Foundation pit dewatering control method and device based on well storage effect of overflowing aquifer

Abstract

The present invention provides a foundation pit dewatering control method and device based on the well storage effect of the overflowing aquifer, which can be applied to the field of geotechnical engineering technology. The method includes: obtaining hydrological data, soil data and well data corresponding to the foundation pit; inputting the permeable layer data, the impermeable layer data, the soil data and the well data into the target control model, and outputting the target water level control result of the foundation pit, wherein the target water level control result represents the distance value between the water level of the target point and the initial water level; wherein the target control model is obtained by the following operation training: obtaining initial sample data and initial water level control result; determining target sample data by using the initial water level control result and the initial sample data; and training the initial control model by using the target sample data and the label corresponding to the target sample data to obtain the target control model. The method can simplify the operation steps, improve the data processing effect, and effectively ensure the safety of foundation pit construction in real time.

Description

Technical Field

[0001] The invention relates to the technical field of geotechnical engineering, and in particular to a foundation pit dewatering control method and device based on the well storage effect of a leaking aquifer. Background Art

[0002] In the process of urban construction, foundation pit excavation is widely used in underground space development and high-rise building infrastructure construction. The complexity of foundation pit dewatering design lies in the need to simultaneously meet the requirements of foundation pit structural stability and control the deformation of the surrounding soil. Especially in soft soil areas, the settlement caused by dewatering is often accompanied by soil deformation in a large range, and may even cause uneven surface settlement, thereby affecting its structural safety. Therefore, the settlement problem caused by foundation pit dewatering has become a major problem in the current engineering field. In related technologies, the monitoring methods of foundation pit dewatering mainly include using water level meters to regularly measure groundwater level changes, monitoring the flow of pumping wells through flow meters, and using settlement meters or total stations to monitor the settlement of foundation pits and surrounding soils.

[0003] The inventors have discovered that the monitoring and control methods for foundation pit dewatering in the relevant technologies have the following defects: the existing foundation pit dewatering and settlement monitoring methods have cumbersome data processing methods and low monitoring accuracy; they mainly rely on manual observation and regular inspections, and the data are not real-time and are time-consuming, labor-intensive, and lack economic efficiency. Summary of the invention

[0004] In view of the above problems, the present invention provides a method, device, equipment, storage medium and program product for controlling foundation pit dewatering based on the well storage effect of overflowing aquifer.

[0005] According to a first aspect of the present invention, there is provided a method for controlling foundation pit dewatering based on the well storage effect of a leaking aquifer, comprising: obtaining hydrological data, soil data and well data corresponding to the foundation pit, the hydrological data comprising permeable layer data and impermeable layer data; inputting the permeable layer data, the impermeable layer data, the soil data and the well data into a target control model, and outputting a target water level control result of the foundation pit, the target water level control result representing the distance value between the water level of the target point and the initial water level; wherein the target control model is obtained by training through the following operations: obtaining initial sample data and initial water level control results; determining target sample data using the initial water level control results and the initial sample data; and training the initial control model using the target sample data and labels corresponding to the target sample data to obtain the target control model.

[0006] The second aspect of the present invention provides a foundation pit dewatering control device based on the well storage effect of overflowing aquifers, comprising: a data acquisition module, used to acquire hydrological data, soil data and well data corresponding to the foundation pit, the above-mentioned hydrological data including permeable layer data and impermeable layer data; a control result output module, used to input the above-mentioned permeable layer data, the above-mentioned impermeable layer data, the above-mentioned soil data and the above-mentioned well data into a target control model, and output the target water level control result of the above-mentioned foundation pit, the above-mentioned target water level control result represents the distance value between the water level of the target point and the initial water level; wherein the above-mentioned target control model is obtained by the following operation training: obtaining initial sample data and initial water level control results; determining target sample data using the above-mentioned initial water level control results and the above-mentioned initial sample data; and training the initial control model using the above-mentioned target sample data and the labels corresponding to the above-mentioned target sample data to obtain the above-mentioned target control model.

[0007] A third aspect of the present invention provides an electronic device, comprising: one or more processors; a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above method.

[0008] The fourth aspect of the present invention also provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the above method.

[0009] The fifth aspect of the present invention also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0010] According to the foundation pit dewatering control method, device, equipment, storage medium and program product based on the well storage effect of the overflowing aquifer provided by the present invention, by targeting the foundation pit with the overflowing aquifer, combining the hydrological data, soil data and well data received in real time, and using the target control model to obtain the target water level control result of the foundation pit, dynamic adjustment and real-time response to the change of the foundation pit water level are achieved, ensuring that the water level is within the standard range during the construction process, avoiding the defects of low accuracy and real-time performance of manual regular monitoring; due to the use of the target control model, the dewatering plan and dewatering amount can be optimized in real time, unnecessary pumping is reduced, resource utilization efficiency is improved, and construction costs are reduced; by accurately controlling the foundation pit water level, the project quality problems caused by water level fluctuations can be effectively reduced, thereby improving the overall quality and stability of the project. At the same time, scientific and reasonable water level control can reduce construction delays caused by water level problems, thereby shortening the foundation pit construction period and time cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The above and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0012] Figure 1 An application scenario diagram of a foundation pit dewatering control method, device, equipment, storage medium, and program product based on the well storage effect of a leaking aquifer according to an embodiment of the present invention is shown;

[0013] Figure 2 A flow chart of a foundation pit dewatering control method based on the well storage effect of a leaking aquifer according to an embodiment of the present invention is shown;

[0014] Figure 3 A flow chart of a method for optimizing initial data based on a hybrid algorithm according to an embodiment of the present invention is shown;

[0015] Figure 4 A schematic cross-sectional view of a site for foundation pit dewatering based on the well storage effect of a leaking aquifer according to an embodiment of the present invention is shown;

[0016] Figure 5 A schematic diagram showing a comparison between a predicted value of a water level control result obtained based on a target control model and an actual monitoring value according to an embodiment of the present invention is shown;

[0017] Figure 6 It shows a structural block diagram of a foundation pit dewatering control device based on the well storage effect of the overflowing aquifer according to an embodiment of the present invention;

[0018] Figure 7 A block diagram of an electronic device suitable for implementing a foundation pit dewatering control method based on the well storage effect of a leaking aquifer according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0019] Below, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present invention. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of embodiments of the present invention. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of concepts of the present invention.

[0020] The terms used herein are only for describing specific embodiments and are not intended to limit the present invention. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0021] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0022] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0023] In the technical solution of the present invention, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0024] In the process of conceiving the present invention, the inventors found that in the related technology for monitoring and controlling foundation pit dewatering, the data processing method in the existing foundation pit dewatering and settlement monitoring is cumbersome and the monitoring and processing accuracy is low; it mainly relies on manual observation and regular inspection, the data real-time performance is poor, and it is time-consuming, labor-intensive, and lacks economy.

[0025] In view of this, the present invention, by targeting foundation pits with overflowing aquifers, combines the real-time received hydrological data, soil data and well data, and uses the target control model to obtain the target water level control result of the foundation pit, so as to realize dynamic adjustment and real-time response to the changes in the foundation pit water level, ensure that the water level is within the standard range during the construction process, and avoid the defects of low accuracy and real-time performance of manual regular monitoring; since the target control model is adopted, the precipitation plan and precipitation amount can be optimized in real time, unnecessary pumping can be reduced, resource utilization efficiency can be improved, and construction costs can be reduced; by accurately controlling the foundation pit water level, the engineering quality problems caused by water level fluctuations can be effectively reduced, thereby improving the overall quality and stability of the project. At the same time, scientific and reasonable water level control can reduce construction delays caused by water level problems, thereby shortening the foundation pit construction period and time cost.

[0026] An embodiment of the present invention provides a foundation pit dewatering control method and device based on the well storage effect of a leaking aquifer, the method comprising: obtaining hydrological data, soil data and well data corresponding to the foundation pit, the hydrological data comprising permeable layer data and impermeable layer data; inputting the permeable layer data, impermeable layer data, soil data and well data into a target control model, and outputting a target water level control result of the foundation pit, the target water level control result representing the distance value between the water level of the target point and the initial water level; wherein the target control model is obtained by training through the following operations: obtaining initial sample data and initial water level control results; determining target sample data using the initial water level control results and the initial sample data; and training the initial control model using the target sample data and labels corresponding to the target sample data to obtain the target control model.

[0027] According to an embodiment of the present invention, a leakage aquifer can characterize a confined aquifer system composed of a weak permeable layer and an aquifer. Aquifers can be connected through leakage, and the weak permeable layer is called a leakage aquifer or a semi-confined aquifer. In projects such as foundation pit excavation, information on the leakage aquifer can help determine strategies and plans for foundation pit dewatering so as to effectively control the foundation pit water level.

[0028] Figure 1 An application scenario diagram of a foundation pit dewatering control method, device, equipment, storage medium and program product based on the well storage effect of a leaking aquifer according to an embodiment of the present invention is shown.

[0029] like Figure 1 As shown, the application scenario according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, a server 105, and a data acquisition device 106. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0030] The data acquisition device 106 can be used to collect hydrological data, soil data and well data around the foundation pit and the foundation pit, such as pressure sensors, flow meters and water level meters, which can be installed at different locations around the foundation pit to monitor groundwater pressure, pumping flow and water level changes in real time. The data acquisition device 106 can also include an inclinometer, a laser rangefinder, a settlement plate and a global positioning system locator, which can be used to monitor the settlement of the surface and structure. The pressure sensor and the water level meter are respectively installed in the observation well according to the preset distance requirements, and the flow meter is installed on the outlet pipe of the precipitation well. The spacing of the observation well and the corresponding monitoring points can be arranged according to the depth, size and groundwater conditions of the foundation pit excavation, and can be determined by referring to relevant standards and specifications and actual engineering information. The data acquisition device 106 can be connected to the server 105 or the service cluster through the network 104.

[0031] The user may use at least one of the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0032] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0033] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0034] It should be noted that the foundation pit dewatering control method based on the well storage effect of the overflowing aquifer provided in the embodiment of the present invention can generally be executed by the server 105. Accordingly, the foundation pit dewatering control device based on the well storage effect of the overflowing aquifer provided in the embodiment of the present invention can generally be set in the server 105. The foundation pit dewatering control method based on the well storage effect of the overflowing aquifer provided in the embodiment of the present invention can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the foundation pit dewatering control device based on the well storage effect of the overflowing aquifer provided in the embodiment of the present invention can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0035] It should be understood that Figure 1 The number of terminal devices, networks, data collection devices and servers in the embodiment is only for illustration. Any number of terminal devices, networks, data collection devices and servers may be provided according to the implementation requirements.

[0036] Figure 2 A flow chart of a foundation pit dewatering control method based on the well storage effect of a leaking aquifer according to an embodiment of the present invention is shown.

[0037] like Figure 2 As shown, the foundation pit dewatering control method based on the overflow aquifer well storage effect of this embodiment includes operations S210 to S220.

[0038] In operation S210, hydrological data, soil data, and well data corresponding to the foundation pit are acquired, where the hydrological data includes permeable layer data and impermeable layer data.

[0039] According to an embodiment of the present invention, a control method for foundation pit dewatering may be a dewatering monitoring and control method for a case where there is a leaking aquifer in a foundation pit. Hydrological data, soil data and well data may be acquired through a data acquisition device. The hydrological data may include permeable layer (confined water layer) data and weak permeable layer data corresponding to different time periods or time points. The soil data may include foundation pit soil data and soil data of an area within a preset distance range from the foundation pit, including thickness data of the confined water layer soil (permeable layer), thickness data of the weak permeable layer soil (impermeable layer), a first permeability coefficient (permeability coefficient of the confined water layer), a second permeability coefficient (permeability coefficient of the weak permeable layer) and a leaking coefficient; the well data may characterize relevant data of a pumping well, including a well radius and a pumping rate.

[0040] In operation S220, the permeable layer data, the impermeable layer data, the soil data and the well body data are input into the target control model, and the target water level control result of the foundation pit is output, where the target water level control result represents the distance value between the water level of the target point and the initial water level.

[0041] According to an embodiment of the present invention, the target control model can be a foundation pit water level monitoring model determined by using a variety of intelligent algorithms combined with sample data. The initial water level can be characterized as the natural water level when precipitation measures are taken, and the water level at the target point (target water level) can be characterized as the water level reached by the foundation pit after the precipitation monitoring operation.

[0042] According to an embodiment of the present invention, the target control model is obtained by training through the following operations: in operation S221, initial sample data and initial water level control results are obtained; in operation S222, target sample data are determined using the initial water level control results and the initial sample data; in operation S223, the initial control model is trained using the target sample data and the labels corresponding to the target sample data to obtain the target control model.

[0043] According to an embodiment of the present invention, the initial water level control result may be a water level control result corresponding to the initial sample data, and the initial sample data may represent sample soil data, sample water level data, and sample well data corresponding to a historical time period or a historical moment. The target sample data may include a test data set and a validation data set. The label corresponding to the target sample data may be an identifier / label obtained by annotating the target sample data using information of different historical time periods and time information. The initial control model is an initial model constructed based on the sample data and the initial parameters.

[0044] According to an embodiment of the present invention, for foundation pits with overflowing aquifers, the target water level control result of the foundation pit is obtained by combining the real-time received hydrological data, soil data and well data, and realizing dynamic adjustment and real-time response to the changes in the foundation pit water level, thereby ensuring that the water level is within the standard range during the construction process and avoiding the defects of low accuracy and real-time performance of manual regular monitoring. The target control model is adopted to optimize the precipitation scheme and precipitation amount in real time, reduce unnecessary pumping, improve resource utilization efficiency and reduce construction costs. By accurately controlling the foundation pit water level, the project quality problems caused by water level fluctuations can be effectively reduced, thereby improving the overall quality and stability of the project. At the same time, scientific and reasonable water level control can reduce construction delays caused by water level problems, thereby shortening the foundation pit construction period and time cost.

[0045] According to an embodiment of the present invention, the well body data includes a pumping rate, and the method further includes: updating the pumping rate according to a target water level control result so that the target water level control result satisfies preset standard data.

[0046] According to an embodiment of the present invention, after generating the target water level control result, the pumping rate of the pumping well can be adjusted according to the target water level control result and the water level control standard data required for the actual project (which can be determined according to relevant specifications and standards) to avoid excessive precipitation or precipitation that does not meet the requirements of the standard data.

[0047] According to an embodiment of the present invention, by real-time control of the pumping rate, it can be dynamically adjusted according to the change of water level, and the efficiency of the pumping system can be optimized. It can be ensured that under different water level conditions, the pumping system always operates in the optimal state. More precise control of the pumping rate can reduce unnecessary pumping, thereby reducing energy consumption and saving operating costs.

[0048] According to an embodiment of the present invention, soil data include permeable layer thickness data, impermeable layer thickness data and permeability coefficient, and hydrological data include water release coefficient and time data; the permeable layer data, impermeable layer data, soil data and well data are input into the target control model, and the target water level control result of the foundation pit is output, including: determining the water conductivity according to the permeability coefficient and the permeable layer thickness data; and inputting the pumping rate, permeable layer thickness data, impermeable layer thickness data, permeability coefficient, water conductivity, water release coefficient, and time data into the target control model to generate the target water level control result.

[0049] According to an embodiment of the present invention, the hydraulic conductivity may include the hydraulic conductivity of the confined aquifer, which may be determined by the thickness of the confined aquifer and the permeability coefficient of the confined aquifer, as shown in the following formula (1):

[0050] (1);

[0051] Among them, T is the hydraulic conductivity of the confined aquifer, K is the permeability coefficient of the confined aquifer, and M is the thickness of the confined aquifer.

[0052] According to an embodiment of the present invention, the target water level control result can be obtained by inputting the acquired soil data, hydrological data and well data into the target control model. The target control model is specifically shown in the following formula (2):

[0053] (2);

[0054] in, It can represent the distance between the water level after precipitation and the natural water level at the target time t at a distance r from the center of the well body. Q is the pumping rate. is the time factor, and the calculation formula is , is the dimensionless time factor, and the calculation formula is , is the correction coefficient, S is the water release coefficient of the confined aquifer, T is the hydraulic conductivity of the confined aquifer; M is the thickness of the confined aquifer, is the thickness of the aquitard, K is the permeability coefficient of the confined aquifer, is the permeability coefficient of the weak permeable layer, L is the overflow coefficient, the calculation formula is L=r / B, B is the overflow factor, the calculation formula is , The calculation formula is , y can represent the normalization of time and space parameters and is a dimensionless parameter. , J 0 is the Bessel 0th order function, r w It can characterize the radius of the well body, ,when < 0, the function is equal to 0, is a dimensionless parameter, m takes the value of (0, ∞) and the calculation formula is , is the water release coefficient of the aquitard.

[0055] According to an embodiment of the present invention, an initial control model is trained using target sample data and labels corresponding to the target sample data to obtain a target control model, including: generating an initial population using the target sample data and a preset generation strategy, wherein the initial population represents multiple initial parameters of the initial control model, and the initial parameters include an initial water conductivity, an initial overflow coefficient, and an initial water release coefficient; determining an evaluation result corresponding to the initial parameters based on a preset evaluation strategy; updating the initial population based on the evaluation result and a preset update strategy to obtain an intermediate population; repeatedly updating the intermediate population, and when the intermediate population meets preset conditions, using the intermediate population as a target population, the target population represents the target parameters corresponding to the initial parameters; and determining the target control model based on the target parameters.

[0056] According to an embodiment of the present invention, the initial water release coefficient may include an initial confined aquifer release coefficient and an initial aquitard release coefficient. The initial population may characterize any one of a plurality of initial parameters based on an intelligent algorithm, such as a comprehensive algorithm QSSA-SA that combines a Quantized Salp Swarm Algorithm (QSSA) and an annealing simulation algorithm (SA) as the basis of a deep learning model, and is initialized through a preset generation strategy to generate the population. The preset generation strategy may include random generation, generation of the initial population based on a heuristic algorithm or empirical knowledge. The hybrid algorithm (QSSA-SA) may be used to perform global optimization and local optimization on the target parameters.

[0057] In a feasible embodiment, an initial population can be randomly generated, and an initial parameter initial hydraulic conductivity T is defined.ini , initial overflow coefficient B ini , initial confined aquifer water release coefficient S ini and the initial aquitard water release coefficient S' ini The specific range is as shown in the following formula (3):

[0058] (3);

[0059] in, is the i-th parameter (T ini , B ini , S ini and S' ini ), lb and ub are the lower and upper bounds of the parameter, is a random number between [0, 1].

[0060] According to an embodiment of the present invention, a preset evaluation strategy is used to evaluate each individual / salp (initial parameter T ini , B ini , S ini and S' ini ), the evaluation result can characterize the quality of each individual, that is, the parameter quality in the parameter optimization process, can judge the quality of the parameters, and can map the actual solution to the fitness score, which is a function of the objective function value. The preset update strategy can characterize the strategy for updating the positions of the leader and follower in the population.

[0061] According to an embodiment of the present invention, the global search capability of QSSA and the fine adjustment advantage of SA can be utilized during the initial parameter optimization process through the QSSA-SA hybrid algorithm, thereby improving the optimization effect and the quality of the solution.

[0062] According to an embodiment of the present invention, the target sample data includes a first evaluation result corresponding to the sample data; determining the evaluation result corresponding to the initial parameter based on a preset evaluation strategy includes: obtaining a second evaluation result corresponding to the initial parameter; and determining the evaluation result based on the first evaluation result, the second evaluation result and the preset evaluation strategy.

[0063] According to an embodiment of the present invention, the preset evaluation strategy may also be referred to as a fitness function, and the fitness function may be specifically shown in the following formula (4):

[0064] (4);

[0065] in, is the monitoring value, is the current parameter T e , predicted values ​​of S, S' and B.

[0066] According to an embodiment of the present invention, an initial population includes multiple individuals, and each individual corresponds to an evaluation result one by one; the initial population is updated based on the evaluation result and a preset update strategy to obtain an intermediate population, including: determining an initial optimal individual from multiple individuals based on the evaluation result, wherein the initial optimal individual includes an initial local optimal individual and an initial global optimal individual; and updating the initial optimal individual using a preset update strategy so that the initial local optimal individual is associated with the initial global optimal individual to obtain an intermediate population.

[0067] According to an embodiment of the present invention, the initial global optimal individual represents the global optimal solution at different stages of optimization and updating, and the initial global optimal individual may also be referred to as the leader salp; the initial local optimal individual represents the local optimal solution at different stages of optimization and updating, and the initial local optimal individual may also be referred to as the follower salp.

[0068] In a feasible embodiment, the position of the leader salp can be updated according to the current parameter T e , S, S' and B are adjusted to guide the population to move towards a better solution, making full use of the influence of the leader in the group, so that the parameter T e , S, S' and B will obtain new values ​​in the next generation, as shown in the following formula (5):

[0069] (5);

[0070] in, is the leader position of the tth generation, is the leader position of the t+1th generation, is the coefficient controlling the step size, is the parameter range, is a random number between [0, 1].

[0071] Furthermore, the position of the follower salps can be updated to maintain the overall coordination and consistency of the population by ensuring that the followers follow the leader. e , the values ​​of S, S' and B can be adjusted by the position update formula (6).

[0072] (6);

[0073] in, is the position of the ith follower of the tth generation, is the position of the ith follower of the t+1th generation, The position of the i-1th individual in the tth generation.

[0074] According to an embodiment of the present invention, repeatedly updating the intermediate population includes: processing the intermediate population to obtain multiple discrete intervals; mapping continuous individuals in the intermediate population one by one to multiple discrete intervals to determine the mapping relationship; and updating the intermediate population based on the mapping relationship to obtain discrete values ​​corresponding to the intermediate individuals.

[0075] According to an embodiment of the present invention, by quantizing the updated individual positions, a more efficient search can be performed in the solution space. The discrete interval can represent the discrete intervals or levels into which the continuous solution space is decomposed. For each continuous parameter in the solution space, it can be mapped to the nearest discrete interval / level to obtain the corresponding discrete value, as shown in the following formula (7):

[0076] (7);

[0077] in, is the position of the i-th individual in the j-th dimension, jb is the quantization step size, Q s is the quantization level.

[0078] In a feasible embodiment, firstly, the quantization level is defined, and the continuous solution space can be divided into multiple discrete levels or intervals. For example, a certain continuous parameter value range [a, b] is divided into N discrete intervals, and the width (the number of intervals) of each discrete interval is determined by setting the corresponding quantization precision. The higher the precision, the more discrete intervals, and the higher the search precision. Then, the continuous parameter value is mapped to the corresponding discrete value. For each continuous parameter value, it is mapped to the nearest discrete level. For example, if a certain parameter value falls within the kth interval, it is quantized to the kth discrete value, 0<k≤N, k and N are both integers. It should be noted that it can ensure that the boundary cases (such as the minimum and maximum values) can be correctly mapped to the discrete levels to avoid calculation errors. Finally, when updating the individual position, the new continuous value is applied with the quantization rule to obtain the discrete value, and the continuous optimization process can be converted into a discrete operation to obtain the updated individual position.

[0079] According to an embodiment of the present invention, by quantizing individual positions, it is possible to search more efficiently in the solution space, thereby improving search accuracy and stability; at the same time, by converting the continuous solution space into a discrete solution space, the complexity of the search space can be reduced, the computing cost and consumption of system resources are reduced, and the algorithm is helped to search more efficiently in a limited discrete space.

[0080] According to an embodiment of the present invention, the method also includes: searching the neighborhood space corresponding to the initial global optimal individual, determining the initial search range of the intermediate population, and obtaining the current individual; updating the initial search range based on a simulated annealing algorithm to obtain an intermediate search range and an intermediate individual; updating the intermediate population based on the difference between the current individual and the intermediate individual and a preset difference threshold so that the intermediate population approaches the target population.

[0081] According to an embodiment of the present invention, during the fitness evaluation process, simulated annealing search can also be performed around the leader position to avoid falling into the local optimum. Through the random search mechanism of simulated annealing, a wider solution space is explored to enhance the global search capability. The new position contains the perturbed parameter T e , S, S' and B; gradually reduce the search range of the temperature control algorithm according to the annealing process, gradually transition from the initial extensive search to the later fine search, improve the convergence speed, and the temperature update affects the random perturbation amplitude in the simulated annealing search, thereby affecting the parameter T e , the adjustment range of S, S' and B, the temperature control algorithm is shown in the following formula (8):

[0082] (8);

[0083] Among them, T e is the updated temperature, T' e is the current temperature, α is the cooling coefficient, between [0, 1].

[0084] In a feasible embodiment, the new parameter T e , S, S' and B are compared with the current solution, and the acceptance probability is calculated according to the fitness difference and the current temperature to avoid the algorithm falling into the local optimum and ensure that the parameter T e , S, S' and B have the opportunity to jump out of the local optimal solution, and can decide whether to accept the new solution according to the Metropolis criterion; the greater the acceptance probability, the higher the temperature T' in the early stage of the algorithm. e Higher, even if the fitness of the new solution is worse than the current solution, there is still a higher probability of accepting the new solution, which helps the algorithm to jump out of the local optimal solution and conduct global search; the smaller the acceptance probability, the higher the temperature T' as the algorithm proceeds. e Gradually decreases, the probability of accepting a worse solution also gradually decreases, and the algorithm gradually converges to an optimal solution, as shown in the following formula (9):

[0085] (9);

[0086] Among them, P is the probability of a new solution being accepted, is the fitness difference between the new solution and the current solution.

[0087] Furthermore, the above steps are repeated, and the update and optimization are repeated until the maximum number of iterations or the convergence criterion is reached, the quality of the solution is gradually improved, the accuracy of the solution is continuously improved, and finally the optimal solution is found. The parameter T after each iteration optimization is e , S, S' and B are closer to the global optimum and can be used to e , S, S' and B are determined as target parameters.

[0088] Figure 3 A flow chart of a method for optimizing initial data based on a hybrid algorithm according to an embodiment of the present invention is shown.

[0089] like Figure 3 As shown, the method for optimizing initial data based on the QSSA-SA hybrid algorithm of this embodiment includes operations S301 to S308.

[0090] In operation S301, the population is initialized, an initial population is randomly generated, and an initial parameter T is defined. ini , B ini , S ini and S' ini range.

[0091] In operation S302, the fitness evaluation is performed by calculating the fitness of each individual (parameter T e , S, S' and B), the fitness function can be the sum of squares of the errors between the actual monitoring values ​​and the values ​​calculated by the precipitation optimization control model.

[0092] In operation S303, a leader and a follower are selected, and the leader position and the follower position are updated. The current global optimal solution is selected as the leader, and the current local optimal solution is selected as the follower. By updating the position of the leader salp, according to the parameter T e , S, S' and B are adjusted to guide the population to move towards a better solution and make full use of the influence of the leader in the group; thereby updating the position of the follower salps to ensure that the followers move with the leader. It can be understood that T e , the values ​​of S, S' and B are adjusted by the position update formula.

[0093] In operation S304, the position is quantized. By converting the continuous solution space into a discrete solution space, the search in the solution space is more efficient, thereby improving the search accuracy and stability.

[0094] In operation S305, annealing simulation search. A simulated annealing search can be performed around the leader position to avoid falling into the local optimum. Through the random search mechanism of simulated annealing, a wider solution space is explored to enhance the global search capability. The new position contains the perturbed parameter T e , S, S' and B.

[0095] In operation S306, the temperature is updated. The search range of the temperature control algorithm can be gradually reduced according to the annealing process, gradually transitioning from the initial broad search to the later fine search, improving the convergence speed. The temperature update affects the random perturbation amplitude in the simulated annealing search, thereby affecting the parameter T e , adjustment range of S, S' and B.

[0096] In operation S307, the fitness difference is calculated to determine whether to accept the new solution. e , S, S' and B are compared with the current solution, and the acceptance probability is calculated according to the fitness difference and the current temperature to avoid the algorithm falling into the local optimum and ensure that the parameter T e , S, S' and B have a chance to jump out of the local optimal solution, and can decide whether to accept the new solution according to the Metropolis criterion. If accepted, proceed to the next step, if not, return to S302.

[0097] In operation S308, the model is verified to determine whether the iterative update reaches the maximum number of iterations or the convergence criterion. If the accuracy of the prediction result of the intermediate control model meets the preset accuracy threshold, the intermediate control model is determined as the target control model.

[0098] According to an embodiment of the present invention, the method also includes: obtaining initial hydrological data, initial soil data and initial well data corresponding to the foundation pit; using a weighted average algorithm to fuse the initial hydrological data, initial soil data and initial well data to obtain a fusion result; comparing the fusion result with the expected result to determine abnormal data; and processing the abnormal data to obtain hydrological data, soil data and well data.

[0099] According to an embodiment of the present invention, initial data (initial hydrological data, initial soil data and initial well data) can be obtained through a data acquisition device. Considering that different data sources affect the accuracy of data calculation results, the initial data is processed through data fusion to obtain a fusion result, which can include: first performing data standardization processing, standardizing the hydrological data, soil data and well data to ensure that the scales of different data are consistent; secondly, defining weights of different types of data, and defining weights for each data type. Weights can be assigned according to their importance or credibility to the final result. For example, the weight of hydrological data may be 0.4, the weight of soil data is 0.3, and the weight of well data is 0.3; then, a weighted average is calculated for each data point to obtain a weighted fusion result; further, the fusion result can be compared with the expected result (determined based on experience or actual monitoring values) to determine abnormal data, and the abnormal data can be eliminated to obtain hydrological data, soil data and well data.

[0100] In a feasible embodiment, the initial data may also include images of the foundation pit area, and these images are corresponded to sampling time points; the initial data may be converted into collated data reflecting the precipitation and settlement characteristics of the foundation pit according to the measurement principles and related formulas of different acquisition devices, and stored in a database; the database may include a cloud storage system and a local storage device, support remote access, backup and recovery of data, ensure efficient reading and writing of data, and provide data encryption and access control functions.

[0101] In a feasible embodiment, clustering algorithms and principal component analysis (PCA) can be used to reduce the dimension and extract features of multi-source data based on the data collected at each different monitoring point, thereby achieving efficient data classification processing; for water level control results, foundation pit dewatering and settlement data can be displayed in a graphical manner, including displaying the time series changes of each measuring point and multi-point comparative distribution maps, providing real-time update and interactive functions to help engineering personnel make quick decisions.

[0102] According to an embodiment of the present invention, by fusing the initial data from different data sources, the noise and errors that may exist in a single data source can be reduced, thereby improving the accuracy of the overall data; combining data from different sources can fill the gaps in a single data source, providing more comprehensive information while reducing dependence on a single data source, further improving the accuracy of the results.

[0103] Figure 4 A schematic diagram of a site cross section of foundation pit dewatering based on the well storage effect of a leaking aquifer according to an embodiment of the present invention is shown.

[0104] like Figure 4 As shown, the soil corresponding to the foundation pit 401 includes a confined water layer, a weakly permeable layer and a phreatic layer from bottom to top. Different permeable layers have different permeabilities and water storage capacities, which leads to overflow. In the absence of precipitation treatment, the water level line (natural water level line) in the phreatic layer is high and cannot meet the requirements of foundation pit excavation. The natural water level line in the phreatic layer is precipitated by using a pumping well 402, and the water level line in the phreatic layer can be observed through an observation well to meet the requirements of foundation pit excavation. At the same time, monitoring or measuring instruments are used to monitor and predict the surface settlement in real time.

[0105] Figure 5 A schematic diagram showing comparison between a predicted value of a water level control result obtained based on a target control model and an actual monitored value according to an embodiment of the present invention is shown.

[0106] like Figure 5As shown, the hydrological data, soil data and well data of three target points (observation point G11-4, observation point G11-5 and observation point G11-7) can be arbitrarily selected and input into the target control model to obtain the target water level control result, and compared with the actual observation value. It can be seen that the target water level control result (calculated value) obtained by the target control model of the present invention is closer to the actual observation value, and the prediction accuracy of the target control model in the present invention meets the actual engineering needs.

[0107] Based on the above-mentioned foundation pit dewatering control method based on the well storage effect of the overflowing aquifer, the present invention also provides a foundation pit dewatering control device based on the well storage effect of the overflowing aquifer. Figure 6 The device is described in detail.

[0108] Figure 6 A structural block diagram of a foundation pit dewatering control device based on the well storage effect of a leaking aquifer according to an embodiment of the present invention is shown.

[0109] like Figure 6 As shown, the foundation pit dewatering control device based on the well storage effect of the overflowing aquifer in this embodiment includes a data acquisition module 610 and a control result output module 620.

[0110] The data acquisition module 610 is used to acquire hydrological data, soil data and well data corresponding to the foundation pit, wherein the hydrological data includes permeable layer data and impermeable layer data. In one embodiment, the data acquisition module 610 can be used to perform the operation S210 described above, which will not be described in detail here.

[0111] The control result output module 620 is used to input the permeable layer data, the impermeable layer data, the soil data and the well body data into the target control model, and output the target water level control result of the foundation pit, wherein the target water level control result represents the distance value between the water level of the target point and the initial water level. In one embodiment, the control result output module 620 can be used to perform the operation S220 described above, which will not be repeated here.

[0112] According to an embodiment of the present invention, the target control model is trained by the following operations: obtaining initial sample data and initial water level control results; determining target sample data using the initial water level control results and the initial sample data; and training the initial control model using the target sample data and labels corresponding to the target sample data to obtain the target control model.

[0113] According to an embodiment of the present invention, through the data acquisition module 610 and the control result output module 620 in the foundation pit dewatering control device based on the well storage effect of the overflowing aquifer, for the foundation pit with the overflowing aquifer, the target water level control result of the foundation pit is obtained by combining the hydrological data, soil data and well data received in real time, using the target control model, so as to realize dynamic adjustment and real-time response to the change of the foundation pit water level, ensure that the water level is within the standard range during the construction process, and avoid the defects of low accuracy and real-time performance of manual regular monitoring; due to the use of the target control model, the dewatering scheme and dewatering amount can be optimized in real time, unnecessary pumping can be reduced, resource utilization efficiency can be improved, and construction costs can be reduced; by accurately controlling the foundation pit water level, the project quality problems caused by water level fluctuations can be effectively reduced, thereby improving the overall quality and stability of the project. At the same time, scientific and reasonable water level control can reduce construction delays caused by water level problems, thereby shortening the foundation pit construction period and time cost.

[0114] According to an embodiment of the present invention, the well data includes a pumping rate, and the device further includes: a pumping rate updating module for updating the pumping rate according to a target water level control result so that the target water level control result meets preset standard data.

[0115] According to an embodiment of the present invention, soil data includes permeable layer thickness data, impermeable layer thickness data and permeability coefficient, and hydrological data includes water release coefficient and time data; the control result output module includes: a water conductivity determination submodule and a result output submodule.

[0116] The hydraulic conductivity determination submodule is used to determine the hydraulic conductivity based on the permeability coefficient and the permeable layer thickness data.

[0117] The result output submodule is used to input the pumping rate, permeable layer thickness data, impermeable layer thickness data, permeability coefficient, hydraulic conductivity coefficient, water release coefficient, and time data into the target control model and output the target water level control result.

[0118] According to an embodiment of the present invention, an initial control model is trained using target sample data and labels corresponding to the target sample data to obtain a target control model, including: generating an initial population using the target sample data and a preset generation strategy, wherein the initial population represents multiple initial parameters of the initial control model, and the initial parameters include an initial water conductivity, an initial overflow coefficient, and an initial water release coefficient; determining an evaluation result corresponding to the initial parameters based on a preset evaluation strategy; updating the initial population based on the evaluation result and a preset update strategy to obtain an intermediate population; repeatedly updating the intermediate population, and when the intermediate population meets preset conditions, using the intermediate population as a target population, the target population represents the target parameters corresponding to the initial parameters; and determining the target control model based on the target parameters.

[0119] According to an embodiment of the present invention, the target sample data includes a first evaluation result corresponding to the sample data; determining the evaluation result corresponding to the initial parameter based on a preset evaluation strategy includes: obtaining a second evaluation result corresponding to the initial parameter; and determining the evaluation result based on the first evaluation result, the second evaluation result and the preset evaluation strategy.

[0120] According to an embodiment of the present invention, an initial population includes multiple individuals, and each individual corresponds to an evaluation result one by one; the initial population is updated based on the evaluation result and a preset update strategy to obtain an intermediate population, including: determining an initial optimal individual from multiple individuals based on the evaluation result, wherein the initial optimal individual includes an initial local optimal individual and an initial global optimal individual; and updating the initial optimal individual using a preset update strategy so that the initial local optimal individual is associated with the initial global optimal individual to obtain an intermediate population.

[0121] According to an embodiment of the present invention, repeatedly updating the intermediate population includes: processing the intermediate population to obtain multiple discrete intervals; mapping continuous individuals in the intermediate population one by one to multiple discrete intervals to determine the mapping relationship; and updating the intermediate population based on the mapping relationship to obtain discrete values ​​corresponding to the intermediate individuals.

[0122] According to an embodiment of the present invention, the method also includes: searching the neighborhood space corresponding to the initial global optimal individual, determining the initial search range of the intermediate population, and obtaining the current individual; updating the initial search range based on a simulated annealing algorithm to obtain an intermediate search range and an intermediate individual; updating the intermediate population based on the difference between the current individual and the intermediate individual and a preset difference threshold so that the intermediate population approaches the target population.

[0123] According to an embodiment of the present invention, the device further includes: an initial data acquisition module, a fusion processing module, an abnormal data determination module and an abnormal data processing module.

[0124] The initial data acquisition module is used to obtain the initial hydrological data, initial soil data and initial well data corresponding to the foundation pit; the fusion processing module is used to fuse the initial hydrological data, initial soil data and initial well data using a weighted average algorithm to obtain a fusion result; the abnormal data determination module is used to compare the fusion result with the expected result to determine the abnormal data; and the abnormal data processing module is used to process the abnormal data to obtain hydrological data, soil data and well data.

[0125] According to an embodiment of the present invention, any multiple modules in the data acquisition module 610 and the control result output module 620 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present invention, at least one of the data acquisition module 610 and the control result output module 620 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware and firmware or in any appropriate combination of any of them. Alternatively, at least one of the data acquisition module 610 and the control result output module 620 can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be executed.

[0126] Figure 7 A block diagram of an electronic device suitable for implementing a foundation pit dewatering control method based on the well storage effect of a leaking aquifer according to an embodiment of the present invention is shown.

[0127] like Figure 7 As shown, the electronic device according to an embodiment of the present invention includes a processor 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 to a random access memory (RAM) 703. The processor 701 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 701 may also include an onboard memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present invention.

[0128] In RAM 703, various programs and data required for the operation of the electronic device are stored. The processor 701, ROM 702 and RAM 703 are connected to each other via a bus 704. The processor 701 performs various operations of the method flow according to the embodiment of the present invention by executing the programs in ROM 702 and / or RAM 703. It should be noted that the program can also be stored in one or more memories other than ROM 702 and RAM 703. The processor 701 can also perform various operations of the method flow according to the embodiment of the present invention by executing the programs stored in the one or more memories.

[0129] According to an embodiment of the present invention, the electronic device may further include an input / output (I / O) interface 705, which is also connected to the bus 704. The electronic device may further include one or more of the following components connected to the input / output (I / O) interface 705: an input portion 706 including a keyboard, a mouse, etc.; an output portion 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 708 including a hard disk, etc.; and a communication portion 709 including a network interface card such as a LAN card, a modem, etc. The communication portion 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the input / output (I / O) interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage portion 708 as needed.

[0130] The present invention also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiment; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present invention is implemented.

[0131] According to an embodiment of the present invention, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, it may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present invention, the computer-readable storage medium may include the ROM 702 and / or RAM 703 described above and / or one or more memories other than ROM 702 and RAM 703.

[0132] The embodiment of the present invention also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the foundation pit dewatering control method based on the well storage effect of the overflowing aquifer provided by the embodiment of the present invention.

[0133] The computer program executes the above functions defined in the system / device of the embodiment of the present invention when it is executed by the processor 701. According to the embodiment of the present invention, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0134] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 709, and / or installed from the removable medium 711. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0135] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the processor 701, the above functions defined in the system of the embodiment of the present invention are performed. According to the embodiment of the present invention, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.

[0136] According to an embodiment of the present invention, the program code for executing the computer program provided by the embodiment of the present invention can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0137] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0138] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present invention may be combined or coupled in various ways, even if such combinations or couplings are not explicitly described in the present invention. In particular, the features described in the various embodiments and / or claims of the present invention may be combined or coupled in various ways without departing from the spirit and teachings of the present invention. All such combinations and / or couplings fall within the scope of the present invention.

[0139] The embodiments of the present invention are described above. However, these embodiments are only for the purpose of illustration, and are not intended to limit the scope of the present invention. Although each embodiment is described above, it does not mean that the measures in each embodiment cannot be used in combination. The scope of the present invention is defined by the attached claims and their equivalents. Without departing from the scope of the present invention, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present invention.

Claims

1. A foundation pit dewatering control method based on the well storage effect of the overflowing aquifer, characterized in that: include: Acquire hydrological data, soil data and well data corresponding to the foundation pit, wherein the hydrological data includes permeable layer data and non-permeable layer data; Inputting the permeable layer data, the impermeable layer data, the soil data and the well body data into a target control model, and outputting a target water level control result of the foundation pit, wherein the target water level control result represents a distance value between the water level of the target point and the initial water level; The target control model is trained by the following operations: Obtain initial sample data and initial water level control results; determining target sample data using the initial water level control result and the initial sample data; and Using the target sample data and the labels corresponding to the target sample data to train an initial control model to obtain the target control model; The target control model is shown in the following formula (2): （2）； in, It represents the distance between the water level after dewatering and the natural water level at the target time t at a distance r from the center of the well body. Q is the pumping rate. is the time factor, and the calculation formula is , is the dimensionless time factor, and the calculation formula is , is the correction coefficient, S is the water release coefficient of the confined aquifer, T is the hydraulic conductivity of the confined aquifer; M is the thickness of the confined aquifer, is the thickness of the aquitard, K is the permeability coefficient of the confined aquifer, is the permeability coefficient of the weak permeable layer, L is the overflow coefficient, the calculation formula is L=r / B, B is the overflow factor, the calculation formula is , The calculation formula is , y represents the normalization of time and space parameters and is a dimensionless parameter. , J0 is Bessel's 0th order function, r w Characterizes the radius of the well body, ,when < 0, the function is equal to 0, is a dimensionless parameter, m takes the value of (0, ∞) and the calculation formula is , is the water release coefficient of the aquitard.

2. The method according to claim 1, characterized in that The well data includes a pumping rate, and the method further includes: The pumping rate is updated according to the target water level control result so that the target water level control result meets the preset standard data.

3. The method according to claim 2, characterized in that The soil data include the thickness data of the permeable layer, the thickness data of the impermeable layer and the permeability coefficient, and the hydrological data include the water release coefficient and time data; The permeable layer data, the impermeable layer data, the soil body data and the well body data are input into the target control model, and the target water level control result of the foundation pit is output, including: Determine the hydraulic conductivity according to the hydraulic conductivity and the thickness data of the permeable layer; as well as The pumping rate, the permeable layer thickness data, the impermeable layer thickness data, the permeability coefficient, the water conductivity coefficient, the water release coefficient, and the time data are input into the target control model, and the target water level control result is output.

4. The method according to claim 1, characterized in that Using the target sample data and the labels corresponding to the target sample data to train an initial control model to obtain the target control model includes: Generate an initial population using the target sample data and a preset generation strategy, wherein the initial population represents a plurality of initial parameters of the initial control model, the initial parameters including an initial hydraulic conductivity, an initial leakage coefficient, and an initial water release coefficient; Determine an evaluation result corresponding to the initial parameter based on a preset evaluation strategy; Based on the evaluation result and a preset update strategy, the initial population is updated to obtain an intermediate population; Repeatingly updating the intermediate population, and when the intermediate population meets a preset condition, taking the intermediate population as a target population, wherein the target population represents a target parameter corresponding to the initial parameter; and The target control model is determined based on the target parameter.

5. The method according to claim 4, characterized in that The target sample data includes a first evaluation result corresponding to the sample data; Determining an evaluation result corresponding to the initial parameter based on a preset evaluation strategy includes: Obtaining a second evaluation result corresponding to the initial parameter; as well as The evaluation result is determined based on the first evaluation result, the second evaluation result and the preset evaluation strategy.

6. The method according to claim 4, characterized in that The initial population includes a plurality of individuals, and the individuals correspond to the evaluation results one by one; The initial population is updated based on the evaluation result and a preset update strategy to obtain an intermediate population, including: Determining an initial optimal individual from the plurality of individuals based on the evaluation result, wherein the initial optimal individual includes an initial local optimal individual and an initial global optimal individual; and The initial optimal individual is updated by using the preset update strategy so that the initial local optimal individual is associated with the initial global optimal individual to obtain the intermediate population.

7. The method according to claim 4, characterized in that Repeatedly updating the intermediate population includes: Processing the intermediate population to obtain a plurality of discrete intervals; and Mapping the continuous individuals in the intermediate population to the plurality of discrete intervals one by one to determine a mapping relationship; and The intermediate population is updated based on the mapping relationship to obtain discrete values ​​corresponding to the intermediate individuals.

8. The method according to claim 6, characterized in that The method further comprises: Searching the neighborhood space corresponding to the initial global optimal individual, determining the initial search range of the intermediate population, and obtaining the current individual; The initial search range is updated based on a simulated annealing algorithm to obtain an intermediate search range and an intermediate individual; The intermediate population is updated based on the difference between the current individual and the intermediate individual and a preset difference threshold, so that the intermediate population approaches the target population.

9. The method according to claim 1, characterized in that: The method further comprises: Acquiring initial hydrological data, initial soil data and initial well data corresponding to the foundation pit; The initial hydrological data, the initial soil data and the initial well data are fused by using a weighted average algorithm to obtain a fusion result; Comparing the fusion result with the expected result to determine abnormal data; and The abnormal data is processed to obtain the hydrological data, the soil data and the well data.

10. A foundation pit dewatering control device based on the well storage effect of the overflowing aquifer, characterized in that: include: A data acquisition module, used to acquire hydrological data, soil data and well data corresponding to the foundation pit, wherein the hydrological data includes permeable layer data and non-permeable layer data; A control result output module, used for inputting the permeable layer data, the impermeable layer data, the soil data and the well body data into a target control model, and outputting a target water level control result of the foundation pit, wherein the target water level control result represents a distance value between the water level of the target point and the initial water level; The target control model is trained by the following operations: Obtain initial sample data and initial water level control results; determining target sample data using the initial water level control result and the initial sample data; and Using the target sample data and the labels corresponding to the target sample data to train an initial control model to obtain the target control model; The target control model is shown in the following formula (2): （2）； in, It represents the distance between the water level after dewatering and the natural water level at the target time t at a distance r from the center of the well body. Q is the pumping rate. is the time factor, and the calculation formula is , is the dimensionless time factor, and the calculation formula is , is the correction coefficient, S is the water release coefficient of the confined aquifer, T is the hydraulic conductivity of the confined aquifer; M is the thickness of the confined aquifer, is the thickness of the aquitard, K is the permeability coefficient of the confined aquifer, is the permeability coefficient of the weak permeable layer, L is the overflow coefficient, the calculation formula is L=r / B, B is the overflow factor, the calculation formula is , The calculation formula is , y represents the normalization of time and space parameters and is a dimensionless parameter. , J0 is Bessel's 0th order function, r w Characterizes the radius of the well body, ,when < 0, the function is equal to 0, is a dimensionless parameter, m takes the value of (0, ∞) and the calculation formula is , is the water release coefficient of the aquitard.

Images