Pile body parameter acquisition method based on genetic optimization algorithm

Abstract

The invention provides a pile body parameter acquisition method based on a genetic optimization algorithm, and the method comprises the steps: generating an initial generation population, and calculating the fitness value of each individual according to the actually measured speed value and fitting speed value of a pile top unit at each moment; generating individuals of the offspring population according to the selection probability, crossover probability and mutation probability of the individuals; continuously evolving and iterating to generate offspring populations, and terminating evolutionary iteration to obtain optimal pile body parameters when evolutionary iteration termination conditions are determined according to fitness values of individuals in the continuous multi-generation populations or evolutionary generations subjected to evolutionary iteration; wherein the fitting speed value of the pile top unit at each moment is calculated according to the stress upgoing wave, the stress downgoing wave and the actually measured stress value of the pile top unit. According to the method, the genetic optimization algorithm is applied to the field of pile body parameter calculation, and a large number of parameters do not need to be manually input, so that the high-strain fitting analysis difficulty is greatly reduced, and the analysis efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of pile foundation detection, and more specifically, to a method for obtaining pile body parameters based on a genetic optimization algorithm. Background Art

[0002] In pile foundation testing, high strain dynamic testing is an important method for pile foundation integrity testing and bearing capacity testing. Compared with traditional static load testing, it has the advantages of convenient testing and lower cost. It is widely used and has broad market prospects.

[0003] To date, the development of high-strain dynamic measurement of pile foundation has a history of more than 60 years. With the development of modern electronic and other technologies, high-strain dynamic measurement has gradually formed many distinctive methods such as dynamic pile driving formula, hammer penetration method, wave equation method, Case method and waveform fitting method. Among them, the curve fitting method is the most complete and reasonable high-strain data analysis method. The current high-strain dynamic measurement specification particularly emphasizes the application of this method. However, this method belongs to the inversion algorithm, and due to the equivalence of pile-soil parameters, there is a problem of multiple solutions. How to reduce the multiple solutions of the fitting results and improve the accuracy and efficiency of the algorithm has become a very concerned issue.

[0004] There are many high-strain fitting software in the industry, but there are common problems such as complex pile-soil parameter configuration, fitting results that violate physical laws and attempts, and low fitting efficiency. No method that can solve these problems has been found in the published data and literature. Summary of the invention

[0005] The present invention aims at solving the technical problems existing in the prior art and provides a method for obtaining pile parameters based on a genetic optimization algorithm, comprising:

[0006] Setting initial parameters of the genetic optimization algorithm, the initial parameters include the population size n, the length L of the pile body parameters included in each individual, the value range of each pile body parameter, the crossover probability, the mutation probability and the maximum evolutionary number T of the population;

[0007] Generate an initial generation population, and calculate the fitness value of each individual in the initial generation population according to the measured speed value and the fitted speed value of the pile top unit at each moment;

[0008] Select individuals from the initial generation population according to the selection probability of each individual, perform crossover and mutation operations on the selected individuals based on the crossover probability and mutation probability, and generate individuals of the offspring population;

[0009] Continuously evolve and iterate to generate offspring populations. According to the fitness values ​​of individuals in multiple generations of populations or the number of evolutionary generations that have evolved and iterated, determine whether the evolutionary iteration termination conditions are met. When the evolutionary iteration termination conditions are met, terminate the evolutionary iteration and obtain the optimal pile parameters.

[0010] The fitting velocity value of the pile top unit at each moment is calculated based on the stress up-going wave, stress down-going wave and measured stress value of the pile top unit.

[0011] The present invention provides a method for obtaining pile body parameters based on a genetic optimization algorithm, which generates an initial generation population, calculates the fitness value of each individual according to the measured speed value and the fitting speed value of the pile top unit at each moment; generates individuals of the offspring population according to the selection probability, crossover probability and mutation probability of the individual; continuously generates offspring populations by evolution iteration, and terminates the evolution iteration when the termination condition of the evolution iteration is determined according to the fitness value of the individuals in the continuous multi-generation population or the evolution generation of the evolution iteration, and obtains the optimal pile body parameters; wherein the fitting speed value of the pile top unit at each moment is calculated according to the stress up-going wave, the stress down-going wave and the measured stress value of the pile top unit. The present invention applies the genetic optimization algorithm to the field of pile body parameter calculation, and since a large number of parameters do not need to be manually input, the difficulty of high strain fitting analysis is greatly reduced, and the analysis efficiency is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A flow chart of a pile body parameter acquisition method based on a genetic optimization algorithm provided by the present invention;

[0013] Figure 2 It is a schematic diagram for determining the calculation area according to the motion displacement of the pile unit;

[0014] Figure 3 The schematic diagram of the pile-soil end calculation model;

[0015] Figure 4 Schematic diagram of the division of the calculation area. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. In addition, the technical features in the various embodiments or single embodiments provided by the present invention can be arbitrarily combined with each other to form a feasible technical solution. This combination is not subject to the constraints of the sequence of steps and / or the structural composition mode, but must be based on the ability of ordinary technicians in this field to achieve. When the combination of technical solutions is contradictory or cannot be achieved, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0017] In view of the problems existing in the existing high-strain fitting analysis technology, the present invention provides a pile body parameter acquisition method based on a genetic optimization algorithm, which can accurately, quickly and efficiently acquire the pile body parameters.

[0018] Figure 1 A flow chart of a pile parameter acquisition method based on a genetic optimization algorithm provided by the present invention, such as Figure 1 As shown, the method includes:

[0019] Step 1, setting the initial parameters of the genetic optimization algorithm, the initial parameters include the population size n, the length L of the pile body parameters included in each individual, the value range of each pile body parameter, the crossover probability, the mutation probability and the maximum evolutionary number T of the population.

[0020] It can be understood that the present invention adopts a genetic optimization algorithm to calculate and obtain pile body parameters, and initializes the genetic optimization algorithm, mainly including setting the population size to n, the number of variables to L (pile-soil parameters to be given in the fitting analysis), the string length of each variable to be determined according to its value range, setting the crossover probability Pc=0.9, the mutation probability to Pm=0.85, the maximum evolutionary generation T=100, and taking the following individuals to form the initial total population S1.

[0021] Step 2: Generate an initial generation population, and calculate the fitness value of each individual in the initial generation population according to the measured speed value and the fitted speed value of the pile top unit at each moment.

[0022] It is understandable that in the present invention, the pile is regarded as a continuous rod model and divided into N elastic units, the units from the pile top to the pile end are numbered from 1 to n, and the length of each unit is taken to ensure that the time Δt for the stress wave to pass is equal. The impedance change of the rod unit at the bottom of the unit only occurs at the interface of the unit, and the wave is not distorted inside the unit. The side resistances of the N units are R1, R2, ..., Rn, and the end resistance is R b , unit N.

[0023] Generate an initial generation population and calculate the fitness value of each individual in the initial generation population. The fitness value of each individual in the initial generation population is calculated according to the measured speed value and the fitted speed value of the pile top unit at each moment. The calculation formula for calculating the fitness value of each individual is:

[0024]

[0025] Where l is the total number of time units, j is the time unit number, and Zvm (1,j) is the measured velocity value of the pile top unit at time j, Zvc (1,j) is the fitting velocity value of the pile top unit at time j, f(x h) is the cumulative velocity difference of the pile top unit in l and time unit, which can be called the objective function, f max is the maximum value of the objective function of each individual in the current generation population, f min is the minimum value of the objective function of each individual in the current generation population, F(x h ) is the fitness value of each individual.

[0026] Among them, the measured velocity value Zvm of the pile top unit at time j is (1,j) It can be obtained according to the sensor measurement, and the fitting velocity value of the pile top unit at each moment is calculated according to the stress up-going wave, stress down-going wave and measured stress value Fm of the pile top unit.

[0027] Among them, the measured velocity value Zvm of the pile top unit (1,j) The acquisition of the measured stress value Fm includes:

[0028] Obtaining time history curve data of measured stress and measured acceleration at the pile top collected by the sensor, that is, measured stress-time curve and measured acceleration-time curve;

[0029] The measured acceleration a is obtained by integration operation to obtain velocity V, V is multiplied by the generalized wave impedance Z1 of the pile top unit to obtain data ZV1, and the strain ε1 value of the pile top unit is multiplied by the generalized wave impedance Z1 of the pile top unit to obtain the stress F1 of the pile top unit;

[0030] The pile body is divided into n units, the length of each pile segment is calculated, and the time Δt for the stress wave to pass through the pile segment is calculated based on the wave velocity. Since the measured data of the sensor is discrete data, a one-dimensional linear interpolation is performed on the discrete ZV1 and F1 according to Δt, so that the calculation time step is equal to Δt, and the continuous measured signals Fm and Zvm are obtained. (1,j) .

[0031] The acquisition of the stress up-going wave and stress down-going wave of the pile top unit includes:

[0032] The stress up-going wave and stress down-going wave of the current unit at the current moment are calculated according to the stress up-going wave and stress down-going wave of the upper and lower adjacent units of the current unit at the previous moment, the generalized wave impedance of the current unit and the adjacent units at the current moment, and the total resistance of the current unit at the current moment.

[0033] The calculating of the stress up-going wave and the stress down-going wave of the current unit at the current moment includes:

[0034]

[0035] Among them, F u (i, j) is the stress up-going wave of the current unit at the current moment, F d(i, j) is the stress downward wave of the current unit at the current moment, F d (i-1, j-1) is the stress downward wave of the previous unit at the previous moment, F u (i+1,j-1) is the stress up-going wave of the next unit at the previous moment, Z i is the generalized wave impedance of the current unit, Z i+1 is the generalized wave impedance of the next unit, and R(i,j) is the total resistance of the current unit at the current moment.

[0036] The boundary conditions of the pile top unit are:

[0037]

[0038] or

[0039]

[0040] Among them, F m (j) is the measured stress value at time j, Zv m (j) is the measured speed value at time j;

[0041] The boundary conditions of the pile bottom unit are:

[0042]

[0043] Among them, R b (j) is the end resistance of the pile end soil on the pile top unit at time j.

[0044] The acquisition of the total resistance R(i,j) of the current unit at the current moment includes:

[0045] According to the stress up-wave and stress down-wave of the current unit at the current moment, the movement speed and movement displacement of the current unit of the pile body at the current moment are calculated;

[0046] According to the displacement of the current unit at the current moment, the pile side static resistance of the previous unit at the previous moment and the limit side resistance of the current unit, the calculation area where the current unit is located at the current moment is determined;

[0047] According to the calculation area where the current unit is located at the current moment and the pile body parameters of the current individual, the static resistance of the current unit at the current moment is calculated;

[0048] According to the image resistance and dynamic resistance of the current unit at the current moment, the total resistance of the current unit at the current moment is calculated.

[0049] Among them, according to the stress up-wave and stress down-wave of the current unit at the current moment, the motion speed and motion displacement of the current unit of the pile body at the current moment are calculated, including:

[0050] The calculation formula of the current unit's motion speed v(i,j) and motion displacement s(i,j) at the current moment is:

[0051]

[0052] Among them, according to the Capwap mechanical model, the calculation area where the current unit is located at the current moment can be jointly confirmed by the particle displacement s(i,j) at the current moment, the particle displacement s(i,j-1) at the previous moment, and the static resistance Rs(i,j-1) at the previous moment. The information at the previous moment is all known input parameters. The current unit is divided into three calculation areas, namely, calculation area 1, the calculation area where the soil loading and unloading paths are the same; calculation area 2, the calculation area where the soil loading and unloading paths are different and are greater than the heavy loading level and less than the maximum side resistance; calculation area 3, the soil loading and unloading paths are different and are less than the heavy loading calculation area and greater than the reverse unloading level.

[0053] For details, see Figure 2 , Figure 2 Rs is the static resistance of the soil, S is the displacement of the unit particle, Ru is the maximum side resistance, Un is the unloading level coefficient, re is the reloading level, and Cs is the unloading coefficient of the pile side soil. The above parameters are all known input coefficients.

[0054] If s(i,j)<Q(i), the loading path is the same as the unloading path, and the calculation area where the current unit is located at the current moment is the first calculation area;

[0055] If s(i,j)>Q(i), and r e R u (i)≤R s (i,j-1)≤R u (i), then the calculation area where the current unit is located at the current moment is the second calculation area;

[0056] If s(i,j)>Q(i), and -u n R u (i)≤R s (i,j-1) <r e R u (i), the calculation area where the current unit is located at the current moment is the third calculation area;

[0057] Where Q(i) represents the maximum elastic displacement of the current unit, R u (i) represents the ultimate pile side resistance of the current unit, Q(i) and R u (i) is the pile parameter output by the genetic optimization algorithm, r e represents the reloading level, u n represents the unloading level factor, R s(i,j - 1) is the static soil resistance of the current element at time j - 1.

[0058] Based on the calculation area where the current element is located at the current time, calculate the static soil resistance R s (i,j) of the current element at the current time.

[0059] Specifically, if the current element is in the first calculation area at the current time, the calculation formula for the static resistance is:

[0060]

[0061] If the current element is in the second calculation area at the current time, if S(i,j) ≥ S(i,j - 1) and the displacement increases, then the soil mass is in the loading state, and the calculation formula for the static resistance is:

[0062]

[0063] If S(i,j) < S(i,j - 1) and the displacement decreases, then the soil mass is in the unloading state, and the calculation formula for the static resistance is:

[0064]

[0065] If the current element is in the third calculation area at the current time, if R s (i,j) < r e R u (i), then the loading and unloading paths of the soil are the same, and the calculation formula for the static resistance is:

[0066]

[0067] If the soil is loaded and exceeds the reloading level r e R u (i), then the calculation method for the static resistance is:

[0068]

[0069] In the calculation of the static resistance in the three calculation areas, if R S (i,j) < -u n R u (i), then the calculation formula for the static resistance is:

[0070] R s (i,j) = -u n R u (i) (14);

[0071] The dynamic resistance at the pile tip is calculated using the Smith dynamic resistance model to obtain R d , and the calculation formula is:

[0072] R d (i,j)=|R s (i,j)|J s (i) V(i, j) (15);

[0073] Among them, J s (i) represents the Smith coefficient of the soil on the pile side of the current unit, V(i,j) represents the particle velocity of the current unit at time j, R d (i, j) represents the dynamic resistance of the soil on the side of the current unit pile at time j;

[0074] The total resistance of the current unit at the current moment is:

[0075] R(i,j)=R s (i,j)+R d (i,j) (16).

[0076] The total resistance of the current unit at the current moment is calculated according to formula (16), and the stress up-wave F of each unit at each moment is calculated according to the above formulas (3), (4), (5) and (6). u (i, j) and stress downward wave F d (i, j), and then according to the stress downward wave F of the pile top unit at time j d (i,j) combined with the measured stress value F m , calculate the fitting velocity value Zvc of the pile top unit at time j (1,j) .

[0077] It should be noted that when calculating the stress upward wave, stress downward wave, static resistance and dynamic resistance of each unit, a calculation model of the pile end soil is established, such as Figure 3 As shown in Figure 1, under normal circumstances, for piles supported on very hard bearing soil layers, there may be a certain gap between the pile end and the soil. Therefore, in the improved pile end soil resistance calculation model, the static reaction force of the soil within the gap range is specified to be zero; at the same time, the tensile stress of the soil at the pile end is also zero. Figure 3 Medium b is the pile end unloading coefficient, and 0≤c b ≤1.

[0078] The process of solving the static resistance of the soil at the pile end Rs(i,j) is the same as that of solving the static resistance of the soil at the pile side, so it will not be repeated here.

[0079] There are also the following expressions:

[0080] R db (j)=|R sb (i,j)|J s (b) V(N,j) (17);

[0081] R b (j) = R sb (j)+R db (j) (18);

[0082] Where:

[0083] Rsb(j) is the static resistance of the soil at the pile end at time j;

[0084] Rdb(j) is the dynamic resistance of the soil at the pile end at time j;

[0085] Rb(j) is the total resistance of the soil at the pile end at time j;

[0086] Js(b) is the Smith damping coefficient of the soil at the pile end.

[0087] See also Figure 4 , the calculation area is divided into a rectangular grid of N rows and M columns, where N is the number of pile units, x is the step length along the x direction of the pile body, and t is the step length along the time t direction; the value of each point on the first column of the grid is defined as 0, and then through a series of iterative calculations, the stress up-wave Fu value and the stress down-wave Fd value of each point on the second to the Mth column can be obtained in turn.

[0088] Among them, the stress up-wave and stress down-wave of the pile top unit at each moment are combined with the measured stress value Fm to calculate the fitting velocity value Zvc of the pile top unit at moment j. (1,j) Specifically include:

[0089] Z c (1,j)=F m (j)-2F u (1,j);

[0090] Among them, F m (j) is the measured stress value of the pile top unit at time j, F u (1, j) is the stress upgoing wave of the pile top unit at time j.

[0091] Then according to the measured speed value Zvm (1,j) And the fitting speed value Zvc (1,j) , calculate the fitness value of each individual according to formula (1).

[0092] Step 3: Select individuals from the initial generation population according to the selection probability of each individual, perform crossover and mutation operations on the selected individuals based on the crossover probability and mutation probability, and generate individuals of the offspring population.

[0093] It is understandable that the selection probability, crossover probability and mutation probability of each individual are calculated separately, where the calculation formula for the selection probability of each individual is:

[0094]

[0095] Among them, P(x h ) is individual x h The selection probability of is, n is the population size.

[0096] Individuals are selected from the initial generation population according to the selection probability of each individual. The crossover operator program uses a multi-point crossover method to generate new individuals for Pc according to the crossover probability, and to generate new individuals for Pm according to the mutation operator probability. The generated new individuals are used as the offspring population.

[0097] Step 4, continuously evolve and iterate to generate offspring populations, and judge whether the evolution iteration termination conditions are met according to the fitness values ​​of individuals in multiple consecutive generations of populations or the number of evolution generations that have evolved and iterated. When the evolution iteration termination conditions are met, terminate the evolution iteration and obtain the optimal pile parameters.

[0098] It is understandable that by continuously executing steps 2 and 3, the offspring population is continuously generated until the evolution iteration termination condition is met, the evolution iteration is terminated, and the pile body parameters corresponding to the optimal individual are obtained.

[0099] Specifically, the maximum value of the fitness values ​​of multiple individuals in each generation of the population is obtained. When the maximum fitness value in multiple consecutive generations of the population does not change or the number of evolutionary generations that have been iterated reaches the maximum number of evolutionary iterations, the evolutionary iteration termination condition is met.

[0100] When the evolution iteration is terminated, the individual with the maximum fitness value in the last generation of the population is obtained, that is, the optimal pile parameters are obtained.

[0101] Among them, the optimal pile body parameters obtained by the genetic optimization algorithm are binary, and the obtained optimal pile body parameters are converted into decimal:

[0102]

[0103] Among them, I max is the maximum decimal number in the range of pile parameters, I min is the minimum decimal number of the pile parameter value range, I is the decimal value of the pile parameter, B is the binary value of I, Dec is the decimal value converted from binary number, 2 L -1 is the maximum number of permutations of binary pile parameters of length L. This operation is equivalent to mapping the binary number to [I max , I Min ] range.

[0104] Its binary precision is:

[0105]

[0106] The embodiment of the present invention provides a pile body parameter acquisition method based on a genetic optimization algorithm. By applying the genetic optimization algorithm to the field of high strain fitting analysis, the difficulty of high strain fitting analysis is greatly reduced and the analysis efficiency is improved because a large number of parameters do not need to be manually input. At the same time, since different parameters are limited in range according to the actual engineering situation, the credibility and accuracy of the results are also improved.

[0107] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0108] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0109] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0110] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0111] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0112] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0113] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for obtaining pile parameters based on genetic optimization algorithm, characterized in that: include: Setting initial parameters of the genetic optimization algorithm, the initial parameters include the population size n, the length L of the pile body parameters included in each individual, the value range of each pile body parameter, the crossover probability, the mutation probability and the maximum evolutionary number T of the population; Generate an initial generation population, and calculate the fitness value of each individual in the initial generation population according to the measured speed value and the fitted speed value of the pile top unit at each moment, wherein the fitted speed value of the pile top unit at each moment is calculated according to the stress down wave and the measured stress value of the pile top unit; Select individuals from the initial generation population according to the selection probability of each individual, perform crossover and mutation operations on the selected individuals based on the crossover probability and mutation probability, and generate individuals of the offspring population; Continuously evolve and iterate to generate offspring populations. According to the fitness values ​​of individuals in multiple consecutive generations of populations or the number of evolutionary generations that have evolved and iterated, it is judged whether the evolutionary iteration termination conditions are met. When the evolutionary iteration termination conditions are met, the evolutionary iteration is terminated to obtain the optimal pile parameters.

2. The method for obtaining pile parameters according to claim 1, characterized in that: The step of calculating the fitness value of each individual in the initial generation population according to the measured speed value and the fitted speed value of the pile top unit at each moment includes: Where l is the total number of time units, j is the time unit number, and Zvm (1,j) is the measured velocity value of the pile top unit at time j, Zvc (1,j) is the fitting velocity value of the pile top unit at time j, f(x h ) is the cumulative velocity difference of the pile top unit in l and time unit, that is, the objective function, f max is the maximum value of the objective function of each individual in the current generation population, f min is the minimum value of the objective function of each individual in the current generation population, F(x h ) is the fitness value of each individual; The pile is regarded as a continuous bar model, which is divided into N units from the top to the end of the pile. The N units are numbered from 0 to N, and the length of each unit is set to ensure that the time Δt of the stress wave is equal. The lateral resistance of the N units is R1, R2, ..., R N , the terminal resistance is R b , unit N.

3. The method for obtaining pile parameters according to claim 1, characterized in that: The calculation formula for the selection probability of each individual is: Among them, P(x h ) is individual x h The probability of selection.

4. The method for obtaining pile parameters according to claim 1, characterized in that: According to the fitness values ​​of individuals in multiple generations of populations or the number of evolutionary generations, it is determined whether the evolutionary iteration termination conditions are met, including: Obtain the maximum value of the fitness values ​​of multiple individuals in each generation of the population. When the maximum fitness value in multiple consecutive generations of the population remains unchanged or the number of evolutionary generations that have been iterated reaches the maximum number of evolutionary generations, the evolutionary iteration termination condition is met; When the evolution iteration termination condition is met, the evolution iteration is terminated to obtain the optimal pile body parameters, including: When the evolution iteration is terminated, the individual with the maximum fitness value in the last generation of the population is obtained, that is, the optimal pile parameters are obtained.

5. The method for obtaining pile parameters according to claim 2, characterized in that: The fitting velocity value of the pile top unit at each moment is calculated based on the stress downlink wave and the measured stress value of the pile top unit, including: Vol. c (1,j)=F m (j)-2F u (1,j); Among them, F m (j) is the measured stress value of the pile top unit at time j, F u (1,j) is the stress upgoing wave of the pile top unit at time j; The measured velocity value Zvm of the pile top unit (1,j) The acquisition of the measured stress value Fm includes: Obtaining time history curve data of measured stress and measured acceleration at the pile top collected by the sensor; The measured acceleration a is obtained by integration operation to obtain velocity V, V is multiplied by the generalized wave impedance Z1 of the pile top unit to obtain data ZV1, and the strain ε1 value of the pile top unit is multiplied by the generalized wave impedance Z1 of the pile top unit to obtain the stress F1 of the pile top unit; According to the division of the pile body into N units, the length of each pile segment is calculated, and the time Δt of the stress wave passing through the pile segment is calculated according to the wave velocity. According to Δt, the discrete ZV1 and F1 are linearly interpolated to obtain the measured signals Fm and Zvm (1,j) .

6. The method for obtaining pile parameters according to claim 5, characterized in that: The acquisition of the stress upgoing wave and the stress downgoing wave of the pile top unit includes: Calculate the stress up-going wave and stress down-going wave of the current unit at the current moment according to the stress up-going wave and stress down-going wave of the upper and lower adjacent units of the current unit at the previous moment, the generalized wave impedance of the current unit and the adjacent units at the current moment, and the total resistance of the current unit at the current moment; The calculating of the stress up-going wave and the stress down-going wave of the current unit at the current moment includes: Among them, F u (i, j) is the stress up-going wave of the current unit i at the current time j, F d (i, j) is the stress downward wave of the current unit at the current moment, F d (i-1, j-1) is the stress downward wave of the previous unit at the previous moment, F u (i+1,j-1) is the stress downward wave of the next unit at the previous moment, Z i is the generalized wave impedance of the current unit, Z i+1 is the generalized wave impedance of the next unit, R(i,j) is the total resistance of the current unit at the current moment; The boundary conditions of the pile top unit are: or Among them, F m (j) is the measured stress value at time j, Zv m (j) is the measured speed value at time j; The boundary conditions of the pile bottom unit are: Among them, R b (j) is the end resistance of the pile end soil on the pile top unit at time j.

7. The method for obtaining pile parameters according to claim 6, characterized in that: The acquisition of the total resistance R(i,j) of the current unit at the current moment includes: According to the stress up-wave and stress down-wave of the current unit at the current moment, the movement speed and movement displacement of the current unit of the pile body at the current moment are calculated; Determine the calculation area where the current element is located at the current moment based on the displacement of the current element at the current moment, the static skin friction of the previous element at the previous moment, and the ultimate skin friction of the current element; Calculate the static skin friction of the current element at the current moment according to the calculation area where the current element is located at the current moment and the pile parameters of the current individual; Calculate the total resistance of the current element at the current moment according to the static resistance and dynamic resistance of the current element at the current moment.

8. The method for obtaining pile parameters according to claim 7, characterized in that: The calculation formula for the movement speed of the current element at the current moment is: Determining the calculation area where the current element is located at the current moment according to the movement speed and movement displacement of the current element at the current moment includes: If s(i,j) < Q(i) and the loading path is the same as the unloading path, the calculation area where the current element is located at the current moment is the first calculation area; If s(i,j)>Q(i), and r e R u (i)≤R s (i,j-1)≤R u (i), then the calculation area where the current unit is located at the current moment is the second calculation area; If s(i,j)>Q(i), and -u n R u (i)≤R s (i,j-1) <r e R u (i), the calculation area where the current unit is located at the current moment is the third calculation area; Among them, Q(i) represents the maximum elastic displacement of the current unit, R u (i) represents the ultimate pile side resistance of the current unit, Q(i) and R u (i) is the pile parameter output by the genetic optimization algorithm, r e represents the reloading level, u n represents the unloading level factor, R s (i,j-1) is the static resistance of the soil in the current unit at time j-1.

9. The method for obtaining pile parameters according to claim 8 or 8, characterized in that: Calculating the static skin friction of the current element at the current moment according to the calculation area where the current element is located at the current moment and the pile parameters of the current individual includes: If the current element is in the first calculation area at the current moment, the calculation formula for the static skin friction is: If the current element is in the second calculation area at the current moment, if S(i,j) ≥ S(i,j - 1) and the displacement increases, the soil mass is in the loading state, and the calculation formula for the static skin friction is: If S(i,j) < S(i,j - 1) and the displacement decreases, the soil mass is in the unloading state, and the calculation formula for the static skin friction is: If the current unit is in the third calculation area at the current moment, if R s (i,j) <r e R u (i), the loading and unloading paths of the soil are the same, and the static resistance is calculated as: If the soil is loaded and exceeds the reload level r e R u (i), the static resistance is calculated as: In the static resistance calculation of the three calculation areas, if R S (i,j)<-u n R u (i), the calculation formula of static resistance is: R s (i,j)=-u n R u (i); The pile end dynamic resistance is calculated using the Smith dynamic resistance model to obtain R d , the calculation formula is: R d (i,j)=|R s (i,j)|J s (i)V(i,j); Among them, J s (i) represents the Smith coefficient of the soil on the pile side of the current unit, V(i,j) represents the particle velocity of the current unit at time j, R d (i, j) represents the dynamic resistance of the soil on the side of the current unit pile at time j, c s represents the side soil unloading coefficient; The total resistance of the current element at the current moment is: R(i,j)=R s (i,j)+R d (i,j)。 10. The method for obtaining pile parameters according to claim 1, characterized in that: The optimal pile parameters obtained through the genetic optimization algorithm are binary. Convert the obtained optimal pile parameters into decimal: Among them, I max is the maximum decimal number in the range of pile parameters, I min is the minimum decimal number of the pile parameter value range, I is the decimal value of the pile parameter, B is the binary value of I, Dec is the decimal value converted from binary number, 2 L -1 is the maximum number of permutations of binary pile parameters of length L; The precision of its binary is:

Images