A method, system, electronic device and storage medium for optimizing a structure of a shield cutter

Abstract

This invention discloses a method, system, electronic device, and storage medium for optimizing the cutterhead structure of a tunnel boring machine (TBM), relating to the field of TBM construction. The method includes: constructing a rock HJC constitutive model using the physical and constitutive parameters of the rock; selecting sensitive factors for cutterhead structure optimization and constructing a cutterhead model; conducting numerical simulations of cutterhead rock breaking using the finite element software LS-DYNA to obtain the reaction force and crushed rock volume experienced by the cutterhead during cutting; constructing a rock breaking energy prediction model and a cutterhead wear prediction model using the XGBoost algorithm; using the rock breaking energy prediction model and the cutterhead wear prediction model as objective optimization functions, and the sensitive factors as decision variables, performing multi-objective optimization using the NSGAⅡ method to obtain the optimal solution; the optimal solution is the optimal cutterhead parameters; and determining the optimal cutterhead structure based on the optimal cutterhead parameters. This invention achieves prediction and multi-objective optimization of cutterhead rock breaking efficiency and wear in a low-cost manner, providing guidance for cutterhead selection and tunneling parameter selection before TBM construction.

Description

Technical Field

[0001] This invention relates to the field of tunnel boring machine (TBM) construction technology, and in particular to a method, system, electronic device, and storage medium for optimizing the cutterhead structure of a TBM. Background Technology

[0002] Due to its advantages such as high mechanization, high construction efficiency, and minimal environmental disturbance, shield tunneling has gradually become the main method for urban tunnel construction. The disc cutter, as the direct rock-breaking tool of the shield machine, has a significant impact on the efficiency and safety of shield tunnel construction. Factors such as the cutter width, penetration depth, and cutting edge angle significantly affect rock-breaking efficiency and also have a considerable impact on its own wear. Traditional research methods, due to limitations in experimental quantity, are mostly based on relevant premises and consider only a limited number of factors, often yielding only partial patterns that are difficult to meet the actual needs of engineering projects. Furthermore, optimization research lacks a systematic consideration of the rock-breaking efficiency and cutter wear of the disc cutter. In application, excessively pursuing rock-breaking efficiency may lead to increased cutter wear, and frequent cutter replacements may actually hinder construction progress and increase construction costs. Summary of the Invention

[0003] The purpose of this invention is to provide a method, system, electronic device, and storage medium for optimizing the cutter head structure of a tunnel boring machine, in order to solve the problem that the prior art lacks a systematic consideration of the cutter head's rock-breaking efficiency and cutter head wear.

[0004] To achieve the above objectives, the present invention provides the following solution:

[0005] A method for optimizing the cutterhead structure of a tunnel boring machine includes:

[0006] The HJC constitutive model of the rock was constructed using its physical and constitutive parameters. The physical parameters included rock density, compressive strength, elastic modulus, Poisson's ratio, shear modulus, and bulk modulus. The constitutive parameters included strain rate effect parameters, limit surface parameters, pressure parameters, and damage parameters.

[0007] Sensitive factors for hob structure optimization are selected, and a hob model is constructed; the sensitive factors include cutting edge radius, cutting edge width, and tool penetration.

[0008] The roller cutter model and the rock HJC constitutive model were imported into the finite element software LS-DYNA to conduct numerical simulation of roller cutter rock breaking, and the reaction force and crushed rock volume during roller cutting were obtained; the reaction force during roller cutting includes: rolling force, normal force and lateral force;

[0009] Based on the aforementioned sensitive factors, the reaction force experienced by the cutter during cutting, and the volume of crushed rock, the XGBoost algorithm is used to construct a rock breaking energy prediction model and a cutter wear prediction model.

[0010] Using the rock breaking energy prediction model and the cutter wear prediction model as objective optimization functions, and the sensitive factors as decision variables, the NSGA II method is used for multi-objective optimization to obtain the optimal solution; the optimal solution is the optimal cutter parameters.

[0011] The optimal hob structure is determined based on the optimal hob parameters.

[0012] Optionally, the rock HJC constitutive model includes: a strength model, a damage evolution equation, and a state equation;

[0013] The expression for the intensity model is as follows:

[0014]

[0015] Where, σ * To characterize the equivalent stress, p * To characterize the pressure, To characterize the strain rates, A, B, N, and S MAX All are limit surface parameters, C is the strain rate effect parameter, and D is the damage parameter;

[0016] The expression for the damage evolution equation is as follows:

[0017]

[0018]

[0019] Where, Δε p , Δμ p This represents the equivalent plastic strain increment and plastic volumetric strain increment of a single element within a computational cycle. T represents the equivalent plastic strain and equivalent plastic volumetric strain in the current calculation step. * D1 and D2 are the normalized tensile strength of the material, and D1 and D2 are the material damage parameters; EF MIN This represents the minimum plastic strain at which the material fails.

[0020] The state equations include the state equations for the elastic compression stage, the state equations for the compaction deformation stage, and the state equations for the post-compaction deformation stage.

[0021] The expression for the state equation during the compression phase is as follows:

[0022] p = Kμ; -T(1-D) ≤ p ≤ p c ;

[0023] The expression for the state equation of the compaction deformation stage is as follows:

[0024]

[0025] p=p0-[(1-F)K+FK1](μ0-μ))

[0026] The expression for the state equation of the post-compaction deformation stage is as follows:

[0027]

[0028]

[0029] Where p is the net water pressure, K is the bulk modulus, μ is the volumetric strain, and T is the maximum tensile net water pressure of the material. c p1 is the elastic limit of the net water pressure, and μ is the compaction limit of the net water pressure. c μ is the volumetric strain corresponding to the elastic limit. p p1 represents the volumetric strain corresponding to the ultimate compaction pressure, p0 represents the pressure corresponding to the volumetric deformation before unloading, and F represents the unloading proportionality coefficient. K1 represents the corrected volumetric strain; K2, K3 are pressure constants.

[0030] Optionally, the expression for the rock breaking energy prediction model is as follows:

[0031]

[0032] The expression for the hob wear prediction model is as follows:

[0033] y2=Iμ f F y l

[0034] Where y1 is the rock-breaking specific energy, y2 is the cutter wear, and F x F y The rolling force and normal force are respectively represented by x3, l, and V, which represent the cutter penetration, rolling distance, and rock breaking volume, respectively. I is the energy wear rate, μ f is the coefficient of friction.

[0035] Optionally, before constructing the rock-breaking energy prediction model and the cutter wear prediction model using the XG Boost algorithm based on the aforementioned sensitive factors, the reaction force experienced by the cutter during cutting, and the volume of crushed rock, the method further includes:

[0036] A noise reduction algorithm is used to reduce the noise of the reaction force experienced by the hob during cutting.

[0037] The present invention also provides a shield tunnel cutterhead structure optimization system, comprising:

[0038] The rock HJC constitutive model construction module is used to construct a rock HJC constitutive model using the physical parameters and constitutive parameters of the rock. The physical parameters include: rock density, compressive strength, elastic modulus, Poisson's ratio, shear modulus, and bulk modulus. The constitutive parameters include: strain rate effect parameters, limit surface parameters, pressure parameters, and damage parameters.

[0039] The hob model construction module is used to select sensitive factors for hob structure optimization and construct a hob model; the sensitive factors include cutting edge radius, cutting edge width, and tool penetration.

[0040] The roller cutter rock-breaking numerical simulation module is used to import the roller cutter model and the rock HJC constitutive model into the finite element software LS-DYNA to carry out roller cutter rock-breaking numerical simulation, and obtain the reaction force and crushed rock volume during roller cutting; the reaction force during roller cutting includes: rolling force, normal force and lateral force;

[0041] The prediction model construction module is used to construct a rock breaking energy prediction model and a cutter wear prediction model based on the sensitive factors, the reaction force experienced by the cutter during cutting, and the volume of crushed rock using the XG Boost algorithm.

[0042] The optimization module is used to perform multi-objective optimization using the rock breaking energy prediction model and the cutter wear prediction model as objective optimization functions, and the sensitive factors as decision variables, and to obtain the optimal solution using the NSGA II method; the optimal solution is the optimal cutter parameters.

[0043] The optimal hob structure is determined based on the optimal hob parameters.

[0044] Optionally, it also includes:

[0045] The noise reduction module is used to perform noise reduction processing on the reaction force received by the hob during cutting using a noise reduction algorithm.

[0046] The present invention also provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to perform the shield cutterhead structure optimization method described above.

[0047] The present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described shield cutterhead structure optimization method.

[0048] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0049] This invention significantly reduces costs by establishing a constitutive model through on-site rock sampling and constructing a sample set through multi-factor numerical simulation of cutter rock breaking. A predictive model for rock breaking energy and cutter wear is established using the XG Boost regression algorithm, replacing the traditional mathematical mapping relationship as the objective function of NSGAII. The Pareto optimal solution for the cutter is obtained through the NSGAII genetic algorithm. This invention fully considers the effects of various sensitive factors. Through the established LS-DYNA numerical simulation sample library and the XG Boost-NSGAII prediction-optimization model, it achieves the prediction of cutter rock breaking energy and cutter wear, and the optimization of cutter dimensions based on these factors. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 A flowchart of the shield tunnel cutterhead structure optimization method provided by the present invention;

[0052] Figure 2 Overall flowchart of the shield tunnel cutterhead structure optimization method provided by the present invention

[0053] Figure 3 This is a schematic diagram of the roller cutter rock breaking size model and sensitive parameters provided by the present invention;

[0054] Figure 4 A finite element mesh model diagram generated using HyperMesh software for this invention;

[0055] Figure 5 The figure shows the numerical simulation results of rock breaking using LS-DYNA software provided by this invention. Detailed Implementation

[0056] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0057] The purpose of this invention is to provide a method, system, electronic device and storage medium for optimizing the cutterhead structure of a tunnel boring machine (TBM), so as to achieve prediction and multi-objective optimization of cutterhead rock-breaking efficiency and wear in a low-cost manner, and to provide guidance for the selection of cutterhead and tunneling parameters before TBM construction.

[0058] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0059] Example 1

[0060] Embodiment 1 of the present invention provides a method for optimizing the cutterhead structure of a tunnel boring machine. For example... Figure 1-2 As shown, the method includes the following steps:

[0061] S1: Construct an HJC constitutive model of the rock using its physical and constitutive parameters; the physical parameters include: rock density ρ, compressive strength f. c The constitutive parameters include: elastic modulus E, Poisson's ratio ν, shear modulus G, and bulk modulus K; the constitutive parameters include: strain rate effect parameter C, limit surface parameters A, B, N, pressure parameters K1, K2, K3, and damage parameter EF.

[0062] Relevant physical and mechanical tests were conducted on the sampled rocks to obtain their physical and mechanical parameters and constitutive parameters, and to construct a Holmquist-Johnson-Cook (HJC) constitutive model. For common rocks, their HJC constitutive model information can be found in existing experimental data. The relevant physical and mechanical tests included wax-sealed density testing, uniaxial compression testing, Brazilian splitting testing, triaxial compression testing, and impact testing.

[0063] Furthermore, the target rock HJC model is established as follows:

[0064] The HJC constitutive model comprehensively considers the effects of compression, strain rate, and damage on rock and concrete materials. The model consists of three parts: a strength model, a damage evolution equation, and a state equation.

[0065] (1) Strength Model: The HJC strength model is described by characteristic equivalent stress.

[0066]

[0067] In the formula, σ * =σ / f c To characterize the equivalent stress, p * =p / f c To characterize the pressure, Characterized strain rates; σ, f c , These are the actual equivalent stress, compressive strength, and actual strain rate, respectively; p, Unit net water pressure and reference strain rate; A, B, N, and S MAX These are collectively referred to as limit surface parameters, where C is the strain rate effect parameter and D is the damage parameter.

[0068] (2) Damage evolution equation: The HJC model posits that plastic damage is formed by the accumulation of plastic strain, which includes equivalent plastic strain and equivalent plastic volumetric strain.

[0069]

[0070]

[0071] In the formula, Δε p , Δμ p This represents the equivalent plastic strain increment and plastic volumetric strain increment of a single element within a computational cycle. T represents the equivalent plastic strain and equivalent plastic volumetric strain in the current calculation step. * =T / f c The normalized tensile strength of the material is given by T, where T is the maximum tensile net water pressure of the material; D1 and D2 are the material damage parameters; EF MIN It represents the minimum plastic strain at which the material fails.

[0072] (3) Equation of state: used to describe the relationship between water pressure and volumetric strain, and is divided into three stages: elastic compression, compaction deformation, and post-compaction deformation.

[0073] ①p=Kμ;-T(1-D)≤p≤p c

[0074] ②

[0075] p = p0 - [(1-F)K + FK1](μ0 - μ)(unload)

[0076] ③

[0077]

[0078] Stage ① is the linear elastic region, where p is the net water pressure, K is the bulk modulus, μ is the volumetric strain, and p c For the elastic limit of the net water pressure, p l The compaction limit water pressure is given by p0, where p0 is the water pressure corresponding to the volume deformation before unloading, F is the unloading proportional coefficient, and μ is the pressure at which the pressure is compacted. c μ is the volumetric strain corresponding to the elastic limit. p To match the compaction limit water purification pressure p l The corresponding volumetric strain, K1 represents the corrected volumetric strain; K2, K3 are pressure constants.

[0079] The rock HJC model is defined using the keyword *MAT JOHNSON HOLMQUIST CONCRETE TITLE in the LS PrePost software. Specifically, RO is the density ρ, G is the elastic modulus, A, B, N, and SFMAX are the limiting surface parameters, C is the strain rate effect parameter, FC is the uniaxial compressive strength of the rock, T is the maximum tensile net water pressure of the material, and ESP0 is the reference strain rate. EFMIN is the minimum plastic strain EF at which the material fails. MIN PC, UC, PL, and UL correspond to p in the state equation, respectively. c p l μ c μ l D1 and D2 are material damage parameters, and K1, K2, and K3 are pressure constants.

[0080] Rock density was measured using the wax-sealing method, elastic modulus and uniaxial compressive strength were obtained through uniaxial compression tests, and maximum tensile net water pressure was measured through splitting or tensile tests. Uniaxial compression tests were conducted at different strain rates to obtain the characteristic equivalent stress (σ) at different strain rates. * =σ / f c Strain hardening index Triaxial compression tests were conducted, and the MC strength envelope was obtained according to the Mohr-Coulomb criterion. Without considering damage, the HJC strength model is: Let p = 0, Solving the two equations simultaneously, we obtain the normalized cohesive strength A. From... The normalized pressure hardening coefficient B and strain rate hardening exponent N were obtained. K1, K2, K3, PC, UC, PL, and UL were obtained from the Hugoniot test data of Los Alamos rock material. Cyclic loading tests were conducted to obtain the stress-strain relationship diagram of sandstone under cyclic loading, and the damage parameter EFMIN was obtained. D1 and D2 can be taken as default values.

[0081] S2: Select the sensitive factors for hob structure optimization and construct a hob model; the sensitive factors include the cutting edge radius, cutting edge width and tool penetration.

[0082] Based on the hob design concept, the hob optimization sensitivity factors are selected as x = (x1, x2, x3), and the value range of each sensitivity factor is determined according to feasibility. Here, x1 is the cutting edge radius, x2 is the cutting edge width, and x3 is the tool penetration. Parameters with low sensitivity to hob optimization, such as the hob radius, remain unchanged.

[0083] like Figure 3 As shown, this embodiment optimizes a CCS disc hob. The hob thickness and inner / outer radii remain constant, while the cutting edge radius (x1), cutting edge width (x2), and penetration (x3) are changed. Specifically, 0 ≤ x1 ≤ 5; 14 ≤ x2 ≤ 22; 4 ≤ x3 ≤ 12. Using SOLIDWORKS to model the hob, a total of 25 hob models need to be created based on the cutting edge radius and cutting edge width values. The penetration can be directly modified in the k-file of the LS-DYNA software.

[0084] S3: Import the roller cutter model and the rock HJC constitutive model into the finite element software LS-DYNA to carry out numerical simulation of roller cutter rock breaking, and obtain the reaction force and crushed rock volume when the roller cutter cuts; the reaction force when the roller cutter cuts includes: rolling force, normal force and lateral force.

[0085] The 3D models of the cutter and rock created in SOLIDWORKS were imported into HyperMesh meshing software for mesh generation. Considering computational accuracy and workload, the mesh was locally refined in the contact area between the rock and the cutter. The cutter was treated as a rigid body, and the element mass was disregarded during mesh generation; instead, the fit between the nodes and the geometry was considered. The resulting mesh is shown in the image. Figure 4 As shown. After meshing, the mesh was imported into LS-PrePost software for further keyword settings, including cutter motion control, rock boundary conditions, contact conditions, and solution output settings. After completing the preprocessing, k-files were exported in batches, and the penetration value was changed to obtain 125 sets of preprocessed files. The k-files were then imported into LS-Run software for finite element calculations of cutter rock breaking. The rock failure and equivalent stress after cutter cutting are shown below. Figure 5 As shown. Simultaneously, data on the rock-breaking force of the roller cutter and element failure were obtained for different models.

[0086] Numerical simulation was performed using LS-DYNA finite element software, considering the cutter radius and rock-breaking process. The rock dimensions were set to 600×250×120mm. The cutter was treated as a rigid body, exhibiting rotational freedom around its central axis and translational freedom in the forward and downward directions, while the remaining three directions were constrained. The rock was defined by the HJC constitutive model, with all degrees of freedom on the bottom surface constrained, and the four sides set as non-reflective boundary conditions to reduce boundary effects. The reaction force F during cutter cutting was monitored. x ,F y ,F z ), where F x For rolling force, F y For normal force, F zThe force is lateral. The change in the number of rock model elements during the cutting process is monitored. The volume of the failed element is calculated by statistically analyzing the number and size of the failed elements, which is equivalent to the crushed rock volume V.

[0087] S4: Based on the aforementioned sensitive factors, the reaction force experienced by the cutter during cutting, and the volume of crushed rock, the XGBoost algorithm is used to construct a rock breaking energy prediction model and a cutter wear prediction model.

[0088] After obtaining the initial sample Sn=[x,F,V],0≤n≤N,n∈Z, a denoising algorithm is used to denoise the F in the sample data to remove noise caused by factors such as cutter rolling and unit continuity, thereby obtaining the true rock-breaking force data. The data of the stable segment is taken as the denoised data. A target value sequence is constructed from the initial sample data, including rock-breaking specific energy y1 and cutter wear y2.

[0089] (1) The rock-breaking energy follows the following mapping relationship:

[0090]

[0091] In the formula, F x F y These represent the rolling force and normal force of the cutter, respectively, while x3, l, and V represent the cutter penetration, rolling distance, and rock breaking volume, respectively.

[0092] (2) Hob wear follows the following mapping relationship:

[0093] y2=Iμ f F y l

[0094] In the formula, I represents the energy wear rate, μ f is the coefficient of friction, and l is the rolling distance of the hob.

[0095] Based on the above mapping relationship, a new training sample set D = {(x1,y1),(x2,y2),…,(x...} is obtained. N ,y N )}. Where, x i =(x i (1) ,x i (2) ,x i (3) T is the eigenvector, y i =(y i (1) ,y i (2) T is the target vector, i = 1, 2, ..., N, and N is the sample size.

[0096] 100 samples were selected as the training set and 25 samples as the test set. XGBRegressor from XG Boost was used for regression prediction, with the gbtree model chosen as the sub-regression tree model. To prevent overfitting and improve speed, the model parameters were optimized. Ultimately, max_depth was set to 20, gamma to 0.1, and learning_rate to 0.2, while other parameters remained at their default settings.

[0097] The final predicted value output is represented as follows:

[0098]

[0099] In the formula, fj represents a regression tree model, J represents the total number of regression tree models, and F is the regression tree space.

[0100] To evaluate the reliability of the prediction model, the root mean square error (RMSE) is used to test the dispersion between the predicted and actual values, and the goodness of fit (R²) is used to measure the fit between the predicted and actual values. Specifically, it is expressed as follows:

[0101]

[0102]

[0103] Where n is the number of samples in the training set; y i , represents the true value of the sample, the predicted value of the sample, and the average of the true values ​​of all samples in the test set, respectively.

[0104] S5: Using the rock breaking energy prediction model and the cutter wear prediction model as objective optimization functions, and the sensitive factors as decision variables, the NSGAⅡ method is used for multi-objective optimization to obtain the optimal solution; the optimal solution is the optimal cutter parameters.

[0105] The NSGA II genetic algorithm is used to achieve multi-objective optimization. The specific implementation steps of the algorithm are as follows:

[0106] ① Determine the initial population size, and obtain the first generation population through selection, crossover, and mutation operations;

[0107] ② Merge the parent and offspring populations and use fast non-dominated sorting to determine the non-dominated level of individuals;

[0108] ③ Introduce an elite strategy, retain elite individuals, and generate a new offspring population through genetic algorithms;

[0109] ④ Repeat the above steps until the number of iterations reaches the maximum, and output the Pareto optimal solution.

[0110] The nonlinear mapping model constructed by the XG Boost algorithm is used as the fitness function of the multi-objective optimization algorithm, expressed as minf1(x) = min(XGBoost1(x)) and minf2(x) = min(XGBoost2(x)), with the constraint being the range of values ​​for the sensitive factor x = (x1, x2, x3). The NSGAⅡ genetic algorithm is used for multi-objective optimization, with 2 objectives, a population size of 80, a maximum evolution generation and a stopping generation of 60, a crossover operator of 0.7, a mutation operator of 0.01, and 10 Pareto optimal solutions. Due to the exclusivity between multi-objective functions, the multi-objective optimization problem does not yield a unique solution but is represented by a set of optimal solutions. For the two input fitness functions, 10 optimal solutions are obtained, representing their dominance over the remaining 115 decision variables. In engineering, one of these solutions can be selected based on the actual situation to obtain the optimal rock-breaking specific energy and rolling wear performance.

[0111] S6: Determine the optimal hob structure based on the optimal hob parameters.

[0112] The method proposed in this invention significantly reduces the time and economic costs of traditional experimental methods by using numerical simulation. Therefore, it can consider the combined influence of multiple sensitive factors and construct a rich and comprehensive sample library based on numerical simulation. It fully leverages the data analysis advantages of machine learning methods, introducing an XG Boost regression model to solve complex nonlinear problems involving multiple factors, and constructing a prediction model for rock breaking energy and cutter wear based on the XG Boost regression algorithm, achieving effective prediction of both. Considering the complex contradictory relationship between rock breaking energy and cutter wear, this invention introduces the NSGA II multi-objective optimization algorithm. The model constructed using the regression algorithm replaces the traditional mathematical function relationship and is imported into the NSGA II model as the objective function, avoiding errors during the conversion between XG Boost and NSGA II models, making the optimization results more reliable.

[0113] Example 2

[0114] In order to implement the method corresponding to Embodiment 1 above and achieve the corresponding functions and technical effects, a shield tunnel cutterhead structure optimization system is provided below.

[0115] The system includes:

[0116] The Rock HJC Constitutive Model Construction Module is used to construct a rock HJC constitutive model using the physical and constitutive parameters of the rock.

[0117] The hob model construction module is used to select the sensitive factors for hob structure optimization and construct the hob model.

[0118] The roller cutter rock breaking numerical simulation module is used to import the roller cutter model and the rock HJC constitutive model into the finite element software LS-DYNA to carry out roller cutter rock breaking numerical simulation and obtain the reaction force and crushed rock volume during roller cutting.

[0119] The prediction model construction module is used to construct a rock breaking energy prediction model and a cutter wear prediction model based on the sensitive factors, the reaction force experienced by the cutter during cutting, and the volume of crushed rock, using the XG Boost algorithm.

[0120] The optimization module is used to perform multi-objective optimization using the rock breaking energy prediction model and the cutter wear prediction model as objective optimization functions, and the sensitive factors as decision variables, and to obtain the optimal solution; the optimal solution is the optimal cutter parameters.

[0121] The optimal hob structure is determined based on the optimal hob parameters.

[0122] Also includes:

[0123] The noise reduction module is used to perform noise reduction processing on the reaction force received by the hob during cutting using a noise reduction algorithm.

[0124] Example 3

[0125] Embodiment 3 of the present invention provides an electronic device, including a memory and a processor. The memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the shield cutterhead structure optimization method provided in Embodiment 1.

[0126] In practical applications, the aforementioned electronic devices can be servers.

[0127] In practical applications, electronic devices include: at least one processor, memory, bus, and communication interface.

[0128] The processor, communication interface, and memory communicate with each other via a communication bus.

[0129] A communication interface is used to communicate with other devices.

[0130] The processor is used to execute programs, specifically the methods described in the above embodiments.

[0131] Specifically, the program may include program code, which includes computer operation instructions.

[0132] The processor may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The electronic device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or they may be processors of different types, such as one or more CPUs and one or more ASICs.

[0133] Memory is used to store programs. Memory may include high-speed RAM, and may also include non-volatile memory, such as at least one disk drive.

[0134] Example 4

[0135] Based on the description of Embodiment 3, Embodiment 4 of the present invention provides a storage medium storing a computer program thereon, which can be executed by a processor to implement the shield tunnel cutterhead structure optimization method of Embodiment 1.

[0136] The shield tunnel cutterhead structure optimization system provided in Embodiment 2 of the present invention exists in various forms, including but not limited to:

[0137] (1) Mobile communication devices: These devices are characterized by their mobile communication capabilities and primarily aim to provide voice and data communication. These terminals include: smartphones (e.g., iPhones), multimedia phones, feature phones, and low-end phones, etc.

[0138] (2) Ultra-mobile personal computer devices: These devices fall under the category of personal computers, possessing computing and processing capabilities, and generally also have mobile internet access capabilities. These terminals include PDAs, MIDs, and UMPCs, such as the iPad.

[0139] (3) Portable entertainment devices: These devices can display and play multimedia content. This category includes: audio and video players (such as iPods), handheld game consoles, e-books, as well as smart toys and portable car navigation devices.

[0140] (4) Other electronic devices with data interaction functions.

[0141] Specific embodiments of the subject matter have now been described. Other embodiments are within the scope of the appended claims. In some cases, the actions described in the claims can be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing can be advantageous.

[0142] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0143] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, in implementing this invention, the functions of each unit can be implemented in one or more software and / or hardware components. Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can 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.

[0144] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0145] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0146] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0147] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0148] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0149] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined in this invention, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0150] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0151] This invention can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules.

[0152] Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific transactions or implement specific abstract data types. This invention can also be practiced in distributed computing environments where transactions are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0153] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to the method section.

[0154] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for optimizing the cutterhead structure of a tunnel boring machine, characterized in that, include: The HJC constitutive model of the rock was constructed using its physical and constitutive parameters. The physical parameters include: rock density, compressive strength, elastic modulus, Poisson's ratio, shear modulus, and bulk modulus; the constitutive parameters include: strain rate effect parameters, limit surface parameters, pressure parameters, and damage parameters. Sensitive factors for hob structure optimization are selected, and a hob model is constructed; the sensitive factors include cutting edge radius, cutting edge width, and tool penetration. The roller cutter model and the rock HJC constitutive model were imported into the finite element software LS-DYNA to conduct numerical simulation of roller cutter rock breaking, and the reaction force and crushed rock volume during roller cutting were obtained; the reaction force during roller cutting includes: rolling force, normal force and lateral force; Based on the aforementioned sensitive factors, the reaction force experienced by the cutter during cutting, and the volume of crushed rock, the XG Boost algorithm is used to construct a rock breaking energy prediction model and a cutter wear prediction model. Using the rock breaking energy prediction model and the cutter wear prediction model as objective optimization functions, and the sensitive factors as decision variables, the NSGA II method is used for multi-objective optimization to obtain the optimal solution; the optimal solution is the optimal cutter parameters. The optimal hob structure is determined based on the optimal hob parameters.

2. The shield tunnel cutterhead structure optimization method according to claim 1, characterized in that, The HJC constitutive model of the rock includes: a strength model, a damage evolution equation, and a state equation; The expression for the intensity model is as follows: in, To characterize equivalent stress, To characterize the pressure, To characterize the strain rates, A, B, N, and All are limit surface parameters, C is the strain rate effect parameter, and D is the damage parameter; The expression for the damage evolution equation is as follows: in, , This represents the equivalent plastic strain increment and plastic volumetric strain increment of a single element within a computational cycle. The equivalent plastic strain and equivalent plastic volumetric strain are given in the current calculation step. For the normalized tensile strength of the material, , For material damage parameters; This represents the minimum plastic strain at which the material fails. The state equations include the state equations for the elastic compression stage, the state equations for the compaction deformation stage, and the state equations for the post-compaction deformation stage. The state equation for the elastic compression stage is expressed as follows: ； The expression for the state equation of the compaction deformation stage is as follows: The expression for the state equation of the post-compaction deformation stage is as follows: ； in, Let be the net water pressure, K be the bulk modulus, μ be the volumetric strain, and T be the maximum tensile net water pressure of the material. The elastic limit of the water purification pressure, To achieve the ultimate water purification pressure, This represents the volumetric strain corresponding to the elastic limit. To meet the ultimate pressure of compaction for water purification The corresponding volumetric strain, The pressure is the net water pressure corresponding to the volume deformation before unloading, and F is the unloading ratio coefficient. This is the corrected volumetric strain; , , is the pressure constant.

3. The shield tunnel cutterhead structure optimization method according to claim 1, characterized in that, The expression for the rock-breaking energy prediction model is as follows: The expression for the hob wear prediction model is as follows: in, For rock breaking specific energy, For hob wear, , These are rolling force and normal force, respectively. , V represents the cutter penetration, rolling distance, and rock breaking volume, respectively, and I represents the energy wear rate. is the coefficient of friction.

4. The shield tunnel cutterhead structure optimization method according to claim 1, characterized in that, Before constructing the rock-breaking energy prediction model and the cutter wear prediction model using the XG Boost algorithm based on the aforementioned sensitive factors, the reaction force experienced by the cutter during cutting, and the volume of crushed rock, the following steps are also included: A noise reduction algorithm is used to reduce the noise of the reaction force experienced by the hob during cutting.

5. A shield tunnel cutterhead structure optimization system, characterized in that, include: The HJC constitutive model construction module for rocks is used to construct HJC constitutive models of rocks using their physical and constitutive parameters. The physical parameters include: rock density, compressive strength, elastic modulus, Poisson's ratio, shear modulus, and bulk modulus; the constitutive parameters include: strain rate effect parameters, limit surface parameters, pressure parameters, and damage parameters. The hob model construction module is used to select sensitive factors for hob structure optimization and construct a hob model; the sensitive factors include cutting edge radius, cutting edge width, and tool penetration. The roller cutter rock-breaking numerical simulation module is used to import the roller cutter model and the rock HJC constitutive model into the finite element software LS-DYNA to carry out roller cutter rock-breaking numerical simulation, and obtain the reaction force and crushed rock volume during roller cutting; the reaction force during roller cutting includes: rolling force, normal force and lateral force; The prediction model construction module is used to construct a rock breaking energy prediction model and a cutter wear prediction model based on the sensitive factors, the reaction force experienced by the cutter during cutting, and the volume of crushed rock using the XG Boost algorithm. The optimization module is used to perform multi-objective optimization using the rock breaking energy prediction model and the cutter wear prediction model as objective optimization functions, and the sensitive factors as decision variables, and to obtain the optimal solution using the NSGA II method; the optimal solution is the optimal cutter parameters. The optimal hob structure is determined based on the optimal hob parameters.

6. The shield tunnel cutterhead structure optimization system according to claim 5, characterized in that, Also includes: The noise reduction module is used to perform noise reduction processing on the reaction force received by the hob during cutting using a noise reduction algorithm.

7. An electronic device, characterized in that, The device includes a memory and a processor, the memory being used to store a computer program, and the processor running the computer program to cause the electronic device to perform the shield cutterhead structure optimization method according to any one of claims 1-4.

8. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the shield cutterhead structure optimization method as described in any one of claims 1-4.

Images