be executed by a device for optimizing the mix ratio of dredged sediment geopolymers, and this device can be implemented in the form of software and / or hardware and integrated in an electronic device. Further, the electronic device includes, but is not limited to: a computer, a laptop, a server, etc.

[0039] As Figure 1 shown, the method includes:

[0040] S110. Obtain the key parameters of the mix ratio of dredged sediment geopolymers and the corresponding compressive strength data, and construct a sample set to be processed. The key parameters of the mix ratio of dredged sediment geopolymers at least include the content of dredged sediment, the concentration of alkali activator, and the modulus of alkali activator.

[0041] The mix ratio of dredged sediment geopolymers can be understood as the dosage of each production material involved in the dredged sediment geopolymers when preparing geopolymers from dredged sediment. Among them, the production materials of dredged sediment geopolymers can include, but are not limited to: dredged sediment, fly ash, granulated blast furnace slag, water glass solution, sodium hydroxide, water.

[0042] The key parameters of the mix ratio of dredged sediment geopolymers can be understood as the key parameters required to determine the mix ratio of dredged sediment geopolymers, at least including the content of dredged sediment, the concentration of alkali activator, and the modulus of alkali activator. Among them, the content of dredged sediment is the mass ratio of dredged sediment in the solid materials of the production materials, the concentration of alkali activator is the mass ratio of the solute in the alkaline activator solution, and the modulus of alkali activator is a parameter reflecting the chemical composition characteristics of the alkaline activator.

[0043] In the case of determining the key parameters of the mix ratio of dredged sediment geopolymers, the dosages of each production material involved in the dredged sediment geopolymers can be determined based on these key parameters, that is, the mix ratio of dredged sediment geopolymers is determined.

[0044] The compressive strength data corresponding to the key parameters of the mix ratio of dredged sediment geopolymers can be the compressive strength of the dredged sediment geopolymers prepared with the mix ratio of dredged sediment geopolymers corresponding to the key parameters of the mix ratio of dredged sediment geopolymers.

[0045] In practical applications, the key parameters of the mix ratio of dredged sediment geopolymers and their corresponding compressive strength data can be used as a sample to be processed, and multiple samples to be processed are obtained to construct a sample set to be processed. Among them, the key parameters of the mix ratio of dredged sediment geopolymers and the corresponding compressive strength data can be data collected at historical times, which is not limited here.

[0046] Table 1 is an example table of samples to be processed. Each row can represent a sample to be processed, and it exemplarily illustrates the key parameters of the dredged sediment geopolymer mix proportion and the corresponding compressive strength data.

[0047] Table 1 Example Table of Samples to be Processed

[0048]

[0049]

[0050] S120. Construct and train a compressive strength prediction model based on the set of samples to be processed, and determine the non - linear mapping relationship function between the key parameters of the dredged sediment geopolymer mix proportion and the compressive strength data.

[0051] The compressive strength prediction model can be a model used to predict the corresponding compressive strength data based on the key parameters of the dredged sediment geopolymer mix proportion. The compressive strength prediction model can be, for example, a Back Propagation (BP) neural network model, and the specific structure of the compressive strength prediction model is not limited. The non - linear mapping relationship function can be a function indicating the non - linear mapping relationship between the key parameters of the dredged sediment geopolymer mix proportion and the compressive strength data.

[0052] In this step, the set of samples to be processed can be divided into a training sample set and a test sample set according to a certain ratio, and the data in the training sample set and the test sample set are normalized to the interval [0, 1]; construct a compressive strength prediction model, use the key parameters of the dredged sediment geopolymer mix proportion as the input and the compressive strength data as the output based on the training sample set, and train the compressive strength prediction model; verify the prediction effect of the trained compressive strength prediction model based on the test sample set; through the trained compressive strength prediction model, output the non - linear mapping relationship function between the key parameters of the dredged sediment geopolymer mix proportion and the compressive strength data, that is, taking a certain key parameter of the dredged sediment geopolymer mix proportion as the input, the non - linear mapping relationship function can determine the corresponding compressive strength data of the input.

[0053] In one embodiment, the ratio of the number of samples in the training sample set to the number of samples in the test sample set can be 2:1 - 9:1, which is not limited here. Optionally, 4:1 can be adopted in practical applications.

[0054] In one embodiment, to normalize the data in the training sample set and the test sample set, the maximum - minimum normalization function can be used, expressed as X’=(X - Xmin) / (Xmax - Xmin), where X is a certain parameter involved in the sample, Xmin is the minimum value of this parameter, Xmax is the maximum value of this parameter, and X’ is the normalized parameter of this parameter.

[0055] S130. Construct an objective fitness function based on the non - linear mapping relationship function, the production material cost of dredged sediment geopolymers, and the production carbon emissions.

[0056] The production material cost of dredged sediment geopolymers can be the sum of the products of the amounts of each production material of dredged sediment geopolymers and the corresponding material unit prices. The production carbon emissions can be the sum of the products of the amounts of each production material of dredged sediment geopolymers and the corresponding life - cycle carbon emissions of the materials.

[0057] The objective fitness function can be a function used to guide the search process in the multi - objective optimization. Through continuous iteration of multi - objective optimization, try to find the solution with the optimal fitness value (which may be the maximum or minimum according to the specific problem) of the objective fitness function, that is, the solution that achieves the best balance among multiple objectives.

[0058] In this step, through the non - linear mapping relationship function, an objective function can be constructed with the maximum compressive strength data as the goal under different key parameters of the mix proportion of dredged sediment geopolymers; an objective function can be constructed with the lowest production material cost of dredged sediment geopolymers as the goal under the amounts of production materials of dredged sediment geopolymers corresponding to different key parameters of the mix proportion; an objective function can be constructed with the lowest production carbon emissions as the goal under the amounts of production materials of dredged sediment geopolymers corresponding to different key parameters of the mix proportion; the combination of the above multiple objective functions is the objective fitness function. That is, subsequently, through multi - objective optimization, a solution that achieves the best balance among the maximum compressive strength data, the lowest production material cost of dredged sediment geopolymers, and the lowest production carbon emissions needs to be found.

[0059] S140. Construct constraint conditions based on the range of key parameters of the mix proportion of dredged sediment geopolymers, the range of production material amounts, and the volume of dredged sediment geopolymers per cubic meter.

[0060] In this step, according to the actual application needs, a corresponding value range can be set for each parameter included in the key parameters of the mix proportion of dredged sediment geopolymers; a corresponding amount range can be set for each production material of dredged sediment geopolymers; a corresponding volume range can be set for the volume of dredged sediment geopolymers per cubic meter. The volume of dredged sediment geopolymers is the sum of the ratios of the amounts of each material included in the production materials of dredged sediment geopolymers to the material density. The combination of the above value range, amount range, and volume range is the constraint condition. Among them, the constraint condition can be a constraint condition used to guide the search process in the multi - objective optimization, and there is no limitation on the above value range, amount range, and volume range.

[0061] S150. Based on the objective fitness function and the constraint conditions, perform multi - objective optimization of the key parameters of the mix proportion of dredged sediment geopolymers through the genetic algorithm to determine the target mix proportion of dredged sediment geopolymers.

[0062] In this step, through the genetic algorithm, based on multiple objectives indicated by the target fitness function, that is, to maximize the compressive strength data under different key parameters of the dredged sediment geopolymer mix ratio, to minimize the production material cost of the dredged sediment geopolymer under the production material consumption of the dredged sediment geopolymer corresponding to different key parameters of the dredged sediment geopolymer mix ratio, and to minimize the production carbon emissions under the production material consumption of the dredged sediment geopolymer corresponding to different key parameters of the dredged sediment geopolymer mix ratio as the search objectives, and based on the constraint conditions, that is, the value range of the above-mentioned key parameters of the dredged sediment geopolymer mix ratio, the consumption range of the production materials of the dredged sediment geopolymer, and the volume of the dredged sediment geopolymer per cubic meter as the search constraints, continuously conduct search iterations to obtain the key parameters of the dredged sediment geopolymer mix ratio that can achieve the best balance among multiple objectives; determine the mix ratio of the dredged sediment geopolymer corresponding to the key parameters of the dredged sediment geopolymer mix ratio with the best balance of multiple objectives as the target mix ratio of the dredged sediment geopolymer. Among them, the genetic algorithm is not limited, such as it can be the third generation of the Non-dominated Sorting Genetic Algorithm (NSGA).

[0063] The technical solution of the embodiment of the present invention is to obtain the key parameters of the dredged sediment geopolymer mix ratio and the corresponding compressive strength data and construct a sample set to be processed; construct and train a compressive strength prediction model through the sample set to be processed, and establish a non-linear mapping relationship function between the key parameters of the dredged sediment geopolymer mix ratio and the compressive strength data; construct a target fitness function according to the non-linear mapping relationship function, the production material cost of the dredged sediment geopolymer and the production carbon emissions; construct constraint conditions according to the range of the key parameters of the dredged sediment geopolymer mix ratio, the range of the production material consumption, and the volume of the dredged sediment geopolymer per cubic meter; based on the target fitness function and the constraint conditions, conduct multi-objective optimization of the key parameters of the dredged sediment geopolymer mix ratio through the genetic algorithm to determine the target mix ratio of the dredged sediment geopolymer. This solution breaks through the bottleneck of "low accuracy, long time consumption, and multi-objective imbalance" in the traditional technology through the high-precision prediction of the compressive strength prediction model and the multi-objective optimization of the mix ratio of the dredged sediment geopolymer in terms of compressive strength, production cost, and carbon emissions, and provides effective support for the large-scale resource utilization of dredged sediment.

[0064] Embodiment 2

[0065] Figure 2It is a flowchart of a method for optimizing the mix proportion of dredged sediment geopolymer according to Embodiment 2 of the present invention. This embodiment further refines the construction and training of a compressive strength prediction model based on the to-be-processed sample set to determine the non-linear mapping relationship function between the key parameters of the dredged sediment geopolymer mix proportion and the compressive strength data on the basis of Embodiment 1 above; further refines the construction of an objective fitness function according to the non-linear mapping relationship function, the production material cost of the dredged sediment geopolymer, and the production carbon emissions; and further refines the construction of constraint conditions according to the range of key parameters of the dredged sediment geopolymer mix proportion, the range of production material usage, and the volume of dredged sediment geopolymer per cubic meter.

[0066] As Figure 2 shown, the method includes:

[0067] S110. Obtain the key parameters of the dredged sediment geopolymer mix proportion and the corresponding compressive strength data, and construct a to-be-processed sample set, where the to-be-processed sample set includes a training sample set and a test sample set.

[0068] S121. Construct a compressive strength prediction model through a backpropagation neural network.

[0069] S122. Use the key parameters of the dredged sediment geopolymer mix proportion of each training sample in the training sample set as input parameters, and use the compressive strength data corresponding to the input parameters as output parameters to train the compressive strength prediction model and determine the model parameters.

[0070] In this step, use the key parameters of the dredged sediment geopolymer mix proportion of each training sample in the training sample set as input parameters, and use the compressive strength data corresponding to the input parameters as output parameters to train the compressive strength prediction model. The grid search method is combined with cross-validation to optimize the model parameters grid and determine the model parameters. The model parameters are not limited and can be the parameters required for the operation of the compressive strength prediction model, such as the number of nodes in the input layer, the number of nodes in the hidden layer, etc.

[0071] In one embodiment, the number of nodes in the input layer of the compressive strength prediction model is 3; the model parameters are determined by grid search using K-fold cross-validation, and K includes 10.

[0072] In one embodiment, the number of nodes in the hidden layer of the compressive strength prediction model can be determined by the following formula: where M is the number of nodes in the hidden layer, n is the number of nodes in the input layer, m is 1, a ∈ [0, 10], and M can be determined by grid search.

[0073] S123. Verify the prediction result of the trained compressive strength prediction model through the test sample set in combination with the model parameters.

[0074] In this step, the trained compressive strength prediction model is run under the above model parameters. Using the key parameters of the dredged sediment geopolymer mix ratio of each test sample in the test sample set as input parameters, the predicted values of the compressive strength data are output and inverse normalization processing is performed to obtain the prediction results of the trained compressive strength prediction model. The predicted values of the compressive strength data are compared with the actual values of the compressive strength data of the corresponding test samples in the test sample set to verify the prediction results of the trained compressive strength prediction model.

[0075] In one embodiment, the prediction results of the trained compressive strength prediction model are verified by at least the following parameters: the root mean square error, mean percentage error, and goodness of fit corresponding to each test sample in the test sample set.

[0076] The root mean square error RMSE corresponding to each test sample can be determined by the following formula: where N is the number of test samples, y i is the actual value of the compressive strength data, and y i ' is the predicted value of the compressive strength data.

[0077] The mean percentage error MAPE corresponding to each test sample can be the mean absolute percentage error and can be determined by the following formula:

[0078] The goodness of fit R 2 of the trained compressive strength prediction model can be determined by the following formula: where is the mean value of the actual values of each compressive strength data.

[0079] S124. When the prediction results meet the set conditions, output the non-linear mapping relationship function between the key parameters of the dredged sediment geopolymer mix ratio and the compressive strength data through the trained compressive strength prediction model.

[0080] In this step, it can be determined that the set conditions are met when the root mean square error corresponding to the prediction results is lower than the first threshold, the mean percentage error is lower than the second threshold, and the goodness of fit exceeds the third threshold. Then, output the non-linear mapping relationship function between the key parameters of the dredged sediment geopolymer mix ratio and the compressive strength data through the trained compressive strength prediction model. The above first threshold, second threshold, third threshold, and set conditions are not limited.

[0081] S131. Construct the objective function corresponding to the non-linear mapping relationship function, indicating to find a set of key parameters of the dredged sediment geopolymer mix ratio such that the corresponding compressive strength data is the largest.

[0082] S132. Construct the objective function corresponding to the cost of the dredged sediment geopolymer production materials, indicating to find a set of dosages of the dredged sediment geopolymer production materials such that the corresponding cost of the dredged sediment geopolymer production materials is minimized, and the dosages of the dredged sediment geopolymer production materials are determined based on the key parameters of the dredged sediment geopolymer mix ratio.

[0083] S133. Construct the objective function corresponding to the production carbon emissions, indicating to find a set of dosages of the dredged sediment geopolymer production materials such that the corresponding production carbon emissions are minimized.

[0084] S134. Construct the objective fitness function according to the objective functions corresponding to the non - linear mapping relationship function, the cost of the dredged sediment geopolymer production materials, and the production carbon emissions respectively.

[0085] The execution order of the above S131 to S133 is not limited. The following explains S131 - S134. The objective fitness function can be expressed by the following formula:

[0086]

[0087] Among them, the objective function corresponding to the non - linear mapping relationship function is f1, X i is the key parameter of the dredged sediment geopolymer mix ratio, is the compressive strength data predicted by the non - linear mapping relationship function based on X i ; the objective function corresponding to the cost of the dredged sediment geopolymer production materials is f2, x i is the dosage of the dredged sediment geopolymer production materials per cubic meter, c i is the unit price of the material for x i ; the objective function corresponding to the production carbon emissions is f3, e i is the life - cycle carbon emissions of the material for x i .

[0088] S141. Construct the value constraint, and the value constraint indicates that each parameter included in the key parameters of the dredged sediment geopolymer mix ratio satisfies its corresponding value range.

[0089] S142. Construct the dosage constraint, and the dosage constraint indicates that the dosages of the dredged sediment, fly ash, granulated blast - furnace slag, sodium silicate solution, sodium hydroxide, and water included in the dredged sediment geopolymer production materials satisfy their corresponding first dosage ranges, and the ratio of the water dosage to the sum of the dosages of the dredged sediment, fly ash, and granulated blast - furnace slag satisfies the second dosage range.

[0090] S143. Construct the volume constraint, where the volume constraint indicates that the volume of the dredged sediment geopolymer per cubic meter is 1, and the volume of the dredged sediment geopolymer is the sum of the ratios of the dosages of the respective materials included in the dredged sediment geopolymer production materials to their material densities.

[0091] There is no limitation on the execution order of S141 to S143 above. The following explains S141 - S143.

[0092] The value constraint can be expressed as:

[0093]

[0094] Among them, X1 is the dosage of dredged sediment, in %; X2 is the concentration of the alkali activator, in %; X3 is the modulus of the alkali activator.

[0095] The dosage constraint can be expressed as:

[0096]

[0097] Among them, x1 to x6 are the dosages of dredged sediment, fly ash, granulated blast furnace slag, sodium silicate solution, sodium hydroxide, and water respectively, all in kg.

[0098] The volume constraint can be expressed as:

[0099]

[0100] Among them, V is the volume of the dredged sediment geopolymer per cubic meter, and ρ i is the density of x i .

[0101] The combination of the above value constraint, dosage constraint, and volume constraint is the constraint condition.

[0102] S150. Based on the target fitness function and the constraint conditions, perform multi-objective optimization of the key parameters of the mix proportion of the dredged sediment geopolymer through a genetic algorithm to determine the target mix proportion of the dredged sediment geopolymer.

[0103] In the technical solution of the embodiment of the present invention, a compressive strength prediction model is constructed through a backpropagation neural network, the constructed compressive strength prediction model is trained through a training sample set, the prediction result of the trained compressive strength prediction model is verified through a test sample set, and when the prediction result meets the set conditions, the trained compressive strength prediction model outputs a nonlinear mapping relationship function between the key parameters of the dredged bottom mud geopolymer mix ratio and the compressive strength data, improving the prediction accuracy of the compressive strength data; by constructing the objective functions corresponding to the nonlinear mapping relationship function, the production material cost of the dredged bottom mud geopolymer, and the production carbon emissions, a search target is provided for subsequent multi-objective optimization; by constructing value constraints, dosage constraints, and volume constraints, constraint conditions are provided for subsequent multi-objective optimization.

[0104] The following is an exemplary description of some contents of this embodiment.

[0105] Figure 3 It is a schematic diagram of optimizing the model parameters of a compressive strength prediction model provided in Embodiment II of the present invention. As Figure 3 shown, based on the root mean square error RMSE, the number of hidden layers (i.e., the number of hidden layer nodes), and the weight decay coefficient (taking 0.001, 0.010, 0.100), the model parameters are optimized. The optimization result shows that when the number of hidden layers is 6 and the decay coefficient is 0.010, the verified RMSE value is the smallest, the coefficient of variation of RMSE is 0.653, and the coefficient of variation is the ratio of RMSE to the ratio.

[0106] Figure 4 It is a schematic diagram of performing regression fitting on the training sample set based on the compressive strength prediction model provided in Embodiment II of the present invention. Figure 5 It is a schematic diagram of performing regression fitting on the test sample set based on the compressive strength prediction model provided in Embodiment II of the present invention. Among them, the goodness of fit R 2 for the training sample set is 0.966, and the R 2 for the test sample set is 0.956. The fitting results are good, and the error between the predicted value and the actual value (i.e., the true value) of the compressive strength data is small.

[0107] Embodiment III

[0108] Figure 6 It is a flowchart of a method for optimizing the mix ratio of dredged bottom mud geopolymer provided in Embodiment III of the present invention. This embodiment is a further refinement of determining the target mix ratio of the dredged bottom mud geopolymer by performing multi-objective optimization on the key parameters of the mix ratio of the dredged bottom mud geopolymer through a genetic algorithm based on the target fitness function and the constraint conditions on the basis of the above Embodiment I.

[0109] As Figure 6As shown, the method includes:

[0110] S110. Obtain key parameters of the dredged sediment geopolymer mix ratio and corresponding compressive strength data, and construct a sample set to be processed.

[0111] S120: constructing and training a compressive strength prediction model based on the sample set to be processed, and determining a nonlinear mapping relationship function between key parameters of the dredged mud geopolymer mix ratio and the compressive strength data.

[0112] S130: Constructing a target fitness function according to the nonlinear mapping relationship function, the production material cost of dredged mud geopolymer, and the production carbon emission.

[0113] S140. Construct constraint conditions based on the key parameter range of the dredged mud geopolymer mix ratio, the production material usage range, and the volume of dredged mud geopolymer per cubic meter.

[0114] S151. Construct a genetic algorithm according to the target fitness function and the constraint conditions.

[0115] The multiple objectives indicated by the target fitness function, namely, the maximum compressive strength data, the lowest cost of dredged mud geopolymer production materials, and the lowest production carbon emissions, are taken as search targets. The constraints, namely, the value range of key parameters of dredged mud geopolymer mix ratio, the dosage range of dredged mud geopolymer production materials, and the volume of dredged mud geopolymer per cubic meter, are taken as search constraints and integrated into the genetic algorithm as the targets and constraints of the genetic algorithm iteration.

[0116] S152. The key parameters of the dredged sediment geopolymer mix ratio are used as decision variables of the genetic algorithm to construct a search space, and an initial population is generated with a set population size. The key parameters of the dredged sediment geopolymer mix ratio are used to form individual chromosomes, and the parameter variables of the key parameters of the dredged sediment geopolymer mix ratio are used to form the genes of the individual chromosomes. The individuals are initialized and structured reference points are generated.

[0117] In this step, the key parameters of the dredged mud geopolymer mix ratio are used as decision variables of the genetic algorithm. The decision variables are the variables that need to be optimized by the genetic algorithm, which means that the genetic algorithm will find the optimal solution by adjusting the key parameters of the dredged mud mix ratio.

[0118] The genetic algorithm searches for the optimal solution within the search space, which is the set of all possible values of the decision variables.

[0119] Generate an initial population \(Y\) with a set population size \(N\). Use the key parameters of the dredged sediment geopolymer mix ratio (i.e., the content of dredged sediment, the concentration of alkali activator, and the modulus of alkali activator) to form an individual chromosome, and use the parameter variables of the key parameters of the dredged sediment geopolymer mix ratio (i.e., the content of dredged sediment, the concentration of alkali activator, or the modulus of alkali activator) to form the genes of the individual chromosome. Initialize the individuals, that is, assign initial values to the genes on the individual chromosome, and these initial values can be randomly generated within the value range of the decision variables.

[0120] Generate structured reference points, which can be multiple reference points generated according to the ideal values and boundary values of the above search objectives. The reference points can effectively guide the genetic algorithm to search for the optimal solution.

[0121] S153. Determine the fitness value of each individual in the initial population under the target fitness function, perform non - dominated sorting of the individuals according to the determined fitness values, and assign the individuals to the nearest reference point based on the distance from the determined fitness value to the reference point.

[0122] In this step, substitute each individual in the initial population into the target fitness function to obtain the fitness value, and evaluate the pros and cons of each individual in the multi - objective optimization problem through the fitness value; perform non - dominated sorting of the individuals according to the determined fitness values to obtain the non - dominated sorting rank of each individual, that is, the result of non - dominated sorting; calculate the vertical distance from the fitness value to the reference point, and assign the individuals to the nearest reference point according to the distance to obtain the result of reference point assignment.

[0123] S154. Based on the results of non - dominated sorting and the results of reference point assignment, select parental individuals from the parental population into the mating pool through binary tournament, and perform crossover and mutation on the genes of the individual chromosomes in the mating pool to form offspring individuals. The parental population includes the initial population.

[0124] In this step, through binary tournament, randomly select two individuals from the parental population for comparison each time. The basis for comparison is the results of non - dominated sorting and the results of reference point assignment. After multiple comparisons, select a certain number of parental individuals from the parental population into the mating pool; in the mating pool, according to the set crossover probability and mutation probability, perform crossover and mutation on the genes of the individual chromosomes to obtain offspring individuals.

[0125] S155. Combine the parental and offspring individuals and select and retain some individuals through optimization. Continue the iteration based on the retained individuals until the iteration termination condition is reached, and determine the target mix ratio of the dredged sediment geopolymer corresponding to the target fitness function.

[0126] The elitist retention strategy is adopted. After merging the parent generation and the offspring generation, non-dominated sorting is carried out, and individuals with a higher non-dominated rank are preferentially retained. If the number of associated solutions of a certain reference point is insufficient, the nearest individual in its direction is supplemented. Based on the retained individuals, the genetic algorithm is continuously iterated until the iteration termination condition is reached, such as reaching the set number of iterations, stopping the iteration, and determining the key parameters of the dredged sediment geopolymer mix ratio that can achieve the best balance among multiple objectives indicated by the objective fitness function, that is, the Pareto optimal solution. The dredged sediment geopolymer mix ratio corresponding to the key parameters of the dredged sediment geopolymer mix ratio with the best balance of multiple objectives is determined as the target mix ratio of the dredged sediment geopolymer.

[0127] Figure 7 It is a schematic diagram of global optimization using the genetic algorithm according to Embodiment 3 of the present invention. Through the genetic algorithm, with a crossover probability of 0.9, a mutation probability of 0.1, a population size of 50, and a maximum number of iterations of 200, global optimization is carried out with the maximum compressive strength, the lowest material cost, and the lowest carbon emission of the dredged sediment geopolymer as the objectives. After 200 iterations, the target mix ratio of the dredged sediment geopolymer is obtained.

[0128] As Figure 7 shown, with the increase in compressive strength, the material cost and carbon emission of the dredged sediment geopolymer increase accordingly. Among them, the compressive strength of the dredged sediment ranges from 20 to 30 MPa, the material cost ranges from 300 to 600 yuan, and the carbon emission ranges from 200 to 360 kg-CO2 / m 3 . When the compressive strength of the dredged sediment geopolymer reaches the compressive strength target of the non-fired brick, the lowest economic cost is 320 yuan / m 3 , and the carbon emission is 240 kg-CO2 / m 3 , the dosage of the dredged sediment in the dredged sediment geopolymer per unit volume is 747 kg, the fly ash is 523 kg, the granulated blast furnace slag is 224 kg, the sodium silicate solution is 166 kg, the sodium hydroxide is 63 kg, the water is 400 kg, and the water-binder ratio is 0.27.

[0129] The technical solution of the embodiment of the present invention simultaneously optimizes the compressive strength, material cost and carbon emissions of dredged mud geopolymers through the NSGA-III algorithm, solves the problem that traditional single-objective optimization methods cannot balance multi-objective contradictions, provides a series of Pareto optimal solution sets, and clarifies the trade-off relationship between different objectives; through hard constraints (such as material usage restrictions and volume balance equations), it ensures that all Pareto solutions meet actual engineering conditions, avoids the generation of invalid solutions, directly outputs feasible mix ratio schemes, and reduces manual screening and secondary verification costs; embeds the carbon emission objective function into multi-objective optimization, quantifies the carbon emissions of the entire process of raw material production, transportation and geopolymer synthesis based on the entire life cycle, and reduces the carbon emissions of dredged mud geopolymer synthesis after mix ratio optimization; through target standardization and elite retention strategy, it avoids the algorithm from falling into local optimality, and ensures that high-quality solution sets can still be stably output under material parameter fluctuations or noise interference.

[0130] Example 4

[0131] Figure 8 Schematic diagram of a device for optimizing the mix ratio of dredged sediment geopolymers according to a fourth embodiment of the present invention. This embodiment is applicable to the case where the mix ratio of dredged sediment geopolymers is optimized, such as Figure 8 As shown, the specific structure of the device includes:

[0132] The module 81 for constructing a sample set to be processed is used to obtain key parameters of the dredged sediment geopolymer mix ratio and corresponding compressive strength data to construct a sample set to be processed, wherein the key parameters of the dredged sediment geopolymer mix ratio include at least the dredged sediment dosage, the alkali activator concentration, and the alkali activator modulus;

[0133] A nonlinear mapping relationship function determination module 82 is used to construct and train a compressive strength prediction model based on the sample set to be processed, and determine a nonlinear mapping relationship function between key parameters of the dredged sediment geopolymer mix ratio and compressive strength data;

[0134] A target fitness function construction module 83 is used to construct a target fitness function according to the nonlinear mapping relationship function, the production material cost of dredged mud geopolymer and the production carbon emission;

[0135] The constraint condition construction module 84 is used to construct the constraint condition according to the key parameter range of the dredged sediment geopolymer mix ratio, the production material dosage range, and the volume of dredged sediment geopolymer per cubic meter;

[0136] The multi-objective optimization module 85 is used to perform multi-objective optimization of key parameters of the dredged sediment geopolymer mix ratio through a genetic algorithm based on the target fitness function and the constraints, and determine the target mix ratio of the dredged sediment geopolymer.

[0137] The dredged sediment geopolymer mix proportion optimization device provided in this embodiment obtains the key parameters of the dredged sediment geopolymer mix proportion and the corresponding compressive strength data through the to-be-processed sample set construction module, and constructs the to-be-processed sample set. The key parameters of the dredged sediment geopolymer mix proportion at least include the dredged sediment content, the concentration of the alkali activator, and the modulus of the alkali activator. The non-linear mapping relationship function determination module constructs and trains a compressive strength prediction model based on the to-be-processed sample set, and determines the non-linear mapping relationship function between the key parameters of the dredged sediment geopolymer mix proportion and the compressive strength data. The target fitness function construction module constructs a target fitness function according to the non-linear mapping relationship function, the production material cost of the dredged sediment geopolymer, and the production carbon emission. The constraint condition construction module constructs constraint conditions according to the range of the key parameters of the dredged sediment geopolymer mix proportion, the range of the production material usage, and the volume of the dredged sediment geopolymer per cubic meter. The multi-objective optimization module performs multi-objective optimization on the key parameters of the dredged sediment geopolymer mix proportion through the genetic algorithm based on the target fitness function and the constraint conditions, and determines the target mix proportion of the dredged sediment geopolymer. This solution breaks through the bottleneck of "low accuracy, long time consumption, and multi-objective imbalance" in the traditional technology through the high-precision prediction of the compressive strength prediction model and the multi-objective optimization of the dredged sediment geopolymer mix proportion in multiple aspects such as compressive strength, production cost, and carbon emission, and provides effective support for the large-scale resource utilization of dredged sediment.

[0138] Further, the to-be-processed sample set includes a training sample set and a test sample set. The non-linear mapping relationship function determination module 82 is specifically used for:

[0139] Construct a compressive strength prediction model through a backpropagation neural network;

[0140] Use the key parameters of the dredged sediment geopolymer mix proportion of each training sample in the training sample set as input parameters, and use the corresponding compressive strength data of the input parameters as output parameters to train the compressive strength prediction model and determine the model parameters;

[0141] Verify the prediction results of the trained compressive strength prediction model through the test sample set in combination with the model parameters;

[0142] In the case where the prediction results meet the set conditions, output the non-linear mapping relationship function between the key parameters of the dredged sediment geopolymer mix proportion and the compressive strength data through the trained compressive strength prediction model.

[0143] Further, the prediction results of the trained compressive strength prediction model are verified by at least the following parameters: the root mean square error, the mean percentage error, and the goodness of fit corresponding to each test sample in the test sample set.

[0144] Further, the number of nodes in the input layer of the compressive strength prediction model is 3; the model parameters are determined by grid search using K-fold cross-validation, where K includes 10.

[0145] Further, the target fitness function construction module 83 is specifically configured to:

[0146] Construct the objective function corresponding to the non-linear mapping relationship function, indicating to find a set of key parameters of the dredged sediment geopolymer mix ratio such that the corresponding compressive strength data is maximized;

[0147] Construct the objective function corresponding to the production material cost of the dredged sediment geopolymer, indicating to find a set of usage amounts of the production materials of the dredged sediment geopolymer such that the corresponding production material cost of the dredged sediment geopolymer is minimized, and the usage amounts of the production materials of the dredged sediment geopolymer are determined based on the key parameters of the dredged sediment geopolymer mix ratio;

[0148] Construct the objective function corresponding to the production carbon emissions, indicating to find a set of usage amounts of the production materials of the dredged sediment geopolymer such that the corresponding production carbon emissions are minimized;

[0149] Construct a target fitness function according to the objective functions corresponding to the non-linear mapping relationship function, the production material cost of the dredged sediment geopolymer, and the production carbon emissions respectively.

[0150] Further, the constraint conditions include value constraints, usage constraints, and volume constraints. The constraint condition construction module 84 is specifically configured to:

[0151] Construct the value constraints, which indicate that each parameter included in the key parameters of the dredged sediment geopolymer mix ratio satisfies its corresponding value range;

[0152] Construct the usage constraints, which indicate that the usage amounts of the dredged sediment, fly ash, granulated blast furnace slag, sodium silicate solution, sodium hydroxide, and water included in the production materials of the dredged sediment geopolymer satisfy their corresponding first usage ranges, and the ratio of the water usage amount to the sum of the usage amounts of the dredged sediment, fly ash, and granulated blast furnace slag satisfies the second usage range;

[0153] Construct the volume constraints, which indicate that the volume of the dredged sediment geopolymer per cubic meter is 1, and the volume of the dredged sediment geopolymer is the sum of the values obtained by dividing the usage amounts of each material included in the production materials of the dredged sediment geopolymer by their material densities.

[0154] Further, the multi-objective optimization module 85 is specifically configured to:

[0155] Construct a genetic algorithm according to the target fitness function and the constraint conditions;

[0156] Take the key parameters of the dredged sediment geopolymer mix proportion as the decision variables of the genetic algorithm, construct a search space, generate an initial population with a set population size, form individual chromosomes with the key parameters of the dredged sediment geopolymer mix proportion, and form the genes of the individual chromosomes with the parameter variables of the key parameters of the dredged sediment geopolymer mix proportion. Initialize the individuals and generate structured reference points.

[0157] Determine the fitness value of each individual in the initial population under the target fitness function, perform non-dominated sorting of the individuals according to the determined fitness values, and assign the individuals to the nearest reference point based on the distance from the determined fitness values to the reference points.

[0158] Based on the results of non-dominated sorting and the results of reference point assignment, select parent individuals from the parent population into the mating pool through binary tournament, and perform crossover and mutation on the genes of the individual chromosomes in the mating pool to form offspring individuals. The parent population includes the initial population.

[0159] Merge the parent and offspring and optimize and retain some individuals from them, and continue to iterate based on the retained individuals until the iteration termination condition is reached, and determine the target mix proportion of the dredged sediment geopolymer corresponding to the target fitness function.

[0160] The device for optimizing the mix proportion of the dredged sediment geopolymer provided by the embodiments of the present invention can execute the method for optimizing the mix proportion of the dredged sediment geopolymer provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0161] Embodiment Five

[0162] Figure 9 It is a schematic structural diagram of an electronic device for implementing the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described herein and / or claimed.

[0163] Such as Figure 9As shown, the electronic device 10 includes at least one processor 11 and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0164] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0165] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the dredged sediment geopolymer mix ratio optimization method.

[0166] In some embodiments, the dredged sediment geopolymer mix ratio optimization method can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the dredged sediment geopolymer mix ratio optimization method described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the dredged sediment geopolymer mix ratio optimization method by any other appropriate means (e.g., by means of firmware).

[0167] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which may be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0168] The computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0169] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0170] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0171] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected with each other by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0172] The computing system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0173] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and this is not limited herein.

[0174] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. An optimization method for the mix proportion of dredged sediment geopolymers, characterized in that, Including: Obtain the key parameters of the dredged sediment geopolymer mix proportion and the corresponding compressive strength data, and construct a sample set to be processed. The key parameters of the dredged sediment geopolymer mix proportion include at least the dredged sediment content, the concentration of the alkali activator, and the modulus of the alkali activator; Based on the sample set to be processed, construct and train a compressive strength prediction model to determine the non-linear mapping relationship function between the key parameters of the dredged sediment geopolymer mix proportion and the compressive strength data; Construct an objective fitness function according to the non-linear mapping relationship function, the production material cost of the dredged sediment geopolymer, and the production carbon emissions; Construct constraint conditions according to the range of the key parameters of the dredged sediment geopolymer mix proportion, the range of the production material dosage, and the volume of the dredged sediment geopolymer per cubic meter; Based on the objective fitness function and the constraint conditions, perform multi-objective optimization of the key parameters of the dredged sediment geopolymer mix proportion through a genetic algorithm to determine the target mix proportion of the dredged sediment geopolymer.

2. The method according to claim 1, wherein The sample set to be processed includes a training sample set and a test sample set. Constructing and training a compressive strength prediction model based on the sample set to be processed to determine the non-linear mapping relationship function between the key parameters of the dredged sediment geopolymer mix proportion and the compressive strength data includes: Construct a compressive strength prediction model through a backpropagation neural network; Use the key parameters of the dredged sediment geopolymer mix proportion of each training sample in the training sample set as input parameters, and use the corresponding compressive strength data of the input parameters as output parameters to train the compressive strength prediction model to determine the model parameters; Verify the prediction results of the trained compressive strength prediction model through the test sample set combined with the model parameters; When the prediction results meet the set conditions, output the non-linear mapping relationship function between the key parameters of the dredged sediment geopolymer mix proportion and the compressive strength data through the trained compressive strength prediction model.

3. The method according to claim 2, characterized in that, The prediction results of the trained compressive strength prediction model are verified by at least the following parameters: the root mean square error, the mean percentage error, and the goodness of fit corresponding to each test sample in the test sample set.

4. The method according to claim 2, wherein The number of nodes in the input layer of the compressive strength prediction model is 3; the model parameters are determined by grid search using K-fold cross-validation, and K includes 10.

5. The method according to claim 1, wherein Constructing an objective fitness function according to the non-linear mapping relationship function, the production material cost of the dredged sediment geopolymer, and the production carbon emissions includes: Construct the objective function corresponding to the non-linear mapping relationship function, indicating to find a set of key parameters of the dredged sediment geopolymer mix proportion such that the corresponding compressive strength data is the largest; Construct the objective function corresponding to the production material cost of the dredged sediment geopolymer, indicating to find a set of production material dosages of the dredged sediment geopolymer such that the corresponding production material cost of the dredged sediment geopolymer is the smallest, and the production material dosage of the dredged sediment geopolymer is determined based on the key parameters of the dredged sediment geopolymer mix proportion; Construct the objective function corresponding to the production carbon emissions, indicating to find a set of production material dosages of the dredged sediment geopolymer such that the corresponding production carbon emissions are the smallest; Construct an objective fitness function according to the non - linear mapping relationship function, the production material cost of dredged sediment geopolymers, and the objective functions corresponding to the production carbon emissions respectively.

6. The method according to claim 1, wherein The constraint conditions include value constraints, dosage constraints, and volume constraints. The constraint conditions are constructed according to the key parameter ranges of the mix proportion of dredged sediment geopolymers, the production material dosage ranges, and the volume of dredged sediment geopolymers per cubic meter, including: Construct the value constraints, where the value constraints indicate that each parameter included in the key parameters of the mix proportion of dredged sediment geopolymers satisfies its corresponding value range. Construct the dosage constraints, where the dosage constraints indicate that the dosages of dredged sediment, fly ash, granulated blast furnace slag, sodium silicate solution, sodium hydroxide, and water included in the production materials of dredged sediment geopolymers satisfy their corresponding first dosage ranges, and the ratio of the water dosage to the sum of the dosages of dredged sediment, fly ash, and granulated blast furnace slag satisfies the second dosage range. Construct the volume constraints, where the volume constraints indicate that the volume of dredged sediment geopolymers per cubic meter is 1, and the volume of dredged sediment geopolymers is the sum of the ratios of the dosages of each material included in the production materials of dredged sediment geopolymers to their material densities.

7. The method according to claim 1, wherein Based on the objective fitness function and the constraint conditions, perform multi - objective optimization of the key parameters of the mix proportion of dredged sediment geopolymers through a genetic algorithm to determine the target mix proportion of dredged sediment geopolymers, including: Construct a genetic algorithm according to the objective fitness function and the constraint conditions. Use the key parameters of the mix proportion of dredged sediment geopolymers as the decision variables of the genetic algorithm, construct a search space, generate an initial population with a set population size, form individual chromosomes with the key parameters of the mix proportion of dredged sediment geopolymers, form genes of individual chromosomes with the parameter variables of the key parameters of the mix proportion of dredged sediment geopolymers, initialize the individuals, and generate a structured reference point. Determine the fitness values of each individual in the initial population under the objective fitness function, perform non - dominated sorting of the individuals according to the determined fitness values, and assign the individuals to the nearest reference point based on the distance from the determined fitness values to the reference point. Based on the results of non - dominated sorting and reference point assignment, select parent individuals from the parent population into the mating pool through binary tournament, and perform crossover and mutation on the genes of the individual chromosomes in the mating pool to form offspring individuals. The parent population includes the initial population. Merge the parent and offspring and optimize and retain some individuals from them, and continue to iterate based on the retained individuals until the iteration termination condition is reached, and determine the target mix proportion of dredged sediment geopolymers corresponding to the objective fitness function.

8. An optimization device for the mix proportion of dredged bottom mud geopolymers, characterized in that, Including: A to - be - processed sample set construction module for obtaining the key parameters of the mix proportion of dredged sediment geopolymers and the corresponding compressive strength data, and constructing a to - be - processed sample set. The key parameters of the mix proportion of dredged sediment geopolymers at least include the dredged sediment content, the concentration of the alkali activator, and the modulus of the alkali activator. A non - linear mapping relationship function determination module for constructing and training a compressive strength prediction model based on the to - be - processed sample set, and determining the non - linear mapping relationship function between the key parameters of the mix proportion of dredged sediment geopolymers and the compressive strength data. A target fitness function construction module for constructing a target fitness function according to the non-linear mapping relationship function, the production cost of the dredged sediment geopolymer production materials, and the production carbon emissions; A constraint condition construction module for constructing constraint conditions according to the key parameter range of the dredged sediment geopolymer mix ratio, the production material dosage range, and the volume of the dredged sediment geopolymer per cubic meter; A multi-objective optimization module for performing multi-objective optimization of the key parameters of the dredged sediment geopolymer mix ratio through a genetic algorithm based on the target fitness function and the constraint conditions, and determining the target mix ratio of the dredged sediment geopolymer.

9. An electronic device, characterized in that, Comprising: At least one processor; And A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method according to any one of claims 1-7.

Images