60 results about "Static stress" patented technology

A method for virtual fatigue testing includes reading a coarse-grid finite-element-model of a component from one or more libraries with a computer, and identifying static stress locations neighboring at least one of fasteners and non-fastener stress concentration regions in the component by a static analysis of a component intermediate-grid finite-element-model of the component, identifying hot spot locations in the component intermediate-grid finite-element-model by performing a fatigue screening on the component, generating details for the component intermediate-grid finite-element-model based on the hot spot locations, and predicting crack results by a deterministic durability-and-damage-tolerance analysis of the details for a component fine-grid finite-element-model of the component, calculating a crack margins for the component fine-grid finite-element-model by a probabilistic durability-and-damage-tolerance analysis of the crack results, and generating an output file that contains the final crack initiation margin and the final crack growth margin.

The invention provides a bridge structure monitoring system and method combined with active early warning, and the method comprises the steps: obtaining dynamic stress data and static stress data of each bridge monitoring point in a bridge section, and constructing a plurality of fatigue stress spectrums according to the dynamic stress data of each bridge monitoring point; determining a damage accumulation coefficient of a bridge structure at each bridge monitoring point according to a stress distribution difference between the fatigue stress spectrums, and extracting a plurality of monitoring key points by combining all the damage accumulation coefficients with dead load characteristics of a bridge section; determining the rigidity of the bridge structure corresponding to each monitoring key point according to the static stress data of each monitoring key point, and determining a confidence interval for performing active early warning on the structural damage of the bridge section according to all the rigidity of the bridge structure; and performing structural damage early warning on the bridge section based on the confidence interval and the current bridge stress at each bridge monitoring point. Accurate early warning of bridge structure damage can be realized under the influence of multi-dimensional load response.

The invention provides a deep coal seam roadway surrounding rock stability intelligent early warning method, and relates to the technical field of coal mine dynamic disaster prevention and control. According to the intelligent early warning method for the stability of the surrounding rock of the deep coal seam roadway, a basic sample library is constructed through a dynamic and static combined loading rock test; synchronously collecting field surrounding rock static stress and micro-seismic data and carrying out time sequence polymerization; constructing an equivalent dynamic and static combined stress index based on a dynamic and static load superposition principle, and forming a seismic-force coupling feature vector; establishing an LSTM early warning model, adopting a transfer learning strategy, pre-training by using laboratory data, and then performing fine tuning by using field data; inputting the real-time feature vector into a model and outputting an instability probability; and verifying and correcting the probability based on actual deformation data of the surrounding rock, and applying a missing report sample to online incremental updating of the model. According to the method, the dynamic and static load coupling effect is quantified, the difficulty of small sample training is overcome, and accurate and self-adaptive early warning of the deep roadway surrounding rock instability risk is realized through a physical feedback closed-loop correction mechanism.

The invention provides a rotary steering fatigue life prediction method and system considering dynamic characteristics, and the method comprises the steps: building a three-dimensional structure model based on a set target test structure, analyzing dangerous points based on a statics finite element simulation model in combination with a set test well section, and determining the static Mises stress of each point; introducing a dynamic boundary load to construct a dynamic finite element simulation model, and analyzing the dynamic Mises stress of each point; calculating a dynamic load addition coefficient of each point according to the dynamic maximum stress and the static stress; in addition, dynamic load characteristics at all points are analyzed from multiple aspects of bit pressure, torque and bending moment; analyzing fatigue characteristics according to the material of the structure corresponding to the dangerous point; and designing a linear damage accumulation operation model, integrating the calculation results to calculate a fatigue index value for multiple input rounds, and further determining the fatigue life of the whole string of tools. According to the scheme, the defects of incomplete operation angles and insufficient accuracy in the prior art can be overcome, and accurate prediction is realized by fully considering dynamic load characteristics and material characteristics of different structures.

The invention discloses a method and a device for determining assembly fastening force of a bolt joint part, and relates to the technical field of intelligent manufacturing. The method comprises the steps that three-dimensional point cloud measurement data of a target joint surface are acquired, and the three-dimensional point cloud measurement data comprise geometric distribution error data and / or position error data; generating a target digital twin model according to the target three-dimensional point cloud measurement data; according to the target digital twin model, stress states of a target joint part corresponding to the target joint surface are simulated, and the stress states comprise a static stress state and / or a dynamic stress state; and according to the stress state simulation information, determining a target assembly fastening force of the target joint part. According to the method, the manual dependence degree in the bolt joint part assembling fastening force determination process can be reduced, so that the labor cost in the bolt joint part assembling fastening force determination process is reduced, and the determination precision and the determination efficiency of the bolt joint part assembling fastening force can be improved.

The invention relates to a blade Goodman curve correction method, device, equipment and medium considering crystal orientation and a multi-axis stress state, and relates to the technical field of mechanical engineering.The method comprises the steps that a blade Goodman curve is determined based on a correction coefficient obtained through a blade vibration fatigue test and a blade material Goodman curve; static stress and modal stress of the blade under different rotating speeds and maximum displacement and vibration frequency of a blade body under different modals are obtained; calculating allowable vibration stress according to the blade Goldman curve and the static stress, and determining the allowable vibration stress of each point on the blade at different rotating speeds; determining a dynamic stress reserve coefficient corresponding to each point on the blade; according to the circumferential displacement of a sensor preset on the blade at the corresponding position on the blade, the minimum value of the dynamic stress reserve coefficient, the maximum displacement of the blade body and the vibration frequency, limit value calculation is conducted, and the blade amplitude limit value corresponding to the blade is determined. The accuracy of the blade amplitude limit value in the blade stress state monitoring process can be improved.

This invention relates to the field of blade crown structure technology and discloses a method for designing the oblique cut angle of crowned blades. By defining the direction and magnitude of the oblique cut angle of the crowned blade and defining evaluation parameters for the rationality of the static design of the crowned blade, simulation models of crowned blades with different sizes and directions of oblique cut angles on the crown contact surface are constructed. Static analysis is performed on the simulation models, and the oblique cut angle and magnitude of the contact surface are determined based on the static evaluation parameters. This invention solves the problems of excessive static stress in the blade due to pre-twist during assembly of crowned blades and crown misalignment due to rubbing. In particular, it addresses the following issues: for short blades with crowns and small aspect ratios and large torsional stiffness, even a small pre-twist angle design can still result in excessive stress. Reducing the pre-twist angle makes it difficult to ensure that the pre-twist angle tolerance meets requirements during processing and assembly. Using traditional improvement methods requires significant modifications to the blade, limiting engineering applications and affecting other blade performance.

The invention relates to the field of blade damping design, in particular to a blade root collision damping design method. Performing finite element analysis on the blade structure, and determining a non-bearing surface area of the blade root of the blade; performing finite element analysis on the wheel disc structure to determine a non-bearing surface area of the wheel disc; according to the non-bearing surface area of the blade root or the non-bearing surface area of the wheel disc, a damping groove position structure is designed; according to the position structure of the damping groove, the appearance and the placement mode of the collision damping body are designed, and it is ensured that the collision damping body has a collision gap in the damping groove; the blade-wheel disc containing the damping grooves and the collision damping bodies is assembled, and an assembly body is obtained; according to the method, static stress and modal analysis is conducted on the blades and the wheel disc, the non-bearing surface area is recognized, it is guaranteed that the structural strength of the blades is not affected by forming of the damping grooves, interference on the blades is further reduced, and the integrity and fatigue life of the blades are guaranteed.

A method for fatigue hot spot screening includes identifying multiple static stress locations neighboring one or more fastener locations and multiple stress concentrations in a finite-element-model of a component in response to analysis results and validated assembly-level analysis results with a computer, generating a fatigue spectrum at each static stress location, generating multiple fatigue analysis control files in response to the fatigue spectrum, reducing the validated assembly-level analysis results, generating a first output file that contains multiple non-fastener stress concentration hot spots in the finite-element-model by a first fatigue analysis at multiple non-fastener stress concentration regions in response to the fatigue analysis control files, calculating one or more local peak stresses for the one or more fastener locations, and generating a second output file that contains multiple fastener hot spots in the finite-element-model by a second fatigue analysis at the fastener locations in response to the fatigue analysis control files.

The present invention provides a cable stress monitoring device, which relates to the technical field of cable monitoring. The device is configured to obtain the installation design data of the cable for state model analysis to obtain the stress data of the cable model; obtain the real-time stress data at the stress monitoring position, and combine the stress data of the cable model for static stress monitoring analysis to form static stress monitoring result data; perform dynamic stress monitoring analysis according to the real-time stress data and in combination with the stress data of the cable model to form dynamic stress monitoring result data; and synthesize the static stress monitoring result data and the dynamic stress monitoring result data to form the cable stress monitoring result data. The device realizes a relatively accurate and comprehensive cable stress monitoring effect through the comparative analysis of the stress model parameter data and the real-time stress monitoring data based on the design data and the force-bearing big data.

The present invention discloses a method for analyzing the thermal shock resistance of ceramic-based composite (CMC) turbine guide blades. The method comprises the following steps: first, establishing a geometric model reflecting the process characteristics of CMC turbine guide blades; second, performing transient flow-thermal coupling calculations on the CMC turbine guide blades under given operating conditions to obtain the temperature variation of the blades over time; third, defining the material properties and principal unit directions of the CMC turbine guide blades and performing meshing; fourth, performing quasi-static stress calculations on the CMC turbine guide blades using the node temperature at a certain moment as the thermal load; and fifth, performing progressive damage analysis at a typical moment to determine the damage location and failure mode of the CMC turbine guide blades. This method fills a gap in the existing thermal shock resistance analysis methods for CMC turbine guide blades, taking into account the influence of anisotropy on the thermal, mechanical, and nonlinear mechanical properties of CMCs, and accurately predicting the thermal shock damage location and failure mode of CMC turbine guide blades.

This invention provides a method and system for predicting the long-term strength of hard rock under the influence of dynamic disturbance frequency in true triaxial tests, relating to the field of deep engineering safety evaluation technology. The method includes: acquiring dynamic disturbance parameters, rock compression process data, and fracture morphology data from long-term dynamic disturbance true triaxial tests; constructing characteristic curves based on the rock compression process data; performing equivalent static mapping based on the dynamic disturbance parameters and characteristic curves to obtain the equivalent static stress state under the limiting frequency condition; fitting the equivalent static stress state to obtain the predicted long-term strength value under the equivalent static condition; constructing a model based on the characteristic curves and fracture morphology data to obtain a multi-dimensional criterion score; and judging and correcting the predicted long-term strength value based on the multi-dimensional criterion score to obtain the output result. This invention achieves quantitative characterization and accurate prediction of the long-term strength under true triaxial conditions for the influence of high-frequency, long-term dynamic disturbances.

The invention discloses a construction method and device for a spindle box of a horizontal machining center, and relates to the technical field of horizontal machining centers. Static stress and inherent frequency of a saddle structure are determined according to stress analysis of a first dangerous point position; the primary optimization model of the spindle box is determined based on the static stress and the inherent frequency of the saddle structure and the additionally arranged guide rail mounting surface, and the accuracy of the primary optimization model of the spindle box is improved. Therefore, a quadratic optimization model of the spindle box is determined based on the first dangerous point position, the second dangerous point position and the strain data of the guide rail mounting surface; determining each damage event based on impact simulation of the secondary optimization model of the spindle box; determining an optimization report based on each destruction event and the corresponding destruction data; and the final model of the spindle box of the horizontal machining center is constructed based on the optimization report, the secondary optimization model of the spindle box and the corresponding form, so that the accuracy of the final model of the spindle box of the horizontal machining center is improved.

This invention relates to the field of vehicle technology and discloses a method, apparatus, device, and storage medium for determining the CAE performance of a sleeper structure. The method includes: acquiring damage parameters of the sleeper structure located inside the vehicle; determining CAE performance analysis materials based on the damage parameters of the sleeper structure; setting static stress-stiffness analysis conditions for the upper and lower sleepers based on the damage parameters of the sleeper structure; and analyzing the CAE performance of the sleeper structure based on the static stress-stiffness analysis conditions for the upper and lower sleepers. By determining the CAE performance analysis materials based on the damage parameters of the sleeper structure located inside the vehicle, and then performing analyses on the set static stress-stiffness analysis conditions for the upper and lower sleepers respectively, the accuracy of analyzing the CAE performance of the sleeper structure can be effectively improved, and the development cycle and cost can be reduced.

The invention discloses a coal mine adjacent goaf roadway surrounding rock load determination and impact instability judgment method, which comprises the following steps: establishing an adjacent goaf working face initial pressure and full mining stage working face roof structure model, an adjacent goaf working face initial pressure and full mining stage working face roof three-dimensional model and adjacent goaf roadway three-load superposition schematic; the adjacent goaf roadway surrounding rock load-bearing characteristics and the roof fracture load transfer rule of the adjacent goaf working face at different mining stages are analyzed; a method for calculating lateral static load stress of an adjacent goaf, advanced static load stress of the adjacent goaf and fracture dynamic load of an overlying thick and hard rock stratum borne by surrounding rock of the adjacent goaf roadway in different mining stages of the adjacent goaf working face is provided, and the load bearing state of the surrounding rock of the adjacent goaf roadway is quantitatively represented; according to the method, the adjacent goaf surrounding rock impact instability criterion is provided, the adjacent goaf surrounding rock stability is theoretically analyzed, the adjacent goaf rock burst prevention and control thought and method are analyzed based on the impact instability criterion, and the method has important theoretical and practical significance on adjacent goaf rock burst prevention and control.

The invention discloses a sealing performance evaluation method and device of a sealing structure, relates to the technical field of liquid rocket engine research, and aims to solve the problem of poor accuracy of sealing performance evaluation of the sealing structure in the prior art. The method comprises the steps of obtaining static stress load data of a target sealing flange structure in a target liquid rocket engine; based on the static stress load data, determining wear parameters between a soft coating and a flange contact surface in the target sealing flange structure by using a soft coating friction wear analysis model; the soft coating frictional wear analysis model is an analysis model obtained by at least performing grid ALE self-adaption on a grid corresponding to a soft coating of a target sealing flange structure in the two-dimensional axisymmetric finite element model and setting a grid node motion control mode; based on the wear parameters, evaluating the sealing performance of the target sealing flange structure; therefore, the accuracy of evaluating the sealing performance of the sealing structure is improved.

The present invention belongs to the technical field of gear design and analysis, and discloses a gear tooth root crack simulation analysis method based on high-cycle fatigue testing. The method comprises the following steps: fixing a test spur gear on a high-frequency fatigue testing machine via a fixture; performing a fatigue test on the test spur gear and collecting vibration signals and image data; analyzing the data to obtain test crack path data L1 and initial crack angle; establishing a finite element simulation model, performing static stress simulation to obtain stress distribution and extract the position of maximum bending stress at the tooth root; establishing a tooth root bending fatigue crack propagation simulation model to obtain simulated crack propagation path data L2; adjusting the crack implantation position and initial crack propagation angle parameters in the crack propagation simulation model, and repeating the simulation until an error condition is satisfied between L2 and L1; and performing tooth root crack propagation simulation based on the optimized crack propagation simulation model. The present invention can analyze the initiation and propagation evolution of spur gear tooth root cracks under multiple working conditions.

The application provides a bridge structure monitoring system and method combined with active early warning, dynamic stress data and static stress data of each bridge monitoring point in a bridge section are acquired, a plurality of fatigue stress spectra are constructed according to the dynamic stress data at each bridge monitoring point, a damage accumulation coefficient of the bridge structure at each bridge monitoring point is determined according to the stress distribution difference between the fatigue stress spectra, a plurality of monitoring key points are extracted by combining all the damage accumulation coefficients with the dead load characteristics of the bridge section, the bridge structure stiffness corresponding to each monitoring key point is determined by the static stress data of each monitoring key point, a confidence interval for active early warning of the structural damage of the bridge section is determined by all the bridge structure stiffnesses, and the structural damage of the bridge section is early warned based on the confidence interval and the current bridge stress at each bridge monitoring point. The application can realize accurate early warning of the bridge structure damage under the influence of multi-dimensional load response.

The invention belongs to the technical field of aero-engines, and provides an aero-engine titanium alloy hollow fan blade strength evaluation method, which comprises the following steps: constructing a finite element analysis model of an aero-engine titanium alloy hollow fan blade, and analyzing the static stress distribution condition of the aero-engine titanium alloy hollow fan blade to obtain the strength of the aero-engine titanium alloy hollow fan blade. Identifying a stress concentration area in the titanium alloy hollow fan blade of the aero-engine; a simulation program is started, the crack initiation risk of the stress concentration area is evaluated, and the strength of the titanium alloy hollow fan blade of the aero-engine is further evaluated; according to the method, the thickness of the titanium alloy hollow fan blade of the aero-engine is optimized, so that the possibility of failure occurrence of the engine is reduced, the overall service life of the aero-engine is prolonged, and the service life of the aero-engine is prolonged. And flight safety is guaranteed.

The invention provides an ore body static stress characterization and blasting method, and belongs to the technical field of mine engineering blasting. The method comprises the following steps: testing ground stress distribution characteristics of a stope ore body by adopting a hydraulic fracturing method, and obtaining horizontal maximum principal stress, horizontal minimum principal stress and vertical stress of a plurality of measuring points in the stope ore body; establishing a three-dimensional finite element model of the stope ore body, and applying the average horizontal maximum principal stress, the average horizontal minimum principal stress and the average vertical stress of a plurality of measuring points in the stope ore body to the model for solving; calculating a static stress influence coefficient according to the solving result; dividing static stress influence degree grades according to the values of the static stress influence coefficients, and generating a static stress influence coefficient cloud picture; and determining blasting parameters of the stope ore body according to the static stress influence coefficient cloud picture and the static stress influence degree grade. According to the internal stress level and the stress difference degree of the ore body, the static stress influence coefficient is calculated for blasting parameter design, and the blasting efficiency and safety are improved.

The present invention discloses a method for determining the buffering performance of a buffer material, which belongs to the technical field of calculating the buffering parameters of buffer materials. The method comprises the following steps: determining a value range of the unit volume deformation energy of the buffer material; selecting n unit volume deformation energies within the value range; determining a set of test data for each unit volume deformation energy to obtain n sets of test data, each set of test data including static stress, the drop height of a mass block, and the thickness of the buffer material; performing a drop test based on each set of test data, and collecting the peak acceleration of the mass block during the test to obtain multiple sets of peak accelerations; determining multiple sets of dynamic stresses based on the multiple peak accelerations; and performing exponential function fitting on the multiple sets of dynamic stresses and the n unit volume deformation energies to obtain the buffering performance of the buffer material. The present invention can improve the efficiency of determining the buffering performance of the buffer material, saving time and effort.

The application discloses a dynamic-static coupling observation system based on a double-mode stress response and a data processing method, platform and storage medium thereof; a double-mode test piece is constructed by combining a transparent photoelastic matrix and a force-induced luminescence sensing layer, and strict time-sharing gate control of dynamic loading and delayed phosphorescence acquisition is realized by means of a time sequence controller, so that transient stress wave observation and static stress memory are integrated in the same system; not only the ability of a traditional photoelastic instrument to record the whole process of stress wave propagation in real time is retained, but also the fundamental limitation that the traditional photoelastic instrument cannot identify a plastic zone is broken through, and full-field quantitative distinction of an elastic zone, a plastic zone and a rupture zone is realized. Meanwhile, the phosphorescence lifetime which is not sensitive to interference is used as a main parameter to inverse stress peak value, a reliability evaluation system based on stripe quality, fitting residual error and registration error is established, and the robustness and reliability of measurement results are improved, so that an advanced observation method with complete information, high precision and mutual verification is provided for explosion mechanics and material impact damage research.

The invention discloses a whole-field stress monitoring method for an ocean engineering structure, which belongs to the technical field of cranes and comprises the following steps: step 1, arranging a strain sensor on the ocean engineering structure to obtain a measured stress value of the ocean engineering structure in a no-load state; step 2, loading loads with different weights on the ocean engineering structure respectively, and obtaining corresponding measured stress values respectively; 3, establishing a finite element model of the ocean engineering structure, and respectively obtaining simulation stress values output by the finite element model; 4, calculating an actual stress value considering the initial static stress; and step 5, collecting and measuring a stress value in real time, and outputting a full-field stress value by a Kriging model. According to the ocean engineering structure full-field stress monitoring method, the initial static strain value of the ocean engineering structure in the no-load state is obtained and used for calculating the actual stress value, the accuracy of full-field stress calculation can be improved, and then the accuracy of monitoring and evaluation can be improved.

The invention relates to the technical field of rock mechanics testing, and discloses a dynamic and static combined loading rock critical energy consumption density testing method. The method comprises the following steps: preparing and screening a rock test piece, fixing the rock test piece between an incident bar and a transmission bar of the split Hopkinson pressure bar system, and ensuring that the incident bar and the transmission bar are coaxial; applying confining pressure and axial pressure to the test piece to enable the test piece to be in a preset three-dimensional static stress state; starting the system, setting initial impact air pressure to impact the test piece, and collecting a strain signal; determining a critical impact air pressure and a corresponding critical strain signal which enable the test piece to reach a set damage state; and crushing energy consumption is calculated based on the critical strain signal, and critical energy consumption density is obtained through conversion. The method fits the actual stress scene of the rock, improves the accuracy and reliability of the test, and can provide technical support for the design and construction of underground engineering.

This application relates to the field of fatigue life prediction technology, specifically to a method and system for predicting the fatigue life of automotive seat hardware molds. The method includes: obtaining the fillet radius, sheet thickness, and load spectrum; thereby obtaining the fillet radius and sheet thickness for a batch; obtaining the static stress concentration factor based on stress analysis, and adjusting it using the fillet radius and sheet thickness to obtain the dynamic stress concentration factor; obtaining the actual equivalent stress by weighting the collected nominal stress and residual stress using the dynamic stress concentration factor; further obtaining the strain amplitude; obtaining the material fixation characteristics of the mold material, and constructing an equation using the stress characteristics, material fixation characteristics, and strain amplitude to obtain the cycle life; determining the damage value based on the cycle life to obtain the remaining fatigue life. This application improves the accuracy of fatigue life prediction.

The invention provides an anti-seismic evaluation method and device for a sluice gate of a nuclear power plant, electronic equipment and a storage medium. The anti-seismic evaluation method comprises the steps of obtaining gate structure parameters, pool geometric parameters and seismic oscillation parameters of a target sluice gate; according to the geometric parameters and the seismic oscillation parameters of the pool, calculating vertical dynamic water pressure, horizontal dynamic water pressure and liquid oscillation pressure acting on the target sluice gate; calculating the dynamic water load stress of the dynamic water load according to the vertical dynamic water pressure, the horizontal dynamic water pressure and the liquid oscillation pressure; calculating the structure inertia stress of the target sluice gate based on the water body additional mass, the gate structure parameters and the seismic oscillation parameters; the static stress of the target sluice gate under the static load is calculated according to the sluice gate structure parameters and the pool geometric parameters; calculating the target total stress of the target sluice gate according to the dynamic water load stress, the structural inertia stress and the static stress; and carrying out anti-seismic evaluation on the target sluice gate according to the target total stress. According to the invention, the calculation efficiency and accuracy of anti-seismic evaluation can be improved.

The application relates to the technical field of finite element analysis, in particular to an elevator load-bearing performance analysis method, system and equipment based on finite elements, which comprises the following steps: collecting vibration frequency, deformation displacement and total weight of a car in real time during elevator operation; analyzing vibration frequency correlation and weight fluctuation characteristics during a load interaction period from door opening to door closing, obtaining a first resonance characteristic value; analyzing weight mutation degree and deformation displacement recovery difference during the period, obtaining a second resonance characteristic value; and fusing the two characteristic values to generate a correction factor to adaptively correct the static stress of a finite element model of a load-bearing beam. The application solves the problem that existing finite element static analysis cannot capture the stress calculation deviation caused by mine elevator resonance and heavy load impact, and improves the accuracy of elevator load-bearing performance analysis.

The present invention provides a method for load analysis and low-cycle fatigue life prediction of helicopter flange bolts. The method comprises: performing load analysis based on the distribution form of the helicopter flange bolts to calculate the maximum load value of the flange bolts; calculating the maximum local stress of the helicopter flange bolts based on the maximum load value of the flange bolts, the first thread circle of the helicopter flange bolts, and the minimum cross-section of the bolt head; obtaining a method for expressing the low-cycle fatigue static stress and dynamic stress of the flange bolts based on the maximum local stress of the helicopter flange bolts; obtaining an expression for the low-cycle fatigue equivalent dynamic stress of the helicopter flange bolts based on a life model, the low-cycle fatigue static stress and dynamic stress of the flange bolts, and evaluating the low-cycle fatigue life using a full-range S-N curve.

The invention discloses a hydroelectric generating set runner static stress data rapid generation method based on a neural network. The method comprises the steps of 1, inputting hydroelectric generating set runner blade static stress data; 2, processing the hydroelectric generating set data input in the step 1; 3, constructing a static stress generation model based on the full-connection residual network; 4, training a static stress generation model; 5, calculating a relative error generated by the model, if the relative error exceeds a preset threshold value, executing the step 6, otherwise, returning to the step 4; and 6, inputting parameters of any unknown working condition and point location data on the hydroelectric generating set into the trained model to obtain static stress distribution of the rotating wheel under the unknown working condition. According to the method, the complex nonlinear relation in the data is captured, efficient and high-precision static stress prediction is achieved with few computing resources, the computing speed is increased, the hardware requirement for equipment is reduced, and an innovative solution is provided for real-time monitoring and state prediction of the hydroelectric generating set.

The present invention discloses a safety assessment method for the metal structure of hydraulic gantry cranes and bridge cranes, comprising: dividing assessment units according to the structure of the assessment object, preliminarily determining the welds and corrosion conditions by visual inspection and marking key locations in the assessment units; performing non-destructive testing on the welds at the key locations marked by visual inspection in the assessment units with the aid of special equipment; performing corrosion detection with the aid of the equipment; performing full-size three-dimensional solid modeling on the steel beam structure, and performing static analysis using ANSYS, wherein fixed constraints are added to the key structures according to the walking characteristics of the steel structures of gantry cranes and bridge cranes, and different loads are added according to actual working conditions, and after the static analysis is solved, the solution results are analyzed using a post-processing tool to determine the most dangerous stress point of the metal structure of the assessment object under each working condition; performing on-site static stress measurement; and determining a comprehensive conclusion. The present invention solves the problem of safety assessment of the metal structure of hydraulic gantry cranes and bridge cranes.