Automatic grouting monitoring management system based on artificial intelligence

Abstract

The invention belongs to the technical field of construction monitoring, and particularly relates to an artificial intelligence-based automatic grouting monitoring management system, which comprises a settlement monitoring module used for monitoring settlement information of a target building at each monitoring point of the target building; the settlement prediction module is used for predicting and outputting the predicted settlement amount of the building, comparing the predicted settlement amount with the settlement amount of the building monitored in real time, and performing early warning on the target building based on a comparison result; the reinforcing platform module is used for generating a reinforcing instruction for reinforcing the structure of the target building; and the construction platform module is used for controlling the automatic grouting machine to reach the grouting position according to the reinforcing instruction, controlling the grouting pressure and the grouting amount according to the reinforcing instruction, and completing the grouting lifting work of the target building. On-site intelligent automatic construction is carried out through the artificial intelligence grouting lifting platform, on-site construction automation can be achieved, the construction safety is improved, and the construction efficiency is improved.

Description

Technical Field

[0006] The invention belongs to the technical field of construction monitoring, and in particular relates to an automatic grouting monitoring and management system based on artificial intelligence. Background Art

[0007] At present, the construction of grouting projects is still mainly manual, with a low degree of automation. Only the processing of prefabricated parts in the factory has achieved partial automation. The project site has a large number of personnel and is relatively backward in terms of informatization and intelligence compared to other industries. Nowadays, labor costs are rising, it is difficult to recruit workers, and professional and technical personnel with rich technical experience are becoming increasingly scarce, so automated construction is extremely urgent.

[0008] In the grouting lifting platform of the related technology, it is impossible to carry out on-site intelligent automated construction, the degree of on-site construction automation is low, and the construction safety needs to be improved, which affects the construction efficiency. Summary of the invention

[0009] The purpose of the embodiments of the present invention is to provide an automatic grouting monitoring and management system based on artificial intelligence, aiming to solve the technical problems raised in the above-mentioned background technology.

[0010] To achieve the above object, the present invention provides the following technical solutions.

[0011] The embodiment of the present invention provides an automatic grouting monitoring and management system based on artificial intelligence, comprising:

[0012] A settlement monitoring module, used to monitor the settlement information of the target building at each monitoring point of the target building;

[0013] A settlement prediction module is used to construct a building settlement prediction model, use the settlement information monitored by the settlement monitoring module as the input of the prediction model, predict and output the predicted settlement amount of the building, compare the predicted settlement amount with the settlement amount monitored in real time by the building, and issue an early warning to the target building based on the comparison result;

[0014] A reinforcement platform module, for responding to the early warning signal and generating a reinforcement instruction for reinforcing the structure of the target building according to the settlement information of the building and the structural information of the building;

[0015] The construction platform module is used to receive reinforcement instructions, control the automatic grouting machine to reach the grouting position according to the reinforcement instructions, and control the grouting pressure and grouting volume according to the reinforcement instructions. During the grouting process, it monitors the settlement of the foundation in real time, and adjusts the grouting parameters according to the settlement until the grouting and lifting work of the target building is completed.

[0016] Furthermore, the settlement monitoring module is configured with a data collection system and a data processing system; wherein:

[0017] The data collection system uses monitoring sensors installed on target buildings and foundations to collect settlement data, tilt data, and groundwater change data in real time, and uploads the collected data to the monitoring platform in real time via wireless transmission;

[0018] The data processing system receives the monitoring data sent from the data collection system, and performs cleaning and anomaly detection on the monitoring data.

[0019] Furthermore, the monitoring sensor includes a displacement sensor and a tilt sensor, and the displacement sensor and the tilt sensor are arranged at four corner points of the target building and at a middle position between two corner points;

[0020] The monitoring sensor also includes a groundwater sensor, which is arranged at different soil layer depths to measure the conditions of groundwater at different depths.

[0021] Furthermore, the step of constructing a building settlement prediction model includes:

[0022] Obtain historical monitoring data from the data collection system; divide the historical monitoring data into a training set and a test set based on the temporal characteristics of the historical monitoring data;

[0023] Set the parameters of the extreme learning machine neural network, including the number of input layer nodes and the number of hidden layer nodes;

[0024] The particle swarm algorithm is used to optimize the parameters of the extreme learning machine neural network, wherein the particle swarm algorithm uses the hidden layer weight as the optimization parameter and the root mean square error of the extreme learning machine as the fitness function, and minimizes the fitness function by continuously iteratively updating the hidden layer weight;

[0025] The training set is used to train the extreme learning machine neural network with optimal parameters, and the test set is used to make predictions, calculate the prediction error, and correct the prediction model to complete the construction of the prediction model.

[0026] Furthermore, in the particle swarm algorithm, set the population Y = (Y 1 , Y 2 , …, Y n )’s position X i =[x i1 x i2 … x iD ] T , the optimal particle is determined according to the particle fitness, and the speed and position update formula in the particle iteration process is expressed as:

[0027]

[0028]

[0029] In the formula, ω represents the inertia weight, c1 and c2 represent the learning factors; r 1 、r 2 Represents a random number between 0 and 1; Indicates the current optimal position of individual particles; represents the current optimal position of the particle population; k represents the number of iterations; represents the velocity of each particle in the population; Indicates the current position of the particle.

[0030] Furthermore, the speed of the particle iteration process is limited to the interval [0, V max ]; the position of the particle during iteration is limited to [-X max , X max ] to increase the search speed of particles.

[0031] Furthermore, a multi-index evaluation system is used to evaluate the prediction results output by the prediction model, where the multi-index evaluation system includes root mean square error, mean absolute error and goodness of fit R 2 ;

[0032] The root mean square error is calculated using the following formula:

[0033] The mean absolute error is calculated using the following formula:

[0034] The goodness of fit R 2 The following formula is used for calculation:

[0035] In the formula, m represents the number of data samples; y i represents the actual value of the target building settlement in the i-th data sample; Represents the predicted value of the target building settlement in the i-th data sample.

[0036] Furthermore, the automatic grouting monitoring and management system based on artificial intelligence also includes:

[0037] The grouting verification module is used to input the prediction model according to the strength parameters of the current target building foundation after the grouting is completed, and to guide whether further grouting reinforcement is needed based on the prediction model results to prevent subsequent building settlement.

[0038] Furthermore, the automatic grouting monitoring and management system based on artificial intelligence also includes:

[0039] The lifting feedback module is used to feed back the progress of the grouting lifting work to the settlement monitoring module, monitor the lifting data of the target building, and prevent the building from being lifted above the original elevation.

[0040] Compared with the prior art, the beneficial effects of the automatic grouting monitoring and management system based on artificial intelligence of the present invention are:

[0041] The present invention ensures the timeliness and accuracy of data by monitoring the settlement information of the target building using a settlement monitoring module at each monitoring point of the target building;

[0042] The present invention constructs a building settlement prediction model, uses the settlement information monitored by the settlement monitoring module as the input of the prediction model, predicts and outputs the predicted settlement of the building, compares the predicted settlement with the settlement monitored in real time, and issues an early warning to the target building based on the comparison result, so as to discover the settlement hazards of the building early and intervene in time, thereby improving the monitoring and management efficiency;

[0043] After the early warning signal is generated, the present invention generates a reinforcement instruction for reinforcing the structure of the target building according to the settlement information of the building and the structural information of the building;

[0044] The automatic grouting machine controlled by the present invention reaches the grouting position according to the reinforcement instruction, and controls the grouting pressure and grouting amount according to the reinforcement instruction. During the grouting process, the settlement of the foundation is monitored in real time, and the grouting parameters are adjusted according to the settlement until the grouting and lifting work of the target building is completed.

[0045] In summary, the present invention performs on-site intelligent automated construction through an artificial intelligence grouting lifting platform, which can realize on-site construction automation, improve construction safety, and improve construction efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] 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.

[0047] Figure 1 This is a structural block diagram of an automatic grouting monitoring and management system based on artificial intelligence of the present invention;

[0048] Figure 2 It is a schematic diagram of the arrangement of the monitoring sensor of the present invention;

[0049] Figure 3 A schematic diagram of the process of constructing a building settlement prediction model according to the present invention; DETAILED DESCRIPTION

[0050] 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.

[0051] At present, the construction of grouting construction projects is still mainly manual. The grouting lifting platform of related technology cannot carry out on-site intelligent automated construction. The degree of on-site construction automation is low, and the construction safety needs to be improved, which affects the construction efficiency.

[0052] To solve the above problems, the present invention provides an automatic grouting monitoring and management system based on artificial intelligence, which monitors the settlement information of the target building by using a settlement monitoring module at each monitoring point of the target building to ensure the timeliness and accuracy of the data; by constructing a building settlement prediction model, the settlement information monitored by the settlement monitoring module is used as the input of the prediction model, the predicted settlement of the building is predicted and output, the predicted settlement is compared with the settlement monitored by the building in real time, and the target building is warned based on the comparison result, so that the settlement hidden dangers of the building can be discovered early, and timely intervention can be achieved, thereby improving the monitoring and management efficiency; after generating an early warning signal, the present invention generates a reinforcement instruction for reinforcing the structure of the target building according to the settlement information of the building and the structural information of the building; controls the automatic grouting machine to reach the grouting position according to the reinforcement instruction, and controls the grouting pressure and grouting amount according to the reinforcement instruction. During the grouting process, the settlement of the foundation is monitored in real time, and the grouting parameters are adjusted according to the settlement until the grouting and lifting work of the target building is completed.

[0053] The specific implementation of the automatic grouting monitoring and management system based on artificial intelligence of the present invention is described in detail below in conjunction with specific embodiments.

[0054] Please refer to Figure 1 In one embodiment of the present invention, an automatic grouting monitoring and management system based on artificial intelligence is provided, and the monitoring and management system includes a settlement monitoring module 101, a settlement prediction module 102, a reinforcement platform module 103 and a construction platform module 104.

[0055] Among them, in an embodiment of the present invention, the settlement monitoring module 101 is used to monitor the settlement information of the target building at each monitoring point of the target building; the settlement prediction module 102 is used to construct a building settlement prediction model, use the settlement information monitored by the settlement monitoring module as the input of the prediction model, predict and output the predicted settlement of the building, compare the predicted settlement with the settlement monitored in real time by the building, and issue an early warning to the target building based on the comparison result; the reinforcement platform module 103 is used to respond to the early warning signal, and generate a reinforcement instruction for reinforcing the structure of the target building according to the settlement information of the building and the structural information of the building; the construction platform module 104 is used to receive the reinforcement instruction, control the automatic grouting machine to reach the grouting position according to the reinforcement instruction, and control the grouting pressure and grouting amount according to the reinforcement instruction. During the grouting process, the settlement of the foundation is monitored in real time, and the grouting parameters are adjusted according to the settlement until the grouting and lifting work of the target building is completed.

[0056] Furthermore, in a preferred embodiment of the present invention, a data collection system and a data processing system are configured in the settlement monitoring module; wherein: the data collection system utilizes monitoring sensors installed on the target building and foundation to collect settlement data, inclination data, and groundwater change data in real time, and uploads the collected data to the monitoring platform in real time via wireless transmission; the data processing system receives the monitoring data sent from the data collection system, and cleans and detects anomalies in the monitoring data.

[0057] For further information, please refer to Figure 2 The monitoring sensor provided in the embodiment of the present invention includes a displacement sensor and a tilt sensor, wherein the displacement sensor and the tilt sensor are arranged at the four corner points of the target building and the middle position between two corner points; the monitoring sensor also includes a groundwater sensor, which is arranged at different soil layer depths to measure the groundwater conditions at different depths.

[0058] In the settlement prediction module 102, the input of the prediction model includes key information such as the building's foundation type, geological conditions, load information, and the form of the building, which is used to calculate the settlement of the building to predict whether the building will continue to settle.

[0059] For further information, please refer to Figure 3 In an embodiment of the present invention, the step of constructing a building settlement prediction model comprises the following steps:

[0060] S201, obtaining historical monitoring data of a data collection system; dividing the historical monitoring data into a training set and a test set based on the temporal characteristics of the historical monitoring data;

[0061] S202, setting parameters of the extreme learning machine neural network, including the number of input layer nodes and the number of hidden layer nodes;

[0062] S203, optimizing the parameters of the extreme learning machine neural network using a particle swarm algorithm, wherein the particle swarm algorithm uses the hidden layer weight as the optimization parameter, uses the root mean square error of the extreme learning machine as the fitness function, and minimizes the fitness function by continuously iteratively updating the hidden layer weight;

[0063] In the particle swarm algorithm of the embodiment of the present invention, the population Y is set to (Y 1 , Y 2 , …, Y n )’s position X i =[x i1 x i2 … x iD ] T , the optimal particle is determined according to the particle fitness, and the speed and position update formula in the particle iteration process is expressed as:

[0064]

[0065]

[0066] In the formula, ω represents the inertia weight, c 1 、c 2 represents the learning factor; r 1 、r 2 Represents a random number between 0 and 1; Indicates the current optimal position of individual particles; represents the current optimal position of the particle population; k represents the number of iterations; represents the velocity of each particle in the population; Indicates the current position of the particle;

[0067] Preferably, the speed of the particle iteration process is limited to the interval [0, V max ]; the position of the particle during iteration is limited to [-X max , X max ] to increase the search speed of particles;

[0068] S204, using the training set to train the extreme learning machine neural network using the optimal parameters, and using the test set to make predictions, calculate the prediction error, correct the prediction model, and complete the construction of the prediction model.

[0069] Furthermore, in the embodiment of the present invention, a multi-index evaluation system is used to evaluate the prediction results output by the prediction model, wherein the multi-index evaluation system includes root mean square error, mean absolute error and goodness of fit R 2 ; The root mean square error is calculated using the following formula: The mean absolute error is calculated using the following formula: The goodness of fit R 2 The following formula is used for calculation: In the formula, m represents the number of data samples; y i represents the actual value of the target building settlement in the i-th data sample; Represents the predicted value of the target building settlement in the i-th data sample.

[0070] Furthermore, in an embodiment of the present invention, the artificial intelligence-based automatic grouting monitoring and management system also includes a grouting verification module. The grouting verification module is used to input a prediction model according to the strength parameters of the current target building foundation after the grouting is completed, and to guide whether further grouting reinforcement is needed according to the prediction model results to prevent subsequent building settlement.

[0071] Furthermore, in an embodiment of the present invention, the artificial intelligence-based automatic grouting monitoring and management system also includes a lifting feedback module, which is used to feed back the progress of the grouting lifting work to the settlement monitoring module, monitor the lifting data of the target building, and avoid the building being lifted above the original elevation.

[0072] In summary, the present invention performs on-site intelligent automated construction through an artificial intelligence grouting lifting platform, which can realize on-site construction automation, improve construction safety, and improve construction efficiency.

[0073] The above solutions are only an illustration of a preferred example, but are not limited thereto. When implementing the present invention, appropriate replacement and / or modification can be performed according to user needs.

[0074] The number of devices and processing scales described here are used to simplify the description of the present invention. Applications, modifications and variations of the present invention will be obvious to those skilled in the art.

[0075] Although the embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the specification and the embodiments. It can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily realized. Therefore, without departing from the general concept defined by the claims and equivalent scope, the present invention is not limited to the specific details and the illustrations shown and described here.

Claims

1. An automatic grouting monitoring and management system based on artificial intelligence, characterized in that: include: A settlement monitoring module, used to monitor the settlement information of the target building at each monitoring point of the target building; A settlement prediction module is used to construct a building settlement prediction model, use the settlement information monitored by the settlement monitoring module as the input of the prediction model, predict and output the predicted settlement amount of the building, compare the predicted settlement amount with the settlement amount monitored in real time by the building, and issue an early warning to the target building based on the comparison result; A reinforcement platform module, for responding to the early warning signal and generating a reinforcement instruction for reinforcing the structure of the target building according to the settlement information of the building and the structural information of the building; The construction platform module is used to receive reinforcement instructions, control the automatic grouting machine to reach the grouting position according to the reinforcement instructions, and control the grouting pressure and grouting volume according to the reinforcement instructions. During the grouting process, it monitors the settlement of the foundation in real time, and adjusts the grouting parameters according to the settlement until the grouting and lifting work of the target building is completed.

2. The automatic grouting monitoring and management system based on artificial intelligence according to claim 1 is characterized in that: The settlement monitoring module is equipped with a data collection system and a data processing system; wherein: The data collection system uses monitoring sensors installed on target buildings and foundations to collect settlement data, tilt data, and groundwater change data in real time, and uploads the collected data to the monitoring platform in real time via wireless transmission; The data processing system receives the monitoring data sent from the data collection system, and performs cleaning and anomaly detection on the monitoring data.

3. The automatic grouting monitoring and management system based on artificial intelligence according to claim 2 is characterized in that: The monitoring sensors include displacement sensors and tilt sensors, and the displacement sensors and tilt sensors are arranged at four corner points of the target building and at a middle position between two corner points; The monitoring sensor also includes a groundwater sensor, which is arranged at different soil layer depths to measure the conditions of groundwater at different depths.

4. An automatic grouting monitoring and management system based on artificial intelligence according to any one of claims 1 to 3, characterized in that: The step of constructing a building settlement prediction model comprises: Obtain historical monitoring data from the data collection system; divide the historical monitoring data into a training set and a test set based on the temporal characteristics of the historical monitoring data; Set the parameters of the extreme learning machine neural network, including the number of input layer nodes and the number of hidden layer nodes; The particle swarm algorithm is used to optimize the parameters of the extreme learning machine neural network, wherein the particle swarm algorithm uses the hidden layer weight as the optimization parameter and the root mean square error of the extreme learning machine as the fitness function, and minimizes the fitness function by continuously iteratively updating the hidden layer weight; The training set is used to train the extreme learning machine neural network with optimal parameters, and the test set is used to make predictions, calculate the prediction error, and correct the prediction model to complete the construction of the prediction model.

5. The automatic grouting monitoring and management system based on artificial intelligence according to claim 4 is characterized in that: In the particle swarm algorithm, set the population Y = (Y1, Y2, ..., Y n )’s position X i =[x i1 x i2 …x iD ] T ,The optimal particle is determined according to the particle fitness. The speed and position update formula of the particle iteration process is expressed as: In the formula, ω represents the inertia weight, c1 and c2 represent the learning factors; r1 and r2 represent random numbers between 0 and 1; Indicates the current optimal position of individual particles; represents the current optimal position of the particle population; k represents the number of iterations; represents the velocity of each particle in the population; Indicates the current position of the particle.

6. The automatic grouting monitoring and management system based on artificial intelligence according to claim 5 is characterized in that: The speed of the particle iteration process is limited to the interval [0, V max ]; the position of the particle during iteration is limited to [-X max , X max ]Inside.

7. The automatic grouting monitoring and management system based on artificial intelligence according to claim 6 is characterized in that: The multi-index evaluation system is used to evaluate the prediction results output by the prediction model, wherein the multi-index evaluation system includes root mean square error, mean absolute error and goodness of fit R 2 ; The root mean square error is calculated using the following formula: The mean absolute error is calculated using the following formula: The goodness of fit R 2 The following formula is used for calculation: In the formula, m represents the number of data samples; y i represents the actual value of the target building settlement in the i-th data sample; Represents the predicted value of the target building settlement in the i-th data sample.

8. The automatic grouting monitoring and management system based on artificial intelligence according to claim 7 is characterized in that: The automatic grouting monitoring and management system based on artificial intelligence also includes: The grouting verification module is used to input the prediction model according to the strength parameters of the current target building foundation after the grouting is completed, and to guide whether further grouting reinforcement is needed based on the prediction model results to prevent subsequent building settlement.

9. The automatic grouting monitoring and management system based on artificial intelligence according to claim 8 is characterized in that: The automatic grouting monitoring and management system based on artificial intelligence also includes: The lifting feedback module is used to feed back the progress of the grouting lifting work to the settlement monitoring module and monitor the lifting data of the target building.

Images