CN108256258A - Cemented fill mechanical response characteristic Forecasting Methodology based on SEM image - Google Patents

Cemented fill mechanical response characteristic Forecasting Methodology based on SEM image Download PDF

Info

Publication number
CN108256258A
CN108256258A CN201810098527.0A CN201810098527A CN108256258A CN 108256258 A CN108256258 A CN 108256258A CN 201810098527 A CN201810098527 A CN 201810098527A CN 108256258 A CN108256258 A CN 108256258A
Authority
CN
China
Prior art keywords
image
sample
cemented fill
sem
microscope
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
Application number
CN201810098527.0A
Other languages
Chinese (zh)
Other versions
CN108256258B (en
Inventor
秦学斌
刘浪
王湃
陈柳
张波
王美
张小艳
孙伟博
王燕
邱华富
辛杰
方治余
朱超
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xian University of Science and Technology
Original Assignee
Xian University of Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xian University of Science and Technology filed Critical Xian University of Science and Technology
Priority to CN201810098527.0A priority Critical patent/CN108256258B/en
Publication of CN108256258A publication Critical patent/CN108256258A/en
Application granted granted Critical
Publication of CN108256258B publication Critical patent/CN108256258B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
    • G01N23/22—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by measuring secondary emission from the material
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • 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
    • G06F2119/06—Power analysis or power optimisation

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Biochemistry (AREA)
  • Health & Medical Sciences (AREA)
  • Analysing Materials By The Use Of Radiation (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Geometry (AREA)
  • Analytical Chemistry (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Computer Hardware Design (AREA)

Abstract

The invention discloses a kind of cemented fill mechanical response characteristic Forecasting Methodology based on SEM image, including step：First, SEM scanning electron microscope examples are made；2nd, scanning forms SEM electron-microscope scannings image and stores into computer；3rd, gaussian filtering process is carried out to SEM electron-microscope scannings image；4th, multiple cemented fill cluster images are obtained；5th, it determines cemented fill microscopic void figure, obtains cemented fill microscopic void binary map；6th, the SEM electron-microscope scannings image after gaussian filtering process with cemented fill microscopic void binary map is merged, obtains test sample image；7th, normalization process is carried out to test sample image；8th, in the Tensorflow deep learnings mechanical response prediction network for building the input of regular test sample image in advance, uniaxial mechanical response prediction result is obtained.Forecasting efficiency of the present invention is high, spends human and material resources less, is of great significance to research cemented fill strength and stability.

Description

Cemented fill mechanical response characteristic Forecasting Methodology based on SEM image
Technical field
The invention belongs to cemented filling mining technical fields, and in particular to a kind of consolidated fill muscle power based on SEM image Learn response characteristic Forecasting Methodology.
Background technology
With the development of national science technology, the requirement to energy conservation and environmental protection technology is also higher and higher, traditional consolidated fill Mining uses cement, and as cementitious material, the cost of cement, which is up to, fills the 75% of totle drilling cost.By research and development, contain in tailings Active silica and aluminium oxide replace part of cement that can not only reduce the discharge of tailings as cementing material using tailings Amount effectively reduces the cost of mining with stowing, additionally it is possible to and it improves strength of filling mass, reduces ground and cave in area, the protection to environment Also play a part of actively promoting.Therefore, the tailings of ore dressing plant discharge is increasingly becoming the main aggregate of mine cemented filling.It is cementing Core content of the obturation as cemented filling method, it is related to mine safety and mine economic profit.With " obturation is made With the mechanical response characteristic of mechanism, strength of filling mass, the Proper Match of obturation and obturation " be content filling mechanics, In the past few years receive the great attention of mining.Eight international filling academic conferences have been held in recent years, in filling mechanics Many aspects have very big progress, academia generally believes that obturation mechanical property is to seriously affect and restrict consolidated fill The key factor of mining codes.
It is direct to realize that different water ash proportionings, different curing ages etc. have the mechanical property of cemented fill using tailings Influence relationship.Tailings while filling aggregate deficiency is solved, is as one of most common filling aggregate of bashing Extremely thick ore body pillar recovery when the rate of dilution is low, loss late is big, " under three " resource exploitation safety is low and deep rock mass it is voltage-controlled The solution for the problems such as system is difficult provides effective way.Many researchers to the composition proportion of Tailing Paste Filling, stabilization process and Mechanical strength has done in-depth study.For example, Kesimal A et al. have studied the pass of desliming copper-lead zinc tailings and lotion intensity System finds that tailings particle size distribution has large effect to cemented fill intensity；The 16th phase of volume 10 phase in 2003 Periodical《Minerals Engineering》Article The effect of desliming by have been delivered on (mineral engineering) Sedimentation on paste backfill performance (the ore body obturation deposition properties of demineralization mud influence)； Fall et al. has studied influence of the curing temperature to the intensity of Cemented Filling；In the 4th phase periodical of volume 10 in 2010 《Engineering Geology》Article A Contribution to understanding have been delivered in (engineering geology) the effects of curing temperature on the mechanical properties of mine Cemented tailings backfill (contribution of the temperature to Cemented Filling Effect on Mechanical Properties)；G Xiu et al. Using different proportion tailings cementing strength with being tested under various concentration in laboratory, it is chemical on the micro level to disclose tailings Reaction mechanism, the influence to the macro-size of obturation stability are studied；In the 6th phase periodical of volume 14 in 2012 《International Journal of Digital Content Technology&Its Applications》(in number Appearance technology and its application) on delivered article Microstructure Test and Macro Size Effect on the Stability of Cemented Tailings Backfill (test and macro-size is to cementing tailing-filled by microstructure The stability influence of body)；Li Wen ministers et al. are tested by glue sand, have studied sulfate to cemented fill uniaxial compressive strength with The influence of elasticity modulus relationship；In the 1st phase periodical of volume 42 in 2016《Chinese coal》On delivered article《Sulfate is to glue Obturation uniaxial compressive strength is tied to study with elasticity modulus relationship affect》.But in the prior art, to consolidated fill mechanics The method that response characteristic prediction uses experiment test more, test period is long, efficiency is low, and the manpower and materials of consuming are high, affects new Cemented fill Rapid Popularization application, be easy to cause mining the duration delay.
Invention content
In view of the above-mentioned deficiencies in the prior art, the technical problem to be solved by the present invention is that it provides a kind of based on SEM The cemented fill mechanical response characteristic Forecasting Methodology of image, method and step is simple, and novel in design reasonable, realization facilitates fast Victory, forecasting efficiency is high, and the period is short, and the manpower and materials of consuming are few, has weight for the strength and stability for studying cemented fill Meaning is wanted, it is highly practical, have a wide range of application, application value is high.
In order to solve the above technical problems, the technical solution adopted by the present invention is：A kind of cemented fill based on SEM image Mechanical response characteristic Forecasting Methodology, which is characterized in that this method includes the following steps：
Step 1: take a part that SEM scanning electron microscope examples are made from cemented fill sample；
Step 2: being scanned using SEM scanning electron microscope to SEM scanning electron microscope examples, SEM electron-microscope scannings image is formed simultaneously It stores in computer；
Step 3: the computer calls gaussian filtering process module to carry out at gaussian filtering SEM electron-microscope scannings image Reason, obtains the SEM electron-microscope scanning images after gaussian filtering process；
Step 4: the computer calls FCM fuzzy clusterings processing module to the SEM Electronic Speculum after carrying out gaussian filtering process Scan image carries out aperture image extraction, obtains and the equal numbers of multiple cemented fill cluster images of cluster centre；
Step 5: the minimum a kind of cemented fill cluster image of gray value is determined as cemented fill by the computer Microscopic void figure, and binary conversion treatment is carried out to cemented fill microscopic void figure, obtain cemented fill microscopic void two-value Figure；
Step 6: the computer is by the SEM electron-microscope scannings image after the gaussian filtering process obtained in step 3 and walks The cemented fill microscopic void binary map obtained in rapid five merges, and obtains test sample image；
Step 7: the computer carries out normalization process to test sample image, it is 960 × 960 just to form pixel Ruleization test sample image；
Step 8: what the computer built the regular test sample image obtained in step 7 input in advance In Tensorflow deep learnings mechanical response prediction network, uniaxial mechanical response prediction result is obtained.
The above-mentioned cemented fill mechanical response characteristic Forecasting Methodology based on SEM image, it is characterised in that：In step 1 Length, width and the height of the SEM scanning electron microscope examples are 10mm.
The above-mentioned cemented fill mechanical response characteristic Forecasting Methodology based on SEM image, it is characterised in that：In step 3 The computer calls gaussian filtering process module to carry out formula that gaussian filtering process uses to SEM electron-microscope scannings image as L (x, y)=I (x, y) * G (x, y), wherein, I (x, y) represent SEM electron-microscope scanning images, G (x, y) be Gaussian filter function, L (x, Y) it is the SEM electron-microscope scanning images after gaussian filtering process, x is the abscissa of image, and y is the ordinate of image.
The above-mentioned cemented fill mechanical response characteristic Forecasting Methodology based on SEM image, it is characterised in that：In step 4 The computer calls FCM fuzzy clusterings processing module to carry out hole to the SEM electron-microscope scannings image after carrying out gaussian filtering process Gap image zooming-out, the detailed process for obtaining multiple cemented fills cluster images equal numbers of with cluster centre are：
Step 401, definition use the FCM fuzzy clustering algorithms based on sample weighting, and object function isThe constraints for meeting extreme value isWherein, U is fuzzy matrix and U=[u11,u22,…,ucn], uikMember for matrix U Element and uikRepresent that k-th of sample point belongs to the degree of membership of the i-th class, n is sample point sum, and c is cluster centre number；V={ v1, v2,...vcBe c class cluster centre, wkFor sample point xkWeights, dikFor sample point xkTo central point viEuclidean distance, viFor the element of V, xkK-th of sample point and X={ x for sample set X1,x2,...xn, m is degree of membership uikWeighted index and M ＞ 1；
Step 402, the value of setting cluster centre number c, degree of membership uikWeighted index m value and minimum iteration error ε Value；
Step 403 uses formulaMore new sample point xkWeight wk；uτjFor matrix U Element and uτjRepresent that j-th of sample point belongs to the degree of membership of τ classes, 1≤τ≤c, 1≤j≤n；vτElement for V；uijFor matrix The element and u of UijRepresent that j-th of sample point belongs to the degree of membership of the i-th class；
Step 404 uses formulaUpdate uik；Wherein, drkFor sample point xkTo central point vr's Euclidean distance, 1≤r≤c；
Step 405 uses formulaUpdate vi；
Step 406 judges whether to meet | | J(t+1)- J (t) | | ＜ ε work as satisfaction | | J(t+1)- J (t) | | during ＜ ε, cluster is stopped Only, extraction obtains and the equal numbers of multiple cemented fill cluster images of cluster centre；Otherwise, return to step 403；Wherein, t For the time.
The above-mentioned cemented fill mechanical response characteristic Forecasting Methodology based on SEM image, it is characterised in that：Step 402 The value of middle setting cluster centre number c is 4, setting degree of membership uikWeighted index m value for 2, set minimum iteration error ε's Value is 0.3.
The above-mentioned cemented fill mechanical response characteristic Forecasting Methodology based on SEM image, it is characterised in that：In step 8 The Tensorflow deep learnings mechanical response characteristic predicts that the construction method of network is：
Step 801 takes a part that SEM scanning electron microscope samples are made from each cemented fill sample after multiple numbers Product, remainder is as uniaxial compressive strength test sample；And to multiple SEM scanning electron microscope examples and multiple intensity tests Sample corresponds number；
Step 802, using cemented fill uniaxial compressive strength test device respectively to multiple intensity test samples Uniaxial compressive strength test is carried out, and mean value is taken to the uniaxial compressive strength of multiple intensity test samples measured, is obtained The uniaxial compressive strength of cemented fill sample；
Step 803, the training sample image for obtaining Tensorflow deep learnings mechanical response characteristic prediction network, specifically Process is：
Step 8031 respectively takes multiple scan multiple SEM scanning electron microscope examples using SEM scanning electron microscope, is formed more A SEM electron-microscope scannings image is simultaneously stored into computer；The quantity of the SEM electron-microscope scannings image is at least 150；
Step 8032, the computer call gaussian filtering process module to be carried out respectively to multiple SEM electron-microscope scannings images Gaussian filtering process obtains the SEM electron-microscope scanning images after multiple gaussian filtering process；
Step 8033, the computer call FCM fuzzy clusterings processing module respectively to multiple carry out gaussian filtering process SEM electron-microscope scannings image afterwards carries out aperture image extraction, obtains multigroup cemented fill cluster image, every group of cemented fill The quantity for clustering cemented fill cluster image in image is equal with cluster centre number；
Every group of cemented fill is clustered the minimum a kind of consolidated fill of gray value in image by step 8034, the computer Body cluster image is determined as cemented fill microscopic void figure, and multiple cemented fill microscopic void figures are carried out at binaryzation Reason, obtains multiple cemented fill microscopic void binary maps；
Step 8035, the computer are by the SEM electron-microscope scannings after the multiple gaussian filtering process obtained in step 8032 Image is merged with obtaining multiple cemented fill microscopic void binary maps in step 8034 according to number is corresponding, is obtained more A training sample image；
Step 804, the computer carry out normalization process to multiple training sample images respectively, and forming multiple pixels is 960 × 960 regularized training sample image；
The number of plies that step 805, the computer build a convolutional network core is five layers, input layer is regularized training sample This image, the Tensorflow deep learning networks that output layer is the corresponding uniaxial compressive strength of regularized training sample image, The multiple regularized training sample images stored instruct Tensorflow deep learning networks as training sample Practice, obtain Tensorflow deep learnings mechanical response characteristic prediction network；The Tensorflow deep learnings mechanical characteristic The size of five layers of convolutional network core of response prediction network from one layer to layer 5 be respectively 3x3,2x2,3x3,2x2,2x2.
The above-mentioned cemented fill mechanical response characteristic Forecasting Methodology based on SEM image, it is characterised in that：Step 802 Described in cemented fill uniaxial compressive strength test device include seat cushion and more pull rods being fixedly connected at the top of seat cushion, with And for applying the axial pressure force transmission mechanism of axial compressive force to cemented fill sample and for giving axial pressure force transmission mechanism The axial pressure dynamical system of power is provided；The bottom of the seat cushion is fixedly connected with multiple pedestals, is set at the top of the seat cushion The sample placing groove for placing cemented fill sample is equipped with, the center of the sample placing groove is located on the seat cushion Place is provided with drain valve；The fixed frame for fixing more pull rods is provided in the middle part of more pull rods, the top of more pull rods is consolidated Surely it is connected with top loading plate；The axial pressure force transmission mechanism includes the cylinder being mounted on top loading plate, the cylinder Piston rod it is down-set, the piston rod bottom of the cylinder is connected with pressure transmitting plates；The axial pressure dynamical system packet Include compressed air gas source and loading controls and one end connect with compressed air gas source, the gas of the other end and cylinder connection Delivery pipe；On the air shooter pneumatic three are disposed with from connection compressed air gas source to the position of connection cylinder The input terminal of part, pressure sensor and cylinder control solenoid valve, the pressure sensor and loading controls connects, the cylinder The output terminal of solenoid valve and loading controls is controlled to connect, the loading controls are connect by communication module with computer.
The above-mentioned cemented fill mechanical response characteristic Forecasting Methodology based on SEM image, it is characterised in that：The sample The O-ring seal for being sleeved on cemented fill sample bottom is provided in placing groove, is provided on the seat cushion positioned at the examination Porous stone around sample placing groove.
The above-mentioned cemented fill mechanical response characteristic Forecasting Methodology based on SEM image, it is characterised in that：The pressurization Controller is programmable logic controller (PLC), and the communication module is RS-485 communication modules.
The above-mentioned cemented fill mechanical response characteristic Forecasting Methodology based on SEM image, it is characterised in that：Step 802 Described in multiple intensity test samples are carried out respectively using cemented fill uniaxial compressive strength test device it is uniaxial anti- Compressive Strength is tested, wherein the detailed process that uniaxial compressive strength test is carried out to each intensity test sample is：
Cemented fill sample after O-ring seal is put into the sample placing groove, is put into the examination by step 8021 In sample placing groove, the center for making cemented fill sample is corresponding with the center of the piston rod of cylinder and pressure transmitting plates；And The porous stone being put on seat cushion around the sample placing groove；
Step 8022 opens compressed air gas source, the pressure for adjusting compressed air gas source by adjusting pneumatic triple piece and exporting The air pressure of contracting air, loading controls control the piston rod of cylinder downward or upward by controlling cylinder that solenoid valve is controlled to commutate Movement applies pressure or unloading pressure to cemented fill sample, loading controls during cemented fill specimen broke is acquired To pressure sensor detection pressure value be denoted as F, pressure value F is transferred to computer by loading controls, and computer is according to public affairs FormulaThe uniaxial compressive strength P of intensity test sample is calculated；Wherein, S is the top of intensity test sample Face area；When the piston rod of cylinder moves downward, pressure transmitting plates is driven to move downward, filled by pressure transmitting plates to cementing Fill out body sample apply pressure, when the piston rod of cylinder moves upwards, drive pressure transmitting plates move upwards, pressure transmitting plates from Open the upper surface of cemented fill sample, unloading pressure.
Compared with the prior art, the present invention has the following advantages：
1st, the present invention is adopted using scanning electron microscope (Scanning Electronic Microscopy, SEM) scanning Collect sample image, cemented fill microscopic void figure is extracted, then using Tensorflow depths using FCM fuzzy clusterings processing method Degree learning network establishes image to the prediction model end to end between mechanical response characteristic, so as to predict the power of cemented fill Response characteristic is learned, method and step is simple, and novel in design rationally realization is convenient and efficient, and forecasting efficiency is high, and the period is short, the people of consuming Power material resources are few.
2nd, the present invention is also used before using FCM fuzzy clusterings processing method extraction cemented fill microscopic void image Gaussian filtering method carries out gaussian filtering process to SEM electron-microscope scannings images, helps to obtain more accurately prediction result.
3rd, the present invention extracts cemented fill microscopic void image using FCM fuzzy clusterings processing method, can avoid sample Different sample vectors are to the Different Effects of cluster result in this space.
4th, the present invention is used the SEM electron-microscope scannings image after gaussian filtering process and cemented fill microscopic void two-value The method that figure merges obtains test sample image, as the input of Tensorflow deep learnings mechanical response prediction network, energy The influence of redundancy in original SEM electron-microscope scannings image is enough avoided, improves mechanical response characteristic precision of prediction.
5th, the present invention is using Tensorflow deep learning network structions SEM electron-microscope scannings image and consolidated fill muscle power The relationship between response characteristic is learned, once carries out structure Tensorflow deep learnings mechanical response prediction network, it can be multiple It conveniently uses so that when carrying out the prediction of cemented fill mechanical response characteristic, without repeatedly doing experiment test again, only need SEM electron-microscope scanning images are collected in computer, you can the whole process of mechanical response characteristic prediction is automatically performed, it is convenient fast It is prompt.
6th, uniaxial compressive strength is an important parameter for reflecting obturation mechanical property, it can be reacted to a certain extent The strength and stability of obturation；During present invention structure Tensorflow deep learnings mechanical response prediction network, export as list Axis compression strength, and using uniaxial compressive strength as uniaxial mechanical response prediction result, for studying the intensity of cemented fill It is of great significance with stability.
7th, the present invention surveys compression strength using the cemented fill uniaxial compressive strength test device of independent research manufacture Test agent carries out intensity test, and the structure of cemented fill uniaxial compressive strength test device is simple, realizes and using behaviour Facilitate, and accurate uniaxial compressive strength can be measured.
8th, the mechanical response characteristic that the present invention studies is the key property of cemented fill, and cemented fill is cementing fill again The core content of mining codes is filled out, therefore the method for the present invention can not only be to study novel cemented fill to contribute share, moreover it is possible to Enough discharge capacitys to reduce tailings, the cost for reducing mining with stowing, environmental protection, improve ore recovery rate, alleviate Temperature Deep, Optimization environment of mining area and control ground settlement etc. are contributed share；The present invention's is highly practical, has a wide range of application, application value It is high.
In conclusion the method for the present invention step is simple, novel in design rationally realization is convenient and efficient, and forecasting efficiency is high, the period Short, the manpower and materials of consuming are few, are of great significance for the strength and stability for studying cemented fill, highly practical, should Wide with range, application value is high.
Below by drawings and examples, technical scheme of the present invention is described in further detail.
Description of the drawings
Fig. 1 is the method flow block diagram of the present invention.
Fig. 2 is the SEM electron-microscope scanning images after gaussian filtering process in the specific embodiment of the invention.
Fig. 3 A are to carry out FCM to the SEM electron-microscope scannings image after progress gaussian filtering process in the specific embodiment of the invention The bright cemented fill cluster image that fuzzy clustering is handled.
Fig. 3 B are to carry out FCM to the SEM electron-microscope scannings image after progress gaussian filtering process in the specific embodiment of the invention The brighter cemented fill cluster image that fuzzy clustering is handled.
Fig. 3 C are to carry out FCM to the SEM electron-microscope scannings image after progress gaussian filtering process in the specific embodiment of the invention The dark cemented fill cluster image that fuzzy clustering is handled.
Fig. 3 D are to carry out FCM to the SEM electron-microscope scannings image after progress gaussian filtering process in the specific embodiment of the invention The most dark cemented fill cluster image that fuzzy clustering is handled.
Fig. 4 is the cemented fill microscopic void binary map in the specific embodiment of the invention.
Fig. 5 is the test sample image in the specific embodiment of the invention.
Fig. 6 is the structure diagram of cemented fill uniaxial compressive strength test device of the present invention.
Reference sign:
1-air shooter；2-cylinder；3-pressure transmitting plates；
4-compressed air gas source；5-drain valve；6-O-ring seal；
7-porous stone；8-pull rod；9-top loading plate；
10-seat cushion；11-sample placing groove；12-pneumatic triple piece；
13-pressure sensor；14-cylinder controls solenoid valve；15-pedestal；
16-communication module；17-computer；18-loading controls；
19-cemented fill sample.
Specific embodiment
As shown in Figure 1, the present invention the cemented fill mechanical response characteristic Forecasting Methodology based on SEM image, including with Lower step：
Step 1: take a part that SEM scanning electron microscope examples are made from cemented fill sample 19；
When it is implemented, SEM scanning electron microscope examples, which are made, has also carried out multiple spray carbon processing.
In the present embodiment, length, width and the height of SEM scanning electron microscope examples described in step 1 are 10mm.
Step 2: being scanned using SEM scanning electron microscope to SEM scanning electron microscope examples, SEM electron-microscope scannings image is formed simultaneously It stores in computer 17；
Step 3: the computer 17 calls gaussian filtering process module to carry out gaussian filtering to SEM electron-microscope scannings image Processing, obtains the SEM electron-microscope scanning images after gaussian filtering process；
In the present embodiment, computer 17 described in step 3 calls gaussian filtering process module to SEM electron-microscope scanning images The formula that uses of gaussian filtering process is carried out as L (x, y)=I (x, y) * G (x, y), wherein, I (x, y) expression SEM electron-microscope scannings Image, G (x, y) are Gaussian filter function, and L (x, y) is the SEM electron-microscope scanning images after gaussian filtering process, and x is the horizontal stroke of image Coordinate, y are the ordinate of image.
In the present embodiment, the SEM electron-microscope scanning images after gaussian filtering process are as shown in Figure 2.
Step 4: the computer 17 calls FCM fuzzy clusterings processing module to the SEM electricity after carrying out gaussian filtering process Scarnning mirror image carries out aperture image extraction, obtains and the equal numbers of multiple cemented fill cluster images of cluster centre；
In the present embodiment, computer 17 described in step 4 calls FCM fuzzy clusterings processing module to carrying out gaussian filtering Treated, and SEM electron-microscope scannings image carries out aperture image extraction, obtains and the equal numbers of multiple consolidated fills of cluster centre Body cluster image detailed process be：
Step 401, definition use the FCM fuzzy clustering algorithms based on sample weighting, and object function isThe constraints for meeting extreme value isWherein, U is fuzzy matrix and U=[u11,u22,…,ucn], uikMember for matrix U Element and uikRepresent that k-th of sample point belongs to the degree of membership of the i-th class, n (corresponds to each coordinate points in the picture for sample point sum Gray value), c is cluster centre number (being classified in the picture according to brightness of image)；V={ v1,v2,...vcIt is c class Cluster centre, wkFor sample point xkWeights, dikFor sample point xkTo central point viEuclidean distance, viFor the element of V, xkFor K-th of the sample point and X={ x of sample set X1,x2,...xn, m is degree of membership uikWeighted index and m ＞ 1；Using based on sample The FCM fuzzy clustering algorithms of this weighting can avoid in sample space Different Effects of the different sample vectors to cluster result；
Step 402, the value of setting cluster centre number c, degree of membership uikWeighted index m value and minimum iteration error ε Value；
In the present embodiment, the value that cluster centre number c is set in step 402 is 4, setting degree of membership uikWeighted index m Value for 2, the value for setting minimum iteration error ε is 0.3.
Step 403 uses formulaMore new sample point xkWeight wk；uτjFor matrix U Element and uτjRepresent that j-th of sample point belongs to the degree of membership of τ classes, 1≤τ≤c, 1≤j≤n；vτElement for V；uijFor matrix The element and u of UijRepresent that j-th of sample point belongs to the degree of membership of the i-th class；
Step 404 uses formulaUpdate uik；Wherein, drkFor sample point xkTo central point vr's Euclidean distance, 1≤r≤c；
Step 405 uses formulaUpdate vi；
Step 406 judges whether to meet | | J(t+1)- J (t) | | ＜ ε work as satisfaction | | J(t+1)- J (t) | | during ＜ ε, cluster is stopped Only, extraction obtains and the equal numbers of multiple cemented fill cluster images of cluster centre；Otherwise, return to step 403；Wherein, t For the time.
In the present embodiment, the value of cluster centre number c is 4, four cemented fill cluster images is obtained, such as Fig. 3 A~figure Shown in 3D, respectively bright, brighter, dark and most dark four cemented fills cluster image.
Step 5: the computer 17 is (most dark cementing to fill by the minimum a kind of cemented fill cluster image of gray value Fill out body cluster image) it is determined as cemented fill microscopic void figure, and cemented fill microscopic void figure is carried out at binaryzation Reason, obtains cemented fill microscopic void binary map；
In the present embodiment, the cemented fill cluster image of gray value minimum is Fig. 3 D, i.e. Fig. 3 D are micro- for cemented fill View hole gap figure, obtained cemented fill microscopic void binary map are as shown in Figure 4.
Step 6: the computer 17 by the SEM electron-microscope scannings image after the gaussian filtering process obtained in step 3 with The cemented fill microscopic void binary map obtained in step 5 merges, and obtains test sample image；Due to original SEM electricity Redundancy in scarnning mirror image is more, i.e., it is generally acknowledged that black region is aperture sections, difference factor during due to being scanned Influence, it is understood that there may be situations such as bright-dark degree's difference one of scanning, therefore, the gaussian filtering that will be obtained in step 3 of the present invention Treated, and SEM electron-microscope scannings image is merged with the cemented fill microscopic void binary map obtained in step 5, is obtained Test sample image can avoid the influence of redundancy, improve uniaxial mechanical response characteristic precision of prediction.
For example, the as shown in figure 5, test sample image as obtained in the present embodiment.
Step 7: the computer 17 carries out normalization process to test sample image, it is 960 × 960 to form pixel Regular test sample image；
Step 8: what the computer 17 built the regular test sample image obtained in step 7 input in advance In Tensorflow deep learnings mechanical response prediction network, uniaxial mechanical response prediction result is obtained.
In the present embodiment, the mechanical response characteristics of Tensorflow deep learnings described in step 8 predict the structure side of network Method is：
Step 801 takes a part that SEM scanning electron microscope samples are made from each cemented fill sample 19 after multiple numbers Product, remainder is as uniaxial compressive strength test sample；And to multiple SEM scanning electron microscope examples and multiple intensity tests Sample corresponds number；For example, the number of multiple cemented fill samples 19 is respectively 1,2 ..., N, multiple SEM scannings electricity The number of mirror sample be respectively A1, A2 ..., AN, the numbers of multiple uniaxial compressive strength test samples be respectively B1, B2 ..., BN；
When it is implemented, SEM scanning electron microscope examples, which are made, has also carried out multiple spray carbon processing.
Step 802, using cemented fill uniaxial compressive strength test device respectively to multiple intensity test samples Uniaxial compressive strength test is carried out, and mean value is taken to the uniaxial compressive strength of multiple intensity test samples measured, is obtained The uniaxial compressive strength of cemented fill sample 19；
In the present embodiment, as shown in fig. 6, the test device of cemented fill uniaxial compressive strength described in step 802 includes Seat cushion 10 is with more pull rods 8 for being fixedly connected on 10 top of seat cushion and for applying axial pressure to cemented fill sample 19 The axial pressure force transmission mechanism of power and the axial pressure dynamical system for providing power to axial pressure force transmission mechanism；The seat The bottom of pad 10 is fixedly connected with multiple pedestals 15, and the top of the seat cushion 10 is provided with to place cemented fill sample 19 Sample placing groove, the center position that the sample placing groove is located on the seat cushion 10 is provided with drain valve 5；More pull rods 8 middle part is provided with the fixed frame 11 for fixing more pull rods 8, and the top of more pull rods 8 is fixedly connected with top loading plate 9；The axial pressure force transmission mechanism includes the cylinder 2 being mounted on top loading plate 9, and the piston rod of the cylinder 2 is to dividing into It puts, the piston rod bottom of the cylinder 2 is connected with pressure transmitting plates 3；The axial pressure dynamical system includes compressed air gas The air shooter 1 that source 4 and loading controls 18 and one end are connect with compressed air gas source 4, the other end and cylinder 2 connect； On the air shooter 1 from connection compressed air gas source 4 to connection cylinder 2 position be disposed with pneumatic triple piece 12, Pressure sensor 13 and cylinder control solenoid valve 14, the pressure sensor 13 are connect with the input terminal of loading controls 18, institute Cylinder control solenoid valve 14 is stated to connect with the output terminal of loading controls 18, the loading controls 18 by communication module 16 and Computer 17 connects.When it is implemented, the pressure transmitting plates 3 are made of rubber.Pressure transmitting plates 3 are made using rubber, one Aspect can distribute the pressure that the piston rod of cylinder 2 transmits, pressure is made more uniformly to be applied to cemented fill sample 19 and is pushed up Portion；It on the other hand, will not be to cemented fill sample 19 when pressure transmitting plates 3 are transmitted in pressure to cemented fill sample 19 Top surface cause to damage.
In the present embodiment, the O-shaped sealing for being sleeved on 19 bottom of cemented fill sample is provided in the sample placing groove 6 are enclosed, the porous stone 7 being provided on the seat cushion 10 around the sample placing groove.It, can by setting O-ring seal 6 Cemented fill sample 19 contacts firmly with seat cushion 10 when preventing from applying axial compressive force to cemented fill sample 19 causes cementing fill Fill out the damage of body sample 19.By setting porous stone 7, the water of the exudation of cemented fill sample 19 can be absorbed.
In the present embodiment, the loading controls 18 are programmable logic controller (PLC), and the communication module 16 is RS-485 Communication module.
In the present embodiment, using cemented fill uniaxial compressive strength test device respectively to multiple described in step 802 Intensity test sample carries out uniaxial compressive strength test, wherein it is strong to carry out uniaxial compressive to each intensity test sample Spending the detailed process tested is：
Cemented fill sample 19 after O-ring seal 6 is put into the sample placing groove, is put into institute by step 8021 It states in sample placing groove, the center for making cemented fill sample 19 is opposite with the center of the piston rod of cylinder 2 and pressure transmitting plates 3 It should；And the porous stone 7 around the sample placing groove is put on seat cushion 10；
Step 8022 opens compressed air gas source 4, is exported by adjusting the adjusting compressed air gas source 4 of pneumatic triple piece 12 Compressed air air pressure, loading controls 18 by control cylinder control solenoid valve 14 commutate, control cylinder 2 piston rod to It down or moves upwards, pressure or unloading pressure is applied to cemented fill sample 19, added when cemented fill sample 19 is ruptured The pressure value of 18 collected pressure sensor 13 of pressure controller detection is denoted as F, and pressure value F is transferred to meter by loading controls 18 Calculation machine 17, computer 17 is according to formulaThe uniaxial compressive strength P of intensity test sample is calculated；Wherein, S is The top surface area of intensity test sample；When the piston rod of cylinder 2 moves downward, pressure transmitting plates 3 is driven to move downward, Apply pressure to cemented fill sample 19 by pressure transmitting plates 3, when the piston rod of cylinder 2 moves upwards, band dynamic pressure Transmission plate 3 moves upwards, and pressure transmitting plates 3 leave the upper surface of cemented fill sample 19, unloading pressure.
Step 803, the training sample image for obtaining Tensorflow deep learnings mechanical response characteristic prediction network, specifically Process is：
Step 8031 respectively takes multiple scan multiple SEM scanning electron microscope examples using SEM scanning electron microscope, is formed more A SEM electron-microscope scannings image is simultaneously stored into computer 17；The quantity of the SEM electron-microscope scannings image is at least 150；
Step 8032, the computer 17 call gaussian filtering process module respectively to multiple SEM electron-microscope scannings images into Row gaussian filtering process obtains the SEM electron-microscope scanning images after multiple gaussian filtering process；
In the present embodiment, the computer 17 calls gaussian filtering process module respectively to multiple SEM electron-microscope scannings images The formula that uses of gaussian filtering process is carried out as L (x, y)=I (x, y) * G (x, y), wherein, I (x, y) expression SEM electron-microscope scannings Image, G (x, y) are Gaussian filter function, and L (x, y) is the SEM electron-microscope scanning images after gaussian filtering process, and x is the horizontal stroke of image Coordinate, y are the ordinate of image.
Step 8033, the computer 17 call FCM fuzzy clusterings processing module to be carried out at gaussian filterings to multiple respectively SEM electron-microscope scannings image after reason carries out aperture image extraction, obtains multigroup cemented fill cluster image, every group of consolidated fill The quantity of cemented fill cluster image is equal with cluster centre number in body cluster image；
In the present embodiment, after the computer 17 calls FCM fuzzy clusterings processing module to carrying out gaussian filtering process The detailed process that SEM electron-microscope scannings image carries out aperture image extraction is identical with step 4.
Every group of cemented fill is clustered minimum the cementing of one kind of gray value in image and filled by step 8034, the computer 17 It fills out body cluster image (most dark cemented fill cluster image) and is determined as cemented fill microscopic void figure, and to multiple cementing Obturation microscopic void figure carries out binary conversion treatment, obtains multiple cemented fill microscopic void binary maps；
Step 8035, the computer 17 sweep the SEM Electronic Speculum after the multiple gaussian filtering process obtained in step 8032 Tracing is obtained as being merged with obtaining multiple cemented fill microscopic void binary maps in step 8034 according to number is corresponding Multiple training sample images；
Step 804, the computer 17 carry out normalization process to multiple training sample images respectively, form multiple pixels For 960 × 960 regularized training sample image；
When it is implemented, when training sample image is more than regular obtained pixel 960 × 960, image is carried out Scaled down obtains regularized training sample image；When training sample image be less than regular obtained pixel 960 × When 960, edge expansion is carried out using white to image, obtains regularized training sample image.
The number of plies that step 805, the computer 17 build a convolutional network core is five layers, input layer is regularized training Sample image, the Tensorflow deep learning nets that output layer is the corresponding uniaxial compressive strength of regularized training sample image Network, the multiple regularized training sample images stored carry out Tensorflow deep learnings network as training sample Training obtains Tensorflow deep learnings mechanical response characteristic prediction network；The Tensorflow deep learnings mechanics is special The size of property response prediction five layers of convolutional network core of network from one layer to layer 5 be respectively 3x3,2x2,3x3,2x2,2x2.
In conclusion the present invention acquires sample image using scanning of scanning electron microscope, using gaussian filtering method pair SEM electron-microscope scannings image carries out gaussian filtering process, and cemented fill microscopic void is extracted using FCM fuzzy clusterings processing method Figure, the SEM electron-microscope scannings image after gaussian filtering process is obtained with the method that cemented fill microscopic void binary map merges Test sample image, as the input of Tensorflow deep learnings mechanical response prediction network, then using Tensorflow depths Degree learning network establishes image to the prediction model end to end between mechanical response characteristic, so as to predict the power of cemented fill Response characteristic is learned, method and step is simple, and novel in design rationally realization is convenient and efficient, and forecasting efficiency is high, and the period is short, the people of consuming Power material resources are few.
The above is only presently preferred embodiments of the present invention, not the present invention is imposed any restrictions, every according to the present invention Any simple modification, change and the equivalent structure that technical spirit makees above example change, and still fall within skill of the present invention In the protection domain of art scheme.

Claims (10)

1. a kind of cemented fill mechanical response characteristic Forecasting Methodology based on SEM image, which is characterized in that this method include with Lower step：
Step 1: take a part that SEM scanning electron microscope examples are made from cemented fill sample (19)；
Step 2: SEM scanning electron microscope examples are scanned using SEM scanning electron microscope, form SEM electron-microscope scannings image and are stored Into computer (17)；
Step 3: the computer (17) calls gaussian filtering process module to carry out at gaussian filtering SEM electron-microscope scannings image Reason, obtains the SEM electron-microscope scanning images after gaussian filtering process；
Step 4: the computer (17) calls FCM fuzzy clusterings processing module to the SEM Electronic Speculum after carrying out gaussian filtering process Scan image carries out aperture image extraction, obtains and the equal numbers of multiple cemented fill cluster images of cluster centre；
Step 5: the minimum a kind of cemented fill cluster image of gray value is determined as cemented fill by the computer (17) Microscopic void figure, and binary conversion treatment is carried out to cemented fill microscopic void figure, obtain cemented fill microscopic void two-value Figure；
Step 6: the computer (17) is by the SEM electron-microscope scannings image after the gaussian filtering process obtained in step 3 and walks The cemented fill microscopic void binary map obtained in rapid five merges, and obtains test sample image；
Step 7: the computer (17) carries out normalization process to test sample image, it is 960 × 960 just to form pixel Ruleization test sample image；
Step 8: what the computer (17) built the regular test sample image obtained in step 7 input in advance In Tensorflow deep learnings mechanical response prediction network, uniaxial mechanical response prediction result is obtained.
2. the cemented fill mechanical response characteristic Forecasting Methodology described in accordance with the claim 1 based on SEM image, feature exist In：Length, width and the height of SEM scanning electron microscope examples described in step 1 is 10mm.
3. the cemented fill mechanical response characteristic Forecasting Methodology described in accordance with the claim 1 based on SEM image, feature exist In：Computer described in step 3 (17) calls gaussian filtering process module to carry out at gaussian filtering SEM electron-microscope scannings image The formula used is managed as L (x, y)=I (x, y) * G (x, y), wherein, I (x, y) represents SEM electron-microscope scanning images, and G (x, y) is height This filter function, L (x, y) are the SEM electron-microscope scanning images after gaussian filtering process, and x is the abscissa of image, and y is image Ordinate.
4. the cemented fill mechanical response characteristic Forecasting Methodology described in accordance with the claim 1 based on SEM image, feature exist In：Computer described in step 4 (17) calls FCM fuzzy clusterings processing module to the SEM Electronic Speculum after carrying out gaussian filtering process Scan image carries out aperture image extraction, obtains specific with the equal numbers of multiple cemented fill cluster images of cluster centre Process is：
Step 401, definition use the FCM fuzzy clustering algorithms based on sample weighting, and object function isThe constraints for meeting extreme value isWherein, U is fuzzy matrix and U=[u11,u22,…,ucn], uikMember for matrix U Element and uikRepresent that k-th of sample point belongs to the degree of membership of the i-th class, n is sample point sum, and c is cluster centre number；V={ v1, v2,...vcBe c class cluster centre, wkFor sample point xkWeights, dikFor sample point xkTo central point viEuclidean distance, viFor the element of V, xkK-th of sample point and X={ x for sample set X1,x2,...xn, m is degree of membership uikWeighted index and M ＞ 1；
Step 402, the value of setting cluster centre number c, degree of membership uikThe value of weighted index m and the value of minimum iteration error ε；
Step 403 uses formulaMore new sample point xkWeight wk；uτjElement for matrix U And uτjRepresent that j-th of sample point belongs to the degree of membership of τ classes, 1≤τ≤c, 1≤j≤n；vτElement for V；uijFor matrix U Element and uijRepresent that j-th of sample point belongs to the degree of membership of the i-th class；
Step 404 uses formulaUpdate uik；Wherein, drkFor sample point xkTo central point vrIt is European Distance, 1≤r≤c；
Step 405 uses formulaUpdate vi；
Step 406 judges whether to meet | | J(t+1)- J (t) | | ＜ ε work as satisfaction | | J(t+1)- J (t) | | during ＜ ε, cluster stops, and carries It obtains and the equal numbers of multiple cemented fill cluster images of cluster centre；Otherwise, return to step 403；Wherein, when t is Between.
5. according to the cemented fill mechanical response characteristic Forecasting Methodology based on SEM image described in claim 4, feature exists In：The value that cluster centre number c is set in step 402 is 4, setting degree of membership uikWeighted index m value for 2, setting is minimum The value of iteration error ε is 0.3.
6. the cemented fill mechanical response characteristic Forecasting Methodology described in accordance with the claim 1 based on SEM image, feature exist In：The mechanical response characteristics of Tensorflow deep learnings described in step 8 predict that the construction method of network is：
Step 801 takes a part that SEM scanning electron microscope samples are made from each cemented fill sample (19) after multiple numbers Product, remainder is as uniaxial compressive strength test sample；And to multiple SEM scanning electron microscope examples and multiple intensity tests Sample corresponds number；
Step 802 respectively carries out multiple intensity test samples using cemented fill uniaxial compressive strength test device Uniaxial compressive strength is tested, and takes mean value to the uniaxial compressive strength of multiple intensity test samples measured, is obtained cementing The uniaxial compressive strength of obturation sample (19)；
Step 803, the training sample image for obtaining Tensorflow deep learnings mechanical response characteristic prediction network, detailed process For：
Step 8031 respectively takes multiple scan multiple SEM scanning electron microscope examples using SEM scanning electron microscope, forms multiple SEM Electron-microscope scanning image is simultaneously stored into computer (17)；The quantity of the SEM electron-microscope scannings image is at least 150；
Step 8032, the computer (17) call gaussian filtering process module to be carried out respectively to multiple SEM electron-microscope scannings images Gaussian filtering process obtains the SEM electron-microscope scanning images after multiple gaussian filtering process；
Step 8033, the computer (17) call FCM fuzzy clusterings processing module respectively to multiple carry out gaussian filtering process SEM electron-microscope scannings image afterwards carries out aperture image extraction, obtains multigroup cemented fill cluster image, every group of cemented fill The quantity for clustering cemented fill cluster image in image is equal with cluster centre number；
Every group of cemented fill is clustered the minimum a kind of consolidated fill of gray value in image by step 8034, the computer (17) Body cluster image is determined as cemented fill microscopic void figure, and multiple cemented fill microscopic void figures are carried out at binaryzation Reason, obtains multiple cemented fill microscopic void binary maps；
Step 8035, the computer (17) are by the SEM electron-microscope scannings after the multiple gaussian filtering process obtained in step 8032 Image is merged with obtaining multiple cemented fill microscopic void binary maps in step 8034 according to number is corresponding, is obtained more A training sample image；
Step 804, the computer (17) carry out normalization process to multiple training sample images respectively, and forming multiple pixels is 960 × 960 regularized training sample image；
The number of plies that step 805, the computer (17) build a convolutional network core is five layers, input layer is regularized training sample This image, the Tensorflow deep learning networks that output layer is the corresponding uniaxial compressive strength of regularized training sample image, The multiple regularized training sample images stored instruct Tensorflow deep learning networks as training sample Practice, obtain Tensorflow deep learnings mechanical response characteristic prediction network；The Tensorflow deep learnings mechanical characteristic The size of five layers of convolutional network core of response prediction network from one layer to layer 5 be respectively 3x3,2x2,3x3,2x2,2x2.
7. according to the cemented fill mechanical response characteristic Forecasting Methodology based on SEM image described in claim 6, feature exists In：The test device of cemented fill uniaxial compressive strength described in step 802 includes seat cushion (10) and is fixedly connected on seat cushion (10) more pull rods (8) at the top of and the axial pressure power transmission for applying axial compressive force to cemented fill sample (19) Mechanism and the axial pressure dynamical system for providing power to axial pressure force transmission mechanism；The bottom of the seat cushion (10) is fixed Multiple pedestals (15) are connected with, is provided at the top of the seat cushion (10) and is put for placing the sample of cemented fill sample (19) Slot is put, the center position that the sample placing groove is located on the seat cushion (10) is provided with drain valve (5)；More pull rods (8) Middle part be provided with fixed frame (11) for fixing more pull rods (8), the top of more pull rods (8) is fixedly connected with top and fills Support plate (9)；The axial pressure force transmission mechanism includes the cylinder (2) being mounted on top loading plate (9), the cylinder (2) Piston rod is down-set, and the piston rod bottom of the cylinder (2) is connected with pressure transmitting plates (3)；The axial pressure dynamical system System includes compressed air gas source (4) and loading controls (18) and one end is connect with compressed air gas source (4), the other end and The air shooter (1) of cylinder (2) connection；From connection compressed air gas source (4) to connection cylinder on the air shooter (1) (2) position is disposed with pneumatic triple piece (12), pressure sensor (13) and cylinder control solenoid valve (14), the pressure Sensor (13) is connect with the input terminal of loading controls (18), the cylinder control solenoid valve (14) and loading controls (18) Output terminal connection, the loading controls (18) are connect by communication module (16) with computer (17).
8. according to the cemented fill mechanical response characteristic Forecasting Methodology based on SEM image described in claim 7, feature exists In：The O-ring seal (6) for being sleeved on cemented fill sample (19) bottom, the seat cushion are provided in the sample placing groove (10) porous stone (7) being provided on around the sample placing groove.
9. according to the cemented fill mechanical response characteristic Forecasting Methodology according to any one of claims 8 based on SEM image, feature exists In：The loading controls (18) are programmable logic controller (PLC), and the communication module (16) is RS-485 communication modules.
10. according to the cemented fill mechanical response characteristic Forecasting Methodology according to any one of claims 8 based on SEM image, feature It is：Using cemented fill uniaxial compressive strength test device respectively to multiple intensity test samples described in step 802 Product carry out uniaxial compressive strength test, wherein carrying out the specific mistake of uniaxial compressive strength test to each intensity test sample Cheng Wei：
Cemented fill sample (19) after O-ring seal (6) is put into the sample placing groove, is put into institute by step 8021 It states in sample placing groove, makes in the center of cemented fill sample (19) and the piston rod and pressure transmitting plates (3) of cylinder (2) The heart is corresponding；And the porous stone (7) around the sample placing groove is put on seat cushion (10)；
Step 8022 opens compressed air gas source (4), defeated by adjusting pneumatic triple piece (12) adjusting compressed air gas source (4) The air pressure of the compressed air gone out, loading controls (18) control cylinder (2) by controlling cylinder that solenoid valve (14) is controlled to commutate Piston rod moves downward or upward, applies pressure or unloading pressure to cemented fill sample (19), by cemented fill sample (19) pressure value that loading controls (18) collected pressure sensor (13) detects when rupturing is denoted as F, loading controls (18) pressure value F is transferred to computer (17), computer (17) is according to formulaIntensity test sample is calculated The uniaxial compressive strength P of product；Wherein, S is the top surface area of intensity test sample；When the piston rod of cylinder (2) is transported downwards When dynamic, pressure transmitting plates (3) is driven to move downward, applies pressure to cemented fill sample (19) by pressure transmitting plates (3), When the piston rod of cylinder (2) moves upwards, pressure transmitting plates (3) is driven to move upwards, pressure transmitting plates (3) leave cementing fill Fill out the upper surface of body sample (19), unloading pressure.
CN201810098527.0A 2018-01-31 2018-01-31 Cemented fill mechanical response characteristic prediction technique based on SEM image Active CN108256258B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810098527.0A CN108256258B (en) 2018-01-31 2018-01-31 Cemented fill mechanical response characteristic prediction technique based on SEM image

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810098527.0A CN108256258B (en) 2018-01-31 2018-01-31 Cemented fill mechanical response characteristic prediction technique based on SEM image

Publications (2)

Publication Number Publication Date
CN108256258A true CN108256258A (en) 2018-07-06
CN108256258B CN108256258B (en) 2019-01-25

Family

ID=62743195

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810098527.0A Active CN108256258B (en) 2018-01-31 2018-01-31 Cemented fill mechanical response characteristic prediction technique based on SEM image

Country Status (1)

Country Link
CN (1) CN108256258B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109858551A (en) * 2019-01-31 2019-06-07 湖南大学 Method, apparatus, equipment and medium based on image recognition detection structure stress
CN113743424A (en) * 2021-09-15 2021-12-03 昆明理工大学 DBSCAN cluster analysis method for extracting characteristic points of full tailings dynamic flocculation sedimentation image

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2000073972A1 (en) * 1999-05-28 2000-12-07 Texas Tech University Adaptive vector quantization/quantizer
CN102622729A (en) * 2012-03-08 2012-08-01 北京邮电大学 Spatial self-adaptive block-matching image denoising method based on fuzzy set theory
CN103632381A (en) * 2013-12-08 2014-03-12 中国科学院光电技术研究所 Extended target tracking method for extracting feature points by using skeleton
CN103839274A (en) * 2014-03-25 2014-06-04 中国科学院光电技术研究所 Extended target tracking method based on geometric proportion relation
CN104750940A (en) * 2015-04-10 2015-07-01 中国矿业大学(北京) Dynamic design method for strength of cemented filling body of underground mining stope
CN106503397A (en) * 2016-11-16 2017-03-15 中国航空工业集团公司北京航空材料研究院 A kind of method for obtaining metal material recrystallized structure evolution crystal boundary mobility parameter
CN106934109A (en) * 2017-02-20 2017-07-07 南京航空航天大学 A kind of Ni3Al based alloys represent the construction method of elementary volume, volume element model

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2000073972A1 (en) * 1999-05-28 2000-12-07 Texas Tech University Adaptive vector quantization/quantizer
CN102622729A (en) * 2012-03-08 2012-08-01 北京邮电大学 Spatial self-adaptive block-matching image denoising method based on fuzzy set theory
CN103632381A (en) * 2013-12-08 2014-03-12 中国科学院光电技术研究所 Extended target tracking method for extracting feature points by using skeleton
CN103839274A (en) * 2014-03-25 2014-06-04 中国科学院光电技术研究所 Extended target tracking method based on geometric proportion relation
CN104750940A (en) * 2015-04-10 2015-07-01 中国矿业大学(北京) Dynamic design method for strength of cemented filling body of underground mining stope
CN106503397A (en) * 2016-11-16 2017-03-15 中国航空工业集团公司北京航空材料研究院 A kind of method for obtaining metal material recrystallized structure evolution crystal boundary mobility parameter
CN106934109A (en) * 2017-02-20 2017-07-07 南京航空航天大学 A kind of Ni3Al based alloys represent the construction method of elementary volume, volume element model

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
OKAN ONAL等: "Artificial neural network application on microstructure–compressive strength relationship of cement mortar", 《ADVANCES IN ENGINEERING SOFLTWARE》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109858551A (en) * 2019-01-31 2019-06-07 湖南大学 Method, apparatus, equipment and medium based on image recognition detection structure stress
CN113743424A (en) * 2021-09-15 2021-12-03 昆明理工大学 DBSCAN cluster analysis method for extracting characteristic points of full tailings dynamic flocculation sedimentation image

Also Published As

Publication number Publication date
CN108256258B (en) 2019-01-25

Similar Documents

Publication Publication Date Title
CN108229062B (en) Method based on sensibility micro-parameter prediction cemented fill mechanical response characteristic
Garboczi et al. Computational materials science of cement-based materials
CN108256258B (en) Cemented fill mechanical response characteristic prediction technique based on SEM image
CN110288258A (en) A kind of high water-cut reservoir Tapping Residual Oil method
CN109523069A (en) A method of filler intensive parameter is predicted using machine learning
CN109800521A (en) A kind of oil-water relative permeability curve calculation method based on machine learning
CN107423466A (en) A kind of proppant embedment and the method for numerical simulation of fracture condudtiviy quantitative forecast
Xiao et al. Texture synthesis: A novel method for generating digital models with heterogeneous diversity of rock materials and its CGM verification
CN108445030B (en) Cemented fill mechanical response characteristic prediction technique based on image and micro-parameter
CN108287254B (en) A kind of cemented fill micro-parameter Sensitivity Analysis based on image procossing
CN110186789A (en) The orthogonal predictor method of building castoff roadbed permanent deformation based on gray system
CN106228197A (en) A kind of satellite image cloud amount recognition methods based on self adaptation extreme learning machine
Dong et al. Size distribution of pores and their geometric analysis in red mud-based autoclaved aerated concrete (AAC) using regression neural network and elastic mechanics
Guo et al. Investigation of additive-assisted microbial-induced calcium carbonate precipitation in 3D printed cross fractures
Li et al. Micro-characteristics and meso-shear mechanism of the soils of a slip zone in a landslide
CN108240940B (en) A kind of cemented fill mechanical response characteristic test macro and method
Burroughs et al. Estimating interrill erodibility of forest soils
Liu et al. Influence of construction-induced damage on the degradation of freeze—thawed lightweight cellular concrete
CN209485862U (en) A kind of buried concrete stray electrical current and cyclical impact loading pilot system
CN110008566A (en) Filling slurry performance index prediction method based on big data
CN108444839A (en) The method for building up of the lower mud dynamical constitutive relation of cyclical loads effect
CN112884739A (en) Rapid detection method for rockfill filling compactness based on deep learning network
Kong et al. Influence mechanism of lightweight aggregate on concrete impermeability: Prediction by ANN
Hao et al. RETRACTED ARTICLE: Mechanical properties of loess in mountainous area based on fuzzy clustering and construction of basketball venues
Wu et al. Prediction of ground movements around parallel tunnels

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