Existing building deformation risk assessment method and device

Abstract

The invention provides an existing building deformation risk assessment method and device which can be applied to the technical field of tunnel engineering and building engineering. The evaluation method comprises the following steps: acquiring tunnel data, and soil mass data and settlement range data corresponding to a new tunnel; inputting the tunnel data, the soil mass data and the settlement range data into a prediction model to obtain settlement results corresponding to the plurality of measuring points; and determining a risk assessment result of the to-be-assessed building based on the settlement result, the to-be-assessed building data and the settlement range data. The prediction model is obtained by training the following operations: constructing an initial prediction model by using sample tunnel data, sample soil body data, sample measuring point data and a plurality of initial parameters; updating the plurality of initial parameters based on the plurality of updating strategies to obtain a plurality of target parameters; and updating the initial prediction model by using the plurality of target parameters to obtain a prediction model. According to the method, the accuracy of a building risk assessment result can be improved, and the consumption of system resources is reduced.

Description

Technical Field

[0001] The invention relates to the technical field of tunnel engineering and construction engineering, and in particular to a method and device for evaluating deformation risk of existing buildings. Background Art

[0002] During the excavation of a new tunnel, ground disturbance will cause varying degrees of surface settlement, which will cause structural deformation or damage to nearby buildings, especially under complex geological conditions, and have a significant impact on the safety of buildings. In related technologies, the prediction methods for the impact of new tunnel construction on building safety mainly include monitoring whether the tunnel construction process causes uneven settlement or tilt of buildings through monitoring equipment (such as settlement markers, crack meters, etc.); or using numerical models to calculate the potential risks of tunnel construction to surrounding buildings.

[0003] The inventors found that the monitoring equipment used in related technologies requires continuous tracking and monitoring, and it is difficult to make a comprehensive assessment of building safety relying solely on settlement data; traditional prediction models lack consideration of existing building information, and the correlation between surface settlement and building deformation is low, resulting in low accuracy of actual prediction results. Traditional prediction models have overfitting problems during training, and the calculation process is cumbersome and complicated, resulting in large consumption of system computing resources. Summary of the invention

[0004] In view of the above problems, the present invention provides a method, device, equipment, medium and program product for evaluating the deformation risk of an existing building.

[0005] According to a first aspect of the present invention, there is provided a method for assessing deformation risk of an existing building, comprising: acquiring tunnel data, soil data and settlement range data corresponding to a newly constructed tunnel, wherein the tunnel data comprises tunnel geometry data and deformation data; inputting the tunnel data, soil data and settlement range data into a prediction model to obtain settlement results corresponding to a plurality of measuring points; determining risk assessment results of the building to be assessed based on the settlement results, data of the building to be assessed and settlement range data; wherein the prediction model is obtained by training through the following operations: constructing an initial prediction model using sample tunnel data, sample soil data, sample measuring point data and a plurality of initial parameters; updating the plurality of initial parameters based on a plurality of update strategies to obtain a plurality of target parameters, wherein the plurality of update strategies comprise a global update strategy and a local update strategy; and updating the initial prediction model using the plurality of target parameters to obtain a prediction model.

[0006] The second aspect of the present invention provides an assessment device for deformation risk of existing buildings, comprising: a data acquisition module for acquiring tunnel data, soil data corresponding to a newly built tunnel, and settlement range data, wherein the tunnel data includes tunnel geometry data and deformation data; a data input module for inputting tunnel data, soil data, and settlement range data into a prediction model to obtain settlement results corresponding to multiple measuring points; an assessment result determination module for determining risk assessment results of a building to be assessed based on the settlement results, data of the building to be assessed, and settlement range data; wherein the prediction model is obtained by training through the following operations: constructing an initial prediction model using sample tunnel data, sample soil data, sample measuring point data, and multiple initial parameters; updating multiple initial parameters based on multiple update strategies to obtain multiple target parameters, wherein the multiple update strategies include a global update strategy and a local update strategy; and updating the initial prediction model using multiple target parameters to obtain a prediction 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 computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the above method.

[0008] The fourth aspect of the present invention further provides a computer-readable storage medium on which a computer program or instruction is stored, and the steps of the above method are implemented when the above computer program or instruction is executed by a processor.

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

[0010] According to the method, device, equipment, medium and program product for evaluating deformation risk of existing buildings provided by the embodiments of the present invention, the correlation between surface settlement and building deformation risk prediction is improved by integrating the settlement results and settlement range data corresponding to multiple measuring points on the surface in a newly built shield tunnel with the building data to be evaluated, so that the accuracy of building risk assessment results is higher. Since the target parameters are updated based on the global update strategy and the local update strategy, the overfitting problem of the traditional prediction model is avoided, the generalization ability of the model is improved, the consumption of system resources is reduced, and the complex engineering problems in practical applications are further met. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The above contents 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 1An application scenario diagram showing the method, device, equipment, medium and program product for assessing deformation risk of existing buildings according to an embodiment of the present invention is shown;

[0013] Figure 2 A flow chart showing a method for assessing deformation risk of an existing building according to an embodiment of the present invention is shown;

[0014] Figure 3 A schematic diagram showing the arrangement of measuring points for settlement monitoring corresponding to shield tunnel excavation according to an embodiment of the present invention is shown;

[0015] Figure 4 A schematic diagram of prediction results based on a prediction model, case 1 and case 2 according to an embodiment of the present invention is shown;

[0016] Figure 5 It shows a structural block diagram of an existing building deformation risk assessment device according to an embodiment of the present invention;

[0017] Figure 6 A block diagram of an electronic device suitable for implementing a method for evaluating deformation risk of an existing building according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.).

[0022] In the process of conceiving the present invention, the inventors found that in the related technology, the equipment monitoring method requires the continuous use of equipment to track and monitor buildings and tunnels, and it is difficult to make a comprehensive assessment of building safety by relying solely on settlement data; the traditional prediction model lacks consideration of the existing building's own data, and the correlation between surface settlement and building deformation is low, resulting in low accuracy of actual prediction results. The traditional prediction model has an overfitting problem during the training process, and the calculation process is cumbersome and complicated, resulting in a large consumption of system computing resources.

[0023] In view of this, the present invention improves the correlation between surface settlement and building deformation risk prediction by integrating the settlement results corresponding to multiple measuring points on the surface in a newly built shield tunnel, the settlement range data and the building data to be assessed, so as to make the building risk assessment results more accurate. Since the target parameters are updated based on the global update strategy and the local update strategy, the overfitting problem of the traditional prediction model is avoided, the generalization ability of the model is improved, the consumption of system resources is reduced, and the complex engineering problems in practical applications are further met.

[0024] An embodiment of the present invention provides an assessment method for deformation risk of an existing building, the assessment method comprising: obtaining tunnel data, soil data and settlement range data corresponding to a newly constructed tunnel, wherein the tunnel data comprises tunnel geometry data and deformation data; inputting the tunnel data, soil data and settlement range data into a prediction model to obtain settlement results corresponding to a plurality of measuring points; determining risk assessment results of the building to be assessed based on the settlement results, data of the building to be assessed and settlement range data; wherein the prediction model is obtained by training through the following operations: constructing an initial prediction model using sample tunnel data, sample soil data, sample measuring point data and a plurality of initial parameters; updating the plurality of initial parameters based on a plurality of update strategies to obtain a plurality of target parameters, wherein the plurality of update strategies comprise a global update strategy and a local update strategy; and updating the initial prediction model using the plurality of target parameters to obtain a prediction model.

[0025] Figure 1 A diagram showing an application scenario of an existing building deformation risk assessment method, device, equipment, medium, and program product according to an embodiment of the present invention.

[0026] like Figure 1As 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.

[0027] The data acquisition device 106 may include different types of settlement sensors, test equipment, and measurement equipment. For example, surface settlement and settlement change data can be collected using optical fiber sensors and laser radars. For example, relevant data of the soil body can be measured using triaxial test equipment. For example, the range data or area data of the area to be monitored can be measured using a measurement device. The data acquisition device 106 can be connected to the server 105 through the network 104 to send the settlement data to the server 105 for corresponding processing. It can be understood that the type of settlement sensor can be determined according to actual conditions and is not limited here.

[0028] The user can use 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 can 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).

[0029] 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.

[0030] 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.

[0031] It should be noted that the method for assessing deformation risk of existing buildings provided in the embodiment of the present invention can generally be executed by the server 105. Accordingly, the device for assessing deformation risk of existing buildings provided in the embodiment of the present invention can generally be set in the server 105. The method for assessing deformation risk of existing buildings 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 device for assessing deformation risk of existing buildings 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.

[0032] 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.

[0033] Figure 2 A flow chart of a method for assessing deformation risk of an existing building according to an embodiment of the present invention is shown.

[0034] like Figure 2 As shown, the method for assessing deformation risk of an existing building in this embodiment may include operations S210 to S230.

[0035] In operation S210, tunnel data, soil data corresponding to the newly built tunnel, and settlement range data are acquired, wherein the tunnel data includes tunnel geometry data and deformation data.

[0036] In an embodiment of the present invention, different types of data acquisition equipment may be used to collect tunnel data, soil data and settlement range data. The soil data may include strength data of the soil within the settlement range. The deformation data may characterize volume deformation-related data of the tunnel. The settlement range data may characterize a settlement monitoring area corresponding to a newly built shield tunnel construction area where there may be a settlement risk.

[0037] In operation S220, tunnel data, soil data, and settlement range data are input into a prediction model to obtain settlement results corresponding to a plurality of measuring points.

[0038] In an embodiment of the present invention, the prediction model can be a model that meets the preset prediction accuracy obtained by training the initial prediction model, and can be used to predict the settlement values ​​of the measuring points at different horizontal distances from the axis of the newly built tunnel. The measuring points can be multiple monitoring points arranged on the surface within the settlement range. The arrangement of the monitoring points can be determined according to the demand for data volume and the actual engineering situation, and is not limited here. The settlement result can be the settlement value of the elevation comparison of the measuring points before and after tunnel excavation for different measuring points.

[0039] In operation S230, a risk assessment result of the building to be assessed is determined based on the settlement result, the building data to be assessed, and the settlement range data.

[0040] In an embodiment of the present invention, the building data to be evaluated may represent building-related data with deformation risk in the vicinity of a newly built tunnel. The risk assessment result may represent the degree of deformation of the building to be evaluated during or after tunnel excavation, which may be represented by different deformation levels.

[0041] Preferably, the prediction model is obtained through the following training operations, and the training operations include operations S221 to S223.

[0042] In operation S221, an initial prediction model is constructed using sample tunnel data, sample soil data, sample measurement point data, and a plurality of initial parameters.

[0043] In operation S222, the multiple initial parameters are updated based on multiple update strategies to obtain multiple target parameters, wherein the multiple update strategies include a global update strategy and a local update strategy.

[0044] In operation S223, the initial prediction model is updated using multiple target parameters to obtain a prediction model.

[0045] In an embodiment of the present invention, the sample data may include sample tunnel data, sample soil data and sample measurement point data. The sample data may be sample data related to the newly built tunnel acquired by a data acquisition device in a historical period, and may be used to construct an initial prediction model.

[0046] In an embodiment of the present invention, the global update strategy may represent a subtraction mean optimization algorithm that uses the subtraction mean of multiple agents to update the positions of population members in the search space. The local update strategy may represent a local reinforcement optimization algorithm. The global update strategy may be combined with the local update strategy, and the combined update strategy may be used to update multiple initial parameters in the initial prediction model to obtain multiple target parameters, and then the target parameters are substituted into the initial prediction model to obtain a prediction model that meets the prediction accuracy.

[0047] In a feasible embodiment, after obtaining tunnel data, soil data corresponding to the newly built tunnel and settlement range data, considering the large amount of data and the impact on calculation efficiency, various data can be processed through data processing technology, including data key feature extraction, data segmentation and data dimensionality reduction.

[0048] For example, extract the features that contribute most to the prediction from various raw data (such as extracting the soil pressure change rate based on soil information) to reduce the dimension of the data and improve the calculation efficiency. It can be understood that the data acquired by the data acquisition device is time series data. For time series data, time series analysis methods (such as autoregressive moving average model, autoregressive integrated moving average model) can be used for preprocessing to extract trend component data, thereby capturing the changing patterns of the data. For long time series data, it can be processed in segments, and each segment of data can be preprocessed and modeled separately to reduce the amount of data processed at a single time and improve calculation efficiency. Through the above data processing method, the complexity and amount of calculation of the data can be effectively reduced, while improving the accuracy and reliability of prediction.

[0049] According to an embodiment of the present invention, by integrating the settlement results corresponding to multiple measuring points on the surface in a newly built shield tunnel, the settlement range data and the building data to be assessed, the correlation between surface settlement and building deformation risk prediction is improved, so that the accuracy of building risk assessment results is higher. Since the target parameters are updated based on the global update strategy and the local update strategy, the overfitting problem of the traditional prediction model is avoided, the generalization ability of the model is improved, the consumption of system resources is reduced, and the complex engineering problems in practical applications are further met.

[0050] Figure 3 A schematic diagram of measuring point arrangement for settlement monitoring corresponding to shield tunnel excavation according to an embodiment of the present invention is shown.

[0051] like Figure 3 As shown in the figure, the surface settlement that occurs during the excavation of the new tunnel 31 poses a risk of settlement and deformation to the existing building 32. By obtaining tunnel data corresponding to the new tunnel, such as the tunnel diameter D, the distance z0 from the center of the tunnel to the ground surface; settlement range data, such as the range and total width 2w of the settlement trough, and soil data corresponding to multiple measuring points 33, the above data are input into the prediction model to obtain the settlement results corresponding to the multiple measuring points 33, including the maximum settlement value S(x) max ; Based on the settlement results and the length L of the building to be evaluated b and settlement range data (settlement tank data) to determine the risk assessment results for the building to be assessed.

[0052] According to an embodiment of the present invention, the method further comprises: determining settlement range data based on tunnel geometry data and soil data.

[0053] In an embodiment of the present invention, the tunnel geometry data may include the diameter of the newly built tunnel and the distance from the center line of the newly built tunnel to the ground surface. The settlement range may be regarded as the range of the settlement trough corresponding to the newly built tunnel (shield tunnel) where there is a risk of surface settlement. The settlement trough may be calculated based on the diameter of the newly built tunnel in the tunnel geometry data and the strength data of the soil (e.g., internal friction angle).

[0054] For example, the internal friction angle of the soil is recorded as φ, the diameter of the new tunnel is recorded as D, and the distance from the center line of the new tunnel to the ground surface is recorded as z0. On this basis, the width w of the settlement trough is calculated as shown in the following formula (1):

[0055] (1);

[0056] Wherein, w can represent the width of the sedimentation tank. It can be understood that the total width of the sedimentation tank is 2w.

[0057] According to an embodiment of the present invention, the settlement result includes a maximum settlement value corresponding to a measuring point;

[0058] Based on the settlement results, the data of the building to be assessed and the settlement range data, the risk assessment results of the building to be assessed are determined, including: using the maximum settlement value, the data of the building to be assessed and the settlement range data to determine the deformation results of the building to be assessed; mapping the deformation results to the risk level data set to determine the risk assessment results.

[0059] In an embodiment of the present invention, the settlement result includes settlement values ​​corresponding to each of the multiple measuring points, including a maximum settlement value and a minimum settlement value. The building to be evaluated includes the length of the building. The deformation result is proportional to the deformation degree of the building. Taking the maximum settlement value as the center point, the deformation result of the adjacent building can be calculated, and the deformation result can characterize the change in the relative angle between different parts of the building. The risk level data set can characterize the significance correspondence between the building deformation result and the building deformation degree, and the determined building deformation degree is used as the risk assessment result of the building to be evaluated.

[0060] For example, the deformation result is recorded as ψ, which can be calculated by the following formula (2):

[0061] (2);

[0062] Among them, S(x) max It can represent the maximum settlement value, x can represent the center point corresponding to the maximum settlement value, L b It can represent the length of the building to be evaluated, and w can represent the width of the sedimentation tank.

[0063] In an embodiment of the present invention, the deformation degree of a building can be divided into different levels, and the relationship between the deformation result of the building and the deformation degree level of the building can be shown in Table 1 below.

[0064] Table 1

[0065]

[0066] According to an embodiment of the present invention, multiple initial parameters are updated based on multiple update strategies to obtain multiple target parameters, including: determining initial values ​​and target functions corresponding to the initial parameters; updating the initial values ​​based on a global update strategy and the target function to obtain a global target value; and determining the target parameters based on the global target value and a local update strategy.

[0067] In an embodiment of the present invention, the initial parameters of the initial prediction model include multiple ones. The initial values ​​corresponding to each of the multiple initial parameters can be determined based on experience or initialization strategy. The objective function can be constructed based on the model prediction value and the actual monitoring value corresponding to the initial parameters. The global target value corresponding to the initial parameters can be obtained by using the global update strategy, and on this basis, the global target value is updated and optimized by using the local update strategy to obtain the target parameter that meets the convergence condition.

[0068] In an embodiment of the present invention, an initial prediction model can be constructed using sample tunnel data, sample soil data, sample measurement point data and a plurality of initial parameters. The initial prediction model is denoted as S(x). The initial prediction model is shown in the following formula (3):

[0069] (3);

[0070] Among them, x can represent the horizontal distance between the measuring point x and the central axis of the new tunnel, V L can characterize the volume change rate of the tunnel, D can characterize the diameter of the new tunnel, φ can characterize the internal friction angle of the soil, and A and B can characterize the initial parameters of the initial prediction model.

[0071] For example, taking the subtraction-average-based optimizer (SABO) as the global update strategy and the partial reinforcement optimizer (PRO) as the local update strategy as an example, the SABO algorithm can be combined with the PRO algorithm, and the advantages of the two algorithms can be combined using a hybrid algorithm (SABO-PRO algorithm) to obtain a strategy with global and local dual optimization. Through the SABO algorithm, a wide search is first performed in the entire parameter space to prevent falling into the local optimal solution, and then the PRO algorithm is used to make local fine adjustments to the candidate solutions based on the global search in order to better adapt to the specific optimization objectives and obtain the target parameters.

[0072] According to an embodiment of the present invention, the SABO-PRO hybrid optimization algorithm combines the advantages of the subtraction average optimization algorithm (SABO) and the local enhancement optimization algorithm (PRO), and can effectively balance the global search and local refined optimization. SABO is responsible for global search to avoid falling into the local optimal solution, while PRO improves the quality of the solution through fine adjustment. When dealing with complex optimization problems, the hybrid algorithm saves the consumption of computing resources in the model training process, and further improves the accuracy of the solution and the optimization efficiency.

[0073] It can be understood that the above has explained the update of the initial parameters based on the global update strategy and the local update strategy. The following will further explain how to use the global update strategy to obtain the global target value.

[0074] According to an embodiment of the present invention, the initial value is updated based on the global update strategy and the objective function to obtain the global objective value, including: updating the initial value based on the global update strategy to obtain an intermediate value; determining the error between the intermediate value and the objective function; when the error is less than or equal to a preset error, determining the intermediate value as the global objective value.

[0075] In an embodiment of the present invention, the intermediate value can represent the intermediate parameter value in the process of updating the initial parameters using the global update strategy. The intermediate prediction value obtained by the intermediate prediction model corresponding to the intermediate parameter value is used to calculate the error between the intermediate prediction value and the target value (actual monitoring value) based on the objective function. When the error (which can be represented by the fitness value) is less than or equal to the preset error, the global target value is obtained.

[0076] For example, the process of updating the initial parameters using the SABO algorithm to obtain the global target value may include operations S301 to S305.

[0077] In operation S301, the optimization goal is to update the initial parameters A and B so that the predicted value of S(x) is consistent with the target value S target (x) is minimized. The objective function f(A,B) can be defined, and the optimization goal is to minimize the error. The objective function f(A,B) is shown in the following formula (4):

[0078] (4);

[0079] Among them, x i It can represent the distance between different measuring points on the ground and the tunnel center axis, S target (x i ) is the settlement value obtained by the settlement sensor at different distances from the tunnel center axis, S(x i ; A, B) are the settlement values ​​of measuring points at different distances from the tunnel center axis calculated after updating the initial parameters A and B, and N can represent the number of surface measuring points.

[0080] In operation S302, the population is initialized. n individuals are randomly generated within the parameter value range of initial parameters A and B as initial values. The corresponding values ​​of initial parameters A and B within the parameter value range can be recorded as A and B respectively. i and B i The specific formulas are as follows (5)-(6):

[0081] (5);

[0082] (6);

[0083] Among them, A i It can represent the value of the i-th individual in the population within the range of A, and the range of A is [0.1,10]; B i is the value of the ith individual in the population within the range of B, and the range of B is [0.1, 10]; rand can represent a uniformly distributed random number [0, 1], A max It can represent the maximum value of the initial parameter A within the value range, A min It can represent the minimum value of the initial parameter A within the value range, B max It can represent the maximum value of the initial parameter B within the value range, B min It can represent the minimum value of the initial parameter B within the value range.

[0084] In operation S303, the fitness is calculated. It can be determined by the square of the error between the intermediate prediction value predicted by the intermediate prediction model and the target value, as shown in the following formula (7):

[0085] (7);

[0086] Among them, f(A i ,B i ) can represent the objective function value (the square of the error between the intermediate prediction value and the target value).

[0087] In operation S304, the population is updated (subtracted mean). Two individuals (A1, B1) and (A2, B2) in the population are randomly selected, and then the average of the difference is calculated to generate a new individual. The details are shown in the following formulas (8)-(9):

[0088] (8);

[0089] (9);

[0090] Among them, A new It can represent the value of the new individual A, B new It can represent the value of the new individual B. A1 and B1 represent the values ​​of the first individual randomly selected from the population, A2 and B2 represent the values ​​of the second individual randomly selected from the population, and α is the scaling factor, which can be (0, 1].

[0091] In operation S305, operations S303 and S304 are repeatedly performed until the fitness value change is less than a set threshold value (for example, the threshold value is set to 10 -6 ), and obtain the global target value (A * , B * ).

[0092] According to an embodiment of the present invention, the SABO algorithm uses a subtraction average strategy to gradually reduce the search range during the search process, so that the potential optimal solution of the initial parameters can be found globally during the model training process. Compared with the traditional local search method, SABO has a stronger global exploration ability. By initially generating multiple candidate solutions in the entire search space and gradually reducing the search range according to the average value, SABO can ensure that the solution space is explored from multiple angles and a better optimization direction is found. It can avoid falling into a local optimal solution.

[0093] It can be understood that the above has described an example of how to use the global update strategy to obtain the global target value, and the following will further describe how to use the local update strategy to determine the target parameter.

[0094] According to an embodiment of the present invention, target parameters are determined based on a global target value and a local update strategy, including: taking the global target value as a local initial value, and determining a local update range based on the local update strategy; determining a candidate value based on the local initial value and the local update range, wherein the local update range is determined based on the global target value; comparing the difference between the candidate value and the global target value based on a preset reward strategy; and determining the target parameters when the difference is less than a first difference threshold.

[0095] In an embodiment of the present invention, the local update range can represent the range of local search using the global target value as the starting point of the local search; thereby searching for candidate values ​​corresponding to the local initial value within the local update range, and determining whether to update the current optimal solution by comparing the performance of the local initial value with the candidate value in the model prediction. The preset reward update strategy can be a method for calculating the reward value by comparing the performance of the current solution and the candidate solution.

[0096] For example, the method of determining the target parameter based on the global target value and the local update strategy may include operations S310 to S340.

[0097] In operation S310, the global target value (A * , B * ) as the starting point of the local update strategy and defines the scope of the local search. The local search range corresponding to the initial parameter A can be , the local search range corresponding to the initial parameter B can be ,in, You can take 10%A * , You can take 10%B * .

[0098] In operation S320, candidate values ​​are generated. Candidate values ​​may be generated within the local update range defined by A and B. Specifically, the candidate values ​​are shown in the following formulas (10)-(11):

[0099] (10);

[0100] (11);

[0101] Among them, rand is a uniformly distributed random number [0, 1], Can represent the candidate value corresponding to the initial parameter A, The candidate value corresponding to the initial parameter B can be characterized.

[0102] In operation S330, the performance of the candidate value and the current optimal solution are compared based on the preset reward strategy, and a reward value is calculated to determine whether to update the optimal solution. The reward value is calculated as shown in the following formula (12).

[0103] (12);

[0104] Where: R(A,B) is the reward value. If it is greater than 0, it means that the candidate value is worse than the current solution. If it is equal to 0, it means that the candidate value is the same as the current solution. If it is less than 0, it means that the candidate value is not as good as the current solution. If the candidate value is better, the current optimal solution is updated.

[0105] In operation S340, a convergence judgment is performed. When the change of R(A, B) is less than a set threshold (e.g., 10 -6 ), which means that the update has stabilized, and then the target parameter A is obtained optimal and B optimal .

[0106] According to an embodiment of the present invention, by using the global target value as the initial value of the local update strategy (PRO), it is possible to avoid the local update strategy from starting training from a random or less than optimal initial point, which can significantly accelerate the convergence process of the model, reduce the initial exploration process, and enable local optimization to quickly focus on more optimal areas, thereby improving the overall update optimization efficiency.

[0107] According to an embodiment of the present invention, a plurality of target parameters are used to update an initial prediction model to obtain a prediction model, including: substituting the target parameters into the initial prediction model to obtain an intermediate prediction model; determining a reference settlement result corresponding to the target measuring point based on the intermediate prediction model; and using the intermediate prediction model as the prediction model when the settlement difference between the reference settlement result and the target settlement result is less than a second difference threshold.

[0108] In an embodiment of the present invention, after obtaining the target parameter A optimal and B optimal Afterwards, the target parameter A can be optimal and B optimal Substitute it into the initial prediction model to obtain the intermediate prediction model, and calculate the maximum surface settlement at the target measuring point (the measuring point corresponding to the central axis of the new tunnel) predicted by the intermediate prediction model at x=0 The maximum settlement value measured by the settlement sensor at the target measuring point The settlement difference is used to determine whether the model parameters need to be iteratively updated. The calculation method of is shown in the following formula (13):

[0109] (13);

[0110] The maximum settlement of the ground surface at the target measuring point x=0 The maximum settlement value measured by the settlement sensor at the target measuring point The error (sedimentation difference) can be expressed as ,error The calculation method of is shown in the following formula (14):

[0111] (14);

[0112] By determining the maximum settlement of the ground surface at the target measuring point x=0 The maximum settlement value measured by the settlement sensor at the target measuring point The error is not less than a second difference threshold (for example, 2%), otherwise the global update strategy and the local update strategy are reused to update the parameters.

[0113] According to an embodiment of the present invention, the initial value is updated based on a global update strategy to obtain an intermediate value, including: selecting a first individual and a second individual from the initial value; and determining the intermediate value based on a scaling factor and an individual difference between the first individual and the second individual.

[0114] In an embodiment of the present invention, the first individual and the second individual may represent individuals (A1, B1) and (A2, B2) corresponding to initial parameters A and B, respectively. The intermediate value may represent a new individual A generated by randomly selecting two individuals (A1, B1) and (A2, B2) in the population and then calculating the average of the differences. new and B new , A new and B new The calculation method of can refer to formula (8) and formula (9).

[0115] According to an embodiment of the present invention, the initial value corresponding to the initial parameter is determined by the following operations: determining the parameter value range corresponding to the initial parameter and the valley value and peak value corresponding to the parameter value range; determining the initial value based on the parameter value range, valley value, peak value and distribution coefficient.

[0116] In an embodiment of the present invention, the initial value may represent the random generation of n individuals as the initial value within the parameter value range of the initial parameters A and B. The estimate may be the maximum value within the parameter value range, and the valley value may represent the minimum value within the parameter value range. The distribution coefficient may represent the random number of individuals uniformly distributed within the value range. The calculation method of the initial value may refer to formula (5) and formula (6).

[0117] Figure 4 A schematic diagram of prediction results based on a prediction model, case 1, and case 2 according to an embodiment of the present invention is shown.

[0118] like Figure 4As shown in Figures (a) and (b) in the figure, in order to verify the technical effect, the relevant data in Case 1 and Case 2 were selected for verification, and the maximum surface settlement caused by shield tunnel excavation was measured using settlement sensors. The maximum settlement S(x; A) at the target measuring point is predicted by using the prediction model. optimal , B optimal ) max The predicted settlement results generated by the prediction model of the present invention are compared and verified based on the monitoring results of different measuring points. The error between the maximum surface settlement value predicted by the prediction model and the actual monitored maximum settlement value is shown in Table 2 below. The error does not exceed 5%. The prediction accuracy of the prediction model can meet the prediction requirements of actual projects.

[0119] Table 2

[0120]

[0121] Based on the above-mentioned evaluation method for deformation risk of existing buildings, the present invention also provides an evaluation device for deformation risk of existing buildings. Figure 5 The device is described in detail.

[0122] Figure 5 A structural block diagram of a device for assessing deformation risk of an existing building according to an embodiment of the present invention is shown.

[0123] like Figure 5 As shown, the device for evaluating deformation risk of existing buildings in this embodiment includes a data acquisition module 510 , a data input module 520 and an evaluation result determination module 530 .

[0124] The data acquisition module 510 is used to acquire tunnel data, soil data corresponding to the newly built tunnel, and settlement range data, wherein the tunnel data includes tunnel geometry data and deformation data. In one embodiment, the data acquisition module 510 can be used to perform the operation S210 described above, which will not be repeated here.

[0125] The data input module 520 is used to input the tunnel data, soil data and settlement range data into the prediction model to obtain settlement results corresponding to multiple measuring points. In one embodiment, the data input module 520 can be used to perform the operation S220 described above, which will not be repeated here.

[0126] The assessment result determination module 530 is used to determine the risk assessment result of the building to be assessed based on the settlement result, the building data to be assessed and the settlement range data. In one embodiment, the assessment result determination module 530 can be used to perform the operation S230 described above, which will not be repeated here.

[0127] Preferably, the prediction model is trained by the following operations: constructing an initial prediction model using sample tunnel data, sample soil data, sample measurement point data and multiple initial parameters; updating the multiple initial parameters based on multiple update strategies to obtain multiple target parameters, wherein the multiple update strategies include global update strategies and local update strategies; and updating the initial prediction model using multiple target parameters to obtain a prediction model.

[0128] According to an embodiment of the present invention, the data acquisition module 510, the data input module 520 and the assessment result determination module 530 in the assessment device for the deformation risk of existing buildings improve the correlation between surface settlement and building deformation risk prediction by integrating the settlement results and settlement range data corresponding to multiple measuring points on the surface in the newly built shield tunnel with the building data to be assessed, so as to make the building risk assessment result more accurate. Since the target parameters are updated based on the global update strategy and the local update strategy, the overfitting problem of the traditional prediction model is avoided, the generalization ability of the model is improved, the consumption of system resources is reduced, and the complex engineering problems in practical applications are further met.

[0129] According to an embodiment of the present invention, the device further comprises: a settlement range data determination module, which is used to determine the settlement range data based on the tunnel geometry data and the soil data.

[0130] According to an embodiment of the present invention, the settlement result includes the maximum settlement value corresponding to the measuring point; the assessment result determination module 530 includes: a deformation result determination submodule and a risk assessment result determination submodule. The deformation result determination submodule is used to determine the deformation result of the building to be assessed by using the maximum settlement value, the building data to be assessed and the settlement range data; the risk assessment result determination submodule is used to map the deformation result to the risk level data set to determine the risk assessment result.

[0131] According to an embodiment of the present invention, multiple initial parameters are updated based on multiple update strategies to obtain multiple target parameters, including: determining initial values ​​and target functions corresponding to the initial parameters; updating the initial values ​​based on a global update strategy and the target function to obtain a global target value; and determining the target parameters based on the global target value and a local update strategy.

[0132] According to an embodiment of the present invention, the initial value is updated based on the global update strategy and the objective function to obtain the global objective value, including: updating the initial value based on the global update strategy to obtain an intermediate value; determining the error between the intermediate value and the objective function; when the error meets the preset error, determining the intermediate value as the global objective value.

[0133] According to an embodiment of the present invention, target parameters are determined based on a global target value and a local update strategy, including: taking the global target value as a local initial value, and determining a local update range based on the local update strategy; determining a candidate value based on the local initial value and the local update range, wherein the local update range is determined based on the global target value; comparing the difference between the candidate value and the global target value based on a preset reward strategy; and determining the target parameters when the difference is less than a first difference threshold.

[0134] According to an embodiment of the present invention, a plurality of target parameters are used to update an initial prediction model to obtain a prediction model, including: substituting the target parameters into the initial prediction model to obtain an intermediate prediction model; determining a reference settlement result corresponding to the target measuring point based on the intermediate prediction model; and using the intermediate prediction model as the prediction model when the settlement difference between the reference settlement result and the target settlement result is less than a second difference threshold.

[0135] According to an embodiment of the present invention, the initial value is updated based on a global update strategy to obtain an intermediate value, including: selecting a first individual and a second individual from the initial value; and determining the intermediate value based on a scaling factor and an individual difference between the first individual and the second individual.

[0136] According to an embodiment of the present invention, the initial value corresponding to the initial parameter is determined by the following operations: determining the parameter value range corresponding to the initial parameter and the valley value and peak value corresponding to the parameter value range; determining the initial value based on the parameter value range, valley value, peak value and distribution coefficient.

[0137] According to an embodiment of the present invention, any multiple modules among the information acquisition module 510, the information input module 520 and the evaluation result determination module 530 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 information acquisition module 510, the information input module 520 and the evaluation result determination module 530 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 information acquisition module 510, the information input module 520 and the evaluation result determination module 530 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.

[0138] Figure 6 A block diagram of an electronic device suitable for implementing a method for evaluating deformation risk of an existing building according to an embodiment of the present invention is shown.

[0139] like Figure 6 As shown, the electronic device according to an embodiment of the present invention includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 to a random access memory (RAM) 603. The processor 601 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 601 may also include an onboard memory for caching purposes. The processor 601 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.

[0140] In RAM 603, various programs and data required for the operation of the electronic device are stored. The processor 601, ROM 602 and RAM 603 are connected to each other via a bus 604. The processor 601 performs various operations of the method flow according to the embodiment of the present invention by executing the programs in ROM 602 and / or RAM 603. It should be noted that the program can also be stored in one or more memories other than ROM 602 and RAM 603. The processor 601 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.

[0141] According to an embodiment of the present invention, the electronic device may further include an input / output (I / O) interface 605, which is also connected to the bus 604. The electronic device may further include one or more of the following components connected to the input / output (I / O) interface 605: an input portion 606 including a keyboard, a mouse, etc.; an output portion 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 608 including a hard disk, etc.; and a communication portion 609 including a network interface card such as a LAN card, a modem, etc. The communication portion 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output (I / O) interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage portion 608 as needed.

[0142] 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.

[0143] 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 602 and / or RAM 603 described above and / or one or more memories other than ROM 602 and RAM 603.

[0144] 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 method for assessing deformation risk of existing buildings provided in the embodiment of the present invention.

[0145] 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 601. According to the embodiment of the present invention, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0146] 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 609, and / or installed from a removable medium 611. 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.

[0147] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, 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.

[0148] 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).

[0149] 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.

[0150] It will be appreciated by those skilled in the art that the features described in the various embodiments of the present invention may be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in the present invention. In particular, without departing from the spirit and teachings of the present invention, the features described in the various embodiments of the present invention may be combined and / or combined in various ways. All of these combinations and / or combinations fall within the scope of the present invention.

[0151] 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 advantageously. 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 method for assessing deformation risk of existing buildings, characterized in that: The method comprises: Acquire tunnel data, soil data corresponding to the newly built tunnel, and settlement range data, wherein the tunnel data includes tunnel geometry data and deformation data; Inputting the tunnel data, the soil data and the settlement range data into a prediction model to obtain settlement results corresponding to a plurality of measuring points; Determine a risk assessment result of the building to be assessed based on the settlement result, the building data to be assessed and the settlement range data; The prediction model is trained by the following operations: An initial prediction model is constructed using sample tunnel data, sample soil data, sample measurement point data and multiple initial parameters; Based on multiple update strategies, the multiple initial parameters are updated to obtain multiple target parameters, wherein the multiple update strategies include a global update strategy and a local update strategy; The initial prediction model is updated using a plurality of the target parameters to obtain the prediction model.

2. The method according to claim 1, characterized in that The method further comprises: The settlement range data is determined based on the tunnel geometry data and the soil data.

3. The method according to claim 1, characterized in that The settlement result includes the maximum settlement value corresponding to the measuring point; Based on the settlement result, the data of the building to be assessed and the settlement range data, a risk assessment result of the building to be assessed is determined, including: Determine the deformation result of the building to be evaluated by using the maximum settlement value, the building data to be evaluated and the settlement range data; The deformation result is mapped to the risk level data set to determine the risk assessment result.

4. The method according to claim 1, characterized in that The multiple initial parameters are updated based on multiple update strategies to obtain multiple target parameters, including: Determining initial values ​​and objective functions corresponding to the initial parameters; Based on the global update strategy and the objective function, the initial value is updated to obtain a global objective value; The target parameter is determined based on the global target value and the local update strategy.

5. The method according to claim 4, characterized in that Updating the initial value based on the global update strategy and the objective function to obtain a global objective value includes: Update the initial value based on the global update strategy to obtain an intermediate value; determining an error between the intermediate value and the objective function; When the error is less than or equal to a preset error, the intermediate value is determined as a global target value.

6. The method according to claim 4, characterized in that Determining the target parameter based on the global target value and the local update strategy includes: Taking the global target value as the local initial value, and determining the local update range based on the local update strategy; Determining a candidate value based on the local initial value and the local update range, wherein the local update range is determined according to the global target value; Comparing the difference between the candidate value and the global target value based on a preset reward strategy; When the difference is less than a first difference threshold, the target parameter is determined.

7. The method according to any one of claims 4 to 6, characterized in that The initial prediction model is updated using the plurality of target parameters to obtain the prediction model, comprising: Substituting the target parameters into the initial prediction model to obtain an intermediate prediction model; Determine a reference settlement result corresponding to a target measuring point based on the intermediate prediction model; When the settlement difference between the reference settlement result and the target settlement result is less than a second difference threshold, the intermediate prediction model is used as the prediction model.

8. The method according to claim 5, characterized in that The initial value is updated based on the global update strategy to obtain an intermediate value, including: Selecting a first individual and a second individual from the initial values; The intermediate value is determined based on a scaling factor, an individual difference between the first individual and the second individual.

9. The method according to claim 4, characterized in that The initial value corresponding to the initial parameter is determined by the following operation: Determine a parameter value range corresponding to the initial parameter and a valley value and a peak value corresponding to the parameter value range; The initial value is determined based on the parameter value range, the valley value, the peak value and the distribution coefficient.

10. An assessment device for deformation risk of existing buildings, characterized in that: The device comprises: A data acquisition module, used to acquire tunnel data, soil data corresponding to the newly built tunnel, and settlement range data, wherein the tunnel data includes tunnel geometry data and deformation data; A data input module, used for inputting the tunnel data, the soil data and the settlement range data into a prediction model to obtain settlement results corresponding to a plurality of measuring points; An assessment result determination module, used to determine a risk assessment result of the building to be assessed based on the settlement result, the building data to be assessed and the settlement range data; The prediction model is trained by the following operations: An initial prediction model is constructed using sample tunnel data, sample soil data, sample measurement point data and multiple initial parameters; Based on multiple update strategies, the multiple initial parameters are updated to obtain multiple target parameters, wherein the multiple update strategies include a global update strategy and a local update strategy; The initial prediction model is updated using a plurality of the target parameters to obtain the prediction model.

Images