CN113779835A - AI and intelligent monitoring system based deep and large foundation pit safety early warning method - Google Patents
AI and intelligent monitoring system based deep and large foundation pit safety early warning method Download PDFInfo
- Publication number
- CN113779835A CN113779835A CN202111065176.1A CN202111065176A CN113779835A CN 113779835 A CN113779835 A CN 113779835A CN 202111065176 A CN202111065176 A CN 202111065176A CN 113779835 A CN113779835 A CN 113779835A
- Authority
- CN
- China
- Prior art keywords
- foundation pit
- deformation
- data
- monitoring
- soil pressure
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/02—Computing arrangements based on specific mathematical models using fuzzy logic
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
Abstract
The invention provides a deep and large foundation pit safety early warning method based on an AI and an intelligent monitoring system. Which comprises the following steps: establishing a soil pressure theory database and an input index database, and compiling an artificial neural network calculation program; by means of deep learning and self-adaption of an artificial neural network calculation program, the deformation of the foundation pit is used as a judgment index, a real-time optimal soil pressure calculation theory and corresponding soil body parameters are automatically called, and the deformation of the foundation pit is calculated; inputting monitoring data sent by an intelligent monitoring system in real time, predicting the deformation of a foundation pit in the future, and continuously correcting input indexes through an artificial neural network calculation program to ensure the accuracy of a prediction result; and setting a monitoring alarm value according to the safety level and the environmental protection level of the foundation pit engineering, and sending alarm information to the user side in time when the deformation exceeds the alarm value. The method can make the safety early warning and emergency guidance of the deep and large foundation pit more accurate and scientific.
Description
Technical Field
The invention belongs to the technical field of deep and large foundation pit construction, and particularly relates to a deep and large foundation pit safety early warning method based on an AI and an intelligent monitoring system.
Background
The foundation pit engineering is one of the project sub-projects with the longest time consumption, the highest cost and the largest risk coefficient in the building project. For this reason, the civil engineering works have especially emphasized that the collapse of earthwork and foundation pit is set as an important prevention and control target. The foundation pit construction is very complicated, has numerous unknown hidden danger factors, hardly accomplishes essential safety, except at the prudent demonstration of design phase and the scientific management of construction phase, the deformation monitoring data of timely master foundation pit formulates effectual solution, becomes the key measure of avoiding foundation pit safety in production accident.
A large number of engineering cases show that although foundation pit engineering cannot achieve intrinsic safety, casualty accidents can be effectively avoided through a reasonable monitoring and early warning method. 21/3/2021, foundation pit collapse accidents occur in urban areas in Hangzhou cities, and field constructors accidentally find that the situation of sinking and breaking of the road surface around the foundation pit exists, take emergency evacuation measures and avoid casualties.
The existing foundation pit deformation control and prediction method mainly has the following three defects: (1) the soil pressure theory is simplified in application, and a proper soil pressure theory cannot be dynamically selected according to the actual foundation pit deformation condition; (2) the soil pressure theory is still imperfect, and a soil pressure calculation theory under special working conditions of rainfall, traffic load, adjacent construction and the like needs to be established urgently; (3) the space-time variability of the physical and mechanical properties of the soil body in the construction process cannot be fully considered.
Disclosure of Invention
In view of the above, the present invention aims to provide a deep and large foundation pit safety early warning method based on an AI and an intelligent monitoring system, so that the deep and large foundation pit safety early warning and emergency guidance are more accurate and scientific, thereby ensuring the life safety of constructors and surrounding pedestrians.
The purpose of the invention can be realized by the following technical scheme: a deep and large foundation pit safety early warning method based on AI and an intelligent monitoring system is characterized by comprising the following steps: establishing a soil pressure theory database and an input index database, and compiling an artificial neural network calculation program; by means of deep learning and self-adaption of an artificial neural network calculation program, the deformation of the foundation pit is used as a judgment index, a real-time optimal soil pressure calculation theory and corresponding soil body parameters are automatically called, and the deformation of the foundation pit is calculated; inputting monitoring data sent by an intelligent monitoring system in real time, predicting the deformation of a foundation pit in the future, and continuously correcting input indexes through an artificial neural network calculation program to ensure the accuracy of a prediction result; and setting a monitoring alarm value according to the safety level and the environmental protection level of the foundation pit engineering, and sending alarm information to the user side in time when the deformation exceeds the alarm value.
In the above deep and large foundation pit safety early warning method based on the AI and the intelligent monitoring system, the establishing of the soil pressure theoretical database includes the following steps:
a1, establishing a deep and large foundation pit soil pressure theory dynamic database: analyzing and summarizing the applicability and the applicable conditions of different soil pressure theoretical models in different working conditions and different stages by comparing the predicted value of each soil pressure theory with finite element simulation and the change trend and the fitting degree of the soil pressure value actually measured in a test, segmenting each soil pressure theory aiming at different deformation stages of the foundation pit, and carrying out re-fusion and encapsulation on the soil pressure theoretical model section with better fitting degree;
a2, considering the influence of complex working conditions: the influence of vehicle load on soil pressure, the influence of short-time heavy rainfall working condition on soil pressure, the influence of foundation pit adjacent construction working condition on soil pressure and the influence of supporting structure failure working condition on soil pressure;
a3, establishing a soil pressure theory dynamic correction and calling criterion: the intelligent monitoring system is used for dynamically monitoring foundation pit engineering construction under various complex working conditions in real time, dynamically verifying and revising a newly-built soil pressure theory continuously according to field monitoring data, establishing a calling criterion of the soil pressure theory under various working conditions, and scientifically and reasonably calling a soil pressure theory dynamic database according to the monitoring data in real time.
In the above deep and large foundation pit safety early warning method based on the AI and the intelligent monitoring system, the establishing of the input index database includes:
b1, parameter sensitivity analysis: establishing a system model of a functional relation between deformation and each soil body parameter; according to the selected soil pressure theory, a corresponding reference parameter set is given; analyzing the sensitivity of each parameter to the deformation of the foundation pit by adopting a variable control method, and defining a main parameter and a secondary parameter; performing parameter sensitivity analysis at different deformation stages, recording analysis results, and writing the analysis results into a cloud database;
b2, quantitatively considering rainfall and adjacent construction conditions: respectively adopting effective rainfall Rc (mm) and disturbance degree rho to quantitatively describe two working conditions of rainfall and adjacent construction disturbance; the effective rainfall and the saturation of the soil in the rainfall influence area can establish the following relation:
d is rainfall influence depth, n is porosity and Si is initial saturation, and further the influence of rainfall analysis on the parameters of the soil body is converted into the influence of analysis saturation on the parameters of the soil body; establishing a relation between the saturation and the disturbance and main soil parameters by adopting a fuzzy mathematical method for correcting the soil parameters under a complex working condition;
b3, soil body parameter inverse analysis: according to parameter sensitivity analysis, selecting the main parameters of the current stage as inversion parameters; establishing a reverse analysis calculation finite element model, and selecting a proper soil pressure theoretical model; carrying out a multi-factor and multi-level test by adopting a uniform design method, and substituting the test simulation condition into a finite element model for calculation to obtain a training sample of the neural network; optimizing the weight and the threshold value by adopting a genetic algorithm, and constructing an optimal neural network; inputting the displacement data at different depths monitored in real time into the trained neural network structure to obtain corresponding inversion parameter values; and (c) under the working condition of rainfall or the working condition close to construction, further optimizing and processing the soil body parameters by combining the correction relation obtained in the step a 5.
In the above deep and large foundation pit safety early warning method based on AI and intelligent monitoring system, the artificial neural network calculation program is compiled by adopting a BP neural network structure, and the compiling step includes:
c1, creating a network: adopting a three-layer BP neural network, adopting an S-type logarithmic function logsig between an input layer and a hidden layer, adopting an S-type tangent function tansig between an output layer and the hidden layer, selecting a training function, adopting an S-type function as a transfer function of a middle hidden layer, wherein the S-type function is as follows:
wherein c is a slope function of the function, and Sigmoid functions with different slopes can be obtained by changing the parameter c;
c2, determination of number of hidden layer neurons: the optimal number of hidden units n1 is selected using the following formula:
wherein n is the number of input units, m is the number of output units, a belongs to [1,10 ]]A constant between;
c3, selecting training samples: monitoring data sent by an early-stage intelligent monitoring system is used as basic input data during intelligent analysis, and a plurality of groups of sample data are selected; carrying out normalization processing on the sample data by adopting a maximum and minimum value method;
c4, training and learning: dynamically monitoring the whole construction period of the foundation pit engineering by relying on an intelligent monitoring system, transmitting detection data to a built cloud intelligent computing platform to preprocess the data, combining the precision achieved by the processing training of the sample data in the step c3, better calculating the evolution process of the foundation pit, synchronously transmitting the data to a BIM model, establishing a dynamic change three-dimensional model of the foundation pit, observing the change process of the foundation pit in the BIM model, accurately predicting the deformation evolution process of the foundation pit in the future 3-7 days, and outputting prediction information to a platform user in real time.
In the deep and large foundation pit safety early warning method based on the AI and the intelligent monitoring system, establishing a command foundation pit monitoring early warning mechanism:
d1, transmitting the real-time monitoring data to a built cloud intelligent computing platform by combining with an intelligent monitoring system of the foundation pit, and preprocessing the obtained monitoring data;
d2, after repeatedly training the existing monitoring foundation pit cases to achieve the target precision, preliminarily calculating the construction information of the foundation pit in the future 3-7 days by the preprocessed monitoring data through a deep learning and self-adaptive system;
d3, importing the real-time foundation pit deformation monitoring data into a BIM model to generate a BIM visual dynamic cloud picture of the foundation pit deformation;
d4, outputting a foundation pit deformation prediction result to a platform user in real time, and providing a BIM visual dynamic deformation diagram according to requirements so as to visually describe the real-time deformation condition of the foundation pit;
d5, formulating different monitoring deformation alarm reference values according to the foundation pit engineering safety level and the environmental protection level. The former proposes the alarm value of the deformation and stress of the enclosure structure from the safety angle of the foundation pit engineering, and the latter is the alarm value of the deformation and water level change set according to the engineering experience and the statistical result of a large amount of measured data;
d6, when the predicted value of the deformation of the foundation pit exceeds the set alarm value, sending alarm information to a platform user, related constructors and related departments in time through the cloud service platform to remind that prevention and control measures are made in advance.
In the deep and large foundation pit safety early warning method based on the AI and the intelligent monitoring system, corresponding emergency control strategies are formulated according to different situations:
e1, extreme weather: when severe weather such as rainstorm and the like suddenly occurs, the underground water level in the foundation pit can be reduced by adopting the precast concrete pipe well, rainwater and ground water are timely removed by assisting an open trench, or settlement deformation is controlled by adopting means such as pressure grouting reinforcement and the like, so that accidents such as foundation pit collapse and the like caused by sudden change of extreme weather are prevented;
e2, construction in close proximity: in the construction process, the information of the foundation pit is monitored in real time under the condition that buildings are adjacent to the periphery, the construction scheme can be modified in time according to the early warning information and the decision made by an expert team, the deformation of the peripheral soil body caused by excavation is strictly controlled, and the peripheral buildings are prevented from being influenced by the excavation of the foundation pit. The measures that can be specifically adopted are: before excavation, adopting compaction grouting reinforcement measures outside the water-stopping pile; the side truss is supported and increased to enhance the controlled deformation strength; reinforcement of adjacent buildings, etc.
e3, environmental sensitivity: similar to the adjacent construction, for the construction beside natural cultural relics or major projects, various protection technologies are adopted in the construction according to the information of real-time monitoring and early warning, for example, an isolation pile is arranged between a foundation pit and a protection building, and the safety of the surrounding building and the environment is ensured.
e4, failure of support: according to the information monitored in real time, starting from monitoring objects such as vertical deformation and support internal force of the maintenance structure, the early warning information sent is combined, and the expert judges whether the supporting structure can ensure safety or not according to the early warning information, and whether reinforcement is needed or not, or support replacement and support removal are carried out, so that the safety of constructors is guaranteed, and unnecessary construction site accidents are avoided.
In the deep and large foundation pit safety early warning method based on the AI and the intelligent monitoring system, the soil pressure theoretical model comprises a sine function model, an exponential-like function model, a hyperbolic function model, a fitting function model and a semi-numerical value semi-analytic model.
In the safety early warning method for the deep and large foundation pit based on the AI and the intelligent monitoring system, the intelligent monitoring system comprises a detection subsystem, a data transmission subsystem and a data summarization processing subsystem, wherein the detection subsystem is used for detecting and outputting data information of inclination measurement, axial force, displacement, water level and inclination of an adjacent building of the foundation pit; the data transmission subsystem is used for transmitting the data information of the detection subsystem to the data summarizing and processing subsystem through the Internet of things and/or a 5G communication network; the data summarization processing subsystem is used for automatically storing and analyzing the received data information, outputting a monitoring report and automatically sending early warning information.
In the AI and intelligent monitoring system based deep and large foundation pit safety early warning method, the detection subsystem comprises a foundation pit inclination measuring module, an axial force monitoring module, a displacement detection module, a water level detection module, an adjacent building inclination module and a precipitation module; the data transmission subsystem comprises a ZigBee module and/or a 5G communication module; the data gathering processing subsystem comprises a user side and a cloud intelligent computing and service platform which can interact with each other, the user side comprises a PC (personal computer) end and a mobile phone end, and the cloud intelligent computing and service platform is connected with a database.
Compared with the prior art, the deep and large foundation pit safety early warning method based on the AI and the intelligent monitoring system has the following advantages: the method comprises the steps of firstly establishing a soil pressure theory under three typical working conditions of considering traffic load, rainstorm erosion and adjacent construction, analyzing the advantages and the applicable conditions of the common soil pressure theory on the basis, segmenting and packaging different theoretical models, establishing a deep and large foundation pit soil pressure theory dynamic database, and determining fuzzy membership functions and weights of all input indexes in foundation pit deformation calculation by using a fuzzy mathematical method. And dynamically verifying the soil pressure theoretical model and the soil body parameters by using real-time dynamic monitoring data and an AI intelligent calculation method, so as to realize accurate prejudgment on dynamic deformation of the foundation pit. And a corresponding early warning mechanism and an emergency control strategy are established, so that the life safety of constructors and surrounding pedestrians is improved.
Drawings
Fig. 1 is a schematic diagram of an intelligent monitoring system of an embodiment.
Fig. 2 is an expanded schematic diagram of the intelligent monitoring system of the embodiment.
Fig. 3 is a schematic diagram illustrating a deep and large foundation pit safety precaution method based on the AI and intelligent monitoring system according to the embodiment.
FIG. 4 is a reverse analysis flow of the embodiment.
Fig. 5 is a flow diagram of an intelligent warning and emergency control strategy of an embodiment.
In the figure, 1, a detection subsystem; 2. a data transmission subsystem; 3. a data summarization processing subsystem; 4. a foundation pit inclination measuring module; 5. an axial force monitoring module; 6. a displacement detection module; 7. a water level detection module; 8. an adjacent building tilt module; 9. a precipitation module; 10. A ZigBee module; 11. 5G communication module; 12. a cloud intelligent computing and service platform; 13. a PC terminal; 14. a mobile phone terminal; 15. a database.
Detailed Description
The following are specific embodiments of the present invention and are further described with reference to the drawings, but the present invention is not limited to these embodiments.
As shown in fig. 1 to 3, the intelligent detection system related to the deep and large foundation pit safety early warning method based on the AI and the intelligent monitoring system is composed of three subsystems: the first subsystem is a detection subsystem 1 with high precision, micro power consumption and good durability, and is used for detecting and outputting data information of foundation pit inclination measurement, axial force, displacement, water level and adjacent building inclination. The second subsystem is a data transmission subsystem 2 which transmits the data information of the detection subsystem 1 to a data summarizing and processing subsystem 3 in real time and dynamically by using the internet of things and 5G transmission technology. The third subsystem is a data summarizing and processing subsystem 3 which is built based on a B/S architecture, is mainly used for automatically storing and analyzing received data information, outputting a monitoring report and automatically sending early warning information.
Specifically, the detection subsystem 1 includes: foundation pit inclination measuring module 4: the method is used for measuring the deep horizontal displacement of the foundation pit support structure or the surrounding soil body. When the area to be measured deforms, the inclinometer pipe also tilts along with the deformation, and the inclinometer sensor is driven. By analyzing the data of the inclinometer sensor, the module fits the section of the inclinometer pipe to obtain the change of the section within a period of time, namely the displacement variation of the area to be measured. The axial force monitoring module 5: for measuring long term strains of foundations, piles, supports, beams, etc. The embedded type or patch type vibrating wire strain gauge is adopted, wherein the embedded type vibrating wire strain gauge can be directly embedded into concrete. The temperature sensor built in the module can monitor the temperature at the measuring point at the same time. The displacement detection module 6: and measuring parameters such as transverse displacement, vertical settlement and the like of the monitoring points. The two-dimensional area array laser displacement meter mainly uses the relative displacement between a laser emission point and a light panel acquisition instrument to mainly measure the parameters of transverse displacement, vertical settlement and the like of a building or a monitoring point. Adjacent building tilt module 8: and directly outputting a horizontal inclination angle value in a digital signal mode by adopting an MEMS accelerometer and a high-resolution differential digital-to-analog converter. Water level detection module 7: the underground water monitoring sensor based on the pressure sensing technology is adopted, the sensor can directly measure the liquid level height through temperature compensation calculation, and the sensor can be applied to sites needing water level data monitoring, such as foundation pits, subways and the like. Precipitation module 9: the module is formed by combining a liquid level sensor and an Internet of things communication controller, can automatically control the operation of a water pump, and can transmit water level data in real time.
The data transmission subsystem 2 comprises a ZigBee module 10 and/or a 5G communication module 11. In this embodiment, it is preferably implemented by a combination of the ZigBee module 10 and the 5G communication module 11. The ZigBee module 10 sends the data information collected by the detection subsystem 1 to the data summarizing and processing subsystem 3 in real time in a bidirectional wireless communication mode based on the Internet of things. After each sensor module of the detection subsystem 1 automatically collects data information through the data collector, the ZigBee module 10 arranged in the data collector sends digital signals generated by the sensor modules to the data summarizing and processing subsystem 3 in a wireless communication mode, and the receiving and sending speed can reach 1 Mbit/s. The 5G communication module 11 is used for transmitting the data information acquired by the detection subsystem 1 to the data summarizing and processing subsystem 3 in real time. Based on the 5G communication transmission technology, each sensor module of the detection subsystem 1 transmits the automatically acquired data information to the data summarizing and processing subsystem 3 in real time through the built-in 5G communication module 11, so that the multi-angle and multi-dimensional reflection of the foundation pit deformation evolution process is realized.
The data summarizing and processing subsystem 3 comprises a user side capable of interacting with the cloud intelligent computing and service platform 12. The user side comprises a PC end 13 and a mobile phone end 14; the built BIM model is prestored in the cloud intelligent computing and service platform 12, and the cloud intelligent computing and service platform 12 is connected with a database 15.
The cloud intelligent computing and service platform 12 adopts an arry server architecture. In order to conduct organizing collection and summary analysis on a large amount of data occurring in the construction process of foundation pit engineering, the cloud intelligent computing and service platform 12 is displayed by a large-screen intelligent monitoring system and mainly comprises project basic information, project quantity statistics, equipment online conditions, monitoring sensor types and real-time data, and storage, data analysis and automatic early warning of received signals by means of a cloud server are achieved preliminarily. It should be noted that: in other embodiments of the present invention, architectures such as an Tencent cloud platform and a Baidu cloud platform may also be employed.
On the basis of the intelligent monitoring system, the deep and large foundation pit safety early warning method based on the AI and the intelligent monitoring system comprises the following steps: establishing a soil pressure theory database and an input index database, and compiling an artificial neural network calculation program; by means of deep learning and self-adaption of an artificial neural network calculation program, the deformation of the foundation pit is used as a judgment index, a real-time optimal soil pressure calculation theory and corresponding soil body parameters are automatically called, and the deformation of the foundation pit is calculated; inputting monitoring data sent by an intelligent monitoring system in real time, predicting the deformation of a foundation pit in the future, and continuously correcting input indexes through an artificial neural network calculation program to ensure the accuracy of a prediction result; and setting a monitoring alarm value according to the safety level and the environmental protection level of the foundation pit engineering, and sending alarm information to the user side in time when the deformation exceeds the alarm value.
Specifically, different soil pressure theories have advantages under different working conditions of foundation pit deformation, and the whole foundation pit deformation process can not be predicted only by using a certain soil pressure theory singly, so that in order to achieve an accurate prediction effect, the existing soil pressure theories are segmented and fused to establish a dynamic database of the soil pressure theory of the deep and large foundation pit; meanwhile, in order to fully consider the complex working conditions and the construction environment in the foundation pit construction process, the influence of each factor on the deformation of the foundation pit is explored by means of theoretical analysis, numerical simulation and model test, and the soil pressure theoretical database is optimized according to the influence; and finally, establishing a scientific and reasonable fine calling criterion of the soil pressure theory based on the soil pressure theory database, and reasonably calling the soil pressure theory dynamic database according to the real-time monitoring data. It should be noted that the soil pressure theoretical model includes a sinusoidal function model, an exponential-like function model, a hyperbolic function model, a fitting function model, a half-numerical semi-analytic model, and the like, and is characterized in that:
TABLE 1 theoretical model of soil pressure
The concrete scheme for establishing the soil pressure theory database and the input index database is as follows:
a1, establishing a deep and large foundation pit soil pressure theory dynamic database: analyzing and summarizing the applicability and the applicable conditions of different soil pressure theoretical models in different working conditions and different stages by comparing the predicted value of each soil pressure theory with finite element simulation and the change trend and the fitting degree of the soil pressure value actually measured in a test, segmenting each soil pressure theory aiming at different deformation stages of the foundation pit, and carrying out re-fusion and encapsulation on the soil pressure theoretical model section with better fitting degree; when the step is executed, the applicability of each soil pressure theoretical model at different stages of foundation pit deformation is analyzed based on the existing soil pressure theoretical model. And simulating the stress deformation of the foundation pit by using research means such as ABAQUS finite element calculation software, model tests and the like. Meanwhile, carrying out finite element simulation by using commercial software ABAQUS, simulating the whole process of foundation pit excavation construction, and extracting the horizontal displacement of the soil body and the soil pressure value on the supporting structure to obtain the rule that the soil pressure changes along with the displacement.
a2, considering the influence of complex working conditions: the influence of vehicle load on soil pressure, the influence of short-time heavy rainfall working condition on soil pressure, the influence of foundation pit close to construction working condition on soil pressure, and the influence of supporting structure failure working condition on soil pressure.
The method aims at the influence of vehicle load on soil pressure. The vehicle load can be decomposed into static force and dynamic force, wherein the static load can be regarded as uniformly distributed load, and the dynamic load can be converted into horizontal inertia force according to a statics method. And deducing a calculation expression of the soil pressure of the support structure under the action of the vehicle load based on a limit balance analysis theory.
And secondly, aiming at the short-time heavy rainfall working condition. The influence of rainfall on soil mass gravity and strength indexes and hydrostatic pressure generated by a supporting structure are considered, a soil mass gravity reduction coefficient, a soil mass shear strength index correction coefficient and a hydrostatic pressure calculation model are introduced, and an existing soil pressure theory is corrected in a mechanism. And thirdly, researching the soil pressure theory under the working condition of the close proximity of the foundation pit to the construction. The excavation of the deep foundation pit can cause the displacement of soil mass below the peripheral earth surface to interact with the existing adjacent underground structures, and meanwhile, the existing adjacent building structures around the foundation pit can also generate additional stress on the foundation pit supporting structure, so that the distribution of the soil pressure on the supporting structure is influenced.
And fourthly, aiming at the research of the soil pressure theory under the working condition of the supporting structure failure, through the foundation pit supporting structure failure model test, the research of the soil pressure theory under the working condition of the supporting structure failure can be developed, and then the soil pressure theory dynamic database is supplemented with relevant theories.
a3, establishing a soil pressure theory dynamic correction and calling criterion: the intelligent monitoring system is used for dynamically monitoring foundation pit engineering construction under various complex working conditions in real time, dynamically verifying and revising a newly-built soil pressure theory continuously according to field monitoring data, establishing a calling criterion of the soil pressure theory under various working conditions, and scientifically and reasonably calling a soil pressure theory dynamic database according to the monitoring data in real time.
And aiming at the time-space variability of the input index, based on the deformation data obtained by a real-time intelligent monitoring system, a BP neural network is adopted to be combined with a genetic algorithm to carry out dynamic inversion analysis, so as to obtain the real-time optimal soil body parameter. The specific scheme is as follows:
b1, parameter sensitivity analysis: the first step of the sensitivity analysis is to establish a system model, namely a functional relation between deformation and each soil body parameter; according to the selected soil pressure theory, a corresponding reference parameter set is given; analyzing the sensitivity of each parameter to the deformation of the foundation pit by adopting a variable control method, and defining that when the variation range of each parameter is +/-30%, if the absolute value of the variation rate of the calculation result exceeds 10%, the parameter is defined as a main parameter, otherwise, the parameter is positioned as a secondary parameter; and in different deformation stages, performing parameter sensitivity analysis, recording analysis results, and writing the analysis results into a cloud database.
b2, quantitatively considering rainfall and adjacent construction conditions: respectively adopting effective rainfall Rc (mm) and disturbance degree rho to quantitatively describe two working conditions of rainfall and adjacent construction disturbance; the effective rainfall and the saturation of the soil in the rainfall influence area can establish the following relation:
d is rainfall influence depth, n is porosity and Si is initial saturation, and further the influence of rainfall analysis on the parameters of the soil body is converted into the influence of analysis saturation on the parameters of the soil body; establishing a relation between the saturation and the disturbance and main soil parameters by adopting a fuzzy mathematical method for correcting the soil parameters under a complex working condition;
b3, soil body parameter inverse analysis: according to parameter sensitivity analysis, selecting the main parameters of the current stage as inversion parameters; establishing a reverse analysis calculation finite element model, and selecting a proper soil pressure theoretical model; carrying out a multi-factor and multi-level test by adopting a uniform design method, and substituting the test simulation condition into a finite element model for calculation to obtain a training sample of the neural network; optimizing the weight and the threshold value by adopting a genetic algorithm, and constructing an optimal neural network; inputting the displacement data at different depths monitored in real time into the trained neural network structure to obtain corresponding inversion parameter values; and (c) under the working condition of rainfall or the working condition close to construction, further optimizing and processing the soil body parameters by combining the correction relation obtained in the step a 5. The specific reverse analysis flow is shown in fig. 4.
The calculation program of the artificial neural network is compiled by adopting a BP neural network structure, and the compiling steps comprise:
c1, creating a network: the S-type logarithmic function logsig is adopted between the input layer and the hidden layer, the S-type tangent function tansig is adopted between the output layer and the hidden layer, the training function selects the tractdx, the BP network structure has a structure with three layers or more than three layers, and any N-dimensional to M-dimensional mapping can be completed by one 3-layer BP network, and any classification and identification can be completed by the S-type transfer function. Therefore, a three-layer BP neural network is adopted, and the transfer function of the middle hidden layer adopts an S shape. The sigmoid function is:
wherein c is a slope function of the function, and Sigmoid functions with different slopes can be obtained by changing the parameter c;
c2, determination of number of hidden layer neurons: the selection of the number of hidden neurons is a very complex problem, and a certain ideal analytical formula does not exist, and the number of hidden neurons needs to be determined according to the experience of a designer and multiple experiments. The number of hidden units has a direct relationship with the requirements of the problem and the number of input and output units. Too many hidden units result in too long learning practice, non-optimal error, poor fault tolerance and inability to identify newly input sample data. The optimal number of hidden units n1 is selected using the following formula:
wherein n is the number of input units, m is the number of output units, a belongs to [1,10 ]]A constant between;
c3, selecting training samples: monitoring data sent by an early-stage intelligent monitoring system is used as basic input data during intelligent analysis, and a plurality of groups of sample data are selected; carrying out normalization processing on the sample data by adopting a maximum and minimum value method;
c4, training and learning: dynamically monitoring the whole construction period of the foundation pit engineering by relying on an intelligent monitoring system, transmitting detection data to a built cloud intelligent computing platform to preprocess the data, combining the precision achieved by the processing training of the sample data in the step c3, better calculating the evolution process of the foundation pit, synchronously transmitting the data to a BIM model, establishing a dynamic change three-dimensional model of the foundation pit, observing the change process of the foundation pit in the BIM model, accurately predicting the deformation evolution process of the foundation pit in the future 3-7 days, and outputting prediction information to a platform user in real time.
The learning and prediction of the intelligent program are realized by utilizing the self-learning function, the association storage function and the capability of searching the optimized solution at high speed of the BP artificial neural network. The hidden layer of the BP artificial neural network is a key layer which exerts the self-learning and self-adaptability functions. Is a layer formed by a plurality of neurons and links between an input layer and an output layer. It inputs the basic indexes and monitoring data of the layer and the time-lapse deformation development changes of the basic indexes and the monitoring data at different moments. The artificial neural network is trained by utilizing the existing large database of foundation pit construction information and a large amount of sample data so as to achieve good calculation precision. The neural network analysis method has learnability, and the larger the sample data quantity is, the more accurate the prediction is. And with the continuous and autonomous learning of the algorithm, the prediction precision can be continuously improved, and with the application of a plurality of projects and the collection of mass data, the optimization and the perfection are continuously realized. With the collection of large data and machine learning, a greater variety of data is utilized, and the accuracy and the operation speed are continuously improved. The method is applied to intelligent monitoring and early warning of a newly-built foundation pit, dynamic correction is carried out on a prediction result by utilizing real-time monitoring data, and then prediction data of corresponding values at the next moment of each measuring point can be output according to a BP artificial neural network.
In an embodiment of the present invention, the method of the present invention further includes establishing a mechanism for commanding monitoring and early warning of the foundation pit, and sending emergency warning information to the platform user when the deformation of the foundation pit exceeds a warning value, and the specific steps are as follows:
d1, transmitting the real-time monitoring data to a built cloud intelligent computing platform by combining with an intelligent monitoring system of the foundation pit, and preprocessing the obtained monitoring data;
d2, after repeatedly training the existing monitoring foundation pit cases to achieve the target precision, preliminarily calculating the construction information of the foundation pit in the future 3-7 days by the preprocessed monitoring data through a deep learning and self-adaptive system;
d3, importing the real-time foundation pit deformation monitoring data into a BIM model to generate a BIM visual dynamic cloud picture of the foundation pit deformation;
d4, outputting a foundation pit deformation prediction result to a platform user in real time, and providing a BIM visual dynamic deformation diagram according to requirements so as to visually describe the real-time deformation condition of the foundation pit;
d5, formulating different monitoring deformation alarm reference values according to the foundation pit engineering safety level and the environmental protection level respectively (as shown in tables 2 and 3). The former proposes the alarm value of the deformation and stress of the enclosure structure from the safety angle of the foundation pit engineering, and the latter is the alarm value of the deformation and water level change set according to the engineering experience and the statistical result of a large amount of measured data;
TABLE 2 determination of alarm values according to the foundation pit engineering safety class
TABLE 3 determination of alarm values according to the environmental protection level of the foundation pit engineering
d6, when the predicted value of the deformation of the foundation pit exceeds the set alarm value, sending alarm information to a platform user, related constructors and related departments in time through the cloud service platform to remind that prevention and control measures are made in advance.
In another embodiment of the present invention, the method of the present invention further comprises formulating corresponding emergency control strategies for different scenarios.
Aiming at emergency situations possibly encountered by the intelligent foundation pit monitoring system in the service process, such as extreme weather, close-proximity construction, environment sensitivity, failure of a supporting structure and other working conditions, a request is sent to the cloud intelligent computing and service platform through a user side, the cloud intelligent computing and service platform calls a foundation pit monitoring and early warning command mechanism and combines an emergency strategy database, corresponding emergency measures are taken for the user to feed back and deal with the working conditions, and part of key control equipment is remotely controlled. And (4) repeatedly training the BP artificial neural network, and calculating the precision of the cloud intelligent calculation and service platform. And (4) combining real-time measurement data, preprocessing the real-time measurement data, making a scientific and reasonable emergency strategy, estimating the implementation effect, and sending early warning information and a corresponding strategy to a user in time. And meanwhile, the catastrophe simulation evolution process of the foundation pit built by the BIM is watched according to the proposed emergency strategy, the drilling is continuously carried out, the emergency result is observed, and the best-fit BIM model is selected by combining the data measured in real time to analyze the future evolution of the foundation pit. In the construction process, engineering technicians serve as auxiliary decisions according to the received early warning information and BIM model emergency drilling results, provide related suggestions and determine a final emergency scheme; the supervision personnel can give an early warning to inform related personnel before an accident occurs, and ask for constructors to stop, so that the safety is ensured; meanwhile, constructors can rapidly respond when danger signals appear, so that dangerous accidents are prevented or the influence of the accidents is reduced.
Fig. 5 shows a flow chart of an intelligent early warning and emergency control strategy for a deep and large foundation pit, the cloud intelligent computing and service platform predicts deformation under an emergency condition and sends early warning information to the client in time, and meanwhile, the cloud intelligent computing and service platform selects a proper emergency measure from the database and sends the measure to constructors of the client according to response to the emergency condition. The invention provides partial automatic early warning information and emergency strategies aiming at different working conditions, and specifically comprises the following steps:
e1, extreme weather: when severe weather such as rainstorm occurs suddenly, the underground water level in the foundation pit can be reduced by adopting the precast concrete pipe well, rainwater and ground water are timely removed by assisting an open trench, or settlement deformation is controlled by adopting means such as pressure grouting reinforcement, and accidents such as foundation pit collapse caused by sudden change of extreme weather are prevented.
e2, construction in close proximity: in the construction process, the information of the foundation pit is monitored in real time under the condition that buildings are adjacent to the periphery, the construction scheme can be modified in time according to the early warning information and the decision made by an expert team, the deformation of the peripheral soil body caused by excavation is strictly controlled, and the peripheral buildings are prevented from being influenced by the excavation of the foundation pit. The measures that can be specifically adopted are: before excavation, adopting compaction grouting reinforcement measures outside the water-stopping pile; the side truss is supported and increased to enhance the controlled deformation strength; reinforcement of adjacent buildings, etc.
e3, environmental sensitivity: similar to the adjacent construction, for the construction beside natural cultural relics or major projects, various protection technologies are adopted in the construction according to the information of real-time monitoring and early warning, for example, an isolation pile is arranged between a foundation pit and a protection building, and the safety of the surrounding building and the environment is ensured.
e4, failure of support: according to the information monitored in real time, starting from monitoring objects such as vertical deformation and support internal force of the maintenance structure, the early warning information sent is combined, and the expert judges whether the supporting structure can ensure safety or not according to the early warning information, and whether reinforcement is needed or not, or support replacement and support removal are carried out, so that the safety of constructors is guaranteed, and unnecessary construction site accidents are avoided.
The specific embodiments described herein are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments or alternatives may be employed by those skilled in the art without departing from the spirit or ambit of the invention as defined in the appended claims.
Claims (9)
1. A deep and large foundation pit safety early warning method based on AI and an intelligent monitoring system is characterized by comprising the following steps: establishing a soil pressure theory database and an input index database, and compiling an artificial neural network calculation program; by means of deep learning and self-adaption of an artificial neural network calculation program, the deformation of the foundation pit is used as a judgment index, a real-time optimal soil pressure calculation theory and corresponding soil body parameters are automatically called, and the deformation of the foundation pit is calculated; inputting monitoring data sent by an intelligent monitoring system in real time, predicting the deformation of a foundation pit in the future, and continuously correcting input indexes through an artificial neural network calculation program to ensure the accuracy of a prediction result; and setting a monitoring alarm value according to the safety level and the environmental protection level of the foundation pit engineering, and sending alarm information to the user side in time when the deformation exceeds the alarm value.
2. The AI and intelligent monitoring system based deep and large foundation pit safety precaution method according to claim 1, wherein said building of a theoretical database of soil pressure comprises the steps of:
a1, establishing a deep and large foundation pit soil pressure theory dynamic database: analyzing and summarizing the applicability and the applicable conditions of different soil pressure theoretical models in different working conditions and different stages by comparing the predicted value of each soil pressure theory with finite element simulation and the change trend and the fitting degree of the soil pressure value actually measured in a test, segmenting each soil pressure theory aiming at different deformation stages of the foundation pit, and carrying out re-fusion and encapsulation on the soil pressure theoretical model section with better fitting degree;
a2, considering the influence of complex working conditions: the influence of vehicle load on soil pressure, the influence of short-time heavy rainfall working condition on soil pressure, the influence of foundation pit adjacent construction working condition on soil pressure and the influence of supporting structure failure working condition on soil pressure;
a3, establishing a soil pressure theory dynamic correction and calling criterion: the intelligent monitoring system is used for dynamically monitoring foundation pit engineering construction under various complex working conditions in real time, dynamically verifying and revising a newly-built soil pressure theory continuously according to field monitoring data, establishing a calling criterion of the soil pressure theory under various working conditions, and scientifically and reasonably calling a soil pressure theory dynamic database according to the monitoring data in real time.
3. The AI-and-intelligent-monitoring-system-based deep and large foundation pit safety pre-warning method according to claim 1 or 2, wherein the establishment of the input index database comprises:
b1, parameter sensitivity analysis: establishing a system model of a functional relation between deformation and each soil body parameter; according to the selected soil pressure theory, a corresponding reference parameter set is given; analyzing the sensitivity of each parameter to the deformation of the foundation pit by adopting a variable control method, and defining a main parameter and a secondary parameter; performing parameter sensitivity analysis at different deformation stages, recording analysis results, and writing the analysis results into a cloud database;
b2, quantitatively considering rainfall and adjacent construction conditions: respectively adopting effective rainfall Rc (mm) and disturbance degree rho to quantitatively describe two working conditions of rainfall and adjacent construction disturbance; the effective rainfall and the saturation of the soil in the rainfall influence area can establish the following relation:
d is rainfall influence depth, n is porosity and Si is initial saturation, and further the influence of rainfall analysis on the parameters of the soil body is converted into the influence of analysis saturation on the parameters of the soil body; establishing a relation between the saturation and the disturbance and main soil parameters by adopting a fuzzy mathematical method for correcting the soil parameters under a complex working condition;
b3, soil body parameter inverse analysis: according to parameter sensitivity analysis, selecting the main parameters of the current stage as inversion parameters; establishing a reverse analysis calculation finite element model, and selecting a proper soil pressure theoretical model; carrying out a multi-factor and multi-level test by adopting a uniform design method, and substituting the test simulation condition into a finite element model for calculation to obtain a training sample of the neural network; optimizing the weight and the threshold value by adopting a genetic algorithm, and constructing an optimal neural network; inputting the displacement data at different depths monitored in real time into the trained neural network structure to obtain corresponding inversion parameter values; and (c) under the working condition of rainfall or the working condition close to construction, further optimizing and processing the soil body parameters by combining the correction relation obtained in the step a 5.
4. The AI-and-intelligent-monitoring-system-based deep and large foundation pit safety early warning method according to claim 1 or 2, wherein the artificial neural network calculation program is compiled by adopting a BP neural network structure, and the compiling step comprises:
c1, creating a network: adopting a three-layer BP neural network, adopting an S-type logarithmic function logsig between an input layer and a hidden layer, adopting an S-type tangent function tansig between an output layer and the hidden layer, selecting a training function, adopting an S-type function as a transfer function of a middle hidden layer, wherein the S-type function is as follows:
wherein c is a slope function of the function, and Sigmoid functions with different slopes can be obtained by changing the parameter c;
c2, determination of number of hidden layer neurons: the optimal number of hidden units n1 is selected using the following formula:
wherein n is the number of input units, m is the number of output units, a belongs to [1,10 ]]A constant between;
c3, selecting training samples: monitoring data sent by an early-stage intelligent monitoring system is used as basic input data during intelligent analysis, and a plurality of groups of sample data are selected; carrying out normalization processing on the sample data by adopting a maximum and minimum value method;
c4, training and learning: dynamically monitoring the whole construction period of the foundation pit engineering by relying on an intelligent monitoring system, transmitting detection data to a built cloud intelligent computing platform to preprocess the data, combining the precision achieved by the processing training of the sample data in the step c3, better calculating the evolution process of the foundation pit, synchronously transmitting the data to a BIM model, establishing a dynamic change three-dimensional model of the foundation pit, observing the change process of the foundation pit in the BIM model, accurately predicting the deformation evolution process of the foundation pit in the future 3-7 days, and outputting prediction information to a platform user in real time.
5. The AI-and-intelligent-monitoring-system-based deep and large foundation pit safety pre-warning method according to claim 1 or 2, further comprising establishing a command foundation pit monitoring pre-warning mechanism:
d1, transmitting the real-time monitoring data to a built cloud intelligent computing platform by combining with an intelligent monitoring system of the foundation pit, and preprocessing the obtained monitoring data;
d2, after repeatedly training the existing monitoring foundation pit cases to achieve the target precision, preliminarily calculating the construction information of the foundation pit in the future 3-7 days by the preprocessed monitoring data through a deep learning and self-adaptive system;
d3, importing the real-time foundation pit deformation monitoring data into a BIM model to generate a BIM visual dynamic cloud picture of the foundation pit deformation;
d4, outputting a foundation pit deformation prediction result to a platform user in real time, and providing a BIM visual dynamic deformation diagram according to requirements so as to visually describe the real-time deformation condition of the foundation pit;
d5, formulating different monitoring deformation alarm reference values according to the foundation pit engineering safety level and the environmental protection level respectively;
d6, when the predicted value of the deformation of the foundation pit exceeds the set alarm value, sending alarm information to a platform user, related constructors and related departments in time through the cloud service platform to remind that prevention and control measures are made in advance.
6. The AI-and-intelligent-monitoring-system-based deep and large foundation pit safety early warning method according to claim 1 or 2, further comprising formulating corresponding emergency control strategies for different scenarios:
e1, extreme weather: when severe weather such as rainstorm and the like suddenly occurs, the underground water level in a foundation pit can be reduced by adopting a precast concrete pipe well, and additionally, open ditches are used for timely removing rainwater and ground water, or pressure grouting reinforcement is adopted;
e2, construction in close proximity: in the construction process, the foundation pit information is monitored in real time under the condition that buildings are arranged near the periphery, and the construction scheme can be modified in time according to the early warning information and the decision made by an expert team;
e3, environmental sensitivity: similar to the adjacent construction, for the construction beside natural cultural relics or major projects, a protection technology is adopted in the construction according to the information of real-time monitoring and early warning;
e4, failure of support: according to the information monitored in real time, starting from monitoring objects such as vertical deformation and support internal force of the maintenance structure, the early warning information sent is combined, and the expert judges whether the supporting structure can ensure safety or not according to the early warning information, and whether reinforcement is needed or not or whether support replacement and support removal are needed or not.
7. The AI-and-intelligent-monitoring-system-based deep and large foundation pit safety pre-warning method of claim 2, wherein the theoretical soil pressure model comprises a sinusoidal function model, an exponential-like function model, a hyperbolic function model, a fitting function model and a semi-numerical semi-analytic model.
8. The AI and intelligent monitoring system based deep and large foundation pit safety precaution method according to claim 1, characterized in that the intelligent monitoring system comprises a detection subsystem (1), a data transmission subsystem (2) and a data summarization processing subsystem (3), the detection subsystem (1) is used for detecting and outputting data information of the foundation pit inclination measurement, axial force, displacement, water level and adjacent building inclination; the data transmission subsystem (2) is used for transmitting the data information of the detection subsystem (1) to the data summarizing and processing subsystem (3) through the Internet of things and/or a 5G communication network; and the data summarizing and processing subsystem (3) is used for automatically storing and analyzing the received data information, outputting a monitoring report and automatically sending early warning information.
9. The AI and intelligent monitoring system based deep and large foundation pit safety precaution method of claim 8, characterized in that the detection subsystem (1) comprises a foundation pit inclination measuring module (4), an axial force monitoring module (5), a displacement detection module (6), a water level detection module (7), an adjacent building inclination module (8) and a precipitation module (9); the data transmission subsystem (2) comprises a ZigBee module (10) and/or a 5G communication module (11); the data summarization processing subsystem (3) comprises a user side capable of interacting and a cloud intelligent computing and service platform (12), the user side comprises a PC (personal computer) end (13) and a mobile phone end (14), and the cloud intelligent computing and service platform (12) is connected with a database (15).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111065176.1A CN113779835A (en) | 2021-09-11 | 2021-09-11 | AI and intelligent monitoring system based deep and large foundation pit safety early warning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111065176.1A CN113779835A (en) | 2021-09-11 | 2021-09-11 | AI and intelligent monitoring system based deep and large foundation pit safety early warning method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113779835A true CN113779835A (en) | 2021-12-10 |
Family
ID=78842728
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111065176.1A Withdrawn CN113779835A (en) | 2021-09-11 | 2021-09-11 | AI and intelligent monitoring system based deep and large foundation pit safety early warning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113779835A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114154226A (en) * | 2022-02-10 | 2022-03-08 | 济宁明珠建筑工程有限公司 | Foundation pit stability monitoring method |
| CN114592525A (en) * | 2022-03-16 | 2022-06-07 | 深圳宏业基岩土科技股份有限公司 | Intelligent monitoring prevention and control system for inner support of deep and large foundation pit |
| CN114844922A (en) * | 2022-04-25 | 2022-08-02 | 海南水文地质工程地质勘察院 | Foundation pit safety monitoring system based on Internet of things |
| CN114855847A (en) * | 2022-07-06 | 2022-08-05 | 江苏中安建设集团有限公司 | Intelligent control method for construction site foundation pit dewatering system |
| CN115167212A (en) * | 2022-07-13 | 2022-10-11 | 中交第三航务工程局有限公司 | Foundation pit dynamic construction control system and method based on monitoring platform |
| CN115404840A (en) * | 2022-08-24 | 2022-11-29 | 中南大学 | Damage perception and catastrophe early warning intelligent geotextile based on deep learning |
| CN115574765A (en) * | 2022-12-08 | 2023-01-06 | 天津风霖物联网科技有限公司 | Big data-based monitoring system for engineering measurement |
| CN116069071A (en) * | 2023-03-24 | 2023-05-05 | 冠鲁建设股份有限公司 | Construction optimization system, method, device and medium based on big data |
| CN116227932A (en) * | 2023-03-06 | 2023-06-06 | 中核大地勘察设计有限公司 | Pit engineering health trend analysis and early warning system |
| CN116465455A (en) * | 2023-04-12 | 2023-07-21 | 山西建筑工程集团有限公司 | Integrated digital monitoring method and system for physical indexes of soil body |
| CN117196893A (en) * | 2023-11-06 | 2023-12-08 | 中交第四航务工程勘察设计院有限公司 | Infrastructure foundation pit real-time monitoring and early warning management method and system |
| CN117235679A (en) * | 2023-11-15 | 2023-12-15 | 长沙金码测控科技股份有限公司 | LUCC-based tensile load and compressive load evaluation method and system for foundation pit monitoring |
| CN117493815A (en) * | 2023-12-28 | 2024-02-02 | 安徽华之语建筑工程有限公司 | BIM-based deep foundation pit monitoring method and system |
| CN117589120A (en) * | 2024-01-18 | 2024-02-23 | 深圳市深勘工程咨询有限公司 | BIM-based foundation pit deformation automatic monitoring and early warning method, system and electronic equipment |
-
2021
- 2021-09-11 CN CN202111065176.1A patent/CN113779835A/en not_active Withdrawn
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114154226B (en) * | 2022-02-10 | 2022-04-29 | 济宁明珠建筑工程有限公司 | Foundation pit stability monitoring method |
| CN114154226A (en) * | 2022-02-10 | 2022-03-08 | 济宁明珠建筑工程有限公司 | Foundation pit stability monitoring method |
| CN114592525A (en) * | 2022-03-16 | 2022-06-07 | 深圳宏业基岩土科技股份有限公司 | Intelligent monitoring prevention and control system for inner support of deep and large foundation pit |
| CN114844922A (en) * | 2022-04-25 | 2022-08-02 | 海南水文地质工程地质勘察院 | Foundation pit safety monitoring system based on Internet of things |
| CN114844922B (en) * | 2022-04-25 | 2024-03-19 | 海南水文地质工程地质勘察院 | Foundation pit safety monitoring system based on Internet of things |
| CN114855847A (en) * | 2022-07-06 | 2022-08-05 | 江苏中安建设集团有限公司 | Intelligent control method for construction site foundation pit dewatering system |
| CN114855847B (en) * | 2022-07-06 | 2022-09-20 | 江苏中安建设集团有限公司 | Intelligent control method for construction site foundation pit dewatering system |
| CN115167212B (en) * | 2022-07-13 | 2023-09-26 | 中交第三航务工程局有限公司 | Dynamic construction control system and method for foundation pit based on monitoring platform |
| CN115167212A (en) * | 2022-07-13 | 2022-10-11 | 中交第三航务工程局有限公司 | Foundation pit dynamic construction control system and method based on monitoring platform |
| CN115404840A (en) * | 2022-08-24 | 2022-11-29 | 中南大学 | Damage perception and catastrophe early warning intelligent geotextile based on deep learning |
| CN115574765A (en) * | 2022-12-08 | 2023-01-06 | 天津风霖物联网科技有限公司 | Big data-based monitoring system for engineering measurement |
| CN116227932A (en) * | 2023-03-06 | 2023-06-06 | 中核大地勘察设计有限公司 | Pit engineering health trend analysis and early warning system |
| CN116227932B (en) * | 2023-03-06 | 2023-11-10 | 中核大地勘察设计有限公司 | Pit engineering health trend analysis and early warning system |
| CN116069071A (en) * | 2023-03-24 | 2023-05-05 | 冠鲁建设股份有限公司 | Construction optimization system, method, device and medium based on big data |
| CN116465455A (en) * | 2023-04-12 | 2023-07-21 | 山西建筑工程集团有限公司 | Integrated digital monitoring method and system for physical indexes of soil body |
| CN116465455B (en) * | 2023-04-12 | 2023-10-20 | 山西建筑工程集团有限公司 | Integrated digital monitoring method and system for physical indexes of soil body |
| CN117196893A (en) * | 2023-11-06 | 2023-12-08 | 中交第四航务工程勘察设计院有限公司 | Infrastructure foundation pit real-time monitoring and early warning management method and system |
| CN117196893B (en) * | 2023-11-06 | 2024-01-05 | 中交第四航务工程勘察设计院有限公司 | Infrastructure foundation pit real-time monitoring and early warning management method and system |
| CN117235679A (en) * | 2023-11-15 | 2023-12-15 | 长沙金码测控科技股份有限公司 | LUCC-based tensile load and compressive load evaluation method and system for foundation pit monitoring |
| CN117493815A (en) * | 2023-12-28 | 2024-02-02 | 安徽华之语建筑工程有限公司 | BIM-based deep foundation pit monitoring method and system |
| CN117493815B (en) * | 2023-12-28 | 2024-04-16 | 安徽华之语建筑工程有限公司 | BIM-based deep foundation pit monitoring method and system |
| CN117589120A (en) * | 2024-01-18 | 2024-02-23 | 深圳市深勘工程咨询有限公司 | BIM-based foundation pit deformation automatic monitoring and early warning method, system and electronic equipment |
| CN117589120B (en) * | 2024-01-18 | 2024-03-26 | 深圳市深勘工程咨询有限公司 | BIM-based foundation pit deformation automatic monitoring and early warning method, system and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113779835A (en) | AI and intelligent monitoring system based deep and large foundation pit safety early warning method | |
| CN111622252B (en) | Intelligent control system and control method for whole process of large open caisson construction | |
| CN113900381B (en) | Steel structure remote health monitoring platform based on Internet of things and application method | |
| CN101477207A (en) | Intelligent geological calamity synthetic monitoring system and multi-stage prediction analysis method | |
| CN112185072B (en) | Deep foundation pit automatic monitoring method, device, equipment and medium based on Internet of things | |
| CN103743441A (en) | Multi-factor coupling on-line monitoring system and multi-factor coupling on-line monitoring system method for slope safety | |
| CN110889588A (en) | Method for evaluating risk level of shield tunnel construction adjacent building by using factor judgment matrix | |
| CN114005278B (en) | Intelligent monitoring and early warning system and method for highway infrastructure group | |
| CN111042143A (en) | Foundation pit engineering early warning method and system based on analysis of large amount of monitoring data | |
| CN108256172A (en) | Dangerous situation early alarming and forecasting method during existing box culvert is worn under a kind of push pipe | |
| CN110795812A (en) | Landslide prediction method and system based on big data analysis | |
| CN115324650A (en) | Early warning grading system and method based on intelligent recognition | |
| CN114357691A (en) | Power facility geological foundation deformation safety assessment method | |
| CN111445165A (en) | Tunnel structure health monitoring online grading early warning evaluation method | |
| CN114638035B (en) | Whole process control method for large open caisson construction and application | |
| CN115423167A (en) | Subway deep foundation pit construction safety early warning and decision-making assisting method and system | |
| CN110173305B (en) | Method for monitoring and early warning whole service life of tunnel structure at fault | |
| CN116911115A (en) | Digital twin tunnel and intelligent construction method and system | |
| CN117473851A (en) | Random forest-based shield tunnel floating process prediction method | |
| CN116402951A (en) | Digital twinning-based side slope safety management method and system | |
| CN116128290A (en) | Intelligent evaluation digital twin system for urban built-up area shield method construction environment risk | |
| CN115563874A (en) | Tunnel health degree analysis method and system based on big data | |
| CN115081311A (en) | Foundation pit support monitoring and early warning method and foundation pit support monitoring and early warning system | |
| CN113624201A (en) | Urban tunnel multi-line overlapping construction settlement monitoring and early warning system and method | |
| CN111767649B (en) | Soft foundation area transformer substation geological deformation safety assessment method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20211210 |
|
| WW01 | Invention patent application withdrawn after publication |