PSO-LSSVM model-based drilling and blasting method construction tunnel over-break and under-break prediction method and related equipment

Abstract

The invention discloses a drilling and blasting method construction tunnel back break prediction method based on a PSO-LSSVM model and related equipment. The method comprises the following steps that S1, parameters of drilling and blasting method construction tunnel back break influence factors are obtained; s2, performing data preprocessing on the parameters; s3, finally determining main parameters influenced by the back break of the tunnel by adopting a grey correlation analysis method; s4, establishing a PSO-LSSVM model by adopting an MATLAB simulation platform; s5, selecting a root-mean-square error as a fitness function, calculating the fitness value of each particle, updating the value of each particle through multiple iterations, comparing and updating the value of Vbest, and judging whether an end condition of PSO is met or not; s6, a PSO-LSSVM model is established according to the optimal parameter combination, prediction is performed by using the model in combination with the back break influence parameters of the specific tunnel blasting engineering, and a blasting effect prediction result is obtained; according to the method, the particle swarm optimization algorithm is adopted to iterate the two key parameters of the optimization model, the blasting effect of the drilling and blasting method can be predicted with high precision, and efficient construction of tunnel engineering is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of tunnel blasting, and in particular to a method for predicting over-excavation and under-excavation of a tunnel constructed by drilling and blasting method based on a PSO-LSSVM model and related equipment. Background Art

[0002] The drilling and blasting method is the most effective and widely used rock breaking method in current rock mass excavation projects. It is also a commonly used excavation method in underground engineering construction. With the development of smooth blasting technology and blasting vibration control technology, drilling and blasting excavation is used as the main construction method in most tunnel construction.

[0003] During tunnel construction, over-break and under-break problems will directly affect the quality of blasting construction and the effect of cost control. Reasonable selection of blasting parameters can actively control the impact of blasting negative effects on the retained surrounding rock, reduce over-break and under-break, and thus reduce the consumption of support materials and drilling and blasting construction costs. Therefore, the prediction of over-break and under-break in tunnels constructed by drilling and blasting has important practical significance.

[0004] The support vector machine (SVM) model is a novel small sample learning method with a solid theoretical foundation. It avoids the traditional process from induction to deduction, realizes efficient sample transduction reasoning, greatly simplifies common classification and regression problems, "eliminates" a large number of redundant samples, and has good "robustness". The LS-SVM algorithm is an extension of the standard SVM algorithm. Its main difference is the introduction of equality constraints. In this way, the LS-SVM algorithm allows the optimization problem to be transformed into a problem of solving a system of linear equations, thereby effectively reducing the complexity of the algorithm. Compared with the standard SVM algorithm, the LS-SVM algorithm shows higher efficiency and accuracy when processing certain data sets, so it is widely used in practical problems.

[0005] In the prediction of over-break and under-break in drill-and-blast tunnel construction, a method with more considerations and higher prediction accuracy is needed to provide support for the prediction of over-break and under-break in drill-and-blast tunnel construction. How to effectively apply support vector machine and particle swarm algorithm theory to the analysis and evaluation of tunnel blasting effects has become a major problem that needs to be solved urgently in this field. Summary of the invention

[0006] In order to solve the above problems, the present application provides a method and related equipment for predicting over-excavation and under-excavation of tunnels constructed by drilling and blasting method based on PSO-LSSVM model. In order to improve the prediction accuracy and convergence speed of LS-SVM model, a particle swarm algorithm (PSO) is used to iteratively optimize two key parameters of the model, which can predict the blasting effect of drilling and blasting method with high accuracy and realize efficient construction of tunnel engineering. The technical solution is as follows:

[0007] The first aspect of the present application provides a method for predicting over-break and under-break of a tunnel constructed by a drill and blast method based on a PSO-LSSVM model, comprising the following steps:

[0008] S1 obtains the parameters of the factors affecting over-break and under-break of tunnels constructed by drilling and blasting method;

[0009] S2 preprocesses the parameters of the factors affecting over-break and under-break of tunnels constructed by drilling and blasting method;

[0010] S3 uses grey correlation analysis to finally determine the main parameters affecting tunnel over-break and under-break;

[0011] S4 used the MATLAB simulation platform to establish the PSO-LSSVM model and set the model initialization parameters;

[0012] After S5 initializes the relevant parameters of the model, it selects the root mean square error as the fitness function and calculates the fitness value of each particle. Then the particle will be based on the two extreme values ​​(P best , G best ) to update its own speed and position, and update the value of each particle through multiple iterations, and compare and update V best The value of , and judge whether the end condition of PSO is met, if the end condition is met, the optimal parameter combination when the fitness value reaches the global optimal position is output; if not, repeat S5 to continue the update process;

[0013] S6 established a PSO-LSSVM model for predicting over-break and under-break of tunnels constructed by drilling and blasting method based on the optimal parameter combination, and used this model to predict the over-break and under-break influencing parameters of specific tunnel blasting projects to obtain the blasting effect prediction results.

[0014] For example, in the method for predicting over-excavation and under-excavation of tunnels constructed by drilling and blasting method based on PSO-LSSVM model provided in one embodiment, in S1, parameters of factors affecting over-excavation and under-excavation of tunnels are selected from blasting specification knowledge, blasting expertise, actual cases of blasting engineering, solutions and data related to tunnel blasting.

[0015] For example, in the PSO-LSSVM model-based method for predicting over-break and under-break of a tunnel constructed by the drilling and blasting method provided in one embodiment, in S2, the sample matrix composed of the parameters of the factors affecting over-break and under-break of a tunnel constructed by the drilling and blasting method is standardized:

[0016]

[0017] Among them, x' a represents the result of normalization of the ath element in any row of the sample matrix; x arepresents the ath element in this row in the sample matrix; μ represents the mean of the elements in this row in the sample matrix; σ represents the standard deviation of the elements in this row in the sample matrix.

[0018] For example, in the method for predicting over-excavation and under-excavation of a tunnel constructed by the drill and blast method based on the PSO-LSSVM model provided in one embodiment, in S3, the grey correlation degree between the system characteristic variable data sequences is calculated to establish a grey correlation matrix, and the principle of dominance analysis is used to obtain the order of the influencing factors, and finally the main parameters affecting the over-excavation and under-excavation of the tunnel are determined.

[0019] For example, in the PSO-LSSVM model-based tunnel over-break prediction method provided in one embodiment, the general expression of correlation coefficient correlation is:

[0020]

[0021] Among them, γ i is the correlation coefficient; ε i (k) is the correlation coefficient; k is the kth influencing factor in the sample set.

[0022] For example, in the method for predicting over-excavation and under-excavation of tunnels constructed by the drill and blast method based on the PSO-LSSVM model provided in one embodiment, in S4, the model initialization parameter settings include setting the population size, the maximum number of iterations, the learning factor C1, the learning factor C2, the inertia weight coefficient, the orthogonalization parameter and the kernel function width coefficient.

[0023] The second aspect of the present application provides a tunnel over-break and under-break prediction system for drill and blast construction based on a PSO-LSSVM model, comprising:

[0024] The data processing module is used to pre-process the parameters of the factors affecting the over-break and under-break of tunnels constructed by the drilling and blasting method, and finally determine the main parameters affecting the over-break and under-break of tunnels by using the grey correlation analysis method;

[0025] Model building module, using MATLAB simulation platform to build PSO-LSSVM model and set the model initialization parameters;

[0026] The calculation module is used to calculate the fitness value of each particle, and then the particle will be based on two extreme values ​​(P best , G best ) to update its own speed and position, and update the value of each particle through multiple iterations, and compare and update V best The value of and judge whether the end condition of PSO is met;

[0027] The prediction module establishes a PSO-LSSVM model for predicting over-break and under-break of tunnels constructed by drilling and blasting method based on the optimal parameter combination, and uses this model to predict the over-break and under-break influencing parameters of specific tunnel blasting projects to obtain the blasting effect prediction results.

[0028] The third aspect of the present application provides an electronic device, including: a memory, a processor, and the processor is used to implement the above-mentioned method for predicting over-excavation and under-excavation of a tunnel constructed by the drill and blast method based on the PSO-LSSVM model when executing a computer management program stored in the memory.

[0029] A fourth aspect of the present application provides a computer-readable storage medium having a computer management program stored thereon. When the computer management program is executed by a processor, the above-mentioned method for predicting over-excavation and under-excavation of a tunnel constructed by the drill and blast method based on the PSO-LSSVM model is implemented.

[0030] Some embodiments of the present application provide a method for predicting over-excavation and under-excavation of tunnels under drilling and blasting method based on PSO-LSSVM model and the beneficial effects of the related equipment are as follows: the present application processes and trains the actual test data of over-excavation and under-excavation of tunnels by establishing a support vector machine algorithm (SVM), and transforms the optimization problem into a problem of solving a system of linear equations through least squares optimization, thereby effectively reducing the complexity of the algorithm, and combining the particle swarm algorithm to improve the prediction accuracy and convergence speed of the LSSVM model, which can achieve the goal of reducing sample training time and improving the accuracy of tunnel over-excavation and under-excavation prediction; the prediction method of the present application can provide theoretical support for the optimization of tunnel blasting schemes, safe construction and operation of tunnels, and the over-excavation and under-excavation results predicted by the present application are highly accurate and efficient, and have broad application prospects in the construction and operation and maintenance of a large number of tunnel projects in the future. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0032] Figure 1 This is a flow chart of the method for predicting over-break and under-break of tunnels constructed by the drill and blast method based on the PSO-LSSVM model of this application;

[0033] Figure 2 This is a schematic diagram of the support vector machine (SVM) principle of this application;

[0034] Figure 3 This is a schematic diagram of the particle swarm algorithm (PSO) principle of this application. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0036] Unless otherwise defined, the technical terms or scientific terms used in the present disclosure should be understood by people with ordinary skills in the field to which the present disclosure belongs. The "first", "second" and similar words used in the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0037] The first aspect of the present application provides a method for predicting over-excavation and under-excavation of a tunnel constructed by a drill and blast method based on a PSO-LSSVM model. Figure 1-3 As shown, the following steps are included:

[0038] S1 obtains the parameters of the factors affecting over-break and under-break of tunnels constructed by drilling and blasting method;

[0039] Specifically, the parameters of factors affecting tunnel over-break and under-break are selected from blasting specification knowledge, blasting expertise, actual blasting engineering cases, solutions, and data related to tunnel blasting, such as: peripheral hole position, peripheral hole spacing, drilling depth, drilling angle, radial uncoupling coefficient, light blasting layer thickness, charge structure, charge amount, etc.;

[0040] S2 preprocesses the parameters of the factors affecting over-break and under-break of tunnels constructed by drilling and blasting method;

[0041] Specifically, the sample matrix composed of the parameters of the factors affecting over-excavation and under-excavation of tunnels constructed by the drilling and blasting method is standardized:

[0042]

[0043] Among them, x' a represents the result of normalization of the ath element in any row of the sample matrix; x arepresents the ath element in the row of the sample matrix; μ represents the mean of the elements in the row of the sample matrix; σ represents the standard deviation of the elements in the row of the sample matrix;

[0044] S3 uses grey correlation analysis to finally determine the main parameters affecting tunnel over-break and under-break;

[0045] Specifically, by calculating the grey correlation between the system characteristic variable data sequences, a grey correlation matrix is ​​established, and the order of the influencing factors is obtained by using the principle of advantage analysis, and finally the main parameters affecting the tunnel over-break and under-break are determined; the general expression of the correlation coefficient correlation is:

[0046]

[0047] Among them, γ i is the correlation coefficient; ε i (k) is the correlation coefficient; k is the kth influencing factor in the sample set;

[0048] S4 used the MATLAB simulation platform to establish the PSO-LSSVM model and set the model initialization parameters;

[0049] Among them, the model initialization parameter settings include setting the population size, maximum number of iterations, learning factor C1, learning factor C2, inertia weight coefficient, orthogonalization parameter and kernel function width coefficient;

[0050] For example, as an embodiment, the population size of the model initialization parameters is set to 20, the maximum number of iterations is 100, the learning factor C1 is 1.5, the learning factor C2 is 1.7, the inertia weight coefficient w is [0.4, 0.95], the orthogonalization parameter γ is [0.1, 100] and the kernel function width coefficient σ is [0.1, 1000].

[0051] After S5 initializes the relevant parameters of the model, it selects the root mean square error as the fitness function and calculates the fitness value of each particle. Then the particle will be based on the two extreme values ​​(P best , G best ) to update its own speed and position, and update the value of each particle through multiple iterations, and compare and update V best The value of , and judge whether the end condition of PSO is met, if the end condition is met, the optimal parameter combination when the fitness value reaches the global optimal position is output; if not, repeat S5 to continue the update process;

[0052] S6 established a PSO-LSSVM model for predicting over-break and under-break of tunnels constructed by drilling and blasting method based on the optimal parameter combination, and used this model to predict the over-break and under-break influencing parameters of specific tunnel blasting projects to obtain the blasting effect prediction results.

[0053] The present invention discloses a method for predicting over-break and under-break of a tunnel constructed by drilling and blasting method based on PSO-LSSVM model. By applying support vector machine and particle swarm algorithm theory to the analysis and evaluation of the rationality of tunnel blasting design, a particle swarm algorithm (PSO) is introduced to find the best combination of LSSVM key parameters: global optimal solution (G best) and self-optimal solution (P best). A tunnel blasting over-break and under-break prediction model based on PSO-LSSVM is constructed. The method can predict the blasting effect of drilling and blasting method with high precision, and realize the efficient construction of tunnel engineering.

[0054] The second aspect of the present application provides a tunnel over-break and under-break prediction system for drill and blast construction based on a PSO-LSSVM model, comprising:

[0055] Model building module, using MATLAB simulation platform to build PSO-LSSVM model and set the model initialization parameters;

[0056] The data processing module is used to preprocess the data set, and based on the preprocessed data set, initialize the particle swarm parameters and determine the fitness function;

[0057] The calculation module is used to calculate the fitness value of each particle, the optimal fitness value and the optimal fitness value of the entire population, set the maximum number of iterations in the initialization particle swarm parameters based on the PSO algorithm principle, update the speed and position of each particle, recalculate the fitness value of each particle, compare and update the value of Vbest, and determine whether the end condition of PSO is met;

[0058] The prediction module establishes a PSO-LSSVM model for predicting over-break and under-break of tunnels constructed by drilling and blasting method based on the optimal parameter combination, and uses this model to predict the over-break and under-break influencing parameters of specific tunnel blasting projects to obtain the blasting effect prediction results.

[0059] The third aspect of the present application provides an electronic device, including: a memory, a processor, and the processor is used to implement the above-mentioned method for predicting over-excavation and under-excavation of a tunnel constructed by the drill and blast method based on the PSO-LSSVM model when executing a computer management program stored in the memory.

[0060] A fourth aspect of the present application provides a computer-readable storage medium having a computer management program stored thereon. When the computer management program is executed by a processor, the above-mentioned method for predicting over-excavation and under-excavation of a tunnel constructed by the drill and blast method based on the PSO-LSSVM model is implemented.

[0061] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0062] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0063] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0064] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0065] Although the implementation scheme of the present application has been disclosed as above, it is not limited to the applications listed in the specification and implementation modes, and it can be fully applicable to various fields suitable for the present application. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present application is not limited to the specific details and the illustrations shown and described herein.

Claims

1. A method for predicting over-break and under-break of tunnels constructed by drilling and blasting method based on PSO-LSSVM model, characterized in that: The following steps are involved: S1 obtains the parameters of the factors affecting over-break and under-break of tunnels constructed by drilling and blasting method; S2 preprocesses the data of the parameters of the factors affecting the over-break and under-break of tunnels constructed by drilling and blasting method; S3 uses grey correlation analysis to finally determine the main parameters affecting tunnel over-break and under-break; S4 used the MATLAB simulation platform to establish the PSO-LSSVM model and set the model initialization parameters; After S5 initializes the relevant parameters of the model, it selects the root mean square error as the fitness function and calculates the fitness value of each particle. Then the particle will be based on the two extreme values ​​(P best , G best ) to update its own speed and position, and update the value of each particle through multiple iterations, and compare and update V best The value of , and judge whether the end condition of PSO is met, if the end condition is met, the optimal parameter combination when the fitness value reaches the global optimal position is output; if not, repeat S5 to continue the update process; S6 established a PSO-LSSVM model for predicting over-break and under-break of tunnels constructed by drilling and blasting method based on the optimal parameter combination, and used this model to predict the over-break and under-break influencing parameters of specific tunnel blasting projects to obtain the blasting effect prediction results.

2. The method for predicting over-break and under-break of tunnels constructed by drilling and blasting method based on PSO-LSSVM model according to claim 1 is characterized in that: In S1, parameters of factors affecting tunnel over-break and under-break are selected from blasting specification knowledge, blasting expertise, actual cases of blasting engineering, solutions, and data related to tunnel blasting.

3. The method for predicting over-break and under-break of tunnels constructed by drilling and blasting method based on PSO-LSSVM model according to claim 2 is characterized in that: In S2, the sample matrix composed of the parameters of the factors affecting over-excavation and under-excavation of tunnels constructed by the drilling and blasting method is standardized: Among them, x' a represents the result of normalization of the ath element in any row of the sample matrix; x a represents the ath element in this row in the sample matrix; μ represents the mean of the elements in this row in the sample matrix; σ represents the standard deviation of the elements in this row in the sample matrix.

4. The method for predicting over-break and under-break of tunnels constructed by drilling and blasting method based on PSO-LSSVM model according to claim 3 is characterized in that: In S3, the grey correlation matrix is ​​established by calculating the grey correlation between the system characteristic variable data sequences, and the order of the influencing factors is obtained by using the principle of advantage analysis, and finally the main parameters affecting the tunnel over-break and under-break are determined.

5. The method for predicting over-break and under-break of tunnels constructed by drilling and blasting method based on PSO-LSSVM model according to claim 4 is characterized in that: The general expression of correlation coefficient is: Among them, γ i is the correlation coefficient; ε i (k) is the correlation coefficient; k is the kth influencing factor in the sample set.

6. The method for predicting over-break and under-break of tunnels constructed by drilling and blasting method based on PSO-LSSVM model according to claim 1 is characterized in that: In S4, the model initialization parameter setting includes setting the population size, the maximum number of iterations, the learning factor C1, the learning factor C2, the inertia weight coefficient, the orthogonalization parameter and the kernel function width coefficient.

7. A prediction system for over-break and under-break of tunnels constructed by drilling and blasting method based on PSO-LSSVM model, characterized in that: include: The data processing module is used to pre-process the parameters of the factors affecting the over-break and under-break of tunnels constructed by the drilling and blasting method, and finally determine the main parameters affecting the over-break and under-break of tunnels by using the grey correlation analysis method; Model building module, using MATLAB simulation platform to build PSO-LSSVM model and set the model initialization parameters; The calculation module is used to calculate the fitness value of each particle, and then the particle will be based on two extreme values ​​(P best , G best ) to update its own speed and position, and update the value of each particle through multiple iterations, and compare and update V best The value of and judge whether the end condition of PSO is met; The prediction module establishes a PSO-LSSVM model for predicting over-break and under-break of tunnels constructed by drilling and blasting method based on the optimal parameter combination, and uses this model to predict the over-break and under-break influencing parameters of specific tunnel blasting projects to obtain the blasting effect prediction results.

8. An electronic device, characterized in that: include: A memory and a processor, wherein the processor is used to implement the over-excavation and under-excavation prediction method for tunnel construction using the drill and blast method based on the PSO-LSSVM model as described in any one of claims 1 to 6 when executing the computer management program stored in the memory.

9. A computer-readable storage medium having a computer management program stored thereon, characterized in that: When the computer management program is executed by the processor, the method for predicting over-excavation and under-excavation of a tunnel constructed by the drill and blast method based on the PSO-LSSVM model as described in any one of claims 1 to 6 is implemented.

Images