Reclamation filling material partition allocation method and device, equipment and storage medium

Abstract

The application provides a reclamation engineering filler partition allocation method, device, equipment and storage medium, which obtains partition engineering data and available filler data of a target reclamation area; constructs a filler allocation matrix according to the data; establishes a multi-objective optimization model containing a target function and a constraint condition; substitutes the filler allocation matrix into the model as a decision variable, iteratively solves by using a multi-objective optimization algorithm, searches for a decision variable value that makes the target function reach a Pareto optimal value under the premise of meeting the constraint condition, and outputs a set of Pareto optimal solution sets, each solution corresponding to a filler partition allocation scheme. The application realizes matrix modeling and multi-objective intelligent optimization, simultaneously meets engineering constraints such as bearing capacity, settlement, elevation, supply amount and minimum thickness, cooperatively optimizes three mutually conflicting targets of inactivity building material utilization rate, engineering cost and construction period, automatically generates multiple optimal comparison schemes, and provides scientific support for reclamation engineering early-stage decision making.

Description

Technical Field

[0001] This invention relates to the field of civil engineering technology, and in particular to a method, apparatus, equipment and storage medium for the zoning and allocation of fill material in land reclamation projects. Background Technology

[0002] Land reclamation is an important means of alleviating the scarcity of land resources in coastal areas. In reclamation projects, the land area is typically divided into several sub-zones based on subsequent use or construction organization needs. The geological conditions, foundation treatment requirements, and intended uses of different sub-zones may vary. Furthermore, the types of fill materials available at the project site are diverse, including sea sand, manufactured sand, inert building materials, and dredged soil. How to rationally configure the type and quantity of fill materials according to the actual conditions of different sub-zones is a challenging issue in reclamation project design.

[0003] Existing methods for preparing filler materials primarily rely on the experience of technical personnel, with each sub-region often determining its filler material scheme independently. This leads to the following problems: First, each sub-region focuses on its own local optimum, lacking global coordination, which easily results in uneven distribution of high-quality filler materials, forcing some sub-regions to adopt high-cost treatment methods. Second, the resource utilization rate of inert building materials (such as construction and demolition waste) is low, making it difficult to achieve large-scale solid waste disposal. Third, there is an inherent contradiction between project cost and construction period, and experience-based solutions struggle to balance multiple conflicting objectives. Furthermore, traditional methods lack systematic modeling of the complex interrelationships between multiple types of filler materials and multiple sub-regions, failing to automatically generate multiple alternative schemes that consider economic efficiency, construction period, and environmental protection requirements, resulting in insufficient decision support capabilities.

[0004] In summary, the shortcomings of the existing technology urgently need to be addressed. Summary of the Invention

[0005] This invention provides a method, apparatus, equipment, and storage medium for the zoned allocation of fill material in land reclamation projects, which addresses the deficiencies in existing technologies and enhances the scientific rigor and flexibility of early-stage decision-making in land reclamation projects.

[0006] This invention provides a method for the zoned allocation of fill material in land reclamation projects, comprising: According to the present invention, a method for zoning and allocating fill material for reclamation projects is provided. The zoning engineering data includes the area, current elevation, design elevation, geological conditions, bearing capacity requirements, and settlement requirements of each sub-zone. The available fill material data includes fill material type, maximum supply quantity of each type of fill material, engineering characteristics, and unit price.

[0007] According to the present invention, a method for zoning and allocating fill material in land reclamation projects includes an objective function comprising three sub-objectives: maximizing the utilization rate of inert building materials, minimizing project cost, and minimizing construction period.

[0008] According to the present invention, a method for zoning and allocating fill material in land reclamation projects includes the following constraints: foundation bearing capacity constraint, post-construction settlement constraint, final elevation constraint, total fill material supply constraint, and minimum fill material laying thickness constraint.

[0009] According to a method for zoning and allocating fill material in a land reclamation project provided by the present invention, the step of substituting the fill material allocation scheme matrix as a decision variable into the multi-objective optimization model and iteratively solving it using a multi-objective optimization algorithm specifically includes: An initial particle swarm is generated based on a hierarchical constraint screening strategy; Assign an initial velocity to each particle; The velocity and position of the particles are iteratively updated using velocity update formulas and position update formulas. The hierarchical constraint screening strategy includes: Coarse screening of randomly generated particles is performed based on constraints of total filler supply and minimum layup thickness. Based on bearing capacity constraints, settlement constraints, and elevation constraints, a fine screening process is conducted to obtain candidate particles that meet all constraints. A portion of the candidate particles are selected to form the initial particle swarm; Unselected candidate particles serve as a velocity reference particle pool.

[0010] According to the present invention, a method for zoning and distributing filler material in land reclamation projects, the step of assigning an initial velocity to each particle specifically includes: A unique reference particle is selected from the velocity reference particle library for each particle in the initial particle swarm. The initial particle's velocity is initialized to the difference between the position of the reference particle and the particle's own position.

[0011] According to the present invention, a method for zoning and distributing filler material in land reclamation projects involves iteratively updating the particle velocity using a velocity update formula, specifically including: Calculate the crowding density of each particle in the particle swarm; For particles located in dense regions, a relatively large inertial weight and a first acceleration constant are used; For particles located in sparse regions, a relatively small inertial weight and a second acceleration constant are used, and a relatively large third acceleration constant is used. The first and second acceleration constants are related to the global optimal leader, and the third acceleration constant is related to the individual's historical optimal position.

[0012] The present invention also provides a zoning and allocation device for fill material in land reclamation projects, comprising: The data acquisition module is used to acquire zoning engineering data and available fill material data for the target reclamation area; The matrix construction module is used to construct a filler allocation matrix based on the partitioned engineering data and the available filler data; The model building module is used to build a multi-objective optimization model, which includes an objective function and constraints. The model solving module is used to substitute the filler allocation scheme matrix as decision variables into the multi-objective optimization model, and perform iterative solving using a multi-objective optimization algorithm. Under the premise of satisfying the constraints, it searches for the decision variable values ​​that make the objective function Pareto optimal, and outputs a set of Pareto optimal solutions, with each solution corresponding to a filler partition allocation scheme.

[0013] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for zoning and allocating filler material for reclamation projects as described above.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for zoning and allocating filler material for reclamation projects as described above.

[0015] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the method for zoning and allocating filler material for reclamation projects as described above.

[0016] This invention provides a method, apparatus, equipment, and storage medium for the zoning and allocation of fill materials in land reclamation projects. By constructing a fill material allocation matrix, it transforms the complex allocation problem of multiple sub-regions and multiple types of fill materials in land reclamation projects into a structured expression of decision variables, thus realizing mathematical modeling of fill material configuration schemes. Based on this, a multi-objective optimization model containing objective functions and constraints is established. The fill material allocation matrix is ​​substituted into the model as a decision variable, and a multi-objective optimization algorithm is used to iteratively solve for the Pareto optimal solution set. This ensures that each scheme output is an "optimal boundary solution" that, under the premise of satisfying hard engineering constraints such as bearing capacity, settlement, elevation, supply quantity, and minimum thickness, cannot be simultaneously dominated by other schemes on all objectives. This mechanism fundamentally overcomes the defects of traditional methods that rely on experience and independent decision-making in each sub-region, leading to local optima and global imbalance. It achieves synergistic optimization of three conflicting objectives: utilization rate of inertial building materials, project cost, and construction period. Users can flexibly choose differentiated solutions from the output Pareto solution set based on their actual engineering preferences, focusing on solid waste disposal, economic efficiency, or the shortest construction period. This significantly improves the scientific nature and flexibility of early-stage decision-making in land reclamation projects and fills the technological gap in automated global optimization and allocation in this field. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the method for zoning and allocating fill material in land reclamation projects provided by the present invention. Figure 2 This is a schematic diagram of the structure of the reclamation engineering fill material zoning and distribution device provided by the present invention; Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0020] To address the problems in existing technologies, this invention proposes a method for the zoning and allocation of fill materials in land reclamation projects, aiming to improve the scientific rigor and flexibility of early-stage decision-making in these projects. The method for zoning and allocating fill materials in land reclamation projects is described below, as follows: Figure 1 As shown, including but not limited to the following steps: Step 110: Obtain the zoning engineering data and available fill material data for the target reclamation area.

[0021] In step 110, the land formation zoning design information is first obtained from the design documents of the reclamation project. Assuming the reclamation project is divided into m sub-zones, each sub-zone is coded, and the zoning project data such as area, current elevation, design elevation, geological conditions (including stratum type, thickness of each layer and mechanical parameters), bearing capacity requirements and allowable post-construction settlement values ​​are obtained for each sub-zone.

[0022] Simultaneously, market research and indoor geotechnical tests were conducted to obtain data on available fill materials at the project site. Assuming there are n types of fill materials, each type is coded, and the maximum supply quantity, engineering characteristics (such as density, compression modulus, cohesion, internal friction angle, etc.), and comprehensive unit price of each type are obtained. The resource utilization of inert building materials (such as construction and demolition waste) is one of the key objectives of this invention.

[0023] Step 120: Construct a filler allocation matrix based on the partitioned engineering data and the available filler data.

[0024] In step 120, each sub-region is treated as a row of a matrix, and each type of packing material is treated as a column, constructing an m-row, n-column packing allocation matrix X. Each element q_{ij} in the matrix represents the volume of the j-th type of packing material used in the i-th sub-region. Each row of this matrix represents the packing configuration scheme of a sub-region, and each column represents the distribution of a type of packing material across the sub-regions. This matrix serves as the decision variable in the subsequent optimization process, fully describing the global packing allocation scheme.

[0025] Step 130: Establish a multi-objective optimization model, which includes an objective function and constraints.

[0026] In step 130, the objective function includes three conflicting sub-objectives: maximizing the utilization rate of inert building materials, minimizing project cost, and minimizing construction period. Project cost includes not only the direct cost of backfilling and land reclamation but also the cost of subsequent foundation treatment, which is closely related to the type and thickness of the backfill material. The construction period depends on the maximum construction period of each sub-zone, which includes the construction period for the original foundation treatment, the backfilling period, and the backfill treatment period.

[0027] The constraints include five categories: foundation bearing capacity constraints, requiring that the bearing capacity of each sub-area after treatment is not lower than the design value; post-construction settlement constraints, requiring that the settlement value does not exceed the allowable value; final elevation constraints, requiring that the ground elevation after treatment is not lower than the design elevation and the difference is within the allowable range; total supply constraints of fill materials, requiring that the total usage of various fill materials does not exceed the maximum market supply; and minimum laying thickness constraints of fill materials, requiring that the thickness of non-dredged soil fill materials be zero or at least 1.0m, and the thickness of dredged soil fill materials be zero or at least 3.0m, in order to avoid difficulties in construction control.

[0028] Step 140: Substitute the packing allocation scheme matrix as a decision variable into the multi-objective optimization model, and use a multi-objective optimization algorithm to iteratively solve the problem. Under the premise of satisfying the constraints, search for the decision variable values ​​that make the objective function Pareto optimal, and output a set of Pareto optimal solutions. Each solution corresponds to a packing partition allocation scheme.

[0029] In step 140, a multi-objective particle swarm optimization algorithm is used for solving the problem. The filler allocation matrix X constructed in step 120 is used as the position vector of the particles, with each particle representing a feasible filler allocation scheme. The algorithm first randomly generates an initial particle swarm under the premise of satisfying the constraints and assigns an initial velocity to each particle. Then, the velocity and position of the particles are continuously updated iteratively: in each iteration, the three objective function values ​​of each particle are calculated, the individual historical best position of each particle is updated according to the non-dominant relationship, and a globally optimal guide is selected from the external archive to guide the particles to move towards a better region. During the iteration process, only particles that satisfy all constraints are retained.

[0030] After a predetermined number of iterations, the algorithm outputs all non-dominated solutions stored in the external archive, i.e., the Pareto optimal solution set. Each solution in this set corresponds to a packing zoning and allocation scheme. These schemes each have their own advantages and disadvantages in terms of inert material utilization, project cost, and construction period, and they are independent of each other. Designers can select the most suitable scheme as the final implementation scheme based on the actual needs of the project (such as prioritizing environmental protection, economy, or schedule).

[0031] As a further optional embodiment, the zoning engineering data includes the area, current elevation, design elevation, geological conditions, bearing capacity requirements, and settlement requirements of each sub-zone; the available filler data includes filler type, maximum supply quantity of each type of filler, engineering characteristics, and unit price.

[0032] In this embodiment, the zoning engineering data includes the area, current elevation, design elevation, geological conditions, bearing capacity requirements, and settlement requirements of each sub-zone. The area and elevation are used to calculate the fill volume; geological conditions (including stratum type, layer thickness, and mechanical parameters) are used for foundation bearing capacity and settlement analysis; and bearing capacity and settlement requirements are the core basis for the constraints. The available fill material data includes fill material type, maximum supply quantity for each type of fill material, engineering characteristics, and unit price. Fill material types include sea sand, manufactured sand, inert building materials, dredged soil, etc.; the maximum supply quantity is used to constrain the upper limit of each fill material's usage; engineering characteristics (such as unit weight, compression modulus, cohesion, internal friction angle, etc.) are used for bearing capacity and settlement calculations; and the unit price is used to calculate the engineering cost objective function. Obtaining the above complete dataset provides the necessary basic parameters for subsequent matrix construction and multi-objective optimization.

[0033] According to the present invention, a method for zoning and allocating fill material in land reclamation projects includes an objective function comprising three sub-objectives: maximizing the utilization rate of inert building materials, minimizing project cost, and minimizing construction period.

[0034] In this embodiment, the objective function includes three sub-objectives: maximizing the utilization rate of inert building materials, minimizing project cost, and minimizing construction period.

[0035] In this embodiment, the three sub-targets are defined as follows: Maximize the utilization rate of inert building materials: Inert building materials mainly refer to construction and demolition waste, which can be used as land reclamation filler to achieve resource utilization. This sub-objective aims to use as many inert building materials as possible, and its utilization rate is defined as the proportion of the total amount of this type of filler used in all sub-areas to its total market supply. The higher the value, the more fully the solid waste is disposed of.

[0036] Minimize project cost: Project cost includes not only the procurement, transportation, and backfilling costs of the fill material, but also the cost of foundation treatment after backfilling. Different types of fill materials are suitable for different foundation treatment methods (such as vibratory compaction, dynamic compaction, vibro-compaction, drainage consolidation, etc.), and their unit prices also differ. Therefore, the project cost is obtained by summing the costs of original foundation treatment for each sub-area, the backfilling costs of various fill materials, and the foundation treatment costs of various fill materials.

[0037] Minimize construction period: Since each sub-area can be constructed independently, the overall construction period depends on the sub-area with the longest construction cycle. The construction cycle of each sub-area consists of three parts: the treatment period for the original soft soil foundation, the backfilling period for various types of fill materials, and the treatment period for various types of fill materials. Among them, the backfilling period and the treatment period are related to the amount of fill material used and the efficiency of construction equipment.

[0038] There are inherent conflicts among the three sub-objectives mentioned above: for example, improving the utilization rate of inert materials may require increasing transportation distance or handling difficulty, thereby increasing costs and construction period; using high-efficiency and high-quality fillers to shorten the construction period may further increase costs. This invention uses a multi-objective optimization model to simultaneously optimize these three sub-objectives under constraints, ultimately outputting a set of Pareto optimal solutions for decision-makers to choose from.

[0039] According to the present invention, a method for zoning and allocating fill material in land reclamation projects includes the following constraints: foundation bearing capacity constraint, post-construction settlement constraint, final elevation constraint, total fill material supply constraint, and minimum fill material laying thickness constraint.

[0040] In this embodiment, the specific meanings of each constraint are as follows: Foundation bearing capacity constraint: It is required that after the backfilling and foundation treatment of each sub-zone are completed, the calculated foundation bearing capacity value shall not be lower than the design bearing capacity requirement of that sub-zone. The bearing capacity calculation is based on the mechanical parameters of the fill material and undisturbed soil (such as unit weight, cohesion, internal friction angle, etc.) and is carried out using standard methods.

[0041] Post-construction settlement constraint: This requires that the post-construction settlement value of each sub-zone after project completion does not exceed the design allowable value for that sub-zone. Settlement calculation is based on the layered summation method, considering the compressibility characteristics of the undisturbed soil layer and backfill material.

[0042] Final elevation constraint: The ground elevation of each sub-zone after backfilling and foundation treatment must not be lower than the design elevation, and the difference between the two elevations must be controlled within a preset allowable range (e.g., not exceeding 1.0 meter). This constraint ensures that the elevation of the land area after formation meets the usage requirements, while avoiding waste caused by excessive filling.

[0043] Total packing supply constraint: This constraint requires that the total amount of all types of packing used in each sub-zone must not exceed its maximum market supply. This constraint reflects the interrelationship between packing allocation in different sub-zones; that is, if the usage of a certain type of packing increases in one sub-zone, the available quantity in other sub-zones will decrease accordingly.

[0044] Minimum fill thickness constraint: Based on construction feasibility, for non-dredged soil fillers such as sea sand, manufactured sand, and inert building materials, the fill thickness in any sub-zone must be either zero (i.e., not used) or at least 1.0 meter; for dredged soil fillers, the fill thickness must be either zero or at least 3.0 meters. This constraint avoids construction control difficulties and uneconomical equipment deployment caused by excessively thin fill layers.

[0045] The above constraints collectively define the feasible region of the packing formulation scheme. Only schemes that satisfy all constraints can be included in the optimization solution process.

[0046] According to a method for zoning and allocating fill material in a land reclamation project provided by the present invention, the step of substituting the fill material allocation scheme matrix as a decision variable into the multi-objective optimization model and iteratively solving it using a multi-objective optimization algorithm specifically includes: An initial particle swarm is generated based on a hierarchical constraint screening strategy; Assign an initial velocity to each particle; The velocity and position of the particles are iteratively updated using velocity update formulas and position update formulas. The hierarchical constraint screening strategy includes: Coarse screening of randomly generated particles is performed based on constraints of total filler supply and minimum layup thickness. Based on bearing capacity constraints, settlement constraints, and elevation constraints, a fine screening process is conducted to obtain candidate particles that meet all constraints. A portion of the candidate particles are selected to form the initial particle swarm; Unselected candidate particles serve as a velocity reference particle pool.

[0047] In this embodiment, firstly, population initialization is performed. For each type of filler, a preliminary allocation sequence in each sub-interval is randomly generated between 0 and its maximum supply, forming candidate particles. Then, a hierarchical constraint screening strategy is adopted: the first level of coarse screening checks whether the candidate particle meets the total filler supply constraint (i.e., the sum of the usage in each sub-interval does not exceed the market supply) and the minimum laying thickness constraint (i.e., the thickness of each type of filler in each sub-interval is 0 or greater than a preset threshold). If it meets the constraints, it proceeds to the second level of fine screening; if it does not meet the constraints, it is regenerated. The second level of fine screening calculates the foundation bearing capacity, post-construction settlement, and final elevation corresponding to the particle to determine whether it meets the bearing capacity constraint, settlement constraint, and elevation constraint. If all constraints are met simultaneously, the particle is included in the candidate particle library. The above process is repeated until the number of particles in the candidate particle library reaches the user-specified scale (e.g., 200).

[0048] Then, half (e.g., 100) of the candidate particle pool are randomly selected as the initial particle swarm, and the remaining half is used as the velocity reference particle pool. Each particle in the initial particle swarm is assigned an initial velocity: a reference particle is selected from the velocity reference particle pool for each particle without repetition, and the initial velocity of that particle is set to the difference between the position of its reference particle and its own position. This method provides particles with non-zero initial velocities, enhancing population diversity in the early stages of iteration.

[0049] Next, the iterative solution process begins. In each iteration, the objective function value (inert material utilization rate, project cost, construction period) is first calculated based on the current particle's position, and the individual historical best position of each particle is updated. Then, a globally optimal leader is selected for each particle from the external archive using the crowding distance roulette wheel method. Afterward, the particle's velocity and position are updated according to the velocity update formula and the position update formula. The updated particle needs to be rechecked to see if it meets all constraints; if not, the coefficients are readjusted and the update is repeated until the constraints are met.

[0050] Finally, add the non-dominated solutions from the current particle swarm to the external archive and delete the dominated solutions. Repeat the above iterative process until the maximum number of iterations is reached or the external archive solution set converges, and output the Pareto optimal solution set.

[0051] According to the present invention, a method for zoning and distributing filler material in land reclamation projects, the step of assigning an initial velocity to each particle specifically includes: A unique reference particle is selected from the velocity reference particle library for each particle in the initial particle swarm. The initial particle's velocity is initialized to the difference between the position of the reference particle and the particle's own position.

[0052] In this embodiment, the specific implementation of velocity initialization is as follows. Assume that N candidate particles are obtained through a hierarchical constraint screening strategy. Half of these (e.g., N / 2) are randomly selected as the initial particle swarm, and the remaining half is used as the velocity reference particle pool. Each particle X_i in the initial particle swarm needs to be assigned an initial velocity v_i.

[0053] Traditional particle swarm optimization (PSO) algorithms typically set the initial velocity to zero. This approach can easily lead to all particles moving slowly in the same direction during the early stages of iteration, resulting in insufficient population diversity and a tendency to get trapped in local optima. To address this issue, this embodiment proposes a reference particle difference method: for each particle X_i in the initial particle swarm, a reference particle Y_i is selected non-repeatingly from the velocity reference particle library (i.e., each reference particle is used only once, forming a one-to-one correspondence). Then, the initial velocity v_i of X_i is set to the difference between Y_i and X_i, i.e., v_i = Y_i - X_i.

[0054] This initialization method has the following advantages: First, the initial velocity is non-zero, so the particles have the ability to move at the beginning of the iteration, which speeds up the convergence speed; Second, since the reference particle itself is a feasible solution that satisfies all constraints, the difference between it and the target particle naturally points to other regions within the feasible region, ensuring that the direction of the initial velocity is reasonable; Third, the one-to-one selection method avoids the repeated use of the same reference particle, ensuring that the motion directions of different particles in the initial particle swarm are different, thereby maintaining the diversity of the population.

[0055] After completing the speed initialization using the above method, you can proceed to the subsequent speed iteration and update steps.

[0056] According to the present invention, a method for zoning and distributing filler material in land reclamation projects involves iteratively updating the particle velocity using a velocity update formula, specifically including: Calculate the crowding density of each particle in the particle swarm; For particles located in dense regions, a relatively large inertial weight and a first acceleration constant are used; For particles located in sparse regions, a relatively small inertial weight and a second acceleration constant are used, and a relatively large third acceleration constant is used. The first and second acceleration constants are related to the global optimal leader, and the third acceleration constant is related to the individual's historical optimal position.

[0057] In this embodiment, the adaptive adjustment strategy of the velocity update formula is implemented as follows. First, in each iteration, the crowding distance of each non-dominated solution in the external archive is calculated and used as a measure of particle crowding. The smaller the crowding, the denser the distribution around the particle, and vice versa.

[0058] For particles with low crowding (i.e., located in dense regions), it indicates that many solutions have already accumulated in the current region, and it is necessary to enhance global exploration capabilities to escape local optima. Therefore, a larger inertia weight w_i is assigned to them (e.g., a value range of 0.8~1.2, with 1.2 for the particle with the lowest crowding), allowing them to inherit more historical velocities and maintain motion inertia; at the same time, a larger second acceleration constant c_{2i} is assigned (related to the global optimal guide, for example, a value of 2.0~2.5), enhancing the global optimal guide's attraction to the particles and prompting them to explore sparse regions.

[0059] For particles with high crowding (i.e., located in sparse regions), it indicates that the exploration of that region is insufficient, and local development capabilities need to be enhanced for finer searching. Therefore, a smaller inertial weight w_i (e.g., 0.4~0.6) and a smaller second acceleration constant c_{2i} (e.g., 0.5~1.0) are assigned to reduce the jump amplitude of global guidance; at the same time, a larger third acceleration constant c_{1i} (related to the individual's historical best position, e.g., 1.5~2.0) is assigned to emphasize the guidance of the particle's own historical best experience, prompting it to search for better solutions more meticulously in the local region.

[0060] As the number of iterations increases, when the distribution of non-dominated solutions in the external archive tends to be balanced (e.g., the change in crowding variance is less than a preset threshold for 20 consecutive generations), the velocity update coefficients of all particles are fixed to uniform values ​​(e.g., w=0.7, c1=c2=1.5) to deepen the local search for the current Pareto front. This adaptive strategy avoids the mechanical nature of traditional fixed-coefficient or linearly decreasing coefficient methods, achieving a better balance between convergence speed and solution set diversity.

[0061] A preferred embodiment of the present invention is as follows: Step 1: Obtain basic data and encode it.

[0062] Obtain land formation zoning information from the reclamation project design documents. Assume there are m sub-zones, sequentially coded as z1, z2, …, z… m For each sub-region, obtain the following parameters: Area A i Current elevation h_pre i Design elevation h_fin i Geological conditions (strata type, thickness, unit weight, compressibility modulus, cohesion, angle of internal friction, etc.), bearing capacity requirements f_a i Post-construction settlement allowable value [S] i ].

[0063] Information on available fill materials was obtained through market research and geotechnical testing. Assume there are n types of fill materials (e.g., sea sand, manufactured sand, inert building materials, dredged soil, etc.), sequentially coded as fill1, fill2, ..., fill... n For each type of filler, obtain: maximum supply quantity V j Engineering properties (density, compressive modulus, cohesion, angle of internal friction, etc.), and the comprehensive unit price (UPF) for backfill land reclamation. j Comprehensive unit price of foundation treatment (UPT) j Backfilling rate VF j Processing rate VT j .

[0064] Step 2: Construct the packing matrix.

[0065] Combine all sub-regions and all packing materials to form an m×n matrix X, where the element q ij Subregion z i Use filler j The volume (m³). This matrix represents a complete packing zoning and allocation scheme.

[0066] Step 3: Establish a multi-objective optimization model.

[0067] The objective function contains three sub-objectives: ① Maximize the utilization rate of inert building materials. Assume the k-th type of filler is an inert building material, and its utilization rate is the proportion of the total amount of filler used in all sub-zones to its supply, i.e., max(∑ i q ik / V k ).

[0068] ② Minimize project cost. Project cost includes three parts: original foundation treatment cost for each sub-area, backfilling and land reclamation cost for each sub-area, and foundation treatment cost for each sub-area's backfill material. That is, min[∑ i (A i ·h_b i ·UPB i ) + ∑ i ∑ j q ij ·(UPF j +UPT j )], where h_b i UPB is the depth for treating the original foundation. i The unit price is for treating the original foundation.

[0069] ③ Minimize the construction period. Each sub-area is constructed independently, and the overall construction period is the maximum value of the construction periods of each sub-area. The construction period of each sub-area includes the period for treating the original foundation, the period for backfilling each fill material, and the period for treating each fill material. That is, min{ maxi [ ∑ j (q ij / VF j + q ij / VT j ) + A i ·h_b i / VB i ]}, where VB i The rate of reinforcement of the original foundation.

[0070] Constraints include five categories: ① Bearing capacity constraint: the foundation bearing capacity p_k after treatment in each sub-zone i ≥ f_a i .

[0071] ② Settlement constraint: Post-construction settlement S_r of each sub-region i ≤ [S i ].

[0072] ③ Elevation constraint: The ground elevation h after processing i ≥ h_fin i , and h i - h_fin i ≤ [Δh] ([Δh] can be taken as 1.0m). Where h i = h_pre i + ∑ j q ij / A i + (S_t i - S_r i ), S_t i This represents the total settlement.

[0073] ④ Total packing quantity constraint: For each type of packing j, ∑ i q ij ≤ V j .

[0074] ⑤ Minimum thickness constraint: For sea sand, manufactured sand, and inert building materials, q ij / A i = 0 or ≥1.0m; for dredged soil, q ij / A i = 0 or ≥3.0m.

[0075] Step 4: Solve iteratively using the multi-objective particle swarm optimization algorithm.

[0076] Use the filler distribution matrix X as the particle position vector. Perform the following sub-steps: (1) Population initialization: A hierarchical constraint screening strategy is adopted. First, particles that meet the total filler volume constraint and minimum thickness constraint are randomly generated. Then, particles that meet the bearing capacity, settlement, and elevation constraints are screened to obtain a candidate particle library (e.g., 200 particles). Half of the candidate particle library is randomly selected as the initial particle population, and the other half is used as the velocity reference particle library.

[0077] (2) Velocity initialization: For each particle X in the initial particle swarm i Select a reference particle Y from the velocity reference particle library without repetition. i Let the initial velocity v i = Y i - X i .

[0078] (3) Establish external archive: Calculate the three objective function values ​​of each particle in the initial particle swarm, perform non-dominated sorting, and store all non-dominated solutions in external archive A.

[0079] (4) Iterative update: For each generation, first calculate the objective function value of each particle and update the individual historical best P_Best[i]; use the crowding distance roulette method to select the global best leader G_Best[i] for each particle from the external archive; then update the velocity and position according to the following formula: v i ' = w i ·v i + c 1i ·R1·(P_Best[i]-X i ) + c 2i ·R2·(G_Best[i]-X i ) X i ' = X i + v i ' Where w i c 1i c 2i Adaptive adjustment is adopted: based on particle crowding, particles in dense regions take a larger w value. i and c 2i In the sparse region, particles take a smaller w. i c 2i and larger c 1i After updating, check if all constraints are met; if not, readjust the coefficients and update again.

[0080] (5) Update external files: Add non-dominated solutions of the current generation to the file and delete dominated solutions.

[0081] (6) Repeat the iteration until the maximum number of iterations is reached or the file converges.

[0082] Step 5: Output the results.

[0083] Output all non-dominated solutions stored in the external archive. Each solution corresponds to a packing partitioning scheme (i.e., a matrix X). These schemes each have advantages in terms of inert material utilization, project cost, and construction period. Designers can choose the final scheme from them according to actual needs.

[0084] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. All modifications and equivalent substitutions made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0085] The following describes the zoning and allocation device for reclamation engineering fill materials provided by the present invention, such as... Figure 2 As shown, the zoning and allocation device for reclamation fill materials described below and the zoning and allocation method for reclamation fill materials described above can be referred to in correspondence.

[0086] A zoning and allocation device for fill material in land reclamation projects, comprising: Data acquisition module 210 is used to acquire zoning engineering data and available fill material data of the target reclamation area; The matrix construction module 220 is used to construct a filler allocation matrix based on the partitioned engineering data and the available filler data; The model building module 230 is used to build a multi-objective optimization model, which includes an objective function and constraints. The model solving module 240 is used to substitute the filler allocation scheme matrix as a decision variable into the multi-objective optimization model, and perform iterative solving using a multi-objective optimization algorithm. Under the premise of satisfying the constraints, it searches for the decision variable values ​​that make the objective function Pareto optimal, and outputs a set of Pareto optimal solutions, with each solution corresponding to a filler partition allocation scheme.

[0087] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3 As shown, the electronic device may include: a processor 310, a communications interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communications interface 320, and the memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute a method for the zoning and allocation of fill material in a reclamation project, which includes: Obtain zoning engineering data and available fill material data for the target reclamation area; Based on the zoning project data and the available filler data, a filler allocation matrix is ​​constructed; A multi-objective optimization model is established, which includes an objective function and constraints. The packing allocation scheme matrix is ​​substituted into the multi-objective optimization model as a decision variable, and a multi-objective optimization algorithm is used for iterative solution. Under the premise of satisfying the constraints, the decision variable values ​​that make the objective function Pareto optimal are searched to output a set of Pareto optimal solutions, with each solution corresponding to a packing partition allocation scheme.

[0088] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0089] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the land reclamation fill material zoning and allocation method provided by the above methods, the method including: Obtain zoning engineering data and available fill material data for the target reclamation area; Based on the zoning project data and the available filler data, a filler allocation matrix is ​​constructed; A multi-objective optimization model is established, which includes an objective function and constraints. The packing allocation scheme matrix is ​​substituted into the multi-objective optimization model as a decision variable, and a multi-objective optimization algorithm is used for iterative solution. Under the premise of satisfying the constraints, the decision variable values ​​that make the objective function Pareto optimal are searched to output a set of Pareto optimal solutions, with each solution corresponding to a packing partition allocation scheme.

[0090] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for zoning and allocating fill material for reclamation projects provided by the methods described above, the method comprising: Obtain zoning engineering data and available fill material data for the target reclamation area; Based on the zoning project data and the available filler data, a filler allocation matrix is ​​constructed; A multi-objective optimization model is established, which includes an objective function and constraints. The packing allocation scheme matrix is ​​substituted into the multi-objective optimization model as a decision variable, and a multi-objective optimization algorithm is used for iterative solution. Under the premise of satisfying the constraints, the decision variable values ​​that make the objective function Pareto optimal are searched to output a set of Pareto optimal solutions, with each solution corresponding to a packing partition allocation scheme.

[0091] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. 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 the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0092] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for zoned allocation of fill material in land reclamation projects, characterized in that, include: Obtain zoning engineering data and available fill material data for the target reclamation area; Based on the zoning project data and the available filler data, a filler allocation matrix is ​​constructed; A multi-objective optimization model is established, which includes an objective function and constraints. The packing allocation scheme matrix is ​​substituted into the multi-objective optimization model as a decision variable, and a multi-objective optimization algorithm is used for iterative solution. Under the premise of satisfying the constraints, the decision variable values ​​that make the objective function Pareto optimal are searched to output a set of Pareto optimal solutions, with each solution corresponding to a packing partition allocation scheme.

2. The method for zoned allocation of fill material in land reclamation projects according to claim 1, characterized in that, The zoning engineering data includes the area, current elevation, design elevation, geological conditions, bearing capacity requirements, and settlement requirements of each sub-zone; the available filler data includes filler type, maximum supply quantity of each type of filler, engineering characteristics, and unit price.

3. The method for zoned allocation of fill material in land reclamation projects according to claim 1, characterized in that, The objective function includes three sub-objectives: maximizing the utilization rate of inert building materials, minimizing project cost, and minimizing construction period.

4. The method for zoned allocation of fill material in land reclamation projects according to claim 1, characterized in that, The constraints include: foundation bearing capacity constraints, post-construction settlement constraints, final elevation constraints, total filler supply constraints, and minimum filler laying thickness constraints.

5. The method for zoned allocation of fill material in land reclamation projects according to claim 1, characterized in that, The step of substituting the filler formulation matrix as a decision variable into the multi-objective optimization model and iteratively solving it using a multi-objective optimization algorithm specifically includes: An initial particle swarm is generated based on a hierarchical constraint screening strategy; Assign an initial velocity to each particle; The velocity and position of the particles are iteratively updated using velocity update formulas and position update formulas. The hierarchical constraint screening strategy includes: Coarse screening of randomly generated particles is performed based on constraints of total filler supply and minimum layup thickness. Based on bearing capacity constraints, settlement constraints, and elevation constraints, a fine screening process is conducted to obtain candidate particles that meet all constraints. A portion of the candidate particles are selected to form the initial particle swarm; Unselected candidate particles serve as a velocity reference particle pool.

6. The method for zoned allocation of fill material in land reclamation projects according to claim 1, characterized in that, The step of assigning an initial velocity to each particle specifically includes: A unique reference particle is selected from the velocity reference particle library for each particle in the initial particle swarm. The initial particle's velocity is initialized to the difference between the position of the reference particle and the particle's own position.

7. The method for zoned allocation of fill material in land reclamation projects according to claim 1, characterized in that, The velocity of the particles is iteratively updated using the velocity update formula, specifically including: Calculate the crowding density of each particle in the particle swarm; For particles located in dense regions, a relatively large inertial weight and a first acceleration constant are used; For particles located in sparse regions, a relatively small inertial weight and a second acceleration constant are used, and a relatively large third acceleration constant is used. The first and second acceleration constants are related to the global optimal leader, and the third acceleration constant is related to the individual's historical optimal position.

8. A zoning and distributing device for fill material in land reclamation projects, characterized in that, include: The data acquisition module is used to acquire zoning engineering data and available fill material data for the target reclamation area; The matrix construction module is used to construct a filler allocation matrix based on the partitioned engineering data and the available filler data; The model building module is used to build a multi-objective optimization model, which includes an objective function and constraints. The model solving module is used to substitute the filler allocation scheme matrix as decision variables into the multi-objective optimization model, and perform iterative solving using a multi-objective optimization algorithm. Under the premise of satisfying the constraints, it searches for the decision variable values ​​that make the objective function Pareto optimal, and outputs a set of Pareto optimal solutions, with each solution corresponding to a filler partition allocation scheme.

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 program, it implements the method for zoning and allocating fill material for reclamation projects as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for zoning and allocating fill material for reclamation projects as described in any one of claims 1 to 7.

Images