Intelligent monitoring method and system for grouting reinforcement lifting of existing building

Abstract

The invention is applicable to the field of building grouting monitoring, and particularly relates to an intelligent monitoring method for grouting reinforcement and lifting of an existing building, which comprises the following steps of: performing grouting lifting construction on the building based on grouting parameters recommended and output; acquiring a plurality of building images continuously shot by the monitoring point in a preset time period, wherein the building images contain monitoring labels pasted on the current building; based on the time sequence relation, two images with the interval time larger than a time threshold value are selected, image recognition processing is conducted on the two selected building images, and lifting data of the current building are obtained; and comparing the lifting data with expected data, and outputting a monitoring state for the current building based on a comparison result. The invention further provides an intelligent monitoring system for grouting reinforcement lifting of the existing building. The accuracy of building lifting construction can be evaluated, the construction deviation can be found in time, correction measures are taken, and the construction quality is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of building grouting monitoring, and in particular to an intelligent monitoring method and system for grouting reinforcement and lifting of an existing building. Background Art

[0002] As the number and speed of infrastructure construction continue to rise, the disasters and diseases encountered in engineering construction have become increasingly prominent, among which the engineering diseases caused by uneven settlement are particularly prominent. Engineering practice has shown that grouting can effectively control the problems of disasters and diseases in infrastructure projects. Grouting lifting has been widely used in the field of correcting the deviation of buildings with rigid foundations such as residential buildings, office buildings and high-rise buildings.

[0003] How to determine the ground surface uplift displacement during the grouting process has become one of the most concerned issues in the grouting engineering community.

[0004] In the related technology, the monitoring of the lifting displacement of the grouting reinforcement of existing buildings is mainly carried out by measuring instruments to detect the buildings to determine the displacement status of the buildings. The operation efficiency is low, the judgment results are not accurate enough, it is difficult to achieve effective monitoring of the displacement status of the buildings, and it is impossible to reasonably evaluate the displacement status of the building as a whole and at each location and provide feedback and early warnings. It is difficult for the corresponding management personnel to make targeted management measures in a timely manner. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide an intelligent monitoring method and system for grouting reinforcement and lifting of existing buildings, aiming to solve the technical problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions.

[0007] An embodiment of the present invention provides an intelligent monitoring method for grouting reinforcement and lifting of an existing building;

[0008] The following steps are involved:

[0009] Acquire structural data of the current building, and match historical building structural data corresponding to the structural data in a database, wherein the historical building structural data includes grouting parameters and structural geological information;

[0010] A BP neural network model including an input layer, a hidden layer and an output layer is constructed, and the BP neural network model is trained using historical building structure data to obtain a recommendation model for recommending building grouting parameters;

[0011] The structural geological information of the current building is used as the input of the recommendation model, and the grouting parameters for building lifting corresponding to the current structural geological information are output; based on the recommended output grouting parameters, the building is subjected to grouting lifting construction;

[0012] Acquire a plurality of building images continuously photographed at a monitoring point within a preset time period, wherein the building images contain a monitoring label attached to the current building;

[0013] Based on the time series relationship, two images with an interval time greater than a time threshold are selected, and image recognition processing is performed on the selected two building images to obtain the lifting data of the current building;

[0014] The lifting data is compared with the expected data, and the monitoring status of the current building is output based on the comparison result.

[0015] Furthermore, the step of outputting the monitoring status of the current building based on the comparison result includes:

[0016] When the difference between the lift data and the expected data is greater than the warning threshold, the recommendation model is modified, and the current lift data and warning information are output as the monitoring status of the current building;

[0017] When the difference between the lift data and the expected data is less than a threshold, the lift data is output as the monitoring status of the current building.

[0018] Furthermore, in the step of constructing a BP neural network model including an input layer, a hidden layer and an output layer, the number of nodes in the hidden layer is determined by the following formula:

[0019]

[0020] Where N is the number of nodes in the hidden layer; Ni is the number of nodes in the input layer; No is the number of nodes in the output layer, and a is a positive integer constant, a∈[1,10];

[0021] In the constructed BP neural network model, the learning rate is set to 0.01;

[0022] The Sigmoid function is selected as the transfer function from the input layer to the hidden layer, and the linear transfer Purelin function is selected as the transfer function from the hidden layer to the output layer. The number of training times is 20,000.

[0023] Furthermore, the step of using historical building structure data to train the BP neural network model to obtain a recommendation model for recommending building grouting parameters includes:

[0024] The krill swarm algorithm is used to optimize the weights and thresholds of the BP neural network model, find the optimal iterative weights and threshold parameters, initialize the population X = [X1, X2, X3...Xn] based on the range of weights and threshold parameters, and calculate the mean square error as the fitness of each population K = [K1, K2, K3...Kn]. The update formula of the population speed is expressed as:

[0025]

[0026] In the formula, Ni represents induced movement, Fi represents foraging movement, and Di represents diffusion movement;

[0027] Individuals in the population update their positions according to the population velocity;

[0028] After completing the position update, the gene propagation mechanism is used to update the population using the crossover operation and the next iteration is performed. After the iteration is completed, the population position with the best fitness is obtained;

[0029] Optimize the network model weights and thresholds, and use the population with the best fitness to optimize the weights and thresholds of the BP neural network model to obtain a recommended model.

[0030] Furthermore, the step of calculating the mean square error as the fitness of each population includes:

[0031] The particle fitness function is determined by taking the mean square error (MSE) of the error between the recommendation result of the BP neural network model and the target expected value as the objective function. The lower the fitness value, the smaller the error and the more accurate the model recommendation result. The fitness function is expressed as:

[0032]

[0033] In the formula, N represents the number of samples, Y represents the number of neurons in the output layer, W represents the expected value of the xth output layer node of the nth sample; nx Represents the actual value of the xth network output layer node for the nth sample.

[0034] Furthermore, the step of performing image recognition processing on the two selected building images to obtain the lift data of the current building includes:

[0035] The convolutional neural network is used to process the two selected building images to extract the first marker and the second marker respectively;

[0036] A deviation value of the monitoring tag is obtained according to the first marker and the second marker, and the deviation value is used as the lifting data of the current building.

[0037] Furthermore, the step of using a convolutional neural network to process the two selected building images to extract the first marker and the second marker respectively includes:

[0038] In the two building images, each pixel of the image is processed into a grayscale marker based on the grayscale value to obtain a first grayscale matrix and a second grayscale matrix;

[0039] Using the convolution kernel of the convolutional neural network, respectively perform convolution operations on each grayscale marker in the first grayscale matrix and the second grayscale matrix, calculate the eigenvalue of each grayscale marker, and obtain the first eigenmatrix and the second eigenmatrix;

[0040] Markers with the same eigenvalues ​​are extracted from the first feature matrix and the second feature matrix respectively, and the extracted markers are used as the first marker and the second marker respectively.

[0041] Furthermore, the step of obtaining the deviation value of the monitoring tag based on the first marker and the second marker includes: calculating the pixel distance between the first marker and the second marker; and calculating the deviation value of the monitoring tag based on the actual size of the monitoring tag and the calculated pixel distance.

[0042] Another embodiment of the present invention provides an intelligent monitoring system for grouting reinforcement and lifting of existing buildings, including the following modules:

[0043] A data preparation module is used to obtain the structural data of the current building and match the historical building structural data corresponding to the structural data in the database, wherein the historical building structural data includes grouting parameters and structural geological information;

[0044] A model training module is used to construct a BP neural network model including an input layer, a hidden layer and an output layer, and train the BP neural network model using historical building structure data to obtain a recommendation model for recommending building grouting parameters;

[0045] A parameter recommendation module is used to use the structural geological information of the current building as the input of the recommendation model, output the grouting parameters for building lifting corresponding to the current structural geological information; and perform grouting lifting construction on the building based on the recommended output grouting parameters;

[0046] The grouting monitoring module is used to obtain multiple building images taken continuously at the monitoring point within a preset time period, wherein the building images contain monitoring tags attached to the current building; based on the time series relationship, two images with an interval time greater than a time threshold are selected, and image recognition processing is performed on the selected two building images to obtain the lifting data of the current building;

[0047] The status output module is used to compare the lifting data with the expected data and output the monitoring status of the current building based on the comparison result.

[0048] Compared with the prior art, the beneficial effects of the intelligent monitoring method and system for grouting reinforcement and lifting of existing buildings of the present invention are:

[0049] First, the present invention obtains the structural data of the current building and matches the historical building structural data corresponding to the structural data in the database, so as to use the historical data to predict and guide the grouting parameters of the current building. By matching the historical building structural data, a more accurate grouting parameter recommendation can be provided for the current building.

[0050] Second, the BP neural network model of the present invention can construct an effective recommendation model by learning the grouting parameters and structural geological information in the historical building structure data. This model can predict the appropriate grouting parameters based on the input structural geological information, thereby improving the accuracy and reliability of the grouting construction. The grouting parameters output by the recommendation model are used for the building lifting construction, which can ensure the rationality of the grouting parameters during the construction process.

[0051] Third, the present invention can effectively capture the changes of buildings within a certain period of time by acquiring images of buildings taken continuously within a preset time period, and selecting two images with an interval time greater than a time threshold for comparison using a time series relationship, and can process these images using image recognition technology to monitor the lifting process of the building in real time, which helps to adjust the construction plan in a timely manner and ensure construction safety and effectiveness;

[0052] Fourthly, the present invention can evaluate the accuracy of building lifting construction by comparing actual lifting data with expected data, and can timely discover construction deviations, take corrective measures, and ensure construction quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0054] Figure 1 This is a flow chart of an intelligent monitoring method for grouting reinforcement and lifting of an existing building according to the present invention;

[0055] Figure 2 It is a sub-flow chart of the intelligent monitoring method of the present invention;

[0056] Figure 3 is another sub-flow chart of the intelligent monitoring method of the present invention;

[0057] Figure 4 This is a structural block diagram of an intelligent monitoring system for grouting reinforcement and lifting of existing buildings according to the present invention;

[0058] Figure 5 A structural schematic diagram of a monitoring terminal provided by the present invention. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0060] At present, the monitoring of the displacement of grouting reinforcement lifting of existing buildings is mainly carried out by measuring instruments to detect the buildings to determine the displacement status of the buildings. The operation efficiency is low, the judgment results are not accurate enough, it is difficult to achieve effective monitoring of the displacement status of the buildings, and it is impossible to reasonably evaluate the displacement status of the building as a whole and at each location and provide feedback and early warnings. It is difficult for the corresponding management personnel to make targeted management measures in a timely manner.

[0061] To solve the above problems, the present invention provides an intelligent monitoring method and system for the grouting reinforcement and lifting of existing buildings. Grouting parameters are recommended by matching historical data and training a BP neural network model, and image recognition technology is used to monitor the lifting status of the building to optimize the construction process and ensure safety.

[0062] The specific implementation of the present invention is described in detail below in conjunction with specific embodiments.

[0063] Please refer to Figure 1 In one embodiment of the present invention, a method for intelligent monitoring of grouting reinforcement and lifting of existing buildings is provided, comprising the following steps:

[0064] S101, obtaining structural data of a current building, and matching structural data of historical buildings corresponding to the structural data in a database, wherein the structural data of historical buildings includes grouting parameters and structural geological information;

[0065] In an embodiment of the present invention, historical building structural data refers to the structural data of other buildings that have completed grouting and lifting construction. The structural data contains the structural geological information of the building and the grouting parameters matching the structural geological information. The structural information includes the basic information of the building, such as the height, settlement data, inclination data, weight, material, structural form, axis, and component specifications. The grouting parameters include grouting pressure, grouting volume, grouting speed, grouting material type, etc.

[0066] The present invention obtains the structural data of the current building, matches the historical building structural data corresponding to the structural data in the database, and can use the historical data to predict and guide the grouting parameters of the current building. By matching the historical building structural data, a more accurate grouting parameter recommendation can be provided for the current building.

[0067] S102, constructing a BP neural network model including an input layer, a hidden layer and an output layer, and training the BP neural network model using historical building structure data to obtain a recommendation model for recommending building grouting parameters;

[0068] Among them, in the BP neural network model of the embodiment of the present invention, the number of nodes in the hidden layer is determined by the following formula: Where N is the number of nodes in the hidden layer; Ni is the number of nodes in the input layer; No is the number of nodes in the output layer, and a is a positive integer constant, a∈[1,10];

[0069] Preferably, in the constructed BP neural network model, the learning rate is set to 0.01;

[0070] As a preferred method, the input layer to hidden layer transfer function is selected as Sigmoid function, which can map the input real number to the interval (0,1), introduce nonlinear factors, and enable the neural network to learn and fit complex nonlinear relationships; and the Sigmoid function is continuous, and its derivative is easy to calculate, which makes it easy to use the gradient descent method for optimization during the neural network training process;

[0071] As a preferred method, the transfer function from the hidden layer to the output layer is the linear transfer Purelin function, and the number of training times is 20,000. When the activation function is set to Purelin, it is equivalent to directly passing the neuron value as the activation value to the next layer, which simplifies the complexity of the model.

[0072] S103, using the structural geological information of the current building as the input of the recommendation model, outputting the grouting parameters for building lifting corresponding to the current structural geological information; and performing grouting lifting construction on the building based on the recommended output grouting parameters;

[0073] The recommendation model provided in the embodiment of the present invention can recommend grouting parameters suitable for grouting and lifting of the current building based on the structural geological information of the current building, thereby improving the efficiency of grouting and lifting construction and assisting staff to quickly determine the grouting parameters of the current building;

[0074] S104, obtaining a plurality of building images continuously shot at a monitoring point within a preset time period, wherein the building images contain a monitoring label attached to the current building; based on a time sequence relationship, selecting two images with an interval greater than a time threshold, performing image recognition processing on the selected two building images, and obtaining lift data of the current building;

[0075] S105: Compare the lifting data with the expected data, and output a monitoring status of the current building based on the comparison result.

[0076] Among them, in an embodiment of the present invention, the step of outputting the monitoring status of the current building based on the comparison result includes the following two situations: first, when the difference between the lifting data and the expected data is greater than the warning threshold, the recommended model is corrected, and the current lifting data and warning information are output as the monitoring status of the current building, so that the staff can obtain the grouting lifting status of the current building, and can also promptly understand the adaptability of the grouting parameters recommended by the current recommended model, and make timely strain treatment of the grouting lifting construction; second, when the difference between the lifting data and the expected data is less than the threshold, the lifting data is output as the monitoring status of the current building, indicating the practicality of the recommended model.

[0077] The present invention can evaluate the accuracy of building lifting construction by comparing actual lifting data with expected data. This method helps to timely discover construction deviations, take corrective measures, and ensure construction quality.

[0078] Furthermore, the Krill Herd Algorithm (KHA) is a global optimization algorithm inspired by the behavior of krill swarms in nature; the Krill Herd Algorithm simulates the foraging behavior and group dynamics of krill swarms in nature, and seeks the optimal solution through cooperation and competition between individuals;

[0079] In step S102 of the present invention, the step of using historical building structure data to train the BP neural network model to obtain a recommendation model for recommending building grouting parameters includes:

[0080] The krill swarm algorithm is used to optimize the weights and thresholds of the BP neural network model to find the optimal iterative weights and threshold parameters;

[0081] Initialize the population X = [X1, X2, X3...Xn] based on the range of weight and threshold parameters;

[0082] The calculated mean square error is used as the fitness of each population K = [K1, K2, K3...Kn], and the population speed update formula is expressed as:

[0083]

[0084] In the formula, Ni represents induced movement, Fi represents foraging movement, and Di represents diffusion movement;

[0085] Individuals in the population update their positions according to the population velocity;

[0086] After completing the position update, the gene propagation mechanism is used to update the population using the crossover operation and the next iteration is performed. After the iteration is completed, the population position with the best fitness is obtained;

[0087] Optimize the network model weights and thresholds, and use the population with the best fitness to optimize the weights and thresholds of the BP neural network model to obtain a recommended model.

[0088] The present invention optimizes the weights and thresholds of the BP neural network through the krill swarm algorithm, which can improve the generalization ability and prediction accuracy of the recommendation model.

[0089] Furthermore, the step of calculating the mean square error as the fitness of each population includes: determining the particle fitness function by taking the mean square error MSE of the error between the recommendation result of the BP neural network model and the target expected value as the objective function. The lower the fitness value, the smaller the error, and the more accurate the model recommendation result. The fitness function is expressed as:

[0090]

[0091] In the formula, N represents the number of samples, Y represents the number of neurons in the output layer, W represents the expected value of the xth output layer node of the nth sample; nx Represents the actual value of the xth network output layer node for the nth sample.

[0092] The BP neural network model of the present invention can construct an effective recommendation model by learning the grouting parameters and structural geological information in the historical building structure data. This model can predict the appropriate grouting parameters based on the input structural geological information, thereby improving the accuracy and reliability of the grouting construction. The grouting parameters output by the recommendation model are used for the building lifting construction, which can ensure the rationality of the grouting parameters during the construction process.

[0093] Please refer to Figure 2 In an embodiment of the present invention, the step of performing image recognition processing on the two selected building images to obtain the lift data of the current building includes:

[0094] S201, using a convolutional neural network to process the two selected building images, and extracting a first marker and a second marker respectively;

[0095] S202. Obtain a deviation value of the monitoring tag according to the first marker and the second marker, and use the deviation value as the lifting data of the current building.

[0096] Please continue to refer to Figure 3 In an embodiment of the present invention, the steps of using a convolutional neural network to process the two selected building images and extracting the first marker and the second marker respectively include:

[0097] S301, in two building images, each pixel of the image is processed into a grayscale marker based on grayscale value conversion, to obtain a first grayscale matrix and a second grayscale matrix;

[0098] In this step, the color images of the two buildings are converted into grayscale images. Each pixel of the grayscale image represents the brightness information of the point, which usually ranges from 0 (black) to 255 (white); the grayscale image is converted into a matrix form, where each element of the matrix corresponds to the grayscale value of a pixel in the image. In this way, each image will be converted into a two-dimensional grayscale matrix;

[0099] S302, using the convolution kernel of the convolutional neural network to perform convolution operations on each grayscale marker in the first grayscale matrix and the second grayscale matrix, respectively, to calculate the eigenvalue of each grayscale marker, and obtain a first eigenmatrix and a second eigenmatrix;

[0100] S303, respectively extracting markers having the same eigenvalues ​​from the first feature matrix and the second feature matrix, and using the extracted markers as the first marker and the second marker respectively;

[0101] In convolutional neural networks, the convolution kernel is a small matrix used to detect specific features in an image. The convolution kernel is slid over each position of the grayscale matrix, and the dot product between the convolution kernel and the local area of ​​the grayscale matrix is ​​calculated to generate a new feature map. For each grayscale marker, the eigenvalue calculated by the convolution operation is used to construct a new feature matrix. The first grayscale matrix and the second grayscale matrix are respectively subjected to convolution operations to generate the first feature matrix and the second feature matrix.

[0102] Wherein, in the embodiment of the present invention, the step of obtaining the deviation value of the monitoring tag according to the first marker and the second marker includes:

[0103] Calculate the pixel distance between the first marker and the second marker; and calculate the deviation value of the monitoring tag according to the actual size of the monitoring tag and the calculated pixel distance.

[0104] The present invention obtains images of buildings taken continuously within a preset time period, and uses a time series relationship to select two images with an interval time greater than a time threshold for comparison, so as to effectively capture the changes of buildings within a certain time period. By processing these images using image recognition technology, the lifting process of the building can be monitored in real time, which helps to adjust the construction plan in time and ensure construction safety and effectiveness.

[0105] Please refer to Figure 4 Another embodiment of the present invention provides an intelligent monitoring system for grouting reinforcement and lifting of existing buildings, including the following modules:

[0106] The data preparation module 401 is used to obtain the structural data of the current building and match the historical building structural data corresponding to the structural data in the database, wherein the historical building structural data includes grouting parameters and structural geological information;

[0107] The model training module 402 is used to construct a BP neural network model including an input layer, a hidden layer and an output layer, and train the BP neural network model using historical building structure data to obtain a recommendation model for recommending building grouting parameters;

[0108] The parameter recommendation module 403 is used to use the structural geological information of the current building as the input of the recommendation model, output the grouting parameters for building lifting corresponding to the current structural geological information; and perform grouting lifting construction on the building based on the recommended output grouting parameters;

[0109] The grouting monitoring module 404 is used to obtain a plurality of building images continuously taken at the monitoring point within a preset time period, wherein the building images contain monitoring tags attached to the current building; based on the time series relationship, two images with an interval time greater than a time threshold are selected, and image recognition processing is performed on the selected two building images to obtain the lifting data of the current building;

[0110] The status output module 405 is used to compare the lifting data with the expected data, and output the monitoring status of the current building based on the comparison result.

[0111] Please refer to Figure 5 In another embodiment of the present disclosure, a monitoring terminal is further provided. The monitoring terminal 500 of the embodiment of the present disclosure includes a memory and a processor. The memory stores a computer program. When the computer program is executed by the processor, the intelligent monitoring method for grouting reinforcement and lifting of existing buildings of any one of the above embodiments is implemented;

[0112] The monitoring terminal 500 may also include: an input system and an output system; the processor, memory, input system and output system may be connected via a bus or other means, the input system may receive input digital or character information, and generate signal inputs related to the intelligent monitoring of grouting reinforcement and lifting of existing buildings.

[0113] The output system may include display devices such as display screens.

[0114] Furthermore, the present invention also provides a computer-readable storage medium, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor, the steps of the intelligent monitoring method for grouting reinforcement and lifting of existing buildings as provided above are implemented.

[0115] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0116] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, the functional units in the various embodiments of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0117] In a typical configuration of an embodiment of the present invention, the terminal, the device of the service network and the computing device include one or more processors (CPU), an input / output interface, a network interface and a memory.

[0118] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0119] Computer readable media include permanent and non-permanent, removable and non-removable media that can store information by any method or technology. The information can be computer readable instructions, data structures, program modules or other data.

[0120] Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include non-transitory media such as modulated data signals and carrier waves.

[0121] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example for illustration. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0122] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some or all of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention.

[0123] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. An intelligent monitoring method for grouting reinforcement and lifting of existing buildings, characterized by: The following steps are involved: Acquire the structural data of the current building, and match the historical building structural data corresponding to the structural data in the database, wherein the historical building structural data includes grouting parameters and structural geological information; A BP neural network model including an input layer, a hidden layer and an output layer is constructed, and the BP neural network model is trained using historical building structure data to obtain a recommendation model for recommending building grouting parameters; Taking the structural geological information of the current building as the input of the recommendation model, and outputting the grouting parameters for building lifting corresponding to the current structural geological information; Based on the recommended grouting parameters, the building is lifted by grouting. Acquire a plurality of building images continuously photographed at a monitoring point within a preset time period, wherein the building images contain a monitoring label attached to the current building; Based on the time series relationship, two images with an interval time greater than a time threshold are selected, and image recognition processing is performed on the selected two building images to obtain the lifting data of the current building; The lifting data is compared with the expected data, and the monitoring status of the current building is output based on the comparison result.

2. The intelligent monitoring method for grouting reinforcement and lifting of existing buildings according to claim 1 is characterized in that: The step of outputting the monitoring status of the current building based on the comparison result includes: When the difference between the lift data and the expected data is greater than the warning threshold, the recommendation model is modified, and the current lift data and warning information are output as the monitoring status of the current building; When the difference between the lift data and the expected data is less than a threshold, the lift data is output as the monitoring status of the current building.

3. The intelligent monitoring method for grouting reinforcement and lifting of existing buildings according to claim 2 is characterized in that: In the step of constructing a BP neural network model including an input layer, a hidden layer and an output layer, the number of nodes in the hidden layer is determined by the following formula: Where N is the number of nodes in the hidden layer; Ni is the number of nodes in the input layer; No is the number of nodes in the output layer, and a is a positive integer constant, a∈[1,10]; In the constructed BP neural network model, the learning rate is set to 0.01; The Sigmoid function is selected as the transfer function from the input layer to the hidden layer, and the linear transfer Purelin function is selected as the transfer function from the hidden layer to the output layer. The number of training times is 20,000.

4. The intelligent monitoring method for grouting reinforcement and lifting of existing buildings according to claim 3 is characterized in that: The step of using historical building structure data to train the BP neural network model to obtain a recommendation model for recommending building grouting parameters includes: The krill swarm algorithm is used to optimize the weights and thresholds of the BP neural network model, find the optimal iterative weights and threshold parameters, initialize the population X = [X1, X2, X3...Xn] based on the range of weights and threshold parameters, and calculate the mean square error as the fitness of each population K = [K1, K2, K3...Kn]. The update formula of the population speed is expressed as: In the formula, Ni represents induced movement, Fi represents foraging movement, and Di represents diffusion movement; Individuals in the population update their positions according to the population velocity; After completing the position update, the gene propagation mechanism is used to update the population using the crossover operation and the next iteration is performed. After the iteration is completed, the population position with the best fitness is obtained; Optimize the network model weights and thresholds, and use the population with the best fitness to optimize the weights and thresholds of the BP neural network model to obtain a recommended model.

5. The intelligent monitoring method for grouting reinforcement and lifting of existing buildings according to claim 4 is characterized in that: The step of calculating the mean square error as the fitness of each population includes: The particle fitness function is determined by taking the mean square error (MSE) of the error between the recommendation result of the BP neural network model and the target expected value as the objective function. The lower the fitness value, the smaller the error and the more accurate the model recommendation result. The fitness function is expressed as: In the formula, N represents the number of samples, Y represents the number of neurons in the output layer, W represents the expected value of the xth output layer node of the nth sample; nx Represents the actual value of the x-th network output layer node for the n-th sample.

6. The intelligent monitoring method for grouting reinforcement and lifting of existing buildings according to claim 5 is characterized in that: The step of performing image recognition processing on the two selected building images to obtain the lift data of the current building includes: The convolutional neural network is used to process the two selected building images to extract the first marker and the second marker respectively; A deviation value of the monitoring tag is obtained according to the first marker and the second marker, and the deviation value is used as the lifting data of the current building.

7. The intelligent monitoring method for grouting reinforcement and lifting of existing buildings according to claim 6 is characterized in that: The step of using a convolutional neural network to process the two selected building images to extract the first marker and the second marker respectively includes: In the two building images, each pixel of the image is processed into a grayscale marker based on the grayscale value to obtain a first grayscale matrix and a second grayscale matrix; Using the convolution kernel of the convolutional neural network, respectively perform convolution operations on each grayscale marker in the first grayscale matrix and the second grayscale matrix, calculate the eigenvalue of each grayscale marker, and obtain the first eigenmatrix and the second eigenmatrix; Markers with the same eigenvalues ​​are extracted from the first feature matrix and the second feature matrix respectively, and the extracted markers are used as the first marker and the second marker respectively.

8. The intelligent monitoring method for grouting reinforcement and lifting of existing buildings according to claim 7 is characterized in that: The step of obtaining the deviation value of the monitoring tag according to the first marker and the second marker includes: calculating the pixel distance between the first marker and the second marker; and calculating the deviation value of the monitoring tag according to the actual size of the monitoring tag and the calculated pixel distance.

9. A monitoring system for implementing the intelligent monitoring method for grouting reinforcement and lifting of existing buildings as claimed in any one of claims 1 to 8, characterized in that: The monitoring system includes the following modules: A data preparation module is used to obtain the structural data of the current building and match the historical building structural data corresponding to the structural data in the database, wherein the historical building structural data includes grouting parameters and structural geological information; A model training module is used to construct a BP neural network model including an input layer, a hidden layer and an output layer, and train the BP neural network model using historical building structure data to obtain a recommendation model for recommending building grouting parameters; A parameter recommendation module, used to take the structural geological information of the current building as the input of the recommendation model, and output the grouting parameters for building lifting corresponding to the current structural geological information; Based on the recommended grouting parameters, the building is lifted by grouting. A grouting monitoring module, used to obtain a plurality of building images taken continuously at a monitoring point within a preset time period, wherein the building images contain a monitoring label attached to the current building; Based on the time series relationship, two images with an interval time greater than a time threshold are selected, and image recognition processing is performed on the selected two building images to obtain the lifting data of the current building; The status output module is used to compare the lifting data with the expected data and output the monitoring status of the current building based on the comparison result.

Images