CN117390381A - Underground diaphragm wall joint seam leakage prediction method and device based on deep learning - Google Patents
Underground diaphragm wall joint seam leakage prediction method and device based on deep learning Download PDFInfo
- Publication number
- CN117390381A CN117390381A CN202311166997.3A CN202311166997A CN117390381A CN 117390381 A CN117390381 A CN 117390381A CN 202311166997 A CN202311166997 A CN 202311166997A CN 117390381 A CN117390381 A CN 117390381A
- Authority
- CN
- China
- Prior art keywords
- leakage
- data
- construction
- information
- continuous wall
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000013135 deep learning Methods 0.000 title claims abstract description 35
- 238000010276 construction Methods 0.000 claims abstract description 169
- 230000003014 reinforcing effect Effects 0.000 claims abstract description 29
- 238000012544 monitoring process Methods 0.000 claims abstract description 23
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 22
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims description 35
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 17
- 230000015572 biosynthetic process Effects 0.000 claims description 16
- 238000013499 data model Methods 0.000 claims description 15
- 230000003993 interaction Effects 0.000 claims description 8
- 238000010206 sensitivity analysis Methods 0.000 claims description 8
- 238000003066 decision tree Methods 0.000 claims description 7
- 230000010354 integration Effects 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 239000002002 slurry Substances 0.000 claims description 6
- 239000011800 void material Substances 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims 1
- 238000004078 waterproofing Methods 0.000 abstract description 2
- 238000012549 training Methods 0.000 description 15
- 238000003062 neural network model Methods 0.000 description 10
- 238000012360 testing method Methods 0.000 description 10
- 230000002787 reinforcement Effects 0.000 description 9
- 230000008901 benefit Effects 0.000 description 6
- 238000005457 optimization Methods 0.000 description 6
- 125000004122 cyclic group Chemical group 0.000 description 5
- 230000000306 recurrent effect Effects 0.000 description 5
- 210000004027 cell Anatomy 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 210000002569 neuron Anatomy 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 230000007787 long-term memory Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000035699 permeability Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000012731 temporal analysis Methods 0.000 description 2
- 238000000700 time series analysis Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007596 consolidation process Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 239000003673 groundwater Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- 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
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Software Systems (AREA)
- Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Computer Hardware Design (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Geometry (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention provides a method and a device for predicting joint seam leakage of a underground diaphragm wall based on deep learning, and relates to the technical field of foundation pit support waterproofing, wherein the method comprises the steps of obtaining first information and second information; preprocessing and converting the first information to obtain underground continuous wall engineering space-time data; establishing a leakage quantity prediction model according to the underground continuous wall engineering space-time data and a preset deep learning algorithm; and obtaining a recommended scheme according to the second information and the leakage quantity prediction model. According to the invention, a leakage prediction model of the joint seam of the underground continuous wall is established based on a deep learning algorithm, and the leakage of the joint seam of the underground continuous wall is predicted by acquiring a stratum distribution map of a history project, a reinforcing scheme of the joint seam of the underground continuous wall and leakage monitoring data and a stratum distribution map of a current construction area, so that recommended construction parameters and corresponding leakage prediction values are obtained, and reliable leakage prediction and guidance of optimizing a construction scheme are provided for underground continuous wall construction.
Description
Technical Field
The invention relates to the technical field of foundation pit support waterproofing, in particular to a method and a device for predicting joint seam leakage of a underground continuous wall based on deep learning.
Background
In recent years, with the comprehensive development of urban construction in China, the construction technology of underground engineering is mature, and the requirements on the restriction of construction precipitation of the construction engineering are strict. Leakage problems in underground diaphragm wall engineering are always important hidden hazards of engineering quality and safety, construction parameters need to be optimized to reduce leakage risks, traditional methods are usually based on experience and expert knowledge, lack of scientificity and reliability, and do not consider multi-factor interaction.
The invention provides a deep learning-based underground continuous wall joint seam leakage prediction method, which is characterized in that a prediction model and decision rules are established through data of historical projects, and construction parameters are optimized and recommended.
Disclosure of Invention
The invention aims to provide a method and a device for predicting joint seam leakage of underground continuous wall based on deep learning, so as to solve the problems. In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
in a first aspect, the present application provides a method for predicting joint seam leakage of a continuous wall under ground based on deep learning, including:
acquiring first information and second information, wherein the first information comprises a stratum distribution map of a history item, an underground continuous wall joint reinforcing scheme and leakage monitoring data, the underground continuous wall joint reinforcing scheme comprises parameters constructed by adopting a high-pressure jet grouting reinforcing method, and the second information comprises a stratum distribution map of a current construction area;
Preprocessing and converting the first information to obtain underground continuous wall construction Cheng Shikong data, wherein the underground continuous wall construction space-time data comprise first stratum distribution space data, leakage information time sequence data and construction scheme model data;
establishing a leakage quantity prediction model according to the underground continuous wall engineering space-time data and a preset deep learning algorithm;
and obtaining a recommended scheme according to the second information and the leakage quantity prediction model, wherein the recommended scheme comprises at least one recommended construction parameter and a corresponding leakage quantity prediction value.
In a second aspect, the present application further provides a device for predicting joint seam leakage of a underground diaphragm wall based on deep learning, including:
the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring first information and second information, the first information comprises a stratum distribution map of a history item, an underground continuous wall joint reinforcing scheme and leakage monitoring data, the underground continuous wall joint reinforcing scheme comprises parameters constructed by adopting a high-pressure jet grouting reinforcing method, and the second information comprises a stratum distribution map of a current construction area;
the conversion module is used for preprocessing and converting the first information to obtain underground continuous wall construction Cheng Shikong data, and the underground continuous wall engineering space-time data comprises first stratum distribution space data, leakage information time sequence data and construction scheme model data;
The construction module is used for constructing a leakage quantity prediction model according to the underground continuous wall engineering space-time data and a preset deep learning algorithm;
and the output module is used for obtaining a recommended scheme according to the second information and the leakage quantity prediction model, wherein the recommended scheme comprises at least one recommended construction parameter and a corresponding leakage quantity prediction value.
The beneficial effects of the invention are as follows:
according to the invention, a leakage prediction model of the joint seam of the underground continuous wall is established based on a deep learning algorithm, and the leakage of the joint seam of the underground continuous wall is predicted by acquiring a stratum distribution map of a history project, a reinforcing scheme of the joint seam of the underground continuous wall and leakage monitoring data and a stratum distribution map of a current construction area, so that a suggested construction parameter and a corresponding leakage prediction value are obtained, reliable leakage prediction and guidance of optimizing the construction scheme are provided for underground continuous wall construction, the construction quality and safety are improved, and the construction cost and time are saved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the embodiments of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for predicting joint seam leakage of a underground diaphragm wall based on deep learning according to an embodiment of the invention;
fig. 2 is a schematic structural diagram of a device for predicting joint seam leakage of underground diaphragm wall based on deep learning according to an embodiment of the invention.
The marks in the figure: 1. an acquisition module; 2. a conversion module; 21. a first processing unit; 22. a second processing unit; 23. a third processing unit; 24. a first integration unit; 241. a first assignment unit; 242. a second assignment unit; 243. a first calculation unit; 244. a first matching unit; 3. constructing a module; 31. a first extraction unit; 32. a fourth processing unit; 33. a first modeling unit; 34. a second modeling unit; 4. an output module; 41. a fifth processing unit; 42. a second calculation unit; 43. a sixth processing unit; 431. a first building unit; 432. a seventh processing unit; 433. an eighth processing unit; 434. a ninth processing unit; 44. and a second integration unit.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Example 1:
the embodiment provides a method for predicting joint seam leakage of a underground diaphragm wall based on deep learning.
Referring to fig. 1, the method is shown to include step S100, step S200, step S300, and step S400.
Step S100, acquiring first information and second information, wherein the first information comprises a stratum distribution map of a history item, a underground continuous wall joint reinforcing scheme and leakage monitoring data, the underground continuous wall joint reinforcing scheme comprises parameters constructed by adopting a high-pressure jet grouting reinforcing method, and the second information comprises a stratum distribution map of a current construction area.
It will be appreciated that in this step, a plurality of diaphragm wall projects are selected from the history project, their formation profiles, leak monitoring data and consolidation schemes are obtained, and then the required first information is obtained by analyzing and processing these data. And simultaneously, acquiring a stratum distribution map of the current construction area as second information through site survey and data acquisition.
Step 200, preprocessing and converting the first information to obtain underground continuous wall construction Cheng Shikong data, wherein the underground continuous wall construction space-time data comprises first stratum distribution space data, leakage information time sequence data and construction scheme model data.
It can be understood that in this step, the stratum distribution map of the history item is digitally processed, the geological features thereof are extracted, the leakage monitoring data are subjected to time series analysis and processing, the leakage rule and trend thereof are extracted, the joint reinforcement scheme is analyzed and arranged, and the reinforcement parameters thereof are extracted. The obtained underground continuous wall engineering space-time data can provide basic data support for subsequent modeling and prediction through processing and conversion. The step is to preprocess and convert the space-time data of the underground continuous wall engineering in the history project to obtain a data format and input data suitable for modeling and prediction, thereby improving the accuracy and efficiency of modeling and prediction of the subsequent deep learning algorithm and providing more reliable data support for leakage prediction. The step S200 includes a step S210, a step S220, a step S230, and a step S240.
Step S210, converting the stratum distribution map into a grid-shaped data structure to obtain first stratum distribution space data, wherein the first stratum distribution space data comprises grid nodes and connecting lines between adjacent grid nodes, the grid nodes represent geological units, and the connecting lines are a space relationship and an interaction relationship between the two geological units.
It can be understood that in this step, the formation distribution map is discretized, converted into a form of grid nodes, and the spatial relationship and the interaction relationship between adjacent grid nodes are described by connection lines, so as to obtain first formation distribution spatial data. Preferably, the stratigraphic distribution map is divided into a plurality of grid cells, each cell representing a geological cell, and the adjacent relationship between the cells is represented as a line. On the basis of the connecting line, parameters such as distance, contact area and the like between adjacent geological units can be further calculated, so that geological features of the underground continuous wall construction area can be more accurately described. The step converts the stratigraphic distribution map into a grid-like data structure so that the spatial relationship of the geological units is quantified and visualized, thereby supporting subsequent data processing and analysis.
Step S220, the leakage amount monitoring data are converted into leakage information time sequence data, and each time point in the leakage information time sequence data represents leakage amount in a preset time period.
It will be appreciated that in this step, the leakage amount monitoring data is converted into leakage information time series data, and leakage amount information at each time point is obtained through time series analysis and processing. Preferably, noise interference is eliminated by smoothing the monitored data, and then fitting and predicting the leakage amount data using a time series model. These predictions can be used to formulate reasonable construction parameters and leakage control schemes to improve engineering quality and efficiency.
And S230, converting the underground continuous wall joint reinforcing scheme into construction scheme model data, wherein the construction scheme model data comprise three-dimensional model data and construction parameters, and the three-dimensional model data comprise three-dimensional patterns of bored piles and three-dimensional patterns of jet grouting piles.
It will be appreciated that in this step, the three-dimensional model data includes a bored pile three-dimensional pattern and a jet grouting pile three-dimensional pattern, and the construction parameters include a bored diameter, a bored pile length, a jet grouting pile diameter, a jet grouting pile spacing, and the like. The method converts the underground diaphragm wall joint reinforcement scheme into an operable three-dimensional model and construction parameters, and provides important data support for subsequent modeling and prediction. And calculating the space coordinates and the reinforcement length of each reinforcement node based on the three-dimensional model data and the construction parameters, so as to predict the leakage amount. By the method, a complex reinforcement scheme can be converted into an operable data form, and important data support is provided for subsequent modeling and prediction.
And step 240, integrating the first stratum distribution space data, the leakage information time sequence data and the construction scheme model data to obtain underground continuous wall engineering space-time data.
It can be appreciated that in this step, the geological data, the construction scheme and the leakage monitoring data of the history project are integrated, so that more comprehensive and accurate underground continuous wall construction Cheng Shikong data is obtained, and a more accurate and reliable data base is provided for the subsequent leakage prediction and the recommendation of suggested construction parameters. Meanwhile, the method improves the utilization rate and the value of the data, and provides support for high efficiency and safety of engineering construction. The step S240 includes a step S241, a step S242, a step S243, and a step S244.
And S241, combining the geological attribute information and the coordinate information of each grid node of the first stratum distribution space data with the leakage amount monitoring data, and adding the leakage information time sequence data into the corresponding geological units to obtain geological unit data with leakage information.
It will be appreciated that in this step, the geological attribute information and the coordinate information of each grid node in the first stratigraphic distribution space data are combined with the leakage amount monitoring data, and the leakage information time sequence data is added to the corresponding geological unit, so as to obtain geological unit data with leakage information. Thus, by integrating different data together, richer and complete underground continuous wall construction Cheng Shikong data is formed, and a more accurate and reliable basis is provided for subsequent leakage prediction and recommendation of recommended construction parameters.
And step S242, adding the void volume information in the construction parameters to the three-dimensional pattern of the bored pile, and adding the slurry orifice information in the construction parameters to the three-dimensional pattern of the jet grouting pile to obtain an integrated data model.
It will be appreciated that bored piles and jet grouting piles are common reinforcement methods in diaphragm wall engineering, and their construction parameters include void volume, slurry openings, etc. In the step, the construction parameters are added into the three-dimensional graph to obtain an integrated data model containing complete construction information, which is favorable for subsequent modeling and analysis and can be used for supporting more accurate leakage prediction and recommendation of recommended construction parameters.
Step S243, calculating to obtain a leakage calculated value according to the integrated data model and a preset finite element calculation formula.
It will be appreciated that in this step, for an underground continuous wall engineering system having a complex structure and multiple parameters, numerical simulation and analysis may be performed by using a finite element method under the influence of various factors such as physical properties of geological units, construction parameters, leakage monitoring data, etc. The method can divide the engineering system into a plurality of finite element units, respectively solve the related parameters such as the permeation flow field, the stress field and the like of each unit, and then combine the parameters into a finite element solution of the whole system. The calculation formula of the seepage flow field is Darcy's law, the calculation formula of the stress field is an elastic mechanical equation, and a final seepage calculation value can be obtained through iterative calculation. The formula involved is as follows:
q＝K×A×(u 2 -u 1 )/L；
wherein q is the volume of liquid passing through the unit cross-sectional area in unit time, K is the permeability coefficient, A is the cross-sectional area, u 1 And u 2 Is the pressure of the liquid at both ends, L is the length.
And step S244, matching the geological unit data, the integrated data model and the leakage calculated value according to the corresponding geological units to obtain the underground continuous wall engineering space-time data.
It can be understood that in this step, firstly, according to coordinate information and time sequence data of leakage information of the geological units, the leakage information is added into the corresponding geological unit data, then the construction parameter information in the integrated data model is matched with the geological unit data to determine the specific construction parameters of each geological unit, and finally, the matched geological unit data, the integrated data model and the leakage calculation value are integrated to obtain underground continuous wall construction Cheng Shikong data, so that support is provided for the follow-up prediction of leakage amount and the recommendation of suggested construction parameters.
And step S300, establishing a leakage quantity prediction model according to the space-time data of the underground diaphragm wall engineering and a preset deep learning algorithm.
It will be appreciated that in this step, the leakage prediction model may predict the leakage using the formation profile of the history item, the underground diaphragm wall joint reinforcing scheme and the leakage monitoring data, and the formation profile of the current construction area. By training and optimizing the deep learning algorithm, the leakage amount can be predicted more accurately. The step S300 includes a step S310, a step S320, a step S330, and a step S340.
And step S310, carrying out feature extraction on the first stratum distribution space data and the construction scheme model data, and corresponding the extracted feature information with the leakage information time sequence data to obtain a feature set.
It will be appreciated that in this step, the process of feature extraction of subsurface wall engineering spatio-temporal data is aimed at converting the data into a form that can be processed by a computer. Preferably, this step may be accomplished by means of feature engineering, including extracting features related to the amount of leakage, such as geological properties of the type, thickness, depth, etc. of the geological unit, and parameter information of the construction scheme, such as diameter, spacing, depth, etc. of the jet grouting pile, from the formation map, the construction scheme model data, and the leakage information timing data. And (3) corresponding the characteristic information with the leakage information time sequence data to obtain a characteristic set for processing and analyzing by a subsequent deep learning algorithm.
Step S320, dividing the feature set into a training set and a testing set according to a preset proportion.
It will be appreciated that in this step, the training set is the data set used to train the deep learning algorithm and the test set is the data set used to evaluate the predictive accuracy and generalization ability of the trained model. Preferably, the data in the feature set may be divided into a training set and a test set in a ratio of 80:20. Wherein 80% of the data is used as a training set for training a model; 20% of the data are used as test sets for testing the predictive effect of the model.
And step S330, training a preset first cyclic neural network model by using a training set, and optimizing the first cyclic neural network model by using a preset back propagation algorithm to obtain an initial model.
It will be appreciated that in this step, the first recurrent neural network model is a neural network model that can process data having time series characteristics, and that model parameters can be optimized to improve the accuracy of model predictions by using a back propagation algorithm. Preferably, in the specific implementation, according to the feature set of the training set and the corresponding leakage information time sequence data, the training and optimization of the model are performed by setting different model super-parameters, training round numbers and other parameters. In model training and optimization, the mean square error is used to evaluate the prediction accuracy of the model for verification in subsequent test sets. The method has the advantages that the accuracy and precision of leakage quantity prediction can be improved through the initial model obtained through training, and therefore reliable data support is provided for follow-up leakage quantity prediction and recommendation of recommended construction parameters.
The first cyclic neural network model used in the step comprises an input layer, a serialization layer, a long-period memory network layer, a full-connection layer and an output layer. The input layer is used for receiving first stratum distribution space data, construction scheme model data and leakage information time sequence data. The serialization layer is used for carrying out serialization processing on the input data so as to enable the input data to meet the input requirement of the cyclic neural network. And the long-term and short-term memory network layer circularly processes the serialized input data and extracts characteristic information in the sequence. The full-connection layer is used for flattening the characteristic information extracted from the long-term memory network layer, and carrying out characteristic fusion and mapping through the full-connection layer to obtain a characteristic vector. The output layer is used for mapping the feature vector to a preset leakage quantity predicted value space to obtain a corresponding leakage quantity predicted value.
Preferably, in this embodiment, according to the actual situation of the data set, the number of neurons of the input layer is 3, which corresponds to the first formation distribution space data, the construction scheme model data, and the leakage information timing data, respectively. The number of neurons of the long-term and short-term memory network layer is 64, and the time sequence length in the corresponding data set is 64. The number of neurons in the full connection layer is 128, which is set according to factors such as data complexity and required accuracy. The final output layer has only one neuron, representing the predicted leakage magnitude.
And step 340, verifying the initial model by using the test set, evaluating the performance of the first cyclic neural network model, and performing parameter adjustment and optimization of the model according to the evaluation result to obtain a leakage quantity prediction model.
It will be appreciated that in this step, the initial model is validated and evaluated using a predetermined test set to understand the performance of the first recurrent neural network model, including accuracy, generalization ability, stability, etc. of the model. Through evaluating the performance of the model, the optimization direction of the model and parameters to be adjusted can be determined, and parameter adjustment and optimization of the model are further carried out, so that a more accurate and reliable leakage quantity prediction model is obtained.
And step 400, obtaining a recommended scheme according to the second information and the leakage amount prediction model, wherein the recommended scheme comprises at least one recommended construction parameter and a corresponding leakage amount prediction value.
It can be understood that in this step, corresponding characteristic information is extracted according to the stratum distribution diagram of the current construction area, and then the characteristic information is input into a trained model to obtain a corresponding leakage quantity predicted value. According to the predicted value and the preset threshold value, the leakage risk degree of the current construction area can be judged, and further suggested construction parameters are provided to reduce leakage risk. The step S400 includes a step S410, a step S420, a step S430, and a step S440.
Step S410, converting the second information into a network-like data structure to obtain second formation distribution space data.
It will be appreciated that in this step, the geological distribution map in the second information is converted into a grid-like data structure, each grid node representing a geological unit, and the spatial relationship and interaction relationship between geological units are represented by the connection between the nodes, so as to obtain the second stratigraphic distribution spatial data. The step converts the second information into a network-like data structure so that the geological distribution information can be processed and analyzed by a computer, and basic data support is provided for the subsequent steps.
And S420, taking the second stratum distribution space data as an input value of a leakage quantity prediction model to obtain a leakage quantity prediction result, wherein the leakage quantity prediction result comprises at least one leakage quantity prediction value.
It will be appreciated that in this step, the second formation spatial data may be geological information data obtained by geological exploration, geological measurement, etc., such as parameters of formation type, thickness, porosity, etc. at different depths. By using these parameters as inputs, the leakage amount prediction model can predict leakage amount prediction values at corresponding depths, thereby recommending appropriate recommended construction parameters.
And step S430, obtaining at least one suggested construction parameter according to the leakage quantity prediction result and a preset decision rule.
It can be understood that in this step, the optimal or suboptimal construction parameter combination is obtained as a part of the recommended solution according to the leakage amount prediction value predicted by the leakage amount prediction model and in combination with a preset decision rule. Preferably, different decision rules can be set according to actual situations and requirements, for example, different suggested construction parameter combinations are given according to the magnitude of leakage quantity predicted values, or trade-offs and decisions are made according to other factors, such as cost, feasibility and the like. It should be noted that step S430 includes step S431, step 432, step S433 and step S434.
And step S431, establishing a decision rule according to the first information and a preset decision tree algorithm, and classifying the construction parameters in the underground diaphragm wall joint reinforcing scheme according to the decision rule to obtain a construction parameter range corresponding to each category.
It can be understood that in this step, firstly, a decision rule is established according to the first information and a preset decision tree algorithm, that is, known construction information is classified and arranged, and a corresponding decision rule is made so as to classify construction parameters in the underground diaphragm wall joint reinforcing scheme. The decision tree algorithm generally branches information according to specific attributes and values to construct a decision tree, so that classification and decision of the information are realized. And classifying the construction parameters in the underground continuous wall joint reinforcing scheme according to the decision rule to obtain the construction parameter range corresponding to each category. For example, the length of the bored pile, the pitch of the holes, the depth of the poured, the spacing of the jet grouting piles, the jet grouting pressure, etc., and then setting the corresponding construction parameter ranges for each category, for example, the length of the bored pile is 10-15 m, the pitch of the holes is 1.5-2.0 m, the depth of the poured is 20-25 m, etc. And finally, according to leakage quantity prediction results and known construction parameter classification, reasoning is carried out by adopting a preset decision rule, and at least one suggested construction parameter is obtained. For example, when the predicted leakage amount is larger, it may be inferred from a preset decision rule that stricter construction parameters need to be adopted, such as increasing the number of bored piles, reducing the distance between the holes to be poured, increasing the depth of pouring, and the like. According to the method, at least one recommended construction parameter is obtained rapidly and effectively according to the second information and the preset decision rule, the accuracy and the efficiency of decision making are improved, the trial-and-error and adjustment cost is reduced, meanwhile, the construction scheme can be optimized, and the engineering risk and the quality hidden danger are reduced.
And step 432, dividing the construction parameter range into at least two subintervals, and carrying out parameter sensitivity analysis on each subinterval to obtain an analysis result, wherein the analysis result comprises the influence degree of each parameter on the leakage quantity prediction result.
It will be appreciated that in this step, the sensitivity analysis is to evaluate the extent of its effect on the leakage amount prediction result by small changes to the construction parameters. Preferably, global sensitivity analysis is adopted in the embodiment, and void volume and slurry orifice parameters in construction scheme model data and first stratum distribution space data in underground continuous wall engineering space-time data are selected as variables for analysis, so that comprehensive evaluation is carried out on influence of a plurality of parameters on leakage quantity prediction results. In the underground diaphragm wall engineering, the influence of a plurality of parameters on the leakage quantity prediction result, such as permeability coefficient, water head, ground water level drop and the like, is considered. The influence degree of each parameter on the leakage quantity prediction result can be obtained through global sensitivity analysis, so that the importance of each parameter can be known. And sampling the parameter space by using a Latin hypercube sampling method, carrying out numerical simulation, calculating the main effect and the interaction effect of each parameter, and finally obtaining the influence degree of each parameter on the model output. Therefore, the construction parameters can be selected more scientifically and reasonably, and the engineering quality and benefit are improved.
And S433, optimizing the construction parameters of each subinterval according to the leakage quantity prediction result and the analysis result to obtain a corresponding leakage quantity prediction value.
It may be appreciated that, preferably, in this embodiment, the leakage amount prediction model is applied to the underground diaphragm wall engineering, the second formation distribution space data generated according to the second information is used as the input of the model, a set of representative construction parameter combinations is generated by using the latin hypercube sampling method, and then these parameter combinations are input into the leakage amount prediction model, so as to obtain the corresponding leakage amount prediction value. And then, evaluating the influence degree of each construction parameter by a global sensitivity analysis method to obtain the sensitivity value of each parameter. And finally, optimizing the construction parameters of each subinterval according to the leakage quantity prediction result and the sensitivity value of each parameter to obtain a corresponding leakage quantity prediction value and an optimal construction parameter combination. The method has the advantages of improving the construction efficiency and the construction quality of the underground diaphragm wall engineering, reducing the construction cost and the construction period, reducing the leakage risk and improving the stability and the safety of the underground diaphragm wall. .
And step S434, according to the optimized construction parameters and the corresponding leakage quantity predicted values, the recommended construction parameters are obtained.
It will be appreciated that in this step, the optimum construction parameters for each sub-section are determined based on the leakage amount prediction results and analysis results obtained in the previous steps, and the recommended construction parameters are obtained.
And S440, integrating all the suggested construction parameters and the corresponding leakage quantity predicted values to obtain a recommended scheme.
It will be appreciated that in this step, the recommended solution includes a plurality of recommended construction parameters, each corresponding to a predicted leakage amount, based on which decision support is provided. According to the method, the multiple schemes can be comprehensively evaluated by integrating various suggested parameters and corresponding leakage quantity predicted values, and then the optimal scheme is selected, so that the construction practice of underground diaphragm wall engineering is effectively guided, and the construction quality and efficiency of the underground diaphragm wall engineering are improved.
Example 2:
as shown in fig. 2, the embodiment provides a device for predicting joint seam leakage of a underground diaphragm wall based on deep learning, the device comprises:
the acquisition module 1 is used for acquiring first information and second information, wherein the first information comprises a stratum distribution map of a history item, a continuous wall joint reinforcing scheme and leakage monitoring data, the continuous wall joint reinforcing scheme comprises parameters constructed by adopting a high-pressure jet grouting reinforcement method, and the second information comprises a stratum distribution map of a current construction area.
And the conversion module 2 is used for preprocessing and converting the first information to obtain underground diaphragm wall construction Cheng Shikong data, wherein the underground diaphragm wall engineering space-time data comprises first stratum distribution space data, leakage information time sequence data and construction scheme model data.
And the construction module 3 is used for building a leakage quantity prediction model according to the underground continuous wall engineering space-time data and a preset deep learning algorithm.
And the output module 4 is used for obtaining a recommended scheme according to the second information and the leakage quantity prediction model, wherein the recommended scheme comprises at least one recommended construction parameter and a corresponding leakage quantity predicted value.
In one embodiment of the present disclosure, the conversion module 2 includes:
the first processing unit 21 is configured to convert the stratigraphic distribution map into a grid-like data structure to obtain first stratigraphic distribution spatial data, where the first stratigraphic distribution spatial data includes grid nodes and connection lines between adjacent grid nodes, the grid nodes represent geological units, and the connection lines are a spatial relationship and an interaction relationship between two geological units.
The second processing unit 22 is configured to convert the leakage amount monitoring data into leakage information time series data, where each time point in the leakage information time series data represents the leakage amount within a preset time period.
The third processing unit 23 is configured to convert the underground diaphragm wall joint reinforcing scheme into construction scheme model data, where the construction scheme model data includes three-dimensional model data and construction parameters, and the three-dimensional model data includes a three-dimensional pattern of a bored pile and a three-dimensional pattern of a jet grouting pile.
The first integration unit 24 is configured to integrate the first formation distribution space data, the leakage information time sequence data, and the construction scheme model data to obtain the underground continuous wall engineering space-time data.
In one embodiment of the present disclosure, the first integration unit 24 includes:
and the first assignment unit 241 is configured to combine the geological attribute information and the coordinate information of each grid node of the first stratigraphic distribution space data with the leakage amount monitoring data, and add the leakage information time sequence data to the corresponding geological unit to obtain geological unit data with leakage information.
And the second assignment unit 242 is used for adding the void volume information in the construction parameters to the three-dimensional pattern of the bored pile, and adding the slurry orifice information in the construction parameters to the three-dimensional pattern of the jet grouting pile, so as to obtain an integrated data model.
The first calculating unit 243 is configured to calculate a leakage calculation value according to the integrated data model and a preset finite element calculation formula.
The first matching unit 244 is configured to match the geological unit data, the integrated data model and the leakage calculation value according to the corresponding geological unit, so as to obtain the space-time data of the underground continuous wall engineering.
In one embodiment of the present disclosure, the build module 3 includes:
the first extracting unit 31 is configured to perform feature extraction on the first formation distribution space data and the construction plan model data, and correspond the extracted feature information to the leakage information time sequence data to obtain a feature set.
The fourth processing unit 32 is configured to divide the feature set into a training set and a test set according to a preset ratio.
The first modeling unit 33 trains the preset first recurrent neural network model using the training set, and optimizes the first recurrent neural network model using the preset back propagation algorithm to obtain an initial model.
The second modeling unit 34 uses the test set to verify the initial model, evaluates the performance of the first recurrent neural network model, and performs parameter tuning and optimization of the model according to the evaluation result to obtain a leakage amount prediction model.
In one embodiment of the present disclosure, the output module 4 includes:
the fifth processing unit 41 is configured to convert the second information into a network-like data structure to obtain second formation distribution space data.
A second calculation unit 42, configured to obtain a leakage amount prediction result using the second formation distribution space data as an input value of the leakage amount prediction model, where the leakage amount prediction result includes at least one leakage amount prediction value.
The sixth processing unit 43 is configured to derive at least one recommended construction parameter according to the leakage amount prediction result and a preset decision rule.
The second integration unit 44 is configured to integrate all the recommended construction parameters and the corresponding leakage amount predicted values to obtain a recommended solution.
In one embodiment of the present disclosure, the sixth processing unit 43 includes:
the first construction unit 431 is configured to establish a decision rule according to the first information and a preset decision tree algorithm, and classify construction parameters in the underground continuous wall joint reinforcement scheme according to the decision rule to obtain a construction parameter range corresponding to each category.
The seventh processing unit 432 is configured to divide the construction parameter range into at least two subintervals, and perform parameter sensitivity analysis on each subinterval to obtain an analysis result, where the analysis result includes a degree of influence of each parameter on the leakage prediction result.
And the eighth processing unit 433 is configured to optimize the construction parameters of each subinterval according to the leakage amount prediction result and the analysis result, so as to obtain a corresponding leakage amount prediction value.
And a ninth processing unit 434, configured to obtain the recommended construction parameter according to the optimized construction parameter and the corresponding leakage prediction value.
It should be noted that, regarding the apparatus in the above embodiments, the specific manner in which the respective modules perform the operations has been described in detail in the embodiments regarding the method, and will not be described in detail herein.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (10)
1. The underground continuous wall joint seam leakage prediction method based on deep learning is characterized by comprising the following steps of:
Acquiring first information and second information, wherein the first information comprises a stratum distribution map of a history item, an underground continuous wall joint reinforcing scheme and leakage monitoring data, the underground continuous wall joint reinforcing scheme comprises parameters constructed by adopting a high-pressure jet grouting reinforcing method, and the second information comprises a stratum distribution map of a current construction area;
preprocessing and converting the first information to obtain underground continuous wall construction Cheng Shikong data, wherein the underground continuous wall construction space-time data comprise first stratum distribution space data, leakage information time sequence data and construction scheme model data;
establishing a leakage quantity prediction model according to the underground continuous wall engineering space-time data and a preset deep learning algorithm;
and obtaining a recommended scheme according to the second information and the leakage quantity prediction model, wherein the recommended scheme comprises at least one recommended construction parameter and a corresponding leakage quantity prediction value.
2. The deep learning-based underground diaphragm wall joint seam leakage prediction method according to claim 1, wherein preprocessing and converting the first information to obtain underground diaphragm wall work Cheng Shikong data comprises:
converting the stratum distribution map into a grid-shaped data structure to obtain first stratum distribution space data, wherein the first stratum distribution space data comprises grid nodes and connecting lines between adjacent grid nodes, the grid nodes represent geological units, and the connecting lines are a space relationship and an interaction relationship between two geological units;
Converting the leakage amount monitoring data into leakage information time sequence data, wherein each time point in the leakage information time sequence data represents leakage amount in a preset time period;
converting the underground diaphragm wall joint reinforcing scheme into construction scheme model data, wherein the construction scheme model data comprise three-dimensional model data and construction parameters, and the three-dimensional model data comprise three-dimensional patterns of bored piles and three-dimensional patterns of jet grouting piles;
and integrating the first stratum distribution space data, the leakage information time sequence data and the construction scheme model data to obtain underground continuous wall engineering space-time data.
3. The deep learning-based underground diaphragm wall joint seam leakage prediction method according to claim 2, wherein integrating the first formation distribution space data, the leakage information time sequence data and the construction scheme model data to obtain underground diaphragm wall construction Cheng Shikong data comprises:
combining the geological attribute information and the coordinate information of each grid node of the first stratum distribution space data with the leakage monitoring data, and adding leakage information time sequence data into corresponding geological units to obtain geological unit data with leakage information;
Adding the void volume information in the construction parameters to the three-dimensional pattern of the bored pile, and adding the slurry orifice information in the construction parameters to the three-dimensional pattern of the jet grouting pile to obtain an integrated data model;
calculating according to the integrated data model and a preset finite element calculation formula to obtain a leakage calculation value;
and matching the geological unit data, the integrated data model and the leakage calculated value according to the corresponding geological unit to obtain underground continuous wall engineering space-time data.
4. The deep learning-based underground diaphragm wall joint seam leakage prediction method according to claim 1, wherein a recommended solution is obtained according to the second information and the leakage amount prediction model, the recommended solution including at least one recommended construction parameter and a corresponding leakage amount prediction value, comprising:
converting the second information into a network-shaped data structure to obtain second stratum distribution space data;
obtaining a leakage quantity prediction result by taking the second stratum distribution space data as an input value of the leakage quantity prediction model, wherein the leakage quantity prediction result comprises at least one leakage quantity prediction value;
according to the leakage quantity prediction result and a preset decision rule, at least one suggested construction parameter is obtained;
And integrating all the recommended construction parameters and the corresponding leakage quantity predicted values to obtain a recommended scheme.
5. The deep learning-based underground diaphragm wall joint seam leakage prediction method according to claim 4, wherein the step of obtaining at least one recommended construction parameter according to the leakage amount prediction result and a preset decision rule comprises the steps of:
establishing a decision rule according to the first information and a preset decision tree algorithm, and classifying construction parameters in the underground diaphragm wall joint reinforcing scheme according to the decision rule to obtain a construction parameter range corresponding to each category;
dividing the construction parameter range into at least two subintervals, and carrying out parameter sensitivity analysis on each subinterval to obtain an analysis result, wherein the analysis result comprises the influence degree of each parameter on the leakage quantity prediction result;
optimizing construction parameters of each subinterval according to the leakage quantity prediction result and the analysis result to obtain a corresponding leakage quantity prediction value;
and obtaining suggested construction parameters according to the optimized construction parameters and the corresponding leakage predicted values.
6. Underground continuous wall joint seam leakage prediction device based on deep learning, characterized by comprising:
The system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring first information and second information, the first information comprises a stratum distribution map of a history item, an underground continuous wall joint reinforcing scheme and leakage monitoring data, the underground continuous wall joint reinforcing scheme comprises parameters constructed by adopting a high-pressure jet grouting reinforcing method, and the second information comprises a stratum distribution map of a current construction area;
the conversion module is used for preprocessing and converting the first information to obtain underground continuous wall construction Cheng Shikong data, and the underground continuous wall engineering space-time data comprises first stratum distribution space data, leakage information time sequence data and construction scheme model data;
the construction module is used for constructing a leakage quantity prediction model according to the underground continuous wall engineering space-time data and a preset deep learning algorithm;
and the output module is used for obtaining a recommended scheme according to the second information and the leakage quantity prediction model, wherein the recommended scheme comprises at least one recommended construction parameter and a corresponding leakage quantity prediction value.
7. The deep learning based subsurface continuous wall joint seam leakage prediction device of claim 6, wherein the transformation module comprises:
The first processing unit is used for converting the stratum distribution map into a grid-shaped data structure to obtain first stratum distribution space data, wherein the first stratum distribution space data comprises grid nodes and connecting lines between adjacent grid nodes, the grid nodes represent geological units, and the connecting lines are a space relationship and an interaction relationship between the two geological units;
the second processing unit is used for converting the leakage amount monitoring data into leakage information time sequence data, and each time point in the leakage information time sequence data represents the leakage amount in a preset time period;
the third processing unit is used for converting the underground diaphragm wall joint reinforcing scheme into construction scheme model data, wherein the construction scheme model data comprise three-dimensional model data and construction parameters, and the three-dimensional model data comprise three-dimensional patterns of bored piles and three-dimensional patterns of jet grouting piles;
and the first integration unit is used for integrating the first stratum distribution space data, the leakage information time sequence data and the construction scheme model data to obtain underground continuous wall engineering space-time data.
8. The deep learning based underground diaphragm wall joint seam leakage prediction apparatus of claim 7, wherein the first integrated unit comprises:
The first assignment unit is used for combining the geological attribute information and the coordinate information of each grid node of the first stratum distribution space data with the leakage monitoring data, and adding leakage information time sequence data into the corresponding geological units to obtain geological unit data with leakage information;
the second assignment unit is used for adding the void volume information in the construction parameters to the three-dimensional pattern of the bored pile, and adding the slurry orifice information in the construction parameters to the three-dimensional pattern of the jet grouting pile to obtain an integrated data model;
the first calculation unit is used for calculating a leakage calculation value according to the integrated data model and a preset finite element calculation formula;
and the first matching unit is used for matching the geological unit data, the integrated data model and the leakage calculated value according to the corresponding geological unit to obtain underground continuous wall engineering space-time data.
9. The deep learning based subsurface continuous wall joint seam leakage prediction device according to claim 6, wherein the output module comprises:
the fifth processing unit is used for converting the second information into a network-shaped data structure to obtain second stratum distribution space data;
The second calculation unit is used for taking the second stratum distribution space data as an input value of the leakage quantity prediction model to obtain a leakage quantity prediction result, and the leakage quantity prediction result comprises at least one leakage quantity prediction value;
the sixth processing unit is used for obtaining at least one suggested construction parameter according to the leakage quantity prediction result and a preset decision rule;
and the second integration unit is used for integrating all the recommended construction parameters and the corresponding leakage quantity predicted values to obtain a recommended scheme.
10. The deep learning based subsurface continuous wall joint seam leakage prediction device according to claim 9, wherein the sixth processing unit comprises:
the first construction unit is used for establishing a decision rule according to the first information and a preset decision tree algorithm, and classifying construction parameters in the underground continuous wall joint reinforcing scheme according to the decision rule to obtain a construction parameter range corresponding to each category;
the seventh processing unit is used for dividing the construction parameter range into at least two subintervals, and carrying out parameter sensitivity analysis on each subinterval to obtain an analysis result, wherein the analysis result comprises the influence degree of each parameter on the leakage quantity prediction result;
The eighth processing unit is used for optimizing the construction parameters of each subinterval according to the leakage quantity prediction result and the analysis result to obtain a corresponding leakage quantity prediction value;
and the ninth processing unit is used for obtaining suggested construction parameters according to the optimized construction parameters and the corresponding leakage predicted values.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311166997.3A CN117390381B (en) | 2023-09-11 | 2023-09-11 | Underground diaphragm wall joint seam leakage prediction method and device based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311166997.3A CN117390381B (en) | 2023-09-11 | 2023-09-11 | Underground diaphragm wall joint seam leakage prediction method and device based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117390381A true CN117390381A (en) | 2024-01-12 |
| CN117390381B CN117390381B (en) | 2024-06-25 |
Family
ID=89463876
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311166997.3A Active CN117390381B (en) | 2023-09-11 | 2023-09-11 | Underground diaphragm wall joint seam leakage prediction method and device based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117390381B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117668762A (en) * | 2024-01-31 | 2024-03-08 | 新疆三联工程建设有限责任公司 | Monitoring and early warning system and method for residential underground leakage |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107092990A (en) * | 2017-05-03 | 2017-08-25 | 西安电子科技大学 | The shield construction ground settlement forecast system and method analyzed based on big data |
| CN112836789A (en) * | 2020-12-27 | 2021-05-25 | 苏州大学 | Ground connection wall deformation dynamic prediction method based on composite neural network algorithm |
| CN114997548A (en) * | 2022-08-05 | 2022-09-02 | 武九铁路客运专线湖北有限责任公司 | Water movement geological seepage real-time early warning method based on genetic neural network |
| CN115470550A (en) * | 2022-08-30 | 2022-12-13 | 广西大学 | Method for calculating uplift displacement of lower horizontal tunnel caused by excavation of layered foundation pit |
| CN115563864A (en) * | 2022-09-27 | 2023-01-03 | 中国电力科学研究院有限公司 | Intelligent prediction method for cable tunnel water leakage |
| CN116611350A (en) * | 2023-07-19 | 2023-08-18 | 青岛理工大学 | Oil well acidizing measure effect prediction method based on transfer learning |
-
2023
- 2023-09-11 CN CN202311166997.3A patent/CN117390381B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107092990A (en) * | 2017-05-03 | 2017-08-25 | 西安电子科技大学 | The shield construction ground settlement forecast system and method analyzed based on big data |
| CN112836789A (en) * | 2020-12-27 | 2021-05-25 | 苏州大学 | Ground connection wall deformation dynamic prediction method based on composite neural network algorithm |
| CN114997548A (en) * | 2022-08-05 | 2022-09-02 | 武九铁路客运专线湖北有限责任公司 | Water movement geological seepage real-time early warning method based on genetic neural network |
| CN115470550A (en) * | 2022-08-30 | 2022-12-13 | 广西大学 | Method for calculating uplift displacement of lower horizontal tunnel caused by excavation of layered foundation pit |
| CN115563864A (en) * | 2022-09-27 | 2023-01-03 | 中国电力科学研究院有限公司 | Intelligent prediction method for cable tunnel water leakage |
| CN116611350A (en) * | 2023-07-19 | 2023-08-18 | 青岛理工大学 | Oil well acidizing measure effect prediction method based on transfer learning |
Non-Patent Citations (2)
| Title |
|---|
| 刘涵宇;夏强;张世殊;卢刚;万媛;: "基于水文地质参数敏感度分析的水库渗漏量不确定性评价", 科学技术与工程, no. 14, 18 May 2017 (2017-05-18) * |
| 金晓飞;梁书亭;朱筱俊;孙崇芳;: ""Ⅱ"型接头嵌岩地下连续墙渗漏监测分析", 建筑结构, no. 02, 25 January 2017 (2017-01-25) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117668762A (en) * | 2024-01-31 | 2024-03-08 | 新疆三联工程建设有限责任公司 | Monitoring and early warning system and method for residential underground leakage |
| CN117668762B (en) * | 2024-01-31 | 2024-05-17 | 新疆三联工程建设有限责任公司 | Monitoring and early warning system and method for residential underground leakage |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117390381B (en) | 2024-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112417573B (en) | GA-LSSVM and NSGA-II shield tunneling multi-objective optimization method based on existing tunnel construction | |
| CN104533400B (en) | Method for reconstructing logging curve | |
| CN117390381B (en) | Underground diaphragm wall joint seam leakage prediction method and device based on deep learning | |
| CN103530818B (en) | A kind of water supply network modeling method based on BRB system | |
| RU2002122397A (en) | Comprehensive reservoir optimization | |
| Behnia et al. | Predicting crest settlement in concrete face rockfill dams using adaptive neuro-fuzzy inference system and gene expression programming intelligent methods | |
| CN104616353A (en) | Modeling for random geologic model of reservoir and preferable method | |
| CN109886506B (en) | Water supply network pipe explosion risk analysis method | |
| CN115654381A (en) | Water supply pipeline leakage detection method based on graph neural network | |
| CN107247888A (en) | Sewage disposal water outlet total phosphorus TP flexible measurement methods based on reserve pool network | |
| Yousef et al. | Predictive data analytics application for enhanced oil recovery in a mature field in the Middle East | |
| CN117219180A (en) | Method and system for monitoring, evaluating and dynamically regulating and enhancing mineralization effect of carbon dioxide | |
| CN111709592A (en) | Deep foundation pit deformation prediction method and system based on neural network and rough set classification | |
| CN117541082B (en) | Comprehensive evaluation method based on oil reservoir-shaft-equipment evaluation index integration | |
| CN117251802B (en) | Heterogeneous reservoir parameter prediction method and system based on transfer learning | |
| CN112396312B (en) | Open caisson sinking construction automatic decision-making method and system | |
| CN117852416A (en) | Multimode grouting precontrolled analysis method and system based on digital geological model | |
| CN116911216B (en) | Reservoir oil well productivity factor assessment and prediction method | |
| CN108765562B (en) | Oil-gas productivity evaluation method based on three-dimensional geological model | |
| CN110566196A (en) | Reservoir connectivity analysis method | |
| CN113627761B (en) | Parallel evaluation method for geotechnical engineering water inrush probability prediction | |
| CN115062552B (en) | Method and system for predicting nitrogen huff and puff effect of fracture-cavity oil reservoir | |
| CN117522173B (en) | Natural gas hydrate depressurization exploitation productivity prediction method based on deep neural network | |
| CN116629112B (en) | Oil reservoir attribute parameter inversion method and system based on scientific intelligence | |
| CN116029402A (en) | Method and device for training and predicting recovery ratio prediction model of reservoir of fractured bedrock down-the-hill |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |