Tunneling method, system and storage medium based on tunnel boring machine feedback perception

Abstract

The application discloses a kind of based on tunnel boring machine feedback sensing's penetration method, system and storage medium, the method comprises: model construction, the discrete element simulation model that can be used to describe the interaction process of penetration probe and karst surrounding rock is constructed;Simulation and calculation, based on discrete element method, gradually loading simulation is carried out, penetration probe continuously acts on the surrounding rock model containing filling cave structure, the data of penetration process are recorded and the related energy subentry is calculated, and the risk index is calculated in combination with fracture index;Optimization control, feedback control is carried out according to risk index.The system comprises: construction unit, penetration simulation unit, calculation unit and control optimization unit.A kind of storage medium, computer program is stored, program is executed when processor realizes the steps of penetration method as described above.The application can simulate the fracture evolution and energy release process when shield cutter penetrates filling cave area.The application can be widely applied in the technical field of tunnel engineering.

Description

Technical Field

[0001] This invention relates to the field of tunnel engineering technology, and in particular to a penetration method, system and storage medium based on feedback sensing of a tunnel boring machine. Background Technology

[0002] Penetration testing is an important in-situ loading method widely used in tunnel engineering for the rapid assessment of the structural integrity and local strength of surrounding rock, especially suitable for determining the local stability and failure risk of surrounding rock in areas containing filled karst caves. Traditional penetration tests mostly rely on force-displacement curves for macroscopic judgment, lacking the ability to analyze the microscopic evolution of cracks, energy dissipation, and local instability processes within the infill structure, making it difficult to meet the needs of refined and transparent modeling and shield tunneling risk control in karst areas.

[0003] Energy changes during penetration, such as bond fracture work, frictional dissipation energy, and elastic storage energy, are directly related to the failure mode and structural integrity assessment of infilled karst areas under external loads. During shield tunneling rock breaking, penetration behavior essentially corresponds to a rapid cycle of local contact between the cutter and the rock mass—fracture—unloading. The energy distribution during this process can reveal the failure evolution path of different structural interfaces (such as the infill-surrounding rock interface and weak joint zones). Detailed analysis of energy components not only helps identify the energy threshold for rock mass failure but also tracks sensitive areas of crack concentration, assisting in delineating the influence range of karst caves and the response zone to construction disturbances. However, current penetration simulation studies generally lack systematic modeling of physical quantities such as input energy, fracture energy, and plastic dissipation. A multi-scale coupled framework spanning "cutter intrusion—structural fracture—energy conversion" has not yet been established, making it difficult to effectively extract a response index system that can be used for shield tunneling parameter adjustment or risk warning. Summary of the Invention

[0004] In view of this, in order to solve the technical problem that existing penetration simulation methods lack systematic modeling of physical quantities such as input energy, fracture energy, and plastic dissipation, thus leading to low simulation accuracy, the present invention proposes a penetration method based on feedback sensing of a tunnel boring machine. This method includes the following steps:

[0005] Model construction: Constructing a discrete element simulation model that can be used to describe the interaction process between the penetration probe and the karst surrounding rock;

[0006] Simulation and calculation: Based on the discrete element method, a step-by-step loading simulation is performed. The penetration probe continuously acts on the surrounding rock model containing the infilled karst structure, records the data of the penetration process and calculates the relevant energy components, and calculates the risk index in combination with the fracture index.

[0007] Optimize control by implementing feedback control based on the risk index.

[0008] In some embodiments of the first aspect, the method further includes plotting data based on the data from the penetration simulation process to achieve visual recording.

[0009] Secondly, the present invention also proposes a penetration system based on feedback sensing of a tunnel boring machine, which is applied to the penetration method based on feedback sensing of a tunnel boring machine as described above. The system includes a model building unit, a penetration simulation unit, a calculation unit, and a control optimization unit.

[0010] Thirdly, the present invention also proposes a storage medium storing a computer program thereon, the computer program being a calibration program, which, when executed by a processor, implements the steps of the penetration method based on feedback sensing of a tunnel boring machine as described above.

[0011] Based on the above scheme, the present invention provides a penetration method, system and storage medium based on feedback sensing of tunnel boring machine. The penetration failure simulation based on the energy dissipation and fracture statistical coupling mechanism of the present invention is not only applicable to mechanical response analysis at the experimental scale, but can also be extended to simulate the fracture evolution and energy release process when shield cutter penetrates the filling karst area, providing core data support for karst three-dimensional transparent modeling, surrounding rock grade identification and construction disturbance risk warning. Attached Figure Description

[0012] Figure 1 This is a flowchart of the steps of a penetration method based on feedback sensing of a tunnel boring machine according to the present invention;

[0013] Figure 2 This is a schematic diagram of the penetration test model;

[0014] Figure 3 This is a schematic diagram of the cumulative dissipated energy versus penetration depth in a specific embodiment of the present invention;

[0015] Figure 4 This is a schematic diagram of the number of bond fractures versus penetration depth in a specific embodiment of the present invention;

[0016] Figure 5 This is a stress cloud diagram of a particle model according to a specific embodiment of the present invention;

[0017] Figure 6 This is a strain cloud diagram of a particle model according to a specific embodiment of the present invention;

[0018] Figure 7 This is a schematic diagram of the fracture index-penetration depth curve in a specific embodiment of the present invention;

[0019] Figure 8 This is a schematic diagram of the risk index versus injection depth curve in a specific embodiment of the present invention. Detailed Implementation

[0020] The Discrete Element Method (DEM) is naturally applicable to complex rock masses with well-developed fractures and discontinuous structures, and it has advantages in simulating fracture propagation, slip failure, and particle rearrangement during the failure of infilled karst caves. Existing studies have attempted to use DEM for numerical simulation of the penetration process, but most are still limited to the reproduction of force-depth response and lack systematic analysis of penetration-induced energy transfer, fracture evolution, and local instability mechanisms.

[0021] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] It should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this application can be combined with each other.

[0023] It should be understood that the terms "system," "apparatus," "unit," and / or "module" used in this application are a method of distinguishing different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0024] As indicated in this application and claims, unless the context clearly indicates otherwise, the words "a," "an," "a," and / or "the" are not specifically singular and may include the plural. Generally, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements. An element defined by the phrase "comprising an..." does not exclude the presence of other identical elements in the process, method, product, or apparatus that includes the element.

[0025] In the description of the embodiments of this application, "a plurality of" refers to two or more. The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0026] Furthermore, flowcharts are used in this application to illustrate the operations performed by the system according to embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, the steps can be processed in reverse order or simultaneously. Additionally, other operations can be added to these processes, or one or more steps can be removed from them.

[0027] Reference Figure 1 This is a flowchart illustrating an optional example of a tunnel boring machine-based feedback sensing penetration method proposed in this invention. This method can be applied to computer equipment, and the penetration method proposed in this embodiment may include, but is not limited to, the following steps:

[0028] Step S1: Construct a penetration simulation model based on the discrete element method;

[0029] Step S2: Load the simulation based on the penetration simulation model and calculate the energy;

[0030] The energy incorporated into the simulation process includes input work, elastic energy, fracture energy, elastic stored energy, dissipated energy, and kinetic energy.

[0031] Step S3: Construct fracture indicators and calculate the risk index in combination with energy;

[0032] Step S4: Optimize control based on the risk index.

[0033] In some feasible embodiments, step S1 specifically includes:

[0034] A discrete element simulation model can be constructed to describe the interaction process between the penetration probe and the karst surrounding rock. The model can be set with structural elements such as irregular geometric filling caves, weak cemented zones and joints and fissures, set the interparticle contact model and mechanical parameters, and initialize the simulated penetration loading path (optional: vertical penetration, shield rotation propulsion, etc.).

[0035] In this embodiment, the input parameters include, but are not limited to, particle size, normal stiffness, tangential stiffness, friction coefficient, normal and tangential bond strength, damping coefficient, density, bond type (such as linear contact or parallel bond), and the loading method of the penetration probe (force control or displacement control).

[0036] The initial coordinates of discrete particles are determined, and the particles are generated within a given boundary using a random dense stacking algorithm to form a stable initial configuration. The position coordinates of each particle are uniformly calibrated according to the selected coordinate system.

[0037] Number the discrete particles and input the corresponding data information, including but not limited to: each particle's number, position coordinates, radius, mass, current velocity and acceleration, force state (normal force, tangential force, friction force, damping force), bond connection state, number and number of contact neighbors, etc.

[0038] Initial boundary conditions are applied and the time step is determined. In this embodiment, the bottom boundary of the model is fixed, and the remaining sides are set as frictional or elastic boundaries. A rigid cylindrical probe is arranged on the top for loading. The time step is determined according to the stability criterion based on the maximum stiffness and minimum mass, so as to balance computational accuracy and efficiency.

[0039] In some feasible embodiments, step S2 specifically includes:

[0040] A step-by-step loading simulation is performed based on the discrete element method, with the penetration probe (which can be simulated as a shield cutterhead or propulsion head) continuously acting on the surrounding rock model containing the infilled karst cave structure.

[0041] Throughout the simulation, the input work, elastic energy, fracture energy, elastic stored energy, dissipated energy, and kinetic energy are calculated in real time.

[0042] The calculation method for input work is as follows:

[0043]

[0044] in, Indicates the initial depth to Deep input capabilities, Indicates the first The thrust of the step, Indicates the initial depth to Number of sampling steps for depth, Indicates the first The increment of the penetration displacement of the step. Indicates the first The torque of the step, Indicates the first Step rotation increment

[0045] The calculation methods for elastic energy, fracture energy, and elastic stored energy are as follows:

[0046]

[0047]

[0048]

[0049] in, Indicates the first The elastic properties of a bonding bond Indicates the first The normal stiffness of the contact, Indicates the first The tangential stiffness of the contact, Indicates the first The normal relative displacement of each contact Indicates the first The tangential relative displacement of the contact; Indicates from the initial time to The cumulative fracture energy at time t, Indicates from the initial time to The set of broken bonds at any given moment. Indicates the moment of fracture; Indicates the first A bonding bond in Elastic energy at time t; Indicates from the initial time to Flexible energy storage at all times Indicates from the initial time to The set of unbroken contacts at any given moment. Indicates the first A bonding bond in Elastic energy at a given time.

[0050] Dissipated energy and energy balance:

[0051]

[0052]

[0053]

[0054]

[0055]

[0056] in, Indicates the time from the initial moment to Energy dissipated by friction at any moment Indicates the time from the initial moment to The contact set of the slip states at any given moment. Indicates the initial time. Indicates tangential stress. Indicates tangential velocity, Indicates instantaneous time. Indicates the time from the initial moment to The set of contacts that actually make contact and transmit force at any given moment. Indicates the time from the initial moment to Viscous dissipation energy at time intervals Indicates normal damping, Indicates normal velocity, Indicates tangential damping. Indicates the time from the initial moment to Total energy dissipation at any given moment; express Kinetic energy at any given moment Indicates the first The mass of a single point mass; Indicates the first The translational velocity of a point mass; Indicates the first Moment of inertia of a point mass; Indicates the first The angular velocity of a point mass.

[0057] In some feasible embodiments, the fracture index in step S3 specifically includes:

[0058]

[0059]

[0060]

[0061] in, Indicates in Energy dissipation rate per unit depth within the depth range Indicates the first Each sampling depth interval, then Indicates the first The depth increment of each sampled depth interval. express Total energy dissipation within the depth range Indicates in The rate of increase in the number of fractures per unit depth within the depth range. As a localized indicator, Indicates in The second invariant of shear strain within the depth range Indicates in The mean of the window within the depth interval.

[0062] In some feasible embodiments, step S3 further includes:

[0063] The formula for calculating the joint inflection point is as follows:

[0064]

[0065]

[0066] like Then this point is determined to be the critical depth. .

[0067] in, Indicates in Energy dissipation rate per unit depth within the depth range This is the threshold coefficient; , Used as a reference scale (window mean / historical quantile); This is the critical depth.

[0068] In some feasible embodiments, the risk index of step S3 specifically includes:

[0069]

[0070]

[0071]

[0072] in, For localized reference scale, These are weighting coefficients. Indicates in Risk index within the depth range.

[0073] In some feasible embodiments, step S4 specifically includes:

[0074] when Trigger an alert and output the feed / speed / pressure and tool strategy. This is the warning threshold.

[0075] In this embodiment, .

[0076] Based on the overall process of the above method embodiment, this embodiment, after the calculation is completed, derives the penetration depth-energy evolution curves and the penetration depth-fracture number curve, and plots the fracture spatial distribution map and energy density cloud map, etc. The analysis results show that there is a clear energy threshold point during penetration, the location of which is highly consistent with the "jump segment" of the number of bond fractures, revealing the energy triggering characteristics of structural failure. This threshold can be used as a quantitative criterion for identifying local instability zones, and can further be embedded in a transparent modeling system for tunnel surrounding rock for risk zone delineation and support optimization decisions in construction disturbance-sensitive sections.

[0077] In the implementation of this invention, the discrete element method (DEM) was used to conduct an in-depth analysis of the energy and structural failure evolution of rock penetration tests, in order to explore the failure mechanism inside the rock mass under external load and its coupling relationship with energy input. By simulating rock penetration tests, the cumulative dissipated energy and the number of bond fractures were calculated. Figure 2 As shown, the particle model used in the discrete element simulation is a 100mm×100mm×50mm cuboid rock sample. The geological strength index (GSI) is determined to be 100 based on the distribution of rock fractures. The specific value is based on the GSI value method, where GSI = 100 is taken when there are no more than two obvious through fractures on the rock surface.

[0078] The experiment used a wedge-shaped cutter. The cutter inclination angle α = 30°, the inter-cone width α0 = 0.5 mm, and the loading rate was set to 0.5 mm / min. The experiment started and continued until the specimen was completely penetrated. The input energy, fracture energy, and elastic deformation energy of the model were monitored, and the cumulative dissipated energy was calculated. The number of bond fractures was also monitored. Finally, the simulation outputs a cumulative dissipated energy versus penetration depth graph and a bond fracture number versus penetration depth graph.

[0079] Through the Figure 3 and Figure 4 A comprehensive analysis reveals that the work done by the penetration force is mainly converted into two parts: one part is the energy stored in the elastic deformation inside the rock mass, and the other part is released in the form of crack formation and propagation, i.e., fracture energy.

[0080] from Figure 3 It can be seen that the input energy continuously accumulates with the penetration depth, resulting in a continuous increase in dissipated energy, exhibiting an overall monotonically increasing trend, and the energy dissipation rate also gradually increases. This characteristic of accelerated energy release usually appears at locations where the internal structure of the rock sample encounters significant damage or abrupt changes in strength, indicating that the externally loaded mechanical energy is efficiently converted into fracture work at this stage, thereby promoting the initiation and propagation of cracks. Meanwhile, Figure 4 The data shows that the number of bond fractures increases slowly in the early stages of penetration, but rises rapidly at certain depths, forming a distinct "jump" segment. This jump coincides with... Figure 3 The accelerated energy growth rate corresponds to the fact that the rock mass underwent a failure evolution process from the accumulation of microcracks to macroscopic penetration within this depth range.

[0081] The synchronous increase in energy conversion and fracture number during penetration not only verifies the effectiveness of this method in tracking the evolution of microscopic fractures, but also reveals that the failure behavior has a clear energy threshold characteristic. That is, before a certain energy input, the rock mass is mainly in an elastic energy storage state, and the bonds remain intact; however, once the energy accumulation exceeds a certain critical point, it triggers concentrated crack propagation, leading to a sharp increase in the number of fractures, marking the entry of the rock sample into a rapid failure stage. This energy threshold and its corresponding depth can serve as an important quantitative criterion for judging the risk of surrounding rock instability, and are applicable to the identification of failure initiation points and the sensitivity analysis of construction risks in penetration tests.

[0082] like Figure 5 As shown in the stress cloud diagram, a distinct high-stress concentration zone is observed between the particles penetrating the probe, exhibiting a vertically expanding distribution characteristic from top to bottom. This indicates that the probe loading first induces a vertical crack zone directly below the probe. The interparticle contact force is dramatically enhanced in this region, serving as the primary controlling channel for crack initiation and propagation. Correspondingly, as... Figure 6As shown, the strain contour map reveals shear bands and localized deformation nuclei extending downwards from the penetration point. These high-strain zones generally develop along diagonal or oblique directions, forming a divergent failure structure centered on the penetration axis. The high overlap between stress concentration and strain anomaly regions reflects the evolution path of the microscopic failure process under local stress-strain coupling. These regions are the key spatial distribution zones in subsequent simulations, characterized by rapid accumulation of bond fractures and a significant increase in energy dissipation. The stress-strain response map output by this invention can not only accurately locate local fracture development and energy release areas, but also serve as the basis for sensitivity weighting of the surrounding structure in transparent geological modeling, assisting in risk zoning of construction disturbance paths and dynamic optimization of tunneling parameters.

[0083] In summary, this invention, based on discrete element method (DEM) simulation and combining energy and bond fracture data with stress and strain contour maps, reveals the failure evolution mechanism during penetration. The stress concentration zone and deformation zone are highly consistent, forming a crack network that extends downwards along the penetration path. Input energy is gradually converted into fracture energy and dissipated energy with increasing depth; the number of bond fractures and the increase in dissipated energy show a synchronous trend, indicating that energy is mainly used for the failure process. This method not only improves the accuracy of identifying the initiation characteristics and evolution path of penetration failure but also provides quantifiable simulation support for three-dimensional transparent modeling, risk-sensitive section identification, and tunneling parameter optimization in karst tunnel engineering.

[0084] The present invention also provides another embodiment for an EPB / slurry / variable density shield tunneling machine for karst-soft-hard interbedded strata, the difference being in steps S1 and S4, wherein the data of the simulation model involved includes:

[0085] Thrust F, cutterhead torque M, rotational speed ω, penetration depth / penetration rate PI, face / mud pressure Pc, screw press current Is, screw press rotational speed ns, slag sample moisture content Wm, feed speed VP, cutter temperature / wear rate Tc.

[0086] The data preprocessing steps include: (1) time alignment and unit unification; (2) mapping the time axis to the penetration depth sequence h and resampling (Δh=0.005~0.02m, 0.01m recommended); (3) smoothing: using a window of m=5 to perform moving averages on M, ω, and Pc; (4) outlier removal: local z-score |z|>3; (5) shield verification amount (discrete gradient of silo pressure with depth):

[0087]

[0088] in, Indicates the i-th sampling depth. This represents the (i-1)th sampling depth. This represents the face / mud pressure at the i-th sampling depth. This represents the face / mud pressure at the (i-1)th sampling depth.

[0089] A DEM was established in the near field at the working face to explicitly embed and fill cavities, weakly cemented zones, and joints and fissures.

[0090] Contact / adhesion parameter set:

[0091]

[0092] in is the normal / tangential stiffness (N / m); Q is the coefficient of friction; The tangential bond strength is expressed in Pa.

[0093] Assimilation objective: using the weight matrix Minimize the cost function of weighted residuals plus regularization;

[0094]

[0095] Among the observations Operating conditions , The regularization coefficient is... For difference / unit operator, As a priori. Convergence: Or the relative improvement between adjacent iterations is <1%. Indicates by parameters The model under operating conditions input The predicted observations generated below.

[0096] The simulation diagram of fracture index and penetration depth in this embodiment is shown below. Figure 7 .

[0097] Recommended weight for tunnel boring machines .

[0098] Figure 8 Risk indicators are given The diagram illustrates the changes in penetration depth, with the marked threshold lines representing only typical warning zones. In practical applications, three thresholds are set. , , Normalized risk indicators Divided into four levels: normal; Early warning (I); Warning (II); High risk (III).

[0099] Target pressure control law:

[0100]

[0101]

[0102] in For target inventory pressure, Baseline warehouse pressure, .

[0103] Triggering strategy: or close to At the same time, increase Pc to the target band and coordinate the screw speed ns and the cutter head speed ω.

[0104] This invention also provides another embodiment, a hard rock TBM (open / single-shield / double-shield), suitable for hard rocks (such as limestone / basalt) and strata with well-developed joints and fractures. The difference lies in steps S1 and S4, where the data acquisition involved includes:

[0105] Thrust F, cutterhead torque M, rotational speed ω, penetration depth / penetration rate PI, feed rate V P Tool temperature / wear agent T c Similarly, as in the previous embodiment, emphasis is placed on the smoothing and alignment of PI, M, and ω to generate a tool / depth of cut partition index.

[0106] Generate a block network and joint set, locally containing infill bodies and weak cementation bands; establish parameters according to equation (19). Mapping with "tool action zone - depth of cut partition"; minimizing the estimated parameters according to equation (20) .

[0107] The cutting depth and torque pulsation are jointly determined by PI and ω, following the "penetration + rotation" path.

[0108] Triggering strategy: At that time, prioritize reducing ω (reducing the depth of cut / reducing the pulsating torque), and then slightly reduce V. P If T c Exceeding limits triggers maintenance / tool ​​replacement.

[0109] The optimization uses a soft upper limit on torque and a risk threshold as dual objectives, and performs online calculations within the permissible range:

[0110]

[0111]

[0112] in, As a soft upper limit for torque, These are weighting coefficients. , This is the allowed range.

[0113] A tunnel boring machine-based feedback sensing penetration system includes:

[0114] The model building unit is used to execute step S1;

[0115] The simulation unit is inserted to execute step S2;

[0116] The calculation unit is used to execute step S3;

[0117] The control optimization unit is used to execute step S4.

[0118] The content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0119] A storage medium storing a computer program thereon, the computer program being a calibration program, which, when executed by a processor, implements the steps of the penetration method based on feedback sensing of a tunnel boring machine as described above.

[0120] The content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0121] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A penetration method based on feedback sensing of a tunnel boring machine, characterized in that, Includes the following steps: A penetration simulation model is constructed based on the discrete element method. The simulation is based on the penetration simulation model, and the energy is calculated, including input work, elastic energy, fracture energy, elastic stored energy, dissipated energy and kinetic energy. Construct a fracture index and calculate a risk index based on the energy level; Control optimization is performed based on the aforementioned risk index; The formula for the fracture index is: in, Indicates in Energy dissipation rate per unit depth within the depth range Indicates the first Each sampling depth interval, then Indicates the first The depth increment of each sampled depth interval. express Total energy dissipation within the depth range Indicates in The rate of increase in the number of fractures per unit depth within the depth range. As a localized indicator, Indicates in The second invariant of shear strain within the depth range Indicates in The mean of the window within the depth interval.

2. The penetration method based on feedback sensing of a tunnel boring machine according to claim 1, characterized in that, Also includes: The joint inflection point is calculated based on the fracture index.

3. The penetration method based on feedback sensing of a tunnel boring machine according to claim 2, characterized in that, Also includes: Penetration visualization is recorded based on the energy, fracture index, and joint inflection point.

4. The penetration method based on feedback sensing of a tunnel boring machine according to claim 2, characterized in that, The formula for calculating the input work is as follows: in, Indicates the initial depth to Deep input capabilities, Indicates the first The thrust of the step, Indicates the initial depth to Number of sampling steps for depth, Indicates the first The increment of the penetration displacement of the step. Indicates the first The torque of the step, Indicates the first The step's rotation increment.

5. The penetration method based on feedback sensing of a tunnel boring machine according to claim 2, characterized in that, The formula for calculating the risk index is as follows: in, Indicates in Risk index within the depth range This represents the corresponding weighting coefficient. This indicates the corresponding reference scale.

6. A tunnel boring machine-based feedback sensing penetration system, characterized in that, A method for performing a tunnel boring machine-based penetration method as described in claim 1 includes: Model building unit, which constructs an in-depth simulation model based on the discrete element method; A penetration simulation unit is used to perform a simulation based on the penetration simulation model. The calculation unit calculates the energy during the penetration process, which includes input work, elastic energy, fracture energy, elastic stored energy, dissipated energy, and kinetic energy; it constructs a fracture index and calculates a risk index based on the energy. A control optimization unit is used to perform collaborative optimization based on the risk index.

7. A storage medium storing a computer program thereon, said computer program being a calibration program, characterized in that, When the calibration program is executed by the processor, it implements the steps of the method as described in any one of claims 1-5.

Images