Earth excavation sequence optimization method and system based on improved genetic algorithm

Abstract

The invention relates to an earthwork excavation sequence optimization method and system based on an improved genetic algorithm, and the method comprises the following steps: obtaining earthwork excavation sequence information which is obtained by carrying out the blocking and numbering of a foundation pit excavation surface, and carrying out the random combination of the blocks; according to the earth excavation sequence information, a foundation pit deformation database considering the excavation sequence is obtained through a batch processing method; and according to the foundation pit deformation database considering the excavation sequence, the corresponding optimal earth excavation sequence under different optimization indexes is obtained through an improved genetic algorithm. Compared with the prior art, accurate optimization of the earth excavation sequence is achieved.

Description

Technical Field

[0001] The present invention relates to the field of foundation pit engineering, and in particular to an optimization method and system for the earthwork excavation sequence based on an improved genetic algorithm. Background Art

[0002] With the continuous deepening of the urbanization process, the building density has been continuously increasing, the urban construction has been gradually improved, and the difficulty of constructing foundation pit engineering in the central urban area has also become greater and greater. On the one hand, the surrounding environment in the central urban area is complex, with overpass bridges, arterial roads, new and old buildings, subway pipelines, etc. crisscrossing. These structures maintain people's daily lives. Once uneven settlement or cracking damage occurs due to foundation pit excavation, affecting the basic functions, it will cause great economic losses and adverse social impacts. On the other hand, accidents such as road cracking, ground subsidence, building cracking, and tunnel cracking in the surrounding environment caused by the failure to pay attention to controlling deformation during foundation pit design and construction are not uncommon. It can be seen that when constructing foundation pit engineering in the central urban area, it is particularly important to take appropriate engineering measures to control foundation pit deformation.

[0003] A commonly used foundation pit deformation control measure is to optimize the earthwork excavation sequence. A reasonable earthwork excavation sequence can give full play to the in-situ bearing capacity of the soil body and optimize the stress of the retaining structure, thereby controlling foundation pit deformation. Compared with other foundation pit control measures, it does not require changing the original foundation pit structure and has the advantages of high efficiency, time saving, and cost saving. The foundation pit deformation has typical "space-time effect", which has been widely proven by engineering practice. The currently commonly used method for determining the earthwork excavation sequence is to select several reasonable excavation sequences based on engineering experience for comparison and optimization. However, on the one hand, this method is highly dependent on engineering experience and is difficult to be widely promoted on a large scale. On the other hand, this method often can only obtain a local optimal solution and hardly can obtain a global optimal solution. Summary of the Invention

[0004] The purpose of the present invention is to overcome the above-mentioned defects existing in the prior art and provide an optimization method and system for the earthwork excavation sequence based on an improved genetic algorithm, which realizes the precise optimization of the earthwork excavation sequence and obtains the optimal earthwork excavation sequence.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] An optimization method for the earthwork excavation sequence based on an improved genetic algorithm includes the following steps:

[0007] Obtain the earthwork excavation sequence information, which is obtained by dividing and numbering the foundation pit excavation surface and randomly combining the divided blocks;

[0008] Obtain a foundation pit deformation database considering the excavation sequence through a batch processing method according to the earthwork excavation sequence information;

[0009] Based on the foundation pit deformation database considering the excavation sequence, the optimal earthwork excavation sequence corresponding to different combinations of optimization indicators is obtained through an improved genetic algorithm.

[0010] Furthermore, the foundation pit deformation database considering the excavation sequence includes the earthwork excavation sequence and the corresponding foundation pit deformation data and retaining wall moment data.

[0011] Furthermore, the specific steps to obtain the optimal earthwork excavation sequence through the improved genetic algorithm include:

[0012] Initialize the parameters of the improved genetic algorithm;

[0013] Convert the earthwork excavation sequence information into chromosome information coding through coding mapping; perform sequential coding to obtain the first-generation population;

[0014] Perform random selection, Davis crossover, segment reversal, and single-point mutation operations on the first-generation population to generate a new population;

[0015] Mix the first-generation population with the new population, calculate the fitness of the newly generated population and the first-generation population, and select the individuals with high fitness by comparing the fitness of the two populations to form the next-generation population;

[0016] Judge whether the next-generation population has reached the maximum number of genetic generations. If satisfied, output the strongest individual in the last generation population as the optimal earthwork excavation sequence.

[0017] Furthermore, the parameters of the improved genetic algorithm include multiple ones among population size, chromosome length, crossover probability, reversal probability, mutation probability, and maximum number of genetic generations.

[0018] Furthermore, the method of sequential coding includes natural coding and one-hot coding.

[0019] Furthermore, the optimization indicators for the foundation pit excavation sequence include the maximum lateral displacement of the left and right retaining walls, the maximum settlement of the left and right ground surfaces, the maximum heave of the foundation pit bottom, and the maximum moment of the left and right retaining walls.

[0020] Furthermore, the optimal earthwork excavation sequence includes the optimal earthwork excavation sequence for single-index optimization and the optimal earthwork excavation sequence for multi-index optimization.

[0021] Furthermore, when the optimal earthwork excavation sequence is the optimal earthwork excavation sequence for single-index optimization, the calculation formula for fitness is:

[0022] fitness = f i (x)

[0023] Wherein, fitness is the fitness, and f i (x) is a single-index calculation function, and x is an optimization index.

[0024] Further, when the optimal earthwork excavation sequence is the optimal earthwork excavation sequence optimized by multiple indexes, the calculation formula of the fitness is:

[0025] fitness = ω1f1(x) + ω2f2(x) + ω3f3(x) +... + ω k f k (x)

[0026] Wherein, fitness is the fitness, f1(x), f2(x), f3(x),..., f k (x) is a single-index calculation function, x is an optimization index, k is the number of optimization indexes, ω is the weight of the optimization index, and ω1 + ω2 + ω3 +... + ω k = 1.

[0027] According to another aspect of the present invention, there is provided an earthwork excavation sequence optimization system based on an improved genetic algorithm, including:

[0028] An earthwork excavation sequence information acquisition module, configured to divide the foundation pit excavation surface into blocks, number the blocks, and obtain earthwork excavation sequence information by randomly combining the blocks;

[0029] A foundation pit deformation database establishment module, configured to obtain a foundation pit deformation database considering the excavation sequence by a batch processing method according to the earthwork excavation sequence information;

[0030] An optimal earthwork excavation sequence acquisition module, configured to obtain the corresponding optimal earthwork excavation sequence under different optimization indexes by an improved genetic algorithm according to the foundation pit deformation database considering the excavation sequence.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] 1. The present invention obtains the earthwork excavation sequence information, obtains a foundation pit deformation database considering the excavation sequence by a batch processing method according to the earthwork excavation sequence information, and obtains the corresponding optimal earthwork excavation sequence under different optimization index combinations by an improved genetic algorithm according to the foundation pit deformation database considering the excavation sequence, improves the accuracy of the algorithm in the optimization of the earthwork excavation sequence of the foundation pit, and realizes the precise optimization of the earthwork excavation sequence.

[0033] 2. The present invention can perform single-index optimization and multi-index optimization according to different optimization indexes. Through single-index optimization, the earthwork excavation sequence can be optimized for a single problem, and through multi-index optimization, a comprehensive solution can be obtained, improving the comprehensiveness of the earthwork excavation sequence optimization. Brief Description of the Drawings

[0034] Figure 1 It is a schematic flow chart of an optimization method for the earthwork excavation sequence based on an improved genetic algorithm proposed by the present invention;

[0035] Figure 2 It is a schematic diagram of the numbering of the foundation pit blocks. Among them, (2a) is a schematic diagram of the two-dimensional earthwork excavation numbering, and (2b) is a schematic diagram of the three-dimensional earthwork excavation numbering;

[0036] Figure 3 It is a schematic flow chart of obtaining the optimal earthwork excavation sequence through the improved genetic algorithm;

[0037] Figure 4 It is a schematic flow chart of the operation of Davis crossover;

[0038] Figure 5 It is a schematic flow chart of the operation of segment reversal;

[0039] Figure 6 It is a schematic flow chart of the operation of single-point mutation;

[0040] Figure 7 It is a schematic diagram of the optimization process of optimizing the left wall displacement, right wall displacement and bottom heave of the foundation pit. Among them, (7a) is a schematic diagram of the fitness varying with the number of generations, and (7b) is a schematic diagram of the population individuals varying with the number of generations;

[0041] Figure 8 It is a schematic diagram of the optimization process of optimizing the left wall displacement, right wall displacement, bottom heave of the foundation pit and the total excavation distance. Among them, (8a) is a schematic diagram of the fitness varying with the number of generations, and (8b) is a schematic diagram of the population individuals varying with the number of generations. Detailed Embodiment

[0042] The present invention will be described in detail below with reference to the drawings and specific embodiments. This embodiment is implemented on the premise of the technical solution of the present invention, and the detailed implementation manners and specific operation processes are given, but the protection scope of the present invention is not limited to the following embodiments.

[0043] Embodiment 1

[0044] This embodiment provides an optimization method for the earthwork excavation sequence based on an improved genetic algorithm, as Figure 1 shown, including the following steps:

[0045] S1. Obtain the earthwork excavation sequence information.

[0046] In this embodiment, the excavation width of the foundation pit is 80m, and the excavation surface is divided into 8 blocks.

[0047] The earthwork excavation sequence information is a set of logical sequences, and coding mapping is required to convert the sequence information into discrete data information in computer language. The processing flow is as follows: If a foundation pit is divided into 8 blocks for excavation, and its excavation sequence is '5, 8, 1, 2, 4, 7, 6, 3', then its chromosome coding rule in the two-dimensional excavation problem is: First, number the divided blocks of the foundation pit accordingly. As shown in Figure 2 below, in the two-dimensional problem, number them from left to right as 1 to 8. As shown in Figure 2 (2a) of, in the three-dimensional problem, number them from left to right and from top to bottom as 1 to 8. As shown in Figure 2 (2b) of, and then arrange the number information together to form an individual. Arrange the excavation sequence. For example, a set of excavation sequences is "5-8-1-2-4-7-6-3" (where '-' represents the connection between genes in the chromosome), which means that the foundation pit starts to be excavated from the block numbered 5, followed by the block numbered 8... until the block numbered 3 is excavated.

[0048] S2. Obtain the foundation pit deformation database considering the excavation sequence through a batch processing method.

[0049] The foundation pit deformation database considering the excavation sequence includes the earthwork excavation sequence and the corresponding foundation pit deformation data and retaining wall bending moment data. Code the sequence {5, 8, 1, 2, 4, 7, 6, 3} containing 8 discrete data obtained according to the excavation sequence information, including natural coding and one-hot coding. When performing natural coding, directly take the number of each excavation block, that is, the value between natural numbers 1 and n as the input value. For example, if the number of the first excavation block is 5, then the first input value is also 5, and so on... The input value of the batch processing algorithm after natural coding is shown as follows: [5 8 1 2 4 7 6 3]

[0051] When performing one-hot coding, use N bit status registers to represent N states. Since the above sequence has 8 blocks, set 8 registers. If the number of the first excavation block is 5, then activate register '5' and inhibit other registers. After coding, it is [0 0 0 0 1 0 0 0], and so on... The input value of the algorithm after one-hot coding is shown as follows:

[0052]

[0053] This conversion process can also be implemented in the form of a permutation matrix (a special square matrix where each row and each column has exactly one element as 1 and other elements are all 0).

[0054] Record the maximum lateral displacement of the foundation pit retaining wall, the maximum settlement of the surface soil, the maximum heave of the foundation pit bottom, and the maximum bending moment of the foundation pit retaining wall. These seven quantities (there is only one data for the maximum heave, and the other six include two data for both the left and right sides) are used as output quantities. Import the randomly generated 1729 excavation sequences as input quantities into the batch algorithm. The algorithm runs automatically and saves the foundation pit response data. An example of the sample database is shown in Table 1. Since the numerical ranges corresponding to the foundation pit deformations are different, for example, the maximum deformation value of the retaining wall is between 40 - 60, while the maximum bending moment of the retaining wall is between 500 - 800, the difference between the two sets of data is relatively large, which easily leads to a slow convergence speed of the algorithm and problems such as gradient explosion or gradient disappearance. Therefore, it is necessary to normalize the output values using the linear normalization formula:

[0055]

[0056] Among them, y represents the output value, min(Y) represents the minimum value in the output values, max(Y) represents the maximum value in the output values, and y′ is the normalized output value.

[0057] Table 1 Sample Database

[0058]

[0059]

[0060] S3. Obtain the corresponding optimal earthwork excavation sequences under different optimization indexes through the improved genetic algorithm based on the foundation pit deformation database considering the excavation sequence.

[0061] The optimal earthwork excavation sequence obtained through the improved genetic algorithm is as Figure 3 shown. The specific steps include:

[0062] Initialize the parameters of the improved genetic algorithm, including multiple parameters such as population size, chromosome length, crossover probability, inversion probability, mutation probability, and maximum number of generations.

[0063] Convert the excavation sequence information into chromosome information encoding through coding mapping; perform sequential encoding to obtain the first-generation population.

[0064] Perform random selection, Davis crossover, segment inversion, and single-point mutation operations on the first-generation population to generate a new population.

[0065] Mix the first-generation population with the new population, calculate the fitness of the newly generated population and the first-generation population, and select the individuals with high fitness by comparing the fitness of the two populations to form the next-generation population.

[0066] Judge whether the next-generation population has reached the maximum number of generations. If it is satisfied, output the strongest individual in the last generation population as the optimal earthwork excavation sequence.

[0067] The operation process of Davis crossover is as Figure 4 shown below:

[0068] 1) Randomly select two positions from the parent generation, and take the sequence between the two positions as the reserved order segment, and copy it into an empty chromosome (select the 4th and 6th positions, and the reserved order segment is 7-2-6);

[0069] 2) Reorder the parent generation starting from the second position of the parent generation (the second position of the parent generation is 6, and the reordered order is 3-8-4-2-1-6-5-7);

[0070] 3) Delete the part of the reordered parent generation order that contains the reserved order segment (the parent generation order after deleting the part that contains the reserved order segment is 3-8-4-1-5);

[0071] 4) Put the order obtained in operation 3 into the chromosome with only the reserved order segment in sequence starting from the second position to generate the offspring chromosome (offspring 1 is 4-1-5-7-2-6-3-8);

[0072] 5) Repeat the above operations for the parent generation;

[0073] The operation process of segment inversion is as Figure 5 shown below: Randomly select two positions in the chromosome (position 2 and position 5), reverse the order information between the two positions (1-5-7-2), and the reversed order information is 2-7-5-1, and insert it into the original chromosome to complete the inversion operation.

[0074] The operation process of single-point mutation is as Figure 6 shown below: Randomly select a certain position on the chromosome (position 6) as the mutation point, and randomly select a position on the chromosome (position 2) as the access point, and swap the order information of the access point and the mutation point to complete the mutation operation.

[0075] The improved genetic algorithm mixes the old population and the population after genetic operations, sorts them according to fitness, and selects the individuals with the top-ranked population fitness to form the new population of the next generation, effectively avoiding the problem of loss of excellent genes existing in the traditional genetic algorithm.

[0076] The mathematical model of the optimal earthwork excavation sequence for multi-index optimization is:

[0077] minf(x) = [f1(x), f2(x), f3(x),..., f k (x)]

[0078]

[0079] where, f1(x), f2(x), f3(x),..., f k (x) is a single-index optimization function, x is the optimization index, k is the number of optimization indices, x is the excavation sequence of foundation pit earthwork, and X is the set of all possible excavation sequences of earthwork.

[0080] The optimization indices for the excavation sequence of the foundation pit include the maximum lateral displacement of the left and right retaining walls, the maximum settlement of the left and right ground surfaces, the maximum heave of the foundation pit bottom, and the maximum bending moment of the left and right retaining walls. The optimal excavation sequence of earthwork includes the optimal excavation sequence of single-index optimization and the optimal excavation sequence of multi-index optimization.

[0081] When the optimal excavation sequence of earthwork is the optimal excavation sequence of multi-index optimization, the calculation formula for fitness is:

[0082] fitness = f i (x)

[0083] where, fitness is the fitness, and f i (x) is a single-index optimization function, and x is the optimization index.

[0084] When the optimal excavation sequence of earthwork is the optimal excavation sequence of multi-index optimization, the calculation formula for fitness is:

[0085] fitness = ω1f1(x) + ω2f2(x) + ω3f3(x) +... + ω k f k (x)

[0086] where, fitness is the fitness, f1(x), f2(x), f3(x),..., f k (x) are single-index optimization functions, k is the number of optimization indices, ω is the weight of the optimization index, and ω1 + ω2 + ω3 +... + ω k = 1.

[0087] Generally, the value ranges of different indices are different. Before optimization, it is necessary to convert them into the same value range first. One commonly used conversion method is mean normalization (dividing each index by its average value).

[0088] If the heave amount of the foundation pit bottom is too large, it is unfavorable for the stability of the foundation pit. If it is necessary to protect the foundation pit bottom while protecting the surrounding environment of the foundation pit, the multi-objective optimization strategy adopted is: the displacement of the left wall the displacement of the right wall and the heave of the pit bottom Its optimization function is:

[0089]

[0090] where, They are the average values of the left wall displacement, the right wall displacement, and the bottom heave of the foundation pit, respectively.

[0091] The initial population size of the improved genetic algorithm is set to 30, the maximum number of generations is set to 100, the crossover probability is set to 0.6, the inversion probability is set to 0.01, and the mutation probability is set to 0.01. The optimal fitness value after optimization is 0.8967, the optimal excavation sequence of the soil is 4-5-3-7-2-6-1-8, the global optimal fitness value is 0.8967, and the optimal plan is 4-5-3-7-2-6-1-8. The fitness after optimization is exactly the same as the plan. Since the maximum heave position of the foundation pit is close to the retaining wall of the foundation pit, the soil in the middle of the foundation pit is excavated first, and then the soil near the retaining wall is excavated synchronously. The optimization process is as Figure 7 shown, and the variation of the fitness with the number of generations is as Figure 7 shown in (7a), and the variation of the population individuals with the number of generations is as Figure 7 shown in (7b). The comparison between the optimized soil excavation plan and other plans is shown in Table 2.

[0092] Table 2 Comparison between the optimized soil excavation plan and other plans

[0093]

[0094] It can be seen from Table 2 that the optimized soil excavation plan has been greatly improved compared with the poor global excavation plan. The retaining wall displacement can be reduced by about 10%, the bottom heave of the foundation pit can be reduced by about 50%, the soil settlement can be reduced by about 5%, and the bending moment of the retaining wall can be reduced by about 20%.

[0095] In another preferred embodiment, the multi-index optimization can add the total excavation distance to simplify the construction path on the above basis, so that different blocks can be connected as much as possible, thereby reducing the construction complexity. The calculation of the total excavation distance is as follows:

[0096]

[0097] where represents the distance between the center points of the i-th excavation block and the (i + 1)-th excavation block, and y can be ignored in the two-dimensional optimization.

[0098] When considering the excavation cost at the same time, the multi-objective optimization strategy adopted is: the left wall displacement (ω1 = 0.25), the right wall displacement (ω2 = 0.25), and the bottom heave of the foundation pit (ω3 = 0.25), the total excavation distance (ω4 = 0.25), and its optimization function is:

[0099]

[0100] The optimized fitness value is 0.8178, the earthwork excavation sequence is 5-6-7-8-4-3-2-1, the fitness value of the global optimal solution is 0.8178, and the excavation sequence is 5-6-7-8-4-3-2-1, and the two are consistent. The corresponding optimization process is as Figure 8 shown, the change of fitness with the number of generations is as Figure 8 shown in (8a) of Figure 8 shown in (8b) of

[0101] Table 3 Comparison of the optimized earthwork excavation plan with other plans

[0102]

[0103] It can be seen from Table 3 that the optimized earthwork excavation plan has been greatly improved compared with the poor global excavation plan. The retaining wall displacement can be reduced by about 10%, the bottom heave of the pit can be reduced by about 50%, the soil settlement can be reduced by about 5%, the bending moment of the retaining wall can be reduced by about 20%, and the excavation cost can be saved by 180%.

[0104] Example 2

[0105] This embodiment provides an earthwork excavation sequence optimization system based on an improved genetic algorithm, including:

[0106] An earthwork excavation sequence information acquisition module, which is used to divide the foundation pit excavation surface into blocks, number the blocks, and obtain the earthwork excavation sequence information by randomly combining the blocks;

[0107] A foundation pit deformation database establishment module, which is used to obtain a foundation pit deformation database considering the excavation sequence by a batch processing method according to the earthwork excavation sequence information;

[0108] An optimal earthwork excavation sequence acquisition module, which is used to obtain the corresponding optimal earthwork excavation sequence under different optimization indexes by an improved genetic algorithm according to the foundation pit deformation database considering the excavation sequence.

[0109] The rest is the same as in Example 1.

[0110] The preferred specific embodiments of the present invention have been described in detail above. It should be understood that those of ordinary skill in the art can make many modifications and variations based on the concept of the present invention without creative efforts. Therefore, all technical solutions that can be obtained by those skilled in the art in the technical field according to the concept of the present invention through logical analysis, reasoning, or limited experiments on the basis of the prior art shall fall within the protection scope determined by the claims.

Claims

1. A method for optimizing earthwork excavation sequence based on an improved genetic algorithm, characterized in that: The following steps are involved: Acquiring earthwork excavation sequence information, wherein the earthwork excavation sequence information is obtained by dividing and numbering the foundation pit excavation surface, and randomly combining the blocks; According to the earthwork excavation sequence information, a foundation pit deformation database considering the excavation sequence is obtained by a batch processing method; According to the foundation pit deformation database considering the excavation sequence, the optimal earth excavation sequence corresponding to different optimization index combinations is obtained by improving the genetic algorithm.

2. The earthwork excavation sequence optimization method based on improved genetic algorithm according to claim 1 is characterized in that: The foundation pit deformation database considering the excavation sequence includes the earthwork excavation sequence and the foundation pit deformation data and retaining wall bending moment data corresponding to the earthwork excavation sequence.

3. The earthwork excavation sequence optimization method based on improved genetic algorithm according to claim 1 is characterized in that: The specific steps of obtaining the optimal earthwork excavation sequence by the improved genetic algorithm include: Initializing parameters of the improved genetic algorithm; The earth excavation sequence information is converted into chromosome information code by coding mapping; sequential coding is performed to obtain a first generation population; The first generation population is subjected to random selection, Davis crossover, segment inversion, and single-point mutation operations to generate a new population; Mix the first generation population with the new population, calculate the fitness of the newly generated population and the first generation population, and select individuals with high fitness to form the next generation population by comparing the fitness of the two populations; It is determined whether the next generation population has reached the maximum genetic generation. If so, the strongest individual in the last generation population is output as the optimal earth excavation sequence.

4. The earthwork excavation sequence optimization method based on improved genetic algorithm according to claim 3 is characterized in that: The parameters of the improved genetic algorithm include multiple ones of population size, chromosome length, crossover probability, reversal probability, mutation probability and maximum genetic generation number.

5. The earthwork excavation sequence optimization method based on improved genetic algorithm according to claim 3 is characterized in that: The sequential encoding methods include natural encoding and one-hot encoding.

6. The earthwork excavation sequence optimization method based on improved genetic algorithm according to claim 1, characterized in that: The optimization indexes for the excavation sequence of the foundation pit include the maximum lateral displacement of the left and right retaining walls, the maximum settlement of the left and right ground surfaces, the maximum uplift of the foundation pit bottom and the maximum bending moment of the left and right retaining walls.

7. The earthwork excavation sequence optimization method based on improved genetic algorithm according to claim 1 is characterized in that: The optimal earthwork excavation sequence includes an optimal earthwork excavation sequence optimized by a single index and an optimal earthwork excavation sequence optimized by multiple indexes.

8. The earthwork excavation sequence optimization method based on improved genetic algorithm according to claim 6, characterized in that: When the optimal earthwork excavation sequence is the optimal earthwork excavation sequence optimized by a single index, the calculation formula of the fitness is: fitness=f i (x) In the formula, fitness is the fitness, f i (x) is a single index calculation function, and x is the optimization index.

9. The earthwork excavation sequence optimization method based on improved genetic algorithm according to claim 6, characterized in that: When the optimal earthwork excavation sequence is the optimal earthwork excavation sequence optimized by multiple indicators, the calculation formula of fitness is: fitness=ω1f1(x)+ω2f2(x)+ω3f3(x)+...+ω k f k (x) Where fitness is the fitness, f1(x),f2(x),f3(x),...,f k (x) is a single index calculation function, x is the optimization index, k is the number of optimization indexes, ω is the optimization index weight, ω1+ω2+ω3+...+ω k =1.

10. An earthwork excavation sequence optimization system based on an improved genetic algorithm, characterized in that: include: The earthwork excavation sequence information acquisition module is used to divide the foundation pit excavation surface into blocks, number the blocks, and obtain the earthwork excavation sequence information by randomly combining the blocks; A foundation pit deformation database establishment module is used to obtain a foundation pit deformation database taking into account the excavation sequence through a batch processing method according to the earthwork excavation sequence information; The optimal earthwork excavation sequence acquisition module is used to obtain the corresponding optimal earthwork excavation sequence under different optimization indicators through an improved genetic algorithm based on the foundation pit deformation database considering the excavation sequence.

Images