242 results about "Principal stress" patented technology

The invention provides a finite element-based method for estimating pulling-out ultimate bearing capacity of a grouting screw anchor in gravelly soil, and relates to the technical field of civil structure engineering.A three-dimensional finite element model containing the grouting screw anchor and surrounding gravelly soil is established, model parameters cover the structure and material characteristics of the grouting screw anchor, and the grouting screw anchor and the surrounding gravelly soil are subjected to finite element modeling; a coordinate axis is established with the center of the anchor bottom as an original point for grid division, a stress concentration area is analyzed, principal stress is calculated to serve as critical bearing stress, vertical pull-out loads are applied step by step through a grouting pull-out test, a pull-out stress influence area is determined, soil stress of the area is analyzed, and soil binding power and friction force are calculated. And a grouting coefficient and a rock crack coefficient are generated, soil parameters are corrected, and the ultimate pulling bearing capacity of the grouting screw anchor is comprehensively obtained. According to the method, the pulling ultimate bearing capacity of the grouting screw anchor is accurately evaluated by establishing the three-dimensional finite element model and the graded loading experiment.

Provided is a method for judging geology of a time-delayed extremely intense rockburst as to deep tunnel engineering. Information about geological structures is recorded according to methods such as geological mapping and advanced geological prediction of the tunnel face. Geometric characteristics of burst craters formed during the rockburst are recorded by utilizing advanced geological drilling and profile scanning technologies in a rockburst-damaged zone. 3D geostress in the rockburst-damaged zone is measured by using a stress relief method or a hydraulic fracturing method to determine the orientation of the maximum principal stress. A 3D numerical calculation model is established based on initial geostress testing results and physical and mechanical parameters of rock and structural discontinuities obtained through on-site geological investigations. By conducting excavation simulations under different combinations of structural discontinuities and performing numerical calculation, the risk of time-delayed extremely intense rockburst disasters at current locations after tunnel excavation is judged.

The invention relates to the technical field of seismic source analysis and inversion, and discloses a seismic source analysis and inversion system based on mine earthquake monitoring, which is characterized in that energy parameters are generated through waveform feature extraction, mine earthquake event identification and accurate positioning are realized by using a space-time aggregation rule, and seismic source mechanism parameters are inverted in combination with a seismic wave initial motion parameter and amplitude relationship. On the basis, a regional stress field initial inversion model is constructed, a stress gradient is calculated in combination with a working face track and stratum information, a principal stress rotation composite index is determined through interlayer mechanical difference and a spatial change rate, and self-adaptive deformable partitions are generated. And finally, secondary stress field inversion is carried out in the subareas, the corrected maximum principal stress direction is output, high-precision dynamic analysis of a mine earthquake mechanism and stress distribution is realized, and the mine disaster prediction and early warning capability is remarkably improved.

The invention provides a structural design optimization method and device for an underground station constructed through a shield tunneling method, and belongs to the technical field of underground engineering.The method comprises the steps that site geological survey data of a station trepanning area are obtained and input into a three-dimensional finite element model, and an initial three-dimensional model is constructed; analyzing a dynamic load effect in a construction stage by combining a load reduction theory to obtain a target three-dimensional model; finite element analysis is carried out based on the target three-dimensional model, and the maximum principal stress of the edge of the opening is extracted; then comparing the maximum principal stress with the allowable stress of the material, and performing load reduction iteration under the condition that the maximum principal stress is greater than the allowable stress of the material to obtain a final load reduction coefficient; and taking the final load reduction coefficient, the trepanning center coordinate and the stress concentration factor as the input of a two-dimensional reinforcement model, generating an equivalent live load, calculating the reinforcement amount, and automatically realizing the reinforcement optimization design. The construction efficiency is improved and the engineering cost is reduced while the safety and stability of the structure are ensured.

The invention relates to an aero-engine stator part crack critical dimension comprehensive determination method and system, and belongs to the technical field of aviation, the method comprises the following steps: obtaining an aero-engine typical hot end stator part geometric model and material parameters, and carrying out static strength analysis according to fluid-thermal-solid coupling load characteristics in actual working conditions; inserting an initial crack into a first principal stress plane of a dangerous part of the real component, carrying out crack propagation simulation to determine a crack propagation path, and calculating a critical crack size of a dangerous point; analyzing critical crack sizes under different failure modes, such as cooling failure and buckling failure; and integrating analysis results under the multi-failure mode, and determining a comprehensive critical dimension as a final judgment standard. According to the method, through combination of fracture failure and function failure analysis, accurate judgment of the critical dimension of the crack is realized, limitation of a traditional single fracture criterion is broken through, comprehensive function failure analysis is realized, the accuracy of a maintenance decision is remarkably improved, and a scientific basis is provided for condition-based maintenance decision.

The invention relates to the technical field of geological engineering safety risk evaluation, in particular to a regional tectonic stress risk quantitative analysis method for tunnel engineering. The method comprises the following steps: collecting multi-source geomechanical parameters, simulating and inverting a tectonic stress field, and verifying the tectonic stress field; constructing a multi-scale geomechanical model, coupling simulation tectonic stress and gravity stress, and generating a stress space basic layer; utilizing Kriging interpolation and inversion decomposition to obtain a stress value and a directional diagram layer; calculating an included angle between the maximum principal stress direction and the tunnel axis, and performing vector decomposition to obtain a vertical stress component; and carrying out standardized normalization on the factors, determining a weight calculation risk value, and finally generating a tectonic stress risk quantitative grading graph and carrying out GIS visual rendering. The tunnel engineering-oriented risk quantitative analysis mechanism is constructed by retaining the directivity and spatial heterogeneity characteristics of the tectonic stress tensor, and the authenticity, resolution and engineering applicability of tectonic stress identification are remarkably improved.

The invention provides an elastic-plastic unified description method and system for nonlinear characteristics of surrounding rock considering medium-principal stress, and belongs to the technical field of computer aided design. The method comprises the following steps: carrying out a true triaxial mechanical property test on surrounding rock to obtain a surrounding rock total stress-strain curve, extracting characteristic stress points of the stress-strain curve, and carrying out stage division on the stress-strain curve; constructing a characteristic yield surface in the stress space based on the characteristic stress points; based on the staged characteristics of the stress-strain curve, plastic deformation capacity characterization functions of different stages are constructed respectively, and the plastic deformation capacity characterization functions are used for describing the plastic deformation capacity of the stress-strain curve; and constructing a nonlinear hardening-softening equation to describe evolution characteristics of the characteristic yield surface. According to the scheme, the nonlinear characteristics of the stress-strain curve can be more comprehensively and accurately described under different minimum principal stresses and medium principal stresses.

The invention discloses a rock burst prediction type control system for geotechnical engineering tunnel construction. The rock burst prediction type control system comprises a data acquisition layer, a data processing layer and a control layer. The data acquisition layer captures rock fracture signals, surrounding rock stress evolution and tunneling state data in real time. The edge calculation layer is used for executing data preprocessing, feature extraction, local model training and real-time reasoning; the federated learning layer is used for constructing a teacher-student model by utilizing a knowledge distillation technology, compressing a global model, and encrypting and transmitting the compressed model to the edge calculation layer through a LoRa module; a rockburst prediction layer: fusing an FLAC3D principal stress vector field as a NeRF position code, constructing an anisotropic radiation field according to a joint surface topological relation extracted by a graph neural network, dynamically adjusting overall rendering density in combination with a microseismic energy release rate, and integrating a physical model and a machine learning model through a Bayesian framework to output a risk probability; and the intelligent decision-making layer is used for generating a multi-objective optimization scheme based on a reinforcement learning framework in combination with digital twinborn simulation, and matching a preset working condition-measure pair through a rule engine.

The invention belongs to the field of airplane strength fatigue life prediction, and particularly relates to an equivalent stress-based airplane typical structure multi-axial fatigue life prediction method. The method comprises the steps of determining a typical aircraft high-lock connection structure test piece; determining a fatigue load spectrum; constructing a finite element model of the typical high-lock connection structure of the aircraft; determining a dangerous part of the airplane typical high-lock connection structure test piece in finite element analysis; determining the maximum principal stress at the dangerous part of the typical airplane high-lock connection structure test piece in finite element analysis; determining the fatigue life of the test piece; fitting S-N curve data under different stress ratios according to the fatigue life of the test piece and the load spectrum stress ratio, and determining a corrected S-N curve; determining an equivalent stress-life equation of the typical high-lock connection structure of the aircraft, and substituting the maximum principal stress and fitting parameters of the corrected S-N curve into the equivalent stress-life equation to calculate and obtain a fatigue prediction life; and correcting the fatigue prediction life according to a test result.

The invention provides a shale reservoir hydraulic fracturing wellbore casing deformation risk judgment method which comprises the steps that geological parameters and principal stress of a target area are obtained, and the principal stress comprises horizontal principal stress, maximum principal stress and vertical principal stress. And determining an included angle between the fault plane and the hydraulic fracture plane according to the normal vector of the fault plane and the normal vector of the hydraulic fracture plane. And calculating by substituting the geological parameters, the principal stress and the included angle into an established stress calculation model of the fault plane to obtain shear stress and normal stress of the fault plane in the target area. And calculating by substituting the shear stress and the normal stress into the established displacement component calculation model to obtain the slip component of the fault plane in the target area. And performing safety early warning based on the risk level. The fault slip amount is calculated by accurately identifying the stratum physical property parameters and the fault structure, so that the casing deformation risk is judged.

The invention discloses a true triaxial test device and test method capable of realizing arbitrary rotation of principal stress, and belongs to the technical field of geotechnical engineering.The true triaxial test device comprises a shear stress device, the shear stress device comprises a shear stress pressure head used for being connected with the surface of a sample, and the shear stress pressure head is connected with two shear stress applying systems; the shear stress applying system applies shear stress parallel to the surface of the sample to the sample, and the directions of the two shear stresses are vertical; the main stress device is connected with the shear stress pressure head, and the main stress device applies pressure perpendicular to the surface of the sample to the sample. According to the invention, random rotation of the principal stress can be realized through the shear stress device, so that the direction and size of the principal stress applied to the rock sample can simulate a real path to continuously change, and the deformation fracture behavior in the rock mechanical bearing process can be more accurately obtained; and a technical support is provided for correctly and accurately evaluating the bearing characteristic, the fracture characteristic and the instability mechanism of the rock.

The invention discloses a quantitative evaluation method and system for fault disturbance of a current crustal stress field of a tight reservoir, and belongs to the technical field of petroleum and natural gas development. The method comprises the following steps: S1, obtaining an actually measured crustal stress value I of a target interval of a target fault and an actually measured crustal stress value II under a non-disturbance condition; s2, obtaining a theoretical ground stress value of a target interval of the target fault under a non-disturbance condition; s3, establishing an average principal stress and shear stress intensity calculation model, and calculating to obtain the average principal stress and shear stress intensity under actual measurement and non-disturbance conditions; s4, a crustal stress fault comprehensive disturbance index calculation model is established, a crustal stress fault comprehensive disturbance index is obtained through calculation, and the larger the index value is, the stronger the fault disturbance is. According to the method, the quantitative characterization of the force-fracture coupling relationship can be realized, and the problems of poor repeatability and lack of unified quantitative standards caused by a qualitative method as a main method are effectively solved, and the technical problem that the geomechanical environment around the well near the fault is not matched with the engineering response is effectively solved.

The invention belongs to the technical field of geotechnical engineering and rock mechanics testing, discloses a stress-strain mixed control-based rock stable failure testing method, and aims to solve the problem that a stress path cannot be maintained and brittle failure cannot be inhibited simultaneously after rock peak strength is detected in an existing true triaxial test. The method comprises the following core steps: firstly, determining a target stress state and a strain growth rate threshold value; then hydrostatic pressure loading is carried out; loading and unloading at a fixed proportional rate in a stress control mode; and when the strain rate reaches a threshold value, switching to a stress-strain hybrid control mode, converting the maximum principal stress direction into strain control to stabilize the damage process, and dynamically coordinating stresses in the other two directions based on real-time feedback to enable the whole damage process to maintain a preset stress path all the time. According to the invention, the complete and stable test of the pre-peak-post-peak mechanical behavior of the rock under any complex stress state can be realized, and a key technical support is provided for accurately verifying the strength criterion and researching the failure mechanism.

The invention discloses a porcelain piece stress reduction method and system based on elasticity modulus regulation and control, and belongs to the technical field of stress research and nondestructive testing, and the method comprises the following steps: generating a temperature-elasticity modulus characteristic curve, collecting geometrical morphology information of microdefects in a porcelain piece, and calculating a temperature-elasticity modulus characteristic curve; inputting a multi-physics field coupling finite element model taking a temperature change process of an extreme low-temperature working condition as a thermal load boundary condition, carrying out iterative optimization calculation to obtain an optimal elastic modulus combination which minimizes the maximum first principal stress in the porcelain part, and reversely solving an optimal manufacturing process parameter combination by utilizing a correlation model to obtain a final manufacturing process parameter combination. And calculating the predicted safe operation life cycle of the porcelain part through the fatigue crack propagation model. According to the method, by introducing dynamically changing material parameters and real microdefect data, the stress state of the porcelain piece under the extreme working condition is predicted and optimized, a corresponding process implementation path and service life evaluation are given, and the problems of inaccurate simulation and poor optimization effect caused by adoption of constant parameters in the prior art are solved.

The invention relates to a mining trackless rubber vehicle centralized control method, which comprises the steps of obtaining an elastic wave signal generated by surrounding rock fracture at the position of a mining trackless rubber vehicle, obtaining surrounding rock three-dimensional principal stress component data at the position of the mining trackless rubber vehicle, processing the elastic wave signal through an edge processing module to obtain micro-seismic event parameters, and outputting the micro-seismic event parameters. The micro-seismic event parameters comprise a seismic source position and an energy characteristic of a micro-seismic event; converting the surrounding rock three-dimensional principal stress component data into a strain energy density field, fusing the strain energy density field with energy characteristics, and calculating to obtain a total energy value of a micro-seismic event; generating a surrounding rock health state evaluation result based on the micro-seismic event total energy value; determining a rockburst risk level and a high-risk area boundary based on the seismic source position of the micro-seismic event and a surrounding rock health state evaluation result; calculating a safe driving track based on the rockburst risk level and the high-risk area boundary; and sending the safe driving track to a vehicle control system of the mining trackless rubber vehicle.

The present application relates to a kind of potential rock burst pit depth quantitative estimation method considering structural plane and excavation disturbance effect, obtain the initial maximum principal stress and rock uniaxial compressive strength of the region to be estimated, preliminary evaluation whether it has the potential to occur rock burst;Surrounding rock is estimated to estimate the scope of excavation damage zone by sound wave test;According to the sound wave test data, the disturbance factor at different depths is estimated;According to the change characteristics of disturbance factor, the height damage zone and weak damage zone range of surrounding rock in excavation damage zone are estimated;Estimate the potential rock burst pit depth of surrounding rock.The present application not only considers rock strength and stress condition, but also considers the influence of structural plane and excavation disturbance on potential rock burst pit depth, uses high-precision, low-cost and convenient sound wave test technology and a small amount of rock indoor strength test can be realized, with greater innovation, practicality, economy and feasibility.

The invention provides a gob-side entry retaining floor heave control method based on blasting weakening floor stress barrier steering, which comprises the following steps of: S1, acquiring dynamic evolution characteristics of complete-period floor principal stress of gob-side entry retaining under typical geological conditions, and obtaining a dynamic evolution rule of a three-way principal stress state of a floor; s2, constructing a bottom plate horizontal beam mechanical model under the action of three-way principal stress, and obtaining a driving mechanism and an influence degree of a three-way principal stress state on deformation and damage of the bottom plate at different layers of the gob-side entry retaining; s3, on the basis of the influence rule of the three-way principal stress state on the floor heave amount, the influence rule of the floor weakening on the floor heave amount of the gob-side entry retaining is analyzed, and the action mechanism of the floor weakening on control over the floor heave of the gob-side entry retaining is obtained; and S4, deep blasting weakening or shallow grouting reinforcement is conducted on the surrounding rock on the basis of the action mechanism of bottom plate weakening for controlling the floor heave of the gob-side entry retaining, and the heavy workload brought by traditional repairing treatment of the floor heave of the gob-side entry retaining is greatly reduced.

The invention belongs to the technical field of geological disaster monitoring, and particularly relates to a geological disaster recognition method based on physical constraints and an attention enhancement gating mechanism, which comprises the following steps: firstly, collecting and preprocessing multi-source data of a target geological area to generate a multi-source data set; multiple types of physical prior feature data are obtained through a physical prior generation unit, and a maximum principal stress direction unit vector field and a stress concentration field are output through a stress field calculation unit; then constructing a deep learning reasoning unit comprising a vibration physical constraint module, a stress constraint module and an attention enhancement gating module; and finally, inputting multi-source data, physical prior features and a stress correlation field, and outputting a geological disaster category probability through feature extraction, vibration vulnerability field and direction consistency modulation quantity generation, feature scaling, attention screening and up-sampling. The problems of low recognition accuracy and insufficient physical consistency in a complex geological environment in the existing geological disaster recognition technology can be solved.

The invention discloses a post-excavation stratum reinforcement grouting effect visualization method based on multi-field coupling, and the method comprises the steps: firstly obtaining the stratum condition, rock mechanics data and grouting parameters of a grouting region, and carrying out the simulation calculation of the distribution condition of effective principal stress after excavation through a specific model; based on the distribution of the effective principal stress in the mechanical field in the porous medium, simulating and calculating the porosity distribution and the permeability coefficient after formation fracturing; analyzing a slurry diffusion path by adopting a specific model, and obtaining the overall change conductivity of the porous medium and the slurry through analog calculation; parameters of a resistivity hole lane combined monitoring system are determined according to the changing conductivity, and the potential value of each point position in the grouting reinforcement process is actually measured through the monitoring system; finally, the actually measured data and the model calculation data are compared and analyzed, the diffusion path and the reinforcement effect of the grout in the grouting reinforcement process are continuously obtained, and dynamic visualization of the stratum reinforcement grouting effect before and after excavation is achieved through comprehensive analysis of the multi-physics field coupling condition.

The invention provides a method for establishing a nonlinear constitutive model of low-temperature marine steel, and relates to the technical field of ships and materials. A heterogeneous time series data set is provided for model construction through multi-type sample multi-axial load tests and full-field strain acquisition; nonlinear mapping of deformation activation energy about temperature and microscopic state variables is established by taking a crystal plasticity theory as a framework, and the defect that a low-temperature dislocation evolution rule cannot be reflected due to the fact that a traditional model solidifies physical parameters into constants is overcome; a damage evolution operator jointly induced by stress triaxial degree and a principal stress threshold is embedded, Bayesian inference is adopted to carry out parameter joint calibration, model dynamic calibration and parameter continuous optimization are realized through a simulation and experiment closed-loop iteration mechanism, and finally a digital design evaluation model capable of being under untested extreme working conditions is produced. And an engineering tool taking physical interpretability and probabilistic safety margin into consideration is provided for the ice-resistant design of the polar region ship.

The application relates to the technical field of cantilever pouring construction, in particular to a cantilever pouring construction method and system based on a finite element method. The method comprises the following steps: constructing a multi-scale finite element analysis model, simulating structural responses in different construction stages under the condition of each age stage through the constructed multi-scale finite element analysis model, determining control parameters of the cantilever pouring construction based on the simulation results; and comparing real-time sensing data with the control parameters of the time step in the multi-scale finite element model constructed before construction, forming a structural dynamic error vector, performing dynamic feedback adjustment of the cantilever pouring construction based on the structural dynamic error vector, and determining the best construction path of the cantilever pouring construction. Through the process parameter inversion technology based on the structural response ternary function group, the application realizes accurate control of response quantities such as structural principal stress, deflection and node axial force in the construction process, and improves the bridge completion precision and structural performance consistency of the cantilever pouring.

This invention relates to the field of deep learning technology, specifically to a numerical simulation method for true triaxial tests of coarse-grained soil materials based on principal stress effects. The method includes the following steps: acquiring three-dimensional geological parameters and boundary condition data of the coarse-grained soil material; and constructing a true triaxial finite element simulation model of the coarse-grained soil based on the three-dimensional geological parameters and boundary condition data. This invention utilizes a loading increment step size for trial calculations and calculates the reward function value based on the convergence state and iteration count of the trial calculation results to update the network parameters, enabling the control strategy to continuously evolve through interaction with the environment. This allows for the identification of dangerous regions with highly nonlinear constitutive relations or near-singular stiffness matrices. In these regions, the step size is automatically reduced to ensure computational convergence, while in stable regions, the step size is increased to improve computational efficiency. This solves the problem that traditional fixed step sizes or simple adaptive step sizes easily lead to computational divergence or excessive iterations under complex stress paths.

The application belongs to the technical field of load identification of structural health monitoring, and provides a concentrated load positioning method based on principal stress constraint and strain gradient trajectory identification, which comprises the following steps: arranging strain sensors in a monitoring area of a planar structure plate and collecting strain data of measuring points, constructing a strain field inversion function based on a radial basis function and establishing an error optimization function containing a fitting error term and a smooth constraint, introducing a principal stress direction constraint and a gradient projection smooth constraint to form a comprehensive error function and solving to obtain an optimal strain field distribution, then calculating strain gradient vectors of each grid node and tracking a gradient trajectory through a gradient descent method, and finally performing an iterative clustering analysis based on distance statistics on a trajectory end point to output a cluster center as a concentrated load application position identification result. The application can improve the concentrated load positioning accuracy, enhance the anti-noise capability, and realize fast, stable and large-sample-free load position identification.

The present application relates to a kind of determination methods of fracturing horizontal well controlled reserves, belong to oil and gas reservoir exploration and development technical field.The determination method of fracturing horizontal well controlled reserves of the present application, comprising the following steps: based on the length of horizontal section of fracturing horizontal well, the angle between horizontal section and maximum horizontal principal stress, limit drainage radius and the half fracture length of fracturing fracture, the area of the region surrounded by the maximum envelope line of fracturing horizontal well seepage field is calculated, and the control area of fracturing horizontal well is obtained;Based on the product of fracturing horizontal well control area, oil layer effective thickness and single storage coefficient, the control reserves of fracturing horizontal well is determined.The determination method of fracturing horizontal well controlled reserves of the present application simplifies single well control area into the maximum drainage area of single well that can control oil layer fluid seepage from the seepage angle, which can effectively simplify the calculation process and improve the calculation efficiency.

This invention relates to the field of structural fatigue life prediction technology, and discloses a method and system for predicting the fatigue life of a hinged coupling, comprising: Step 1, acquiring torque and input shaft angular position data, mapping time to angular position and dividing it equally to obtain angular domain torque; Step 2, constructing a load vector based on the angular domain torque and mapping matrix, and converting it into bending stress and torsional stress; Step 3, determining the equivalent stress, principal stress surface direction angle, and rotation rate; Step 4, calculating and correcting the average equivalent stress per revolution; Step 5, calculating the load concentration factor based on the assembly misalignment angle and angular position, generating a dual-sector weight core, and combining it with the rotation rate to obtain a follow-up amplification factor; Step 6, integrating the corrected stress, weight core, and amplification factor to obtain the cumulative damage per revolution; Step 7, determining the life by accumulating multi-revolution damage, and estimating the remaining life revolutions and time if no failure occurs. This invention achieves accurate prediction of the fatigue life of hinged couplings under complex working conditions.

The invention provides a deep rock mass stress state characterization method based on rock strength nondimensionalization, and belongs to the field of rock mechanics engineering. The method comprises the following steps: firstly, acquiring true three-dimensional stress of a rock mass and basic mechanical parameters of the rock, then carrying out dimensionless processing on principal stress according to the ratio of stress to rock strength parameters, and constructing a stress difference coefficient based on dimensionless stress difference to represent the three-dimensional stress non-uniformity. According to the method, the absolute magnitude of stress, the strength closeness and the three-dimensional stress non-uniformity can be reflected at the same time, and a universal and scientific evaluation system is provided for deep rock mass health evaluation, dynamic disaster prediction and underground engineering design.

This invention provides a magnetic measurement method for planar vector stress, relating to the field of stress testing technology for iron-based materials. The method includes: obtaining the principal stress difference between the maximum and minimum principal stresses of the iron-based specimen; obtaining the principal stress sum of the maximum and minimum principal stresses of the iron-based specimen; and combining the principal stress difference and the principal stress sum to obtain the maximum and minimum principal stresses. This invention can directly obtain the precise values ​​of the maximum and minimum principal stresses, as well as the directions of the principal stresses, avoiding subsequent calculation errors and cumulative errors. It solves the problem that existing calculation methods can only determine the principal stress direction angle and the principal stress difference.

The invention discloses an underwater robot depth and course control system, which relates to the technical field of underwater robots, and is characterized in that an equivalent strain energy anomaly index and a local maximum principal stress anomaly index are extracted through a structure-heat-fluid coupled three-dimensional finite element simulation model, and a failure risk prediction model is constructed by using a machine learning model; taking the comprehensive feature vector as input, and outputting a sealing structure failure prediction coefficient as a basis for dynamically adjusting a control strategy; the system limits or optimizes the propeller power, buoyancy adjusting frequency and course angle change rate in real time according to the failure prediction coefficient of the sealing structure so as to reduce the structural load and delay the fatigue process, a prediction model is continuously optimized through an error sample driven incremental learning mode, closed-loop self-learning and self-adaptive evolution of the control system are achieved, and the system reliability is improved. Therefore, the operation safety and the task execution stability of the underwater robot in the complex deep sea environment are improved.

The tunnel lining reliability evaluation method considering space-time coupling provided by the application comprises the following steps: based on the target tunnel site geological survey data, a probability distribution model of a karst cave radius is established; based on the probability distribution model of the karst cave radius, a quantile sampling method is used to generate a plurality of karst cave radius samples; the karst cave radius samples are input into numerical simulation software to simulate and calculate the minimum principal stress value of the tunnel vault lining under different karst cave radii; based on the karst cave radius samples and the minimum principal stress, a function relationship fitting model between the karst cave radius and the minimum principal stress is established; based on the probability distribution model of the karst cave radius and the function relationship fitting model, a stress ratio probability distribution model is derived through a random variable function distribution conversion method; a strength degradation time-varying model of concrete under the action of freeze-thaw cycles under different stress ratios is established; based on the stress ratio probability distribution model and the strength degradation time-varying model, the marginal failure probability of the tunnel lining is calculated by coupling using a total probability formula.

The invention discloses an external prestress design method and system combined with a shield segment pre-embedded sliding groove, and the method comprises the steps: after the shield segment is assembled, anchoring a steel beam at the outer side of the segment through the sliding groove, arranging a plurality of displacement sensors along the segment pre-embedded sliding groove, obtaining the actual displacement data of the steel beam at different tensioning stages, and calculating the actual displacement data of the steel beam; calculating the relative slippage displacement between the steel beam and the sliding chute at a certain position along the direction of the sliding chute; according to initial prestress tension applied to the tensioning end and the relative slippage displacement, effective prestress tension transmitted to the duct piece through the steel beam at a certain position in the sliding groove direction is calculated, and according to the effective prestress tension, the maximum forward main stress of the section at the certain position in the sliding groove direction is calculated; and according to the relative slippage displacement and the maximum forward principal stress, setting a comprehensive design objective function, and adjusting a design variable to enable the comprehensive design objective function to be optimal.