CN114114426A - Coastal zone salt water invasion intelligent monitoring and identification method and system - Google Patents
Coastal zone salt water invasion intelligent monitoring and identification method and system Download PDFInfo
- Publication number
- CN114114426A CN114114426A CN202111261614.1A CN202111261614A CN114114426A CN 114114426 A CN114114426 A CN 114114426A CN 202111261614 A CN202111261614 A CN 202111261614A CN 114114426 A CN114114426 A CN 114114426A
- Authority
- CN
- China
- Prior art keywords
- data
- fixedly connected
- training
- invasion
- seawater
- 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.)
- Pending
Links
- 230000009545 invasion Effects 0.000 title claims abstract description 60
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 45
- 150000003839 salts Chemical class 0.000 title claims abstract description 32
- 238000012544 monitoring process Methods 0.000 title claims abstract description 22
- 238000004088 simulation Methods 0.000 claims abstract description 61
- 239000013535 sea water Substances 0.000 claims abstract description 58
- 238000005070 sampling Methods 0.000 claims abstract description 44
- 230000007246 mechanism Effects 0.000 claims abstract description 43
- 238000012549 training Methods 0.000 claims description 37
- 238000007789 sealing Methods 0.000 claims description 29
- 238000004140 cleaning Methods 0.000 claims description 19
- 239000011159 matrix material Substances 0.000 claims description 18
- 238000001914 filtration Methods 0.000 claims description 16
- 230000006835 compression Effects 0.000 claims description 14
- 238000007906 compression Methods 0.000 claims description 14
- 230000000694 effects Effects 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 12
- 238000013528 artificial neural network Methods 0.000 claims description 11
- 238000005553 drilling Methods 0.000 claims description 10
- 238000003825 pressing Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 239000013505 freshwater Substances 0.000 claims description 9
- 230000002146 bilateral effect Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 8
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 239000000463 material Substances 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000012806 monitoring device Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 5
- 238000010801 machine learning Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 230000035699 permeability Effects 0.000 claims description 3
- 230000004913 activation Effects 0.000 claims description 2
- 238000004422 calculation algorithm Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000012937 correction Methods 0.000 claims description 2
- 238000010219 correlation analysis Methods 0.000 claims description 2
- 230000008030 elimination Effects 0.000 claims description 2
- 238000003379 elimination reaction Methods 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 claims description 2
- 230000004044 response Effects 0.000 claims description 2
- 230000009466 transformation Effects 0.000 claims description 2
- 238000007599 discharging Methods 0.000 claims 2
- 239000011435 rock Substances 0.000 abstract description 18
- 230000009471 action Effects 0.000 abstract description 8
- 238000001514 detection method Methods 0.000 abstract description 3
- 239000004576 sand Substances 0.000 description 8
- FAPWRFPIFSIZLT-UHFFFAOYSA-M Sodium chloride Chemical compound [Na+].[Cl-] FAPWRFPIFSIZLT-UHFFFAOYSA-M 0.000 description 5
- 239000007788 liquid Substances 0.000 description 5
- 239000011780 sodium chloride Substances 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 239000012267 brine Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000003673 groundwater Substances 0.000 description 4
- HPALAKNZSZLMCH-UHFFFAOYSA-M sodium;chloride;hydrate Chemical compound O.[Na+].[Cl-] HPALAKNZSZLMCH-UHFFFAOYSA-M 0.000 description 4
- 239000000243 solution Substances 0.000 description 4
- 239000004575 stone Substances 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000002844 melting Methods 0.000 description 2
- 230000008018 melting Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000010030 laminating Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V3/00—Electric or magnetic prospecting or detecting; Measuring magnetic field characteristics of the earth, e.g. declination, deviation
- G01V3/08—Electric or magnetic prospecting or detecting; Measuring magnetic field characteristics of the earth, e.g. declination, deviation operating with magnetic or electric fields produced or modified by objects or geological structures or by detecting devices
- G01V3/081—Electric or magnetic prospecting or detecting; Measuring magnetic field characteristics of the earth, e.g. declination, deviation operating with magnetic or electric fields produced or modified by objects or geological structures or by detecting devices the magnetic field is produced by the objects or geological structures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V3/00—Electric or magnetic prospecting or detecting; Measuring magnetic field characteristics of the earth, e.g. declination, deviation
- G01V3/36—Recording data
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V3/00—Electric or magnetic prospecting or detecting; Measuring magnetic field characteristics of the earth, e.g. declination, deviation
- G01V3/38—Processing data, e.g. for analysis, for interpretation, for correction
-
- 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
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- 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
- G06N3/045—Combinations of 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- 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
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Geophysics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Environmental & Geological Engineering (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Strategic Management (AREA)
- Geology (AREA)
- Development Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Geometry (AREA)
- Electromagnetism (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
Abstract
The invention discloses the technical field of underground seawater simulation equipment, and particularly relates to a coastal zone salt water invasion intelligent monitoring and recognition method and system. According to the invention, under the action of the sampling mechanism, the hydraulic rod can drive the sampling tube to move up and down, the sampling tube is inserted into the simulation box, the simulation rock stratum in the simulation box can be sampled, so that a worker can conveniently perform data detection and recording on the simulation rock stratum, the ejector block can be driven to move downwards by extruding the T-shaped rod, the ejector block can quickly eject the sample rock stratum in the sampling tube, the sampling tube is convenient to take out, the operation is simple, time and labor are saved, and residual samples in a sampling shop can be prevented.
Description
Technical Field
The invention relates to the technical field of salt water simulation equipment, in particular to a coastal zone salt water invasion intelligent monitoring and identification method and system.
Background
The salt water invasion is a phenomenon that a salt water interface and a fresh water interface move towards the land direction due to the change of underground water power conditions in coastal areas, and is a geological disaster commonly faced by global coastal zone areas. The traditional research methods for salt water invasion mainly comprise two methods: hydrological geochemistry and geophysical. The hydrological geochemistry method is to evaluate the invasion level of salt water by drilling, logging and directly analyzing salinity parameters by taking water samples. The hydrological geochemical method has the advantages of simplicity, directness and accurate result, and has the defects of large resource investment, long working period and difficulty in completely covering an investigation area; the geophysical method is to obtain electrical parameters such as underground resistivity, polarizability and the like through a geophysical method, and obtain underground salinity field distribution information through inversion so as to evaluate the salt water invasion degree. The geophysical method has the advantages of rapid deployment, low cost and capability of realizing large depth exploration, and has the defects of low inversion result accuracy and poor reliability due to the multi-solution problem of the geophysical method, and the inversion result is difficult to be directly used by users.
In the work in the past, to the discernment research of salt water invasion, need to rely on a large amount of drilling data to support, this kind of direct drilling sample is with high costs, the degree of difficulty is big, low efficiency, it is difficult to satisfy the actual demand of user at different levels to environmental management and novel urbanization construction, current salt water invasion degree simulation monitoring devices, at the in-process of its use, do not possess the function of simulation rock stratum sample, the unable nimble operation of taking a sample to different rock stratums of operation personnel, make the simulation detect and have certain limitation, and the unable used secondary use of grit and sea water in the simulation process, improve simulation operation cost.
The invention adopts a salt water invasion degree simulation monitoring device to carry out numerical simulation on a groundwater salt water invasion system through an artificial intelligence method, integrates the advantages of two methods of geophysical exploration and hydrogeological testing, uses the device to simulate hydrogeological parameters of drilling holes and wells, trains and identifies a salt water invasion identification mode of a large-range comprehensive geophysical prospecting profile, and combines a geological, geophysical and geochemical multi-aspect information cycle training model, thereby improving the evaluation precision of the traditional method, and identifying and evaluating the salt water invasion in coastal zones more accurately and more efficiently.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments, and in this section as well as in the abstract and the title of the invention of this application some simplifications or omissions may be made to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions are not intended to limit the scope of the invention.
The invention provides a device for simulating and monitoring the invasion degree of the saline water, which solves the problems that the conventional saline water invasion degree simulating and monitoring device does not have the function of simulating rock stratum sampling in the using process, and operating personnel cannot flexibly sample different rock strata, so that the simulation detection has certain limitation, and sandstone and seawater used in the simulation process cannot be reused, so that the simulation operation cost is improved.
To solve the above technical problem, according to an aspect of the present invention, the present invention provides the following technical solutions:
an intelligent monitoring and identification method for salt water intrusion in coastal zones comprises the following steps:
step 1, acquiring resistivity information of different positions of an underground space by a geophysical exploration method.
Step 2, analyzing the seawater invasion index according to hydrogeological parameters of the simulated borehole and the water well, calculating the correlation between the seawater invasion index and the logging data, analyzing the correlation between the logging data and the seawater invasion degree, and calculating a correlation coefficient formula as follows:
here, Y is the seawater invasion level and X is the logging data. Cov () is covariance and Var () is variance.
and 4, processing the data by combining a bilateral filtering form, wherein the main purpose is to reduce noise of the data and simultaneously maintain boundary information, and the boundary information has a better maintenance effect on a seawater invasion interface. The definition is as follows:
here, R isi，jRepresenting the resistivity data at a point of input,
representing the filtered resistivity data at a certain point, S represents the spatial domain,
representing the weight of the spatial gaussian,
representing a gray value Gaussian weight, | (m, n) - (i, j) | | represents a Euclidean distance between the position (i, j) and the position (m, n), | Ri，j-Rm，nAnd | represents a resistivity difference. Wi，jTo normalize the function, the sum of weights is guaranteed to be 1.
here, r isi，jRepresenting the resistivity at a point after filtering, rmaxRepresents the maximum value of the sparse matrix, rminRepresenting the sparse matrix minimum.
And 6, dividing the resistivity data and the seawater intrusion boundary calibration data into a training set and a verification set, wherein the resistivity data is input data, and the intrusion boundary is target data.
Step 7, training the data by using a neural network and selecting a Tanh activation function, which is defined as
Judging deviation between the model predicted value and the real label through a loss function, carrying out superposition average processing on the predicted error to obtain an overall error loss,
wherein, yiAs a predicted value, YiIs true.
And 8, defining an optimizer in a random gradient descent mode.
As initial filter, a matrix of size 4 x 4:
x＝(rand(4，4)-0.5)*2*sqrt(6/f)
where x denotes the initial filter, by generating a random matrix operation, f denotes the filter parameters, f 144 (1-2), f 288 (1-4), 1 denotes the layer number of the neural network, the initial filter is processed through the Tanh function and then rotated by different angles:
wherein z represents a directional filter, and the directional filter is respectively rotated by 0 degree, 90 degrees and 180 degrees;
i represents the serial number of the filter, and the directional filter is used as the filter of the multi-scale convolutional neural network to obtain an initialized multi-scale depth network;
the multi-scale deep convolutional neural network is supported by 7 layers: the first layer is an input layer, the second layer and the fourth layer are convolution layers, convolution is composed of a plurality of directional filters, the third layer and the fifth layer are down-sampling layers, the sixth layer is a full-connection layer, the seventh layer is a regression classifier, a multi-scale depth network is trained, the feature vector of 28 x1 of training sample data is input into an initialized multi-scale depth data network, and the training process comprises the following steps:
(a) taking the input feature vector as a network input layer, and performing forward propagation to obtain an output column label (class label) of an output layer;
(b) according to a loss function, carrying out error calculation on an output class label (class label) of an output layer of the multi-scale deep convolutional neural network and a seawater invasion limit;
(c) a back propagation algorithm is adopted to minimize the training error and obtain a training model;
and training a neural network, inputting main data comprising training data, training labels, training round number and learning rate, evaluating the model after each round of training is finished, and outputting a prediction result of a training set and a real label of the training set after the training is finished.
And step 10, storing the training model and storing a model weight file.
And step 11, calling the generated model weight file to predict the seawater intrusion position by using the verification data, comparing a prediction result with the verification data, and performing precision evaluation.
And step 12, predicting the seawater invasion positions of other areas by using the prediction model with higher evaluation precision.
In the step 2, correlation coefficients between the porosity and the seawater salinity, between the saturation and the seawater salinity, and between the permeability and the seawater salinity are respectively calculated through correlation analysis, and logging data with higher correlation coefficients are selected as judgment bases of the seawater invasion indexes.
In the step 2, in the machine learning fitting by using the extreme random tree method, the data with high correlation is the first layer data, other data are sequentially superposed according to the correlation size and used as the boundary calibration input data, and the calibration result is 2 classification data.
In the step 2, the definition category code is converted into the one-hot code, and the data set is loaded in a queue form, so that the data set is disturbed.
In step 11, the verification accuracy is calculated, and the overall error, the kappa coefficient, the recall rate, and the iou value are calculated based on the confusion matrix.
In the above step 2, the simulation coastal zone area model is realized by a salt water invasion degree simulation monitoring device, which comprises a workbench, wherein the bottom end of the workbench is fixedly connected with a support column, the bottom end of the workbench is fixedly connected with a simulation box, one side of the simulation box is embedded and connected with a discharge groove, the inner wall of the discharge groove is fixedly connected with a first filter screen, one side of the workbench is fixedly connected with a storage groove, one side of the storage groove is embedded and connected with a drain valve, one side of the top end of the simulation box is fixedly provided with a seawater pipe, one side of the top end of the simulation box is fixedly provided with a fresh water pipe, one side of the inner wall of the simulation box is fixedly provided with a hole seam sensing module, the other side of the inner wall of the simulation box is fixedly connected with a resistance sensing module, the other side of the inner wall of the simulation box is fixedly provided with a salinity sensing module, and the upper end of the simulation box is provided with a sampling mechanism, and inside portal frame including of sampling mechanism, portal frame inner wall both sides gomphosis respectively are connected with first spout, and the inside activity of first spout has cup jointed first slider, first slider opposite side regulation is connected with the layer board, and the inside gomphosis of layer board is connected with the sampling tube, portal frame top gomphosis is connected with the hydraulic stem, and hydraulic stem and layer board top fixed connection, the inside activity of portal frame has cup jointed T type pole, and T type pole bottom fixedly connected with kicking block to fixedly connected with reset spring between this T type pole and the portal frame top, install actuating mechanism between portal frame and the workstation, arrange the silo one side and install sealing mechanism, it has filter equipment to accomodate the inslot internally mounted.
Preferably, the supporting plate forms a sliding structure through the first sliding block and the first sliding groove, and the supporting plate forms a lifting structure through the hydraulic rod and the portal frame.
Preferably, the ejector block is movably sleeved with the interior of the sampling tube, and the T-shaped rod forms an elastic telescopic structure with the portal frame through the return spring.
Preferably, actuating mechanism is inside including the first electric slide rail with workstation top fixed connection, and first electric slide rail surface sliding connection has first electric sliding sleeve, first electric sliding sleeve opposite side fixedly connected with connecting plate, and connecting plate top fixedly connected with second electric slide rail, second electric slide rail top sliding connection has second electric sliding sleeve, and second electric sliding sleeve top fixedly connected with loading board to this loading board and portal frame bottom fixed connection.
Preferably, the bearing plate forms a first sliding structure through the second electric sliding sleeve and the second electric sliding rail, and the connecting plate forms a second sliding structure through the first electric sliding sleeve and the first electric sliding rail.
Preferably, sealing mechanism is inside including the draw-in groove with row material groove inner wall both sides fixed connection, and the inside activity of draw-in groove has cup jointed the closing plate, closing plate inner wall melting is connected with the rubber slab, and closing plate top fixedly connected with handle, bolt is twisted to draw-in groove one side threaded connection has the hand, and bolt one end fixedly connected with clamp plate is twisted to the hand.
Preferably, the pressing plate is movably connected with the sealing plate, and the pressing plate is screwed by hands to form a telescopic structure between the bolt and the clamping groove.
Preferably, the inside second filter screen that includes and accomodate inslot wall fixed connection of filter mechanism, and accomodate groove top fixedly connected with second spout, the inside activity of second spout has cup jointed the second slider, and second slider other end welded connection has the connecting rod, connecting rod bottom fixedly connected with compression spring, and compression spring bottom fixedly connected with cleaning brush.
Preferably, be swing joint between cleaning brush and the second filter screen, and cleaning brush constitutes elastic telescopic structure through between compression spring and the connecting rod.
Aiming at the problems of the traditional method for predicting seawater intrusion by using resistivity data, the identification method combines a limit random tree, bilateral filtering and a neural network method to establish a prediction model. Compared with the prior art, the identification method has the following beneficial effects:
the logging data and the seawater invasion data are analyzed and calibrated in a mode of an extreme random tree, and the precision is higher than that of other conventional statistical methods.
Bilateral filtering effectively ensures that the seawater invades the interface and simultaneously removes noise factors influencing the resistivity value due to other ground objects and the like.
The multi-layer model of the neural network is used for training data, the anisotropic characteristics of the data are effectively utilized, and the method has unique advantages in the judgment process of adapting to background data of different areas.
Compared with the prior device for simulating the coastal zone region, the device has the beneficial effect that
1. According to the invention, under the action of the sampling mechanism, the hydraulic rod can drive the sampling tube to move up and down, the sampling tube is inserted into the simulation box, the rock stratum of the simulation coastal zone area in the simulation box can be sampled, so that workers can conveniently perform data detection and recording on the rock stratum of the simulation coastal zone, the ejector block can be driven to move downwards by extruding the T-shaped rod, the ejector block can quickly eject the sample rock stratum in the sampling tube, the sampling tube is convenient to take out, the operation is simple, time and labor are saved, and residual samples in a sampling shop can be prevented.
2. According to the invention, under the action of the driving mechanism, the first electric sliding sleeve can transversely move on the surface of the first electric sliding rail, and the second electric sliding sleeve can longitudinally move on the surface of the second electric sliding rail, so that the sampling mechanism can be driven to freely move at the top end of the simulation box, the sampling mechanism can carry out sampling operation on any position in the simulation box, and the device is flexible to operate.
3. According to the invention, under the action of the sealing mechanism, the output end of the discharge groove can be blocked through the sealing plate, the bolt is screwed by rotating the hand, the pressing plate can be driven to extrude the sealing plate, the discharge groove can be completely sealed by matching with the rubber plate, the leakage condition is prevented, the sealing plate can be drawn out from the discharge groove by pulling the handle, the moisture in the simulation box can be discharged, and the secondary simulation operation is facilitated.
4. According to the invention, under the action of the filtering mechanism, the liquid discharged from the discharge groove can be secondarily filtered through the second filter screen, sand and stone in the liquid are screened and accumulated on the surface of the second filter screen, so that the sand and stone can be recycled for secondary use, the experiment cost is reduced, the connecting rod is manually pulled, the cleaning brush can be driven to scrape and rub on the surface of the second filter screen, and the second filter screen can be prevented from being blocked by the sand and stone.
5. According to the invention, the compression spring is arranged, and the cleaning brush can be extruded to move downwards through the elastic characteristic of the compression spring, so that the cleaning brush can be tightly attached to the second filter screen, and the cleaning effect of the cleaning brush is improved.
6. According to the method, the rock sand layer in the simulated coastal zone area model is subjected to data monitoring through the hole seam sensing module, the resistance sensing module and the salinity sensing module, so that the resistivity of different positions of the underground space of the coastal zone area, which is obtained by an operator in advance through a geophysical exploration method, can be accurately simulated, and effective help is provided for a subsequent seawater intrusion position prediction experiment and a prediction model with higher evaluation precision.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and detailed embodiments, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise. Wherein:
FIG. 1 is a schematic perspective view of an apparatus for simulating and monitoring the invasion level of underground seawater according to the present invention;
FIG. 2 is a schematic view of the structure within a discharge chute of the present invention;
FIG. 3 is a perspective view of the sampling mechanism of the present invention;
FIG. 4 is a side view of the sampling mechanism of the present invention;
FIG. 5 is a schematic diagram of the interior of the side view portion of the sampling mechanism of the present invention;
FIG. 6 is a schematic view of the drive mechanism of the present invention;
FIG. 7 is a schematic top view of the sealing mechanism of the present invention;
FIG. 8 is a schematic view of the structure of the filter mechanism of the present invention;
FIG. 9 is a diagram of the present invention in accordance with the ranking;
FIG. 10 is a flow chart of the system of the present invention
FIG. 11 is a diagram of a neural network architecture in accordance with the present invention;
FIG. 12 is a data plot of resistivity profiles in accordance with the present invention.
Reference numbers in the figures: 1. a work table; 2. a support pillar; 3. a simulation box; 4. a discharge chute; 5. a first filter screen; 6. a receiving groove; 7. a drain valve; 8. a sea water pipe; 9. a fresh water pipe; 10. a hole seam sensing module; 11. a resistance sensing module; 12. a salinity sensing module; 13. a sampling mechanism; 1301. a gantry; 1302. a first chute; 1303. a first slider; 1304. a support plate; 1305. a sampling tube; 1306. a hydraulic lever; 1307. a T-shaped rod; 1308. a top block; 1309. a return spring; 14. a drive mechanism; 1401. a first electrical slide rail; 1402. a first electrical sliding sleeve; 1403. a connecting plate; 1404. a second electrical slide rail; 1405. a second electrical sliding sleeve; 1406. a carrier plate; 15. a sealing mechanism; 1501. a card slot; 1502. a sealing plate; 1503. a rubber plate; 1504. a handle; 1505. screwing the bolt by hand; 1506. pressing a plate; 16. a filtering mechanism; 1601. a second filter screen; 1602. a second chute; 1603. a second slider; 1604. a connecting rod; 1605. a compression spring; 1606. a cleaning brush.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Please refer to fig. 1-8:
as shown in figures 1-8, an underground seawater invasion degree simulation monitoring device comprises a workbench 1, a support column 2 is fixedly connected at the bottom end of the workbench 1, a simulation box 3 is fixedly connected at the bottom end of the workbench 1, a discharge groove 4 is connected at one side of the simulation box 3 in an embedding manner, a first filter screen 5 is fixedly connected with the inner wall of the discharge groove 4, an accommodating groove 6 is fixedly connected at one side of the workbench 1, a drain valve 7 is connected at one side of the accommodating groove 6 in an embedding manner, a seawater pipe 8 is fixedly installed at one side of the top end of the simulation box 3, a fresh water pipe 9 is fixedly installed at one side of the top end of the simulation box 3, a hole seam sensing module 10 is fixedly installed at one side of the inner wall of the simulation box 3, a resistance sensing module 11 is fixedly installed at the other side of the inner wall of the simulation box 3, a salinity sensing module 12 is fixedly installed at the other side of the inner wall of the simulation box 3, and a sampling mechanism 13 is installed at the upper end of the simulation box 3, and the inside portal frame 1301 that includes of sampling mechanism 13, portal frame 1301 inner wall both sides are respectively the gomphosis be connected with first spout 1302, and the inside activity of first spout 1302 is cup jointed first slider 1303, first slider 1303 opposite side regulation is connected with layer board 1304, and the inside gomphosis of layer board 1304 is connected with sampling tube 1305, portal frame 1301 top gomphosis is connected with hydraulic stem 1306, and hydraulic stem 1306 and layer board 1304 top fixed connection, the inside activity of portal frame 1301 is cup jointed T type pole 1307, and T type pole 1307 bottom fixed connection has kicking block 1308, and fixedly connected with reset spring 1309 between this T type pole 1307 and the portal frame 1301 top, install actuating mechanism 14 between portal frame 1301 and the workstation 1, discharge tank 4 one side is installed sealing mechanism 15, receive tank 6 internally mounted with filter mechanism 16.
Watch 1
And the first table is that a relation between the groundwater seawater invasion degree and the formation resistivity and the lithology parameters is fitted by using a random forest method/DL, an underground seawater invasion degree grade evaluation result L is generated by referring to relevant standards, and the resistivity, the lithology parameters, the groundwater parameters and the L are obtained at X monitoring points in a detected area.
The hole seam sensing module 10, the resistance sensing module 11 and the salinity sensing module 12 are externally connected with a display module through connecting wires, and data monitoring can be carried out on the rock sand layer.
The supporting plate 1304 forms a sliding structure through the first sliding block 1303 and the first sliding groove 1302, the supporting plate 1304 forms a lifting structure through the hydraulic rod 1306 and the portal frame 1301, and the hydraulic rod 1306 can drive the supporting plate 1304 to move up and down, so that the sampling tube 1305 of the supporting plate can move up and down.
The top block 1308 is movably sleeved with the interior of the sampling tube 1305, the T-shaped rod 1307 forms an elastic telescopic structure with the portal frame 1301 through a return spring 1309, and the sample rock stratum in the sampling tube 1305 can be quickly ejected out through the top block 1308.
The driving mechanism 14 includes a first electric slide rail 1401 fixedly connected to the top end of the workbench 1, the surface of the first electric slide rail 1401 is slidably connected to a first electric slide sleeve 1402, the other side of the first electric slide sleeve 1402 is fixedly connected to a connecting plate 1403, the top end of the connecting plate 1403 is fixedly connected to a second electric slide rail 1404, the top end of the second electric slide rail 1404 is slidably connected to a second electric slide sleeve 1405, the top end of the second electric slide sleeve 1405 is fixedly connected to a bearing plate 1406, the bearing plate 1406 is fixedly connected to the bottom end of the gantry 1301, and the first electric slide sleeve 1402 can move laterally on the surface of the first electric slide rail 1401.
The loading plate 1406 forms a first sliding structure between the second electrical sliding sleeve 1405 and the second electrical sliding rail 1404, the connecting plate 1403 forms a second sliding structure between the first electrical sliding sleeve 1402 and the first electrical sliding rail 1401, and the second electrical sliding sleeve 1405 can move longitudinally on the surface of the second electrical sliding rail 1404.
The pressing plate 1506 is movably connected with the sealing plate 1502, the pressing plate 1506 is screwed by hands to form a telescopic structure between the bolt 1505 and the clamping groove 1501, and the sealing plate 1502 can be pressed by the pressing plate 1506, so that the leakage of the discharge groove 4 can be prevented.
Inside including and accomodating 6 inner wall fixed connection's in groove second filter screen 1601 of filtering mechanism 16, and accomodate 6 top fixedly connected with second spout 1602 in groove, second slider 1603 has been cup jointed in the inside activity of second spout 1602, and second slider 1603 other end welded connection has connecting rod 1604, connecting rod 1604 bottom fixedly connected with compression spring 1605, and compression spring 1605 bottom fixedly connected with cleaning brush 1606, can accomodate exhaust sea water or fresh water through accomodating groove 6.
Be swing joint between cleaning brush 1606 and the second filter screen 1601, and cleaning brush 1606 passes through to constitute elastic telescopic structure between compression spring 1605 and the connecting rod 1604, and the elasticity characteristic of pulling compression spring 1605 can be extrudeing cleaning brush 1605 and the close laminating of second filter screen 1601.
The invention is a coastal zone salt water invasion intelligent monitoring and identification system, firstly, the rock sand layer simulated according to hydrogeological data and shallow drilling logging data is put into a simulation box 3, then, two sides of a sealing plate 1502 are inserted into a clamping groove 1501 in a sleeved mode, a hand-screw bolt 1505 is manually rotated, the hand-screw bolt 1505 drives a pressing plate 1506 to extrude the sealing plate 1502 and fix the sealing plate 1502 in the clamping groove 1501, then, seawater is added into the simulation box 3 through a seawater pipe 8 for testing, the rock sand layer data are monitored through a pore seam sensing module 10, a resistance sensing module 11 and a salinity sensing module 12, the rock sand layer data are compared with resistivity information of different positions of underground space acquired by an operator through a geophysical exploration method in advance and are kept consistent in real time, the sampling mechanism 13 is driven to transversely move through the first electric sliding sleeve 1402 transversely on the surface of a first electric sliding rail 1401, the second electric sliding sleeve 1405 longitudinally moves on the surface 1404 of a second electric sliding rail, so as to drive the sampling mechanism 13 to move longitudinally, after the sampling mechanism is adjusted to a proper position, the hydraulic rod 1306 pushes the support plate 1304, the support plate 1304 moves downwards in the first sliding chute 1302 through the first slide block 1303, the support plate 1304 drives the sampling tube 1305 to move downwards, the sampling tube 1305 is inserted into the simulation box 3 to sample the simulated rock stratum in the simulation box 3, the hydraulic rod 1306 drives the sampling tube 1305 to move upwards, the T-shaped rod 1307 is manually pressed downwards, the T-shaped rod 1307 presses the return spring 1309 to drive the top block 1308 to move downwards, the top block 1308 quickly ejects the sample rock stratum in the sampling tube 1305 out, a worker picks up the sample to detect, after the monitoring operation is completed, the hand is rotated reversely to screw the bolt 1505, the pressure plate 1506 loosens the sealing plate 1502, the handle 1504 is pulled to drive the sealing plate 1502 to be drawn out from the clamping groove, the liquid in the simulation box 3 is discharged from the discharge groove 4, entering the storage tank 6, filtering the liquid discharged from the discharge tank 4 through the second filter screen 1601, screening and accumulating gravels in the liquid on the surface of the second filter screen 1601, manually pulling the connecting rod 1604, driving the cleaning brush 1606 to scrape on the surface of the second filter screen 1601 by the connecting rod 1604, and simultaneously extruding the cleaning brush 1606 to move downwards through the elastic characteristic of the compression spring 1605, so that the cleaning brush 1606 is tightly attached to the second filter screen 1601, thereby completing the working raw material of the invention.
Please refer to fig. 9-12:
the specific steps for realizing the identification of the resistivity data and the seawater invasion boundary in the embodiment are as follows:
the method comprises the steps of firstly, selecting an area which simultaneously has a resistivity measuring section and shallow drilling logging data, wherein the logging data comprise apparent resistivity, natural gamma, natural potential, porosity, saturation, permeability and TDS (total dissolved solids) values, carrying out threshold segmentation according to the TDS values, and dividing fresh water, brackish water, saline water, brine and brine.
The groundwater quality type and resistivity characteristics of the lazhou coastal zone are shown in table two:
watch two
| Type of water quality | TDS(g/L) | Resistivity of |
| Fresh water | ＜1 | 320 |
| Brackish water | 1-3 | 160 |
| Salt water | 3-10 | 80 |
| Salt water | 10-50 | 40 |
| Brine | ＞＝50 | 20 |
And secondly, performing independent thermal coding on water quality division, namely fresh water 00001, brackish water 00010, saline water 00100, saline water 01000 and brine 10000.
And thirdly, respectively calculating correlation coefficients between the logging data and the water quality. And arranging the logging data as input data at one time according to the correlation sequence, taking the water quality division data as target data, modeling by using a limit random number method, and generating a seawater intrusion boundary division model taking the logging data as input. The input data is X ═ (X1, X2, x3., X7), the target data is Y ═ onehot (Y), and the Model is constructed as Model1 ═ ExtraTree (X, Y).
And fourthly, selecting other areas simultaneously provided with the drilling data and the resistivity profile data, calling the constructed model, and generating the seawater invasion boundary data of the drilling data area.
And fifthly, marking the resistivity section according to the seawater invasion boundary generated according to the logging data, and connecting the seawater invasion area according to a bilinear quadratic interpolation mode to generate a seawater invasion boundary section diagram. The profile is used as marking data, and the resistivity profile data is input data.
Sixthly, constructing a resistivity section data coefficient matrix Ri，jGenerating seawater invasion target data with the same data size as the seawater invasion target data, and normalizing the input data through norm (R).
And seventhly, performing bilateral filtering operation on the resistivity section data, wherein in the example, the resistivity interpolation is set to be 25, and the spatial distance difference is set to be 35.
And eighthly, cutting the resistivity section data by using the size of 28 × 28 as a template and sliding a window to generate convolution neural network input data. The target data is clipped in the same manner.
And ninthly, establishing a data set according to a mode that the resistivity data of the drilling data area and the seawater invasion data correspond to each other, and dividing a training set and a test set according to a ratio of 9: 1.
And step ten, carrying out seawater invasion boundary model training according to the multi-scale depth convolution neural network model to obtain a training model file. Model2 is the multi-scale depth CNN (X, Y), where X is the resistivity data and Y is the seawater intrusion limit data.
And eleventh, performing sparse matrix conversion on other arbitrary resistivity section data, and performing normalization processing and bilateral filtering processing.
In a twelfth step, the sliding window extracts a feature vector of 28 × 28 size.
And step thirteen, calling a multi-scale deep convolution neural network, importing the data in the previous step, and generating seawater invasion boundary data of any region.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (9)
1. An intelligent monitoring and identification method for salt water intrusion in coastal zones comprises the following steps:
step 1, acquiring resistivity information of different positions of an underground space by a geophysical exploration method;
step 2, simulating a coastal zone area model according to hydrogeological data and shallow drilling logging data, analyzing a seawater invasion index, calculating the correlation between the seawater invasion index and the logging data, analyzing the correlation between the logging data and the seawater invasion degree, and calculating a correlation coefficient formula as follows:
here, Y is the seawater invasion level, X is the logging data, Cov () is the covariance, and Var () is the variance;
step 3, calibrating a seawater invasion boundary by adopting an extreme random tree in a machine learning method according to logging data, converting the acquired resistivity information data into a two-dimensional sparse matrix after distortion point elimination and terrain correction, extracting the resistivity data of a region corresponding to training data and a neighborhood, and constructing an original data matrix according to the following modes:
and 4, processing the data by combining a bilateral filtering form, wherein the main purpose is to reduce noise of the data and simultaneously maintain boundary information, and the boundary information has a better maintenance effect on a seawater invasion interface. The definition is as follows:
here, R isi，jRepresenting the resistivity data at a point of input,
representing the filtered resistivity data at a certain point, S represents the spatial domain,
representing the weight of the spatial gaussian,
representing a gray value Gaussian weight, | (m, n) - (i, j) | | represents a Euclidean distance between the position (i, j) and the position (m, n), | Ri，j-Rm，nI represents the resistivity difference, Wi，jFor the normalization function, the sum of weights is guaranteed to be 1;
step 5, in order to ensure that the data of different resistivity profiles can be utilized, better model generalization is carried out, and normalization processing is carried out on the sparse matrix subjected to bilateral filtering processing:
here, r isi，jRepresenting the resistivity at a point after filtering, rmaxRepresents the maximum value of the sparse matrix, rminRepresents the sparse matrix minimum;
step 6, dividing the resistivity data and the seawater intrusion boundary calibration data into a training set and a verification set, wherein the resistivity data is input data, and the intrusion boundary is target data;
step 7, training the data by using a neural network and selecting a Tanh activation function, which is defined as
Judging deviation between the model predicted value and the real label through a loss function, carrying out superposition average processing on the predicted error to obtain an overall error loss,
wherein, yiAs a predicted value, YiIs true value;
step 8, defining an optimizer in a random gradient descent mode;
step 9, the serialization model is created as follows: initializing the network, performing convolution operation, performing local convolution characteristic transformation through the convolution operation to obtain corresponding convolution characteristic response output defined as
As initial filter, a matrix of size 4 x 4:
x＝(rand(4，4)-0.5)*2*sqrt(6/f)
where x denotes the initial filter, by generating a random matrix operation, f denotes the filter parameters, f 144 (1-2), f 288 (1-4), 1 denotes the layer number of the neural network, the initial filter is processed through the Tanh function and then rotated by different angles:
wherein z represents a directional filter, and the directional filter is respectively rotated by 0 degree, 90 degrees and 180 degrees;
i represents the serial number of the filter, and the directional filter is used as the filter of the multi-scale convolutional neural network to obtain an initialized multi-scale depth network;
the multi-scale deep convolutional neural network is supported by 7 layers: the first layer is an input layer, the second layer and the fourth layer are convolution layers, convolution is composed of a plurality of directional filters, the third layer and the fifth layer are down-sampling layers, the sixth layer is a full-connection layer, the seventh layer is a regression classifier, a multi-scale depth network is trained, the feature vector of 28 x1 of training sample data is input into an initialized multi-scale depth data network, and the training process comprises the following steps:
(a) taking the input feature vector as a network input layer, and performing forward propagation to obtain an output column label (class label) of an output layer;
(b) according to a loss function, carrying out error calculation on an output class label (class label) of an output layer of the multi-scale deep convolutional neural network and a seawater invasion limit;
(c) a back propagation algorithm is adopted to minimize the training error and obtain a training model;
training a neural network, inputting main data including training data, training labels, training round number and learning rate, evaluating the model after each round of training is finished, and outputting a prediction result of a training set and a real label of the training set after the training is finished;
step 10, saving the training model and saving a model weight file;
step 11, utilizing the verification data, calling the generated model weight file to predict the seawater intrusion position, comparing a prediction result with the verification data, evaluating the precision, calculating the verification precision, and respectively calculating a total error, a kappa coefficient, a recall rate and an iou value on the basis of a confusion matrix;
and step 12, predicting the seawater invasion positions of other areas by using the prediction model with higher evaluation precision.
2. The coastal zone salt water intrusion intelligent monitoring and identification method according to claim 1, characterized in that:
in the step 2, correlation coefficients between the porosity and the seawater salinity, between the saturation and the seawater salinity, and between the permeability and the seawater salinity are respectively calculated through correlation analysis, and well logging data with high correlation coefficients are selected as judgment bases of seawater invasion indexes;
in the machine learning fitting by using the extreme random tree method, the data with high correlation is the first layer data, other data are sequentially superposed according to the correlation size and serve as boundary calibration input data, and the calibration result is 2 classification data;
defining class codes to be converted into one-hot codes, loading the data set in a queue form, and disturbing the data set.
3. An intelligent monitoring and identification system for the invasion of salt water in coastal zones, which is characterized by comprising the intelligent monitoring and identification method for the invasion of salt water in coastal zones as claimed in any one of claims 1-2, wherein in the step 2, the simulation model of coastal zone areas is realized by a salt water invasion degree simulation monitoring device, which comprises a workbench (1), and is characterized in that: the device comprises a workbench (1), a support column (2) and a simulation box (3) which is fixedly connected with the bottom end of the workbench (1), wherein a material discharging groove (4) is connected to the embedding of one side of the simulation box (3), a first filter screen (5) is fixedly connected with the inner wall of the material discharging groove (4), a storage groove (6) is fixedly connected with one side of the workbench (1), a drain valve (7) is connected to the embedding of one side of the storage groove (6), a seawater pipe (8) is fixedly mounted on one side of the top end of the simulation box (3), a fresh water pipe (9) is fixedly mounted on one side of the top end of the simulation box (3), a hole seam sensing module (10) is fixedly mounted on one side of the inner wall of the simulation box (3), a resistance sensing module (11) is fixedly connected to the other side of the inner wall of the simulation box (3), and a salinity sensing module (12) is fixedly mounted on the other side of the inner wall of the simulation box (3), the simulation box comprises a simulation box (3), a sampling mechanism (13) is installed at the upper end of the simulation box (3), a portal frame (1301) is arranged inside the sampling mechanism (13), first sliding chutes (1302) are respectively connected to two sides of the inner wall of the portal frame (1301) in an embedded mode, first sliding blocks (1303) are movably sleeved inside the first sliding chutes (1302), supporting plates (1304) are connected to the other sides of the first sliding blocks (1303) in a specified mode, sampling pipes (1305) are connected to the supporting plates (1304) in an embedded mode, hydraulic rods (1306) are connected to the top end of the portal frame (1301) in an embedded mode, the hydraulic rods (1306) are fixedly connected to the top end of the supporting plates (1304), T-shaped rods (1307) are movably sleeved inside the portal frame (1301), ejector blocks (1308) are fixedly connected to the bottom end of the T-shaped rods (1307), return springs (1309) are fixedly connected between the T-shaped rods (1307) and the top end of the portal frame (1301), and a driving mechanism (14) is installed between the portal frame (1301) and the workbench (1), arrange material tank (4) one side and install sealing mechanism (15), accomodate groove (6) internally mounted and have filtering mechanism (16).
4. The coastal zone salt water invasion intelligent monitoring and identification system according to claim 3, characterized in that: the supporting plate (1304) forms a sliding structure with the first sliding groove (1302) through the first sliding block (1303), and the supporting plate (1304) forms a lifting structure with the portal frame (1301) through the hydraulic rod (1306); the ejector block (1308) is movably sleeved with the interior of the sampling tube (1305), and the T-shaped rod (1307) forms an elastic telescopic structure with the portal frame (1301) through a return spring (1309); the driving mechanism (14) is internally provided with a first electric sliding rail (1401) fixedly connected with the top end of the workbench (1), the surface of the first electric sliding rail (1401) is connected with a first electric sliding sleeve (1402) in a sliding manner, the other side of the first electric sliding sleeve (1402) is fixedly connected with a connecting plate (1403), the top end of the connecting plate (1403) is fixedly connected with a second electric sliding rail (1404), the top end of the second electric sliding rail (1404) is connected with a second electric sliding sleeve (1405) in a sliding manner, the top end of the second electric sliding sleeve (1405) is fixedly connected with a bearing plate (1406), and the bearing plate (1406) is fixedly connected with the bottom end of the portal frame (1301).
5. The coastal zone salt water invasion intelligent monitoring and identification system according to claim 4, characterized in that: the bearing plate (1406) and the second electric sliding rail (1404) form a first sliding structure through the second electric sliding sleeve (1405), and the connecting plate (1403) and the first electric sliding rail (1401) form a second sliding structure through the first electric sliding sleeve (1402).
6. The coastal zone salt water invasion intelligent monitoring and identification system according to claim 5, characterized in that: sealing mechanism (15) inside including draw-in groove (1501) with row material groove (4) inner wall both sides fixed connection, and draw-in groove (1501) inside activity has cup jointed sealing plate (1502), sealing plate (1502) inner wall melt is connected with rubber slab (1503), and sealing plate (1502) top fixedly connected with handle (1504), draw-in groove (1501) one side threaded connection has hand to twist bolt (1505), and hand to twist bolt (1505) one end fixedly connected with clamp plate (1506).
7. The coastal zone salt water invasion intelligent monitoring and identification system according to claim 6, characterized in that: the pressing plate (1506) is movably connected with the sealing plate (1502), and the pressing plate (1506) forms a telescopic structure with the clamping groove (1501) through screwing a bolt (1505) by hand.
8. The coastal zone salt water invasion intelligent monitoring and identification system according to claim 7, characterized in that: inside including and receiving groove (6) inner wall fixed connection's second filter screen (1601) of filtering mechanism (16), and receive groove (6) top fixedly connected with second spout (1602), second slider (1603) has been cup jointed in second spout (1602) inside activity, and second slider (1603) other end welded connection has connecting rod (1604), connecting rod (1604) bottom fixedly connected with compression spring (1605), and compression spring (1605) bottom fixedly connected with cleaning brush (1606).
9. The coastal zone salt water invasion intelligent monitoring and identification system according to claim 8, characterized in that: be swing joint between cleaning brush (1606) and second filter screen (1601), and cleaning brush (1606) pass through to constitute elastic telescopic structure between compression spring (1605) and connecting rod (1604).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111261614.1A CN114114426A (en) | 2021-10-28 | 2021-10-28 | Coastal zone salt water invasion intelligent monitoring and identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111261614.1A CN114114426A (en) | 2021-10-28 | 2021-10-28 | Coastal zone salt water invasion intelligent monitoring and identification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114114426A true CN114114426A (en) | 2022-03-01 |
Family
ID=80377314
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111261614.1A Pending CN114114426A (en) | 2021-10-28 | 2021-10-28 | Coastal zone salt water invasion intelligent monitoring and identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114114426A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116165359A (en) * | 2023-01-10 | 2023-05-26 | 常州大学怀德学院 | Unmanned ship data intelligent collection system capable of automatically controlling sampling |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102520131A (en) * | 2011-12-09 | 2012-06-27 | 中国地质大学（武汉） | Multi-layered aquifer underground flow system-based underground water pollution simulator |
| CN105258970A (en) * | 2015-10-23 | 2016-01-20 | 哈尔滨师范大学 | Lake underwater automatic mud scraping and stone grinding inlet pipe connection type sampling device |
| CN106089193A (en) * | 2016-07-05 | 2016-11-09 | 高琴 | Gas hydrates exploitation seabed rock deformation analogue experiment installation and experimental technique |
| CN212195900U (en) * | 2020-04-15 | 2020-12-22 | 深圳市瑞杰创新科技有限公司 | Unmanned aerial vehicle formula pollution sources monitoring devices based on satellite positioning |
| CN213456219U (en) * | 2020-10-28 | 2021-06-15 | 牛妍 | Sampling device for resource exploration |
| WO2021174449A1 (en) * | 2020-03-04 | 2021-09-10 | 昆山贝名新材料科技有限公司 | Water quality sampling device for environmental protection technology development |
-
2021
- 2021-10-28 CN CN202111261614.1A patent/CN114114426A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102520131A (en) * | 2011-12-09 | 2012-06-27 | 中国地质大学（武汉） | Multi-layered aquifer underground flow system-based underground water pollution simulator |
| CN105258970A (en) * | 2015-10-23 | 2016-01-20 | 哈尔滨师范大学 | Lake underwater automatic mud scraping and stone grinding inlet pipe connection type sampling device |
| CN106089193A (en) * | 2016-07-05 | 2016-11-09 | 高琴 | Gas hydrates exploitation seabed rock deformation analogue experiment installation and experimental technique |
| WO2021174449A1 (en) * | 2020-03-04 | 2021-09-10 | 昆山贝名新材料科技有限公司 | Water quality sampling device for environmental protection technology development |
| CN212195900U (en) * | 2020-04-15 | 2020-12-22 | 深圳市瑞杰创新科技有限公司 | Unmanned aerial vehicle formula pollution sources monitoring devices based on satellite positioning |
| CN213456219U (en) * | 2020-10-28 | 2021-06-15 | 牛妍 | Sampling device for resource exploration |
Non-Patent Citations (4)
| Title |
|---|
| 佟雪;孟庆生;杨俊;韩凯;肖志广;: "咸水入侵探测中电阻率法测量数值模拟研究", 物探化探计算技术, no. 01, 15 January 2016 (2016-01-15), pages 1 - 6 * |
| 许丹;孙志林;潘德炉;: "钱塘江河口盐度的神经网络模拟", 浙江大学学报(理学版), no. 02, 15 March 2011 (2011-03-15), pages 235 - 238 * |
| 陈学群, 李成光, 田婵娟, 刘丹, 辛光明, 管清花: "高密度电阻率法在咸水入侵监测中的应用", 物探与化探, vol. 45, no. 5, 31 October 2021 (2021-10-31), pages 1347 - 1353 * |
| 陈能汪, 余镒琦, 陈纪新, 等: "人工神经网络模型在水质预警中的应用研究进展", 环境科学学报, vol. 41, no. 12, 9 November 2021 (2021-11-09), pages 4771 - 4782 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116165359A (en) * | 2023-01-10 | 2023-05-26 | 常州大学怀德学院 | Unmanned ship data intelligent collection system capable of automatically controlling sampling |
| CN116165359B (en) * | 2023-01-10 | 2023-10-13 | 常州大学怀德学院 | Unmanned ship data intelligent collection system capable of automatically controlling sampling |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Marcellus shale lithofacies prediction by multiclass neural network classification in the Appalachian Basin | |
| AU2010245112B2 (en) | Method for uncertainty quantification in the performance and risk assessment of a carbon dioxide storage site | |
| CN111080021B (en) | Sand body configuration CMM neural network prediction method based on geological information base | |
| Eydinov et al. | Simultaneous estimation of relative permeability and porosity/permeability fields by history matching production data | |
| CN107436452A (en) | Hydrocarbon source rock Forecasting Methodology and device based on probabilistic neural network algorithm | |
| CN105093348A (en) | Multilayer oil gas resource amount prediction method | |
| CN113344050A (en) | Lithology intelligent identification method and system based on deep learning | |
| US11670073B2 (en) | System and method for detection of carbonate core features from core images | |
| NO20230264A1 (en) | Core-level high resolution petrophysical characterization method | |
| Gu et al. | Permeability prediction using hybrid techniques of continuous restricted Boltzmann machine, particle swarm optimization and support vector regression | |
| CN114114426A (en) | Coastal zone salt water invasion intelligent monitoring and identification method and system | |
| Ma et al. | Tight gas sandstone reservoirs, Part 1: Overview and lithofacies | |
| NO20180859A1 (en) | Classification and regression tree analysis of formation realizations | |
| Behdad | A step toward the practical stratigraphic automatic correlation of well logs using continuous wavelet transform and dynamic time warping technique | |
| CN1896458B (en) | System and methods of deriving fluid properties of downhole fluids and uncertainty thereof | |
| Mahmoodi et al. | Clustering of downhole physical property measurements at the Victoria property, Sudbury for the purpose of extracting lithological information | |
| Chen et al. | NMR-data-driven prediction of matrix permeability in sandstone aquifers | |
| Manda et al. | Identifying and characterizing solution conduits in karst aquifers through geospatial (GIS) analysis of porosity from borehole imagery: An example from the Biscayne aquifer, South Florida (USA) | |
| US9121256B2 (en) | Method of constructing a flow model associated with capillary pressure curves and/or relative permeability curves | |
| Abedini et al. | Porosity classification from thin sections using image analysis and neural networks including shallow and deep learning in Jahrum formation | |
| CN111965720B (en) | Method for acquiring hydraulic conductivity based on ground-well combination | |
| CN114896468A (en) | File type matching method and intelligent data entry method based on neural network | |
| CN109577946B (en) | Method for identifying oolitic beach type by using well logging data | |
| Igboekwe et al. | Geostatistical Correlation of Aquifer Potentials in Abia State, South-Eastern Nigeria | |
| Velis | Statistical segmentation of geophysical log data |
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 |