CN103984788A - Automatic intelligent design and optimization system for anchor bolt support of coal tunnel - Google Patents

Abstract

The invention relates to an automatic intelligent design and optimization system for an anchor bolt support of a coal tunnel. The system comprises a tunnel surrounding-rock index obtainment and stability classification subsystem, an anchor bolt support parameter intelligent-matching subsystem and a support design verification and optimization subsystem, wherein the tunnel surrounding-rock index obtainment and stability classification subsystem realizes the classification and evaluation of tunnel surrounding-rock stability by processing data input by a user or calling parameters in relevant knowledge bases; the anchor bolt support parameter intelligent-matching subsystem establishes a training model based on a sample tunnel training BP (Back Propagation) neural network in an internal knowledge base of the system to realize the intelligent matching of anchor bolt support parameters of the coal tunnel; the support design verification and optimization subsystem implements theoretic checking calculation based on a suspension theory, a combined beam theory, a combined arch theory and an energy theory according to the anchor bolt support parameters obtained by the anchor bolt support parameter intelligent-matching subsystem, and automatically analyzes various support schemes to select the support scheme which meets the deformation requirements of tunnel surrounding-rocks, wherein the selected support scheme being the optimal support scheme is recommended to the user. By applying the system, the scientificity and the reasonability of the anchor bolt support structure and parameters are effectively guaranteed; the reliability of an anchor bolt support system is improved; the healthy development of an anchor bolt support technique for the coal tunnel in our country is promoted.

Description

A kind of coal entry anchor rod support automated intelligent design and optimization system

Technical field

The present invention relates to a kind of system for coal mine roadway Design of bolt support and optimization.

Background technology

Along with the development of coal industry, China's high-yield and high-efficiency workplace is more and more, and output increases substantially.Colliery digging supporting is very important production link.Anchor pole technology is a systematic engineering of business, and it relates to the various aspects such as design, construction, support material, measurement technology means.Design of bolt support is a gordian technique in bolt supporting engineering, is related to the quality good or not of bolt supporting engineering, the major issue such as whether whether safe and reliable and economy reasonable.Complicacy and uncertainty due to geologic condition, the approximate description of selection, rock mass and the various character of rock of various parameters in support engineering design, the final evaluation of supporting effect all relies on expert's experience and individual know-how, owing to doing criterion by quantitative or unified standard, unavoidably with larger randomness and blindness, if it is unreasonable that bolt support form and parameter are selected, tend to cause two kinds extremely, roadway support insufficient strength, effective deformation controlling for rock surrounding gateways, and then cause tunnel to occur the accidents such as roof fall wall caving; Roadway support intensity is too high not only wastes support material, and has reduced tunnelling speed, has had a strong impact on the raising of mine economic benefit.Strengthen the sci-tech innovation, realize the management of coal enterprise's information resources, accelerate informationalized construction, for efficient, the safety in production of coal enterprise, there is far-reaching influence and huge effect.Along with popularizing of rapid economic development and Computer and Its Application knowledge, computer literacy is applied in coal production design, there is extremely important theory significance and production practices meaning.

Coal system is due to the singularity of producing, and aspect computing machine, the application of technology is compared with other industry, or relatively backward.The first-line many units that produce in China mine, technical work is still and adopts traditional tactics of human sea and hand labour, not only wastes a large amount of technical forces, and should not carry out scientific management.Therefore, to carry out the exploitation of coal production design and production management system be the problem that first In Modern Mine must solve to Applied Computer Techniques.

Current Design of bolt support system complex operation, the parameter that needs user to input is too numerous and diverse, too professional, and the general production scene of a lot of data is difficult to obtain, and requires user to have higher professional standards.So just limited this type systematic promoting the use of in production reality.

Summary of the invention

The present invention seeks to provide in order to overcome the deficiencies in the prior art a kind of intelligent design of bolt support for seam gateway and optimization system.

For achieving the above object, the technical solution used in the present invention is: a kind of coal entry anchor rod support automated intelligent design and optimization system, and it comprises,

Roadway surrounding rock index selection and Stability Classification subsystem, it,, by processing the data of user's input or calling the parameter in relevant knowledge storehouse, is realized the classification of improving stability of surrounding rocks in roadway and assessment;

Bolting Parameters Intelligent Matching subsystem, it is by using BP neural networks principles, sample tunnel training BP neural network based in internal system knowledge base, sets up training pattern, realizes the Bolting Parameters Intelligent Matching in this tunnel after the concrete correlation parameter in the tunnel that user provides;

Design of its support checking and optimization subsystem, its Bolting Parameters obtaining according to described Bolting Parameters Intelligent Matching subsystem is carried out theory checking computations based on suspention theory, compound beam theory, built-up arch theory, and call in numerical simulation module, automatically carry out FLAC3D modeling, simulation, optimization process, automatically various supporting schemes are analyzed, usingd and choose the supporting scheme that meets deformation of the surrounding rock in tunnel requirement and recommend user as Optimum Support scheme.

Optimally, described roadway surrounding rock index selection and Stability Classification subsystem are automatically according to the sample data importing, pre-service, standardization, weighting, demarcation, clustering processing according to the automatic completed sample certificate of fuzzy clustering algorithm based on relation of equivalence, and according to user's selection or system automatic decision, classified in sample tunnel, provide cluster centre.

Optimally, the inner establishment of described system roadway surrounding rock index selection and Stability Classification subsystem has a set of basic sample data.

Optimally, described roadway surrounding rock index selection is helped intensity, base plate strength, tunnel buried depth, first roof caving step pitch, is risen the parameters such as ratio, coal pillar width, maximum horizontal principal stress as Surrounding Rock Stability Classification in Tunnel and evaluation index with the selected strength of roof, two of Stability Classification subsystem, user inputs the data corresponding with above-mentioned parameter in new pick tunnel, system is passed judgment on this improving stability of surrounding rocks in roadway based on fuzzy comprehensive evaluation method automatically, obtains the stability of surrounding rock classification in this tunnel.

Optimally, described Bolting Parameters Intelligent Matching subsystem, it will carry out the prediction union of tunnel parameter for the required parameter of improving stability of surrounding rocks in roadway, described computing comprises first carries out learning training to sample data and supporting parameter knowledge base, weights after being optimized and threshold values, then, by the parameter to be predicted of having inputted, calculate with weights, threshold values, obtain the supporting basic parameter value of system prediction.

Optimally, the checking of described roadway surrounding rock index selection and Stability Classification subsystem and Bolting Parameters Intelligent Matching subsystem and design of its support is used as the integral body that is mutually related with optimizing subsystem, disposable and systematically complete surrounding rock mass stability classification, Bolting Parameters Intelligent Matching, the work of supporting scheme intelligent optimization in tunnel.

Optimally, described roadway surrounding rock index selection and Stability Classification subsystem and Bolting Parameters Intelligent Matching subsystem and design of its support checking are independent respectively according to user's actual conditions with optimization subsystem.

Because technique scheme is used, the present invention compared with prior art has following advantages: native system utilizes intelligent expert system to carry out quantitative test and optimal design to bolt supporting, science and the rationality of bolt supporting structure and parameter have effectively been guaranteed, improved the reliability of Bolt System, realized the maximizing the benefits of bolt supporting, improve supporting safety, fundamentally change the extensively shortcomings and limitations of the engineering analog method of employing of current China bolt supporting, promoted the development of China's coal-mine roadway bolt support technology and digital mine.System made to provide reference data to call for user, makes user just can meet the demand data of Soil Anchor Design only inputting under prerequisite less, that reality can obtain data based on relevant expert, 8 large mining area typical case " expert's level " knowledge bases; System has been acted on brief interface, and the operator scheme of " foolproof " is easy to grasp and use; Intelligent Plan decision-making, improves design of its support rationality and production management standardization, standardization; Abundant in content " expert's rank " roadway support knowledge base, science and the accuracy of the decision-making of effective guarantee supporting scheme; Hommization and flexibly initial parameter input and select mechanism, really realized system practicality, available, can use, easy-to-use development goal; Perfect operation instruction and help system, Effective Way by Using Project personnel design level.

Accompanying drawing explanation

Accompanying drawing 1 is coal entry anchor rod support automated intelligent design and optimization system flowchart of the present invention;

Accompanying drawing 2 is roadway surrounding rock index selection of the present invention and corresponding Stability Classification system flowchart;

Accompanying drawing 3 is Bolting Parameters Intelligent Matching subsystem process flow diagrams of the present invention;

Accompanying drawing 4 is design of its support checking of the present invention and optimization subsystem process flow diagram;

Embodiment

Below in conjunction with accompanying drawing, the preferred embodiment of the invention is elaborated:

Coal entry anchor rod support automated intelligent design and optimization system of the present invention, as shown in Figure 1, it comprises roadway surrounding rock index selection and stability subclass system, Bolting Parameters Intelligent Matching subsystem, design of its support checking and optimizes subsystem.Specific as follows:

One, roadway surrounding rock index selection and Stability Classification subsystem

As shown in Figure 2, in roadway surrounding rock index selection and Stability Classification subsystem, system has been selected strength of roof σ _top, two help intensity σ _side, base plate strength σ _{the end}, tunnel buried depth H, first roof caving step pitch L, rise than N, coal pillar width B, maximum horizontal principal stress σ _hdeng 8 parameters as Surrounding Rock Stability Classification in Tunnel and evaluation index.User can input related data by operation interface, system also carries the knowledge bases such as country rock physical and mechanical parameter knowledge base, terrestrial stress knowledge base simultaneously in inside by investigation and analysis, finishing collecting related data, so that user's reference when being difficult to obtain related data is selected.

When initially being used, subsystem need to import the typical tunnel sample of some to complete surrounding rock mass stability classification work.System can be automatically according to the sample data importing, the processing such as the pre-service of the fuzzy clustering algorithm automatic completed sample certificate of foundation based on relation of equivalence, standardization, weighting, demarcation, cluster, and can be classified in sample tunnel according to user's selection or system automatic decision, and provide cluster centre.Internal system also has a set of basic sample, so that user calls when being difficult to obtain sample.

After completing classification work, user inputs 8 related datas in new pick tunnel, and system is passed judgment on this improving stability of surrounding rocks in roadway based on fuzzy comprehensive evaluation method automatically, obtains the stability of surrounding rock classification in this tunnel.

Concrete processing mode is:

(1) improving stability of surrounding rocks in roadway cluster

1. input data pre-service

By the information of input n bar tunnel sample, every 8, tunnel index, is respectively strength of roof σ _top, two help intensity σ _side, base plate strength σ _{the end}, tunnel buried depth H, first roof caving step pitch L, rise than N, coal pillar width B, maximum horizontal principal stress σ _h.Be the matrix of n * 8.

The pre-service of data:

When coal is cherry coal (σ _side<10MPa), time, W ' value is as follows:

$W^{,}=\exp [-2.6{\left(\frac{B-\frac{B_0}{3}}{B_0}\right)}^2]$

Hard (10MPa< σ in coal is _side<20MPa), time, W ' value is as follows:

$W^{,}=\exp [-{\left(3.6\frac{B-\frac{B_0}{4}}{B_0}\right)}^2]$

When coal is hard (20MPa< σ _side) time, W ' value is as follows:

$W^{,}=0.3\exp [-3.6{\left(\frac{B-\frac{B_0}{4}}{B_0}\right)}^2$

According to following table, select B ₀value

Here the H value that buried depth is inputted above,

N > 4 gets 4, H, L, σ _hdo not process.

2. data normalization

By i index x of j sample _ijbe transformed into x ' _ij,

${x_{\mathrm{ij}}}^{\&prime;}=\frac{x_{\mathrm{ij}}-{\stackrel{\&OverBar;}{x}}_j}{s_j}$

(2) standardization with extreme difference

By i index x ' of j sample after standard deviation standardization _ijbe transformed into x " _ij,

$x_{\mathrm{ij}}^{\&prime;\&prime;}=\frac{x_{\mathrm{ij}}^{\&prime;}-\{x_{\mathrm{ij}}^{\&prime;}{\}}_{\min }}{\{x_{\mathrm{ij}}^{\&prime;}{\}}_{\max }-\{x_{\mathrm{ij}}^{\&prime;}{\}}_{\min }}$

3. weighting

Data are after above processing, and each index will be multiplied by corresponding weights.

4. demarcate

Calculate similarity coefficient γ _ij

$r_{\mathrm{ij}}=\frac{{\mathrm{\&Sigma;}}_{k=1}^n(x_{\mathrm{ik}}-\stackrel{\&OverBar;}{x_i})(x_{\mathrm{jk}}-\stackrel{\&OverBar;}{x_j})}{\sqrt{{\mathrm{\&Sigma;}}_{k=1}^n{(x_{\mathrm{ik}}-\stackrel{\&OverBar;}{x_i})}^2}\sqrt{{\mathrm{\&Sigma;}}_{k=1}^n{\left(x_{\text{jk}}\text{-}\stackrel{\&OverBar;}{x_j}\right)}^2}}$

After demarcating, obtain: 0≤γ _ij≤ 1, (i=1,2 ..., m; J=1,2 ..., m); So can determine fuzzy relation matrix

5. cluster analysis

The similar matrix of gained will be demarcated the transmission bag R trying to achieve by quadratic method ^*, be to comprise least confusion equivalent matrice, then press R ^*λ-cut relation, X is carried out to Dynamic Cluster Analysis, what be less than λ is designated as 0, what be greater than λ is designated as 1, finally identical row is classified as to a class,

6. determine optimal classification number

F-statistics variable method: the number of categories of establishing corresponding λ is r, and the sample number of j class is n _j, the mean value of k feature of j class is make F-statistic: $F=\frac{\underset{j=1}{\overset{r}{\mathrm{\&Sigma;}}}{n}_j\&CenterDot;\underset{k=1}{\overset{m}{\mathrm{\&Sigma;}}}\frac{{(\stackrel{\&OverBar;}{x_k^{\left(j\right)}}-\stackrel{\&OverBar;}{x_k})}^2}{r-1}}{\underset{j=1}{\overset{r}{\mathrm{\&Sigma;}}}\underset{i=1}{\overset{n_j}{\mathrm{\&Sigma;}}}\underset{k=1}{\overset{m}{\mathrm{\&Sigma;}}}\frac{{(x_{\mathrm{ik}}^{\left(j\right)}-\stackrel{\&OverBar;}{x_k^{\left(j\right)}})}^2}{n-r}}$

F-statistic is to obey the F-that degree of freedom is (r-1, n-1) to distribute.Its molecule representation class and the distance between class, the distance in denominator representation class between sample.Therefore, F value is larger, illustrates that the distance between class and class is larger, and the difference between class and class is larger, and classifying quality is just better.

If F > is F _1-λ(r-1, n-r) (α=0.05), can know according to the variance analysis theory of mathematical statistics, and the significant difference between class and class illustrates that classification is optimum.

If meet F > F _1-λmore than one of the F value of (r-1, n-r), can further investigate F-F _αsize, from the greater, select the F value of a satisfaction as optimum classification.

Divided the mean value of getting each index of Different categories of samples tunnel after class to obtain (tentatively) cluster centre.

(2) improving stability of surrounding rocks in roadway fuzzy comprehensive evoluation

1. build fuzzy relation matrix

Build fuzzy relationship matrix r={ r _ij9*5, wherein r _ijexpression is had in mind from i factor, and this factor can be chosen as the subjection degree of j class.R _ijask method from following several method, to select:

Method one. normal state Subordinate Function:

$r_{\mathrm{ij}}=e^{-{\left(\frac{x_i-a_{\mathrm{ij}}}{{\mathrm{\&sigma;}}_i}\right)}^2}$

2. blurring mapping

Set C={c ₁, c ₂, c ₃, c ₄, c ₅, c ₆, c ₇, c ₈, c ₉be 9 factors affect weights (with last program).Be blurring mapping B=C ^or.Fuzzy vector B={b ₁, b ₂, b ₃, b ₄, b ₅t={b j}, wherein b ₁, b ₂, b ₃, b ₄, b ₅represent respectively the subordinate degree of tunnel to be predicted to each cluster centre, the classification in tunnel to be predicted is determined with the large sample of the subjection degree between cluster centre by this tunnel.

B _jalgorithm have following four kinds of methods:

Method one. main factor decision type: wherein ∧ is for both get its little symbol, and ∨ is for both get its large symbol;

Method two. main factor protruding type:

Method three. main factor protruding type:

Method four. weighted mean type:

Can obtain Judgement Matrix B={b ₁, b ₂, b ₃, b ₄, b ₅t={b _j}

3. evaluation index is processed:

Method one, maximum membership degree method:

B ₁to b ₅the corresponding subscript j of middle maximal value is tunnel to be measured classification.

Method two: method of weighted mean:

Make v '=(b ₁+ 2b ₂+ 3b ₃+ 4b ₄+ 5b ₅)/(b ₁+ b ₂+ b ₃+ b ₄+ b ₅), which class v ' belongs to close to several tunnels]

Two, Bolting Parameters Intelligent Matching subsystem

In this subsystem, as shown in Figure 3, first by required parameter, as first roof caving step pitch, strength of roof, base plate strength, tunnel buried depth, tunnel clear span, tunnel clear height are input on interface, then carry out the prediction of tunnel parameter, carry out computing.Computing is mainly carried out on system backstage, be that system is first carried out learning training to sample and supporting parameter knowledge base, the weights after being optimized and threshold values, then by the parameter to be predicted of having inputted, carry out a series of calculating with weights, threshold values, finally obtain the supporting basic parameter value of system prediction.

The first step, netinit, is normalized input and output.

To each, connect weights and compose respectively the random number in an interval (1,1), specification error function ε, given computational accuracy value and maximum study number of times.

Second step, chooses k input sample and corresponding desired output at random

d _o(k)＝(d ₁(k)，d ₂(k)，…，d _q(k))

x(k)＝(x ₁(k)，x ₂(k)，…，x _n(k))

The 3rd step, calculates each neuronic input and output of hidden layer.

The 4th step, utilizes network desired output and actual output, error of calculation function each neuronic partial derivative δ to output layer _o(k).

The 5th step, utilizes hidden layer to the connection weights of output layer, the δ of output layer _o(k) and the output error of calculation function of hidden layer to each neuronic partial derivative δ of hidden layer _h(k).

The 6th step, utilizes each neuronic δ of output layer _o(k) and each neuronic output of hidden layer revise connection weight w _ho(k)

The 7th step, utilizes each neuronic δ of hidden layer _hand each neuronic input correction connection weight of input layer (k).

The 8th step, calculates global error $E=\frac{1}{2m}\underset{k=1}{\overset{m}{\mathrm{\&Sigma;}}}\underset{o=1}{\overset{q}{\mathrm{\&Sigma;}}}{(d_o\left(k\right)-y_o\left(k\right))}^2.$

The 9th step, judges whether network error meets the demands.When error reaches default precision or learns the maximum times that number of times is greater than setting, finish algorithm.Otherwise, choose next learning sample and corresponding desired output, turn back to the 3rd step, enter next round study.

Three, design of its support checking and optimization subsystem

As shown in Figure 4, resulting Bolting Parameters is called in this subsystem automatically above, first according to theoretical calculation, this design proposal is automatically imported and is carried out based on suspention theory, compound beam theory, built-up arch theory, energy theory checking computations.Design proposal is after checking computations meet the demands, call again backstage and obtain a series of supporting design scheme based on orthogonal test module, these schemes are called in to numerical simulation module, automatically carry out the processing such as FLAC3D modeling, simulation, optimization, automatically various supporting schemes are analyzed, chosen the most economical supporting scheme that meets deformation of the surrounding rock in tunnel requirement and recommend user as Optimum Support scheme.

System comprises stability of surrounding rock intelligent classification subsystem, Bolting Parameters Intelligent Matching subsystem, three subsystems of supporting scheme intelligent optimization subsystem.Three subsystems both can be used as the integral body that is mutually related and had used, the surrounding rock mass stability classification that completes tunnel, Bolting Parameters Intelligent Matching, the work of supporting scheme intelligent optimization with disposable system, also can be according to user's actual conditions, the independent some modules wherein of using realize relevant function respectively, make system have stronger applicability and selectivity.Be conducive to system play stably, efficiently, safety function, guarantee subsystem coordinative coherence and sustainability each other simultaneously.

Above-described embodiment is only explanation technical conceive of the present invention and feature; its object is to allow person skilled in the art can understand content of the present invention and implement according to this; can not limit the scope of the invention with this; all equivalences that Spirit Essence is done according to the present invention change or modify, within all should being encompassed in protection scope of the present invention.

Claims (7)

1. a coal entry anchor rod support automated intelligent design and optimization system, is characterized in that: it comprises,

Roadway surrounding rock index selection and Stability Classification subsystem, it,, by processing the data of user's input or calling the parameter in relevant knowledge storehouse, is realized the classification of improving stability of surrounding rocks in roadway and assessment;

Bolting Parameters Intelligent Matching subsystem, it is by using BP neural networks principles, BP neural network is practiced in sample tunnel training based in internal system knowledge base, sets up training pattern, realizes the Bolting Parameters Intelligent Matching in this tunnel after the concrete correlation parameter in the tunnel that user provides;

Design of its support checking and optimization subsystem, its Bolting Parameters obtaining according to described Bolting Parameters Intelligent Matching subsystem is theoretical based on suspention, give close beam theory, built-up arch theory is carried out theory and is checked, and call in numerical simulation module, automatically carry out FLAC3D modeling, simulation, optimization process, automatically various supporting schemes are analyzed, usingd and choose the supporting scheme that meets deformation of the surrounding rock in tunnel requirement and recommend user as Optimum Support scheme.

2. coal entry anchor rod support automated intelligent design and optimization system according to claim 1, it is characterized in that: described roadway surrounding rock index selection and Stability Classification subsystem are automatically according to the sample data importing, pre-service, pushing away of mark, weighting, demarcation, clustering processing according to the automatic completed sample certificate of fuzzy clustering algorithm based on relation of equivalence, and according to user's selection or system automatic decision, classified in sample tunnel, cheat out cluster centre.

3. coal entry anchor rod support automated intelligent design and optimization system according to claim 2, is characterized in that: the inner establishment of described system roadway surrounding rock index selection and Stability Classification subsystem has a set of basic sample data.

4. coal entry anchor rod support automated intelligent design and optimization system according to claim 2, it is characterized in that: described roadway surrounding rock index selection and Stability Classification subsystem are selected strength of roof, two help intensity, base plate strength, tunnel buried depth, first roof caving step pitch, rise ratio, coal pillar width, the parameters such as maximum horizontal principal stress are as Surrounding Rock Stability Classification in Tunnel and evaluation index, user inputs the data corresponding with above-mentioned parameter in new pick tunnel, system is passed judgment on this improving stability of surrounding rocks in roadway based on fuzzy comprehensive evaluation method automatically, obtain the stability of surrounding rock classification in this tunnel.

5. coal entry anchor rod support automated intelligent design and optimization system according to claim 1, it is characterized in that: described Bolting Parameters intelligence can be mated subsystem, it will carry out the prediction union of tunnel parameter for the required parameter of improving stability of surrounding rocks in roadway, described computing comprises first carries out learning training to sample data and supporting parameter knowledge base, weights after being optimized and threshold values, then by the parameter to be predicted of having inputted, calculate with weights, threshold values, obtain the supporting basic parameter value of system prediction.

6. according to the coal entry anchor rod support automated intelligent design and optimization system described in claim l, it is characterized in that: the checking of described roadway surrounding rock index selection and Stability Classification subsystem and Bolting Parameters Intelligent Matching subsystem and design of its support is used as the integral body that is mutually related with optimizing subsystem, disposable and systematically complete surrounding rock mass stability classification, Bolting Parameters Intelligent Matching, the work of supporting scheme intelligent optimization in tunnel.

7. coal entry anchor rod support automated intelligent design and optimization system according to claim 1, is characterized in that: described roadway surrounding rock index selection and Stability Classification subsystem and Bolting Parameters Intelligent Matching subsystem and design of its support checking are independent respectively according to user's actual conditions with optimization subsystem.