56 results about "Stress ratio" patented technology

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 discloses a PMCR assembly type refrigerating machine room construction simulation optimization method and system, and relates to the technical field of construction simulation, and the method comprises the steps: S1, collecting machine room construction stress data and machine room refrigeration data, and carrying out the preprocessing of the collected data; s2, constructing a coordinate system, forming an initial data set of the structural units, carrying out quantitative evaluation on the stress safety of each structural unit, and dividing stress intervals; s3, a stress ratio data set is solved, stress interval checking is completed, the refrigeration risk is evaluated, and grading instructions are generated for all stress intervals; and S4, when a construction risk prompt instruction is received, generating an initial hoisting passage path sequence, evaluating passage feasibility of each path control point, generating a final hoisting passage path, and outputting a final construction adjustment scheme. The problems that an existing machine room model is emphasized in completion display and operation and maintenance and lacks construction stage modeling and stress simulation, so that the hoisting safety margin is insufficient, and the hidden danger of local cracking of components is caused are solved.

The invention discloses a deep learning-based large deformation prediction method for a high ground stress soft rock tunnel, and belongs to the field of tunnel engineering geological disaster prediction. By constructing a double-branch network architecture of'geological mode identification-deep learning prediction ', accurate prediction of large deformation of the tunnel is realized. The method comprises the following steps: firstly, collecting six qualitative indexes such as a rock mass structure, a weathering degree and an underground water condition and three quantitative indexes such as a strength-stress ratio, support rigidity and an equivalent hole diameter, performing encoding and normalization preprocessing, and respectively inputting the indexes into an upper-layer network and a lower-layer network; outputting probability distribution of six types of modes prone to large deformation, such as a weak homogeneous type mode and a block crack structure type mode; and the lower layer predicts the deformation and divides risk levels through a full-connection neural network based on the geological mode identification result and the quantitative index. According to the method, the complex coupling mechanism of large deformation of the high-crustal-stress soft rock tunnel can be fully reflected; adaptability prediction is realized for different geological modes.

The invention relates to the technical field of intelligent optimization design, in particular to a bridge prestressed steel beam intelligent optimization design method based on multi-factor coupling, and the method comprises the steps: carrying out the quantitative modeling of a plurality of parameters in the arrangement process of a bridge prestressed steel beam, achieving the precise expression of controllable variables, and improving the design precision of the bridge prestressed steel beam. The overall search capability of the arrangement scheme under multi-target tradeoff is enhanced, the rationality and stability of steel beam distribution are integrally improved, the structure local overload risk is reduced, an energy function sequence is constructed through indexes such as a midspan displacement value, a section stress ratio and the total length, the quality of a solution set is controlled by utilizing an energy difference value, intervention and screening of a residual value are introduced, and the stability of the structure is improved. The robustness of the design under the multivariable condition is enhanced, through logic judgment of displacement and counterforce, unqualified arrangement is eliminated, feasible arrangement output under structural consistency is achieved, structural efficiency and material use economy are enhanced, and design reliability, optimization solution efficiency and structural response control precision are remarkably improved.

This invention discloses a rapid assessment method for hydrogen damage in ultra-long-life structures under alternating loads, relating to the field of materials performance evaluation. The method includes the following steps: S1: Analyzing the service conditions of typical ultra-long-life structures and key components to determine the service environment of key component materials; S2: Conducting ultra-high cycle fatigue tests under different stress ratios to obtain stress-life data for different lifespans; S3: Observing the fracture morphology of high-cycle fatigue and ultra-high cycle fatigue samples using scanning electron microscopy; S4: Performing hydrogen element detection to obtain the hydrogen content distribution around micro-defects; S5: Using the Basquin formula, piecewise linearly fitting the S-N data for the high-cycle fatigue and ultra-high cycle fatigue stages to obtain the slopes of two fitted lines; S6: Using the ratio of the slopes of the two fitted lines as the hydrogen damage factor. The method disclosed in this invention can achieve rapid assessment of hydrogen damage in long-life structures under alternating loads while ensuring the reliability of the assessment results.

This invention relates to a design method for reinforcing rock mass structures with small-diameter piles under post-load conditions in the field of slope protection. The method first obtains the inclination angle θ of the outward-dipping structural surface, the internal friction angle and cohesion c, the sliding mass weight γ, the sliding mass height H, the stress ratio n between the pile and the rock mass at the structural surface, the vertical load q applied to the upper part of the sliding mass after the construction of a single deeply embedded small-diameter anti-slide pile, the sliding mass width b, and the horizontal extension length l. Then, using these parameters, it calculates the initial axial force of the deeply embedded small-diameter anti-slide pile before sliding, the deflection angle of the deeply embedded small-diameter anti-slide pile when the anti-slide force is at its maximum, the minimum compressive stiffness of the small-diameter anti-slide pile, and the axial force and anchorage length of the deeply embedded small-diameter anti-slide pile caused by compression after minor deflection deformation at the structural surface. This invention saves resources compared to empirical design methods.

The application belongs to the field of structural strength design, and relates to a helicopter metal moving part high-cycle fatigue damage evolution method considering load sequence. The method comprises the following steps: according to a high-cycle fatigue damage model considering stress ratio and load sequence effect, based on finite element theory, evaluating a high-cycle fatigue damage evolution process of a helicopter rotor metal structure under variable amplitude loading, and predicting a high-cycle fatigue life.

This invention discloses a concrete mix design and manufacturing method for underground engineering concrete in a coupled environment of underground environment and load, relating to the field of underground engineering concrete technology. It aims to address the problem that traditional concrete mix design does not fully consider the coupling effect of underground environment and load. The underground environment includes groundwater erosion, wet-dry cycle, and temperature fluctuation; the load includes stress ratio. α s Dynamic load frequency and dynamic load amplitude α d This leads to technical problems such as insufficient erosion resistance, crack resistance, and mechanical stability of concrete, resulting in a short service life. This mix design is based on quantitative analysis of coupled environmental parameters. With cement, composite admixtures, recycled aggregates, modifiers, water, and additives as core components, the basic mix proportion is determined through a mapping model between "environment-load" coupled parameters and component content. The target mix proportion is then obtained through orthogonal experimental optimization. The manufacturing method includes four core steps: raw material pretreatment, graded mixing, gradient curing, and coupled environmental simulation curing.

The invention relates to a saturated sand dynamic constitutive model construction method considering pore pressure fluctuation growth, which comprises the following steps: determining total pore water pressure including residual pore pressure component and transient pore pressure component, and constructing a normalized stress ratio skeleton curve independent of a pore pressure state; correcting the total pore water pressure to obtain corrected pore water pressure, and updating the average effective stress at the current moment by using the corrected pore water pressure; coupling the normalized stress ratio skeleton curve and the updated average effective stress to obtain a maximum shear stress value; the maximum shear stress value is used as a target state point, a dynamic virtual hysteretic curve is constructed, the stress-strain behavior of saturated sandy soil is described, accumulated damage and alternate shear shrinkage-shear expansion effects of a soil body in the cyclic loading process can be effectively considered, a pore pressure development curve and cyclic shear stress-strain response which better conform to the test rule are captured, and the test accuracy is improved. And a valuable tool is provided for evaluating the response and liquefaction strength of the saturated sand under the undrained cyclic loading condition.

The invention belongs to the technical field of metallurgy, and particularly relates to a 420 MPa-grade wind power steel welded joint with the fatigue grade of DC112 and a preparation method. According to the 420 MPa grade wind power steel welded joint, under the tension-tension fatigue test condition that the stress ratio R is equal to 0.5, after 2 * 106 times of cyclic loading, the fatigue strength of the 420 MPa grade wind power steel welded joint reaches 112 MPa, and the strict requirement for the DC112 grade fatigue grade in the international standard DNV-ST-0126 is completely met. The performance index is obviously superior to the prior art level, and key technical support is provided for high-reliability design and light-weight manufacturing of a wind power tower tube structure.

The application discloses a high-stress soft rock tunnel large deformation prediction method based on deep learning, and belongs to the field of tunnel engineering geological disaster prediction. Through the construction of a double-branch network architecture of "geological pattern identification-deep learning prediction", the accurate prediction of tunnel large deformation is realized. First, six qualitative indexes such as rock mass structure, weathering degree and underground water condition and three quantitative indexes such as strength stress ratio, support stiffness and equivalent hole diameter are collected, and after coding and normalization preprocessing, they are respectively input into the upper and lower networks: the upper layer adopts a convolutional neural network to identify the surrounding rock geological pattern, and outputs the probability distribution of six types of large deformation modes such as soft homogeneous type and block structure type; the lower layer predicts the deformation amount and divides the risk grade through a fully connected neural network based on the geological pattern identification result and the quantitative index. The application can fully reflect the complex coupling mechanism of high-stress soft rock tunnel large deformation; and adaptive prediction is realized for different geological patterns.

The application discloses a steel structure installation measurement method, which comprises the following steps: establishing and maintaining a hierarchical dynamic measurement reference system, wherein the system comprises at least one fixed first-level absolute reference and one second-level partition dynamic reference arranged on a body of an installed steel structure; arranging strain sensors at key positions of the steel structure to monitor stress changes of the components in the installation process in real time; taking the second-level partition dynamic reference as a reference, measuring the geometric pose of a component to be installed; meanwhile, comparing real-time stress data obtained in the second step with theoretical expected values; and coupling analysis is performed based on the geometric measurement result and the stress comparison result in the third step, including generating adjustment suggestions for the geometric pose of the component when the stress deviation exceeds an allowable threshold, so that the installation tends to be in a low-stress natural state; and the target pose of the component installation is a predicted installation shape obtained based on simulation analysis and calculation of a construction process, and the shape is an intermediate state of the structure after bearing subsequent loads and deforming to tend to a design shape.

The invention belongs to the technical field of aviation electromechanics, and particularly relates to a method for predicting the ultra-high cycle fatigue life of a hydraulic pump cylinder body through a bimetal combination process. Analyzing the key position where the hydraulic pump cylinder body is prone to fatigue faults, and determining the stress condition of the key position of the hydraulic pump cylinder body; according to the geometric parameters of the key position of the hydraulic pump cylinder body, designing a test piece of an ultra-high cycle fatigue test; according to the stress form of the key position and the load-stress ratio condition, an ultra-high cycle fatigue test of the test piece is carried out; obtaining a stress-life relationship of the bimetal bonding process test piece; and predicting the service life of the hydraulic pump cylinder body structure according to the allowable safety coefficient of the hydraulic pump cylinder body structure and the stress of the key position of the structure. According to the invention, the fatigue performance verification test of the bimetallic bonding process of the hydraulic plunger pump cylinder body can be rapidly realized, and the ultrahigh-cycle fatigue strength and fatigue life evaluation of the structure in a high-temperature service environment can be realized.

The application provides a design method of an additional damping ring of an aero thin-webbed gear. The design method comprises the steps of determining initial parameters, obtaining an energy dissipation model of the gear after the additional damping ring, checking the initial parameters and adjusting the design parameters. The method can be used to determine the energy dissipation parameters of the damping ring corresponding to the actual amplitude and frequency of the thin-webbed gear with different numbers of pitch diameters and harmful resonance points, and then determine the contact pressure. By comparing whether the system amplitude ratio and the gear measuring point stress ratio meet the conditions, the damping performance of the damping ring can be effectively improved.

The application provides an aero-engine part creep-fatigue life design method. A part finite element model is established, mission profile stress analysis is carried out to obtain the principal stress cycle peak stress σ max and the principal stress cycle stress ratio R of the dangerous position of the part; a creep-fatigue interaction judgment criterion is established by using the relationship between (1-R)*σ max and twice the material proportional limit 2σ s ; a creep-fatigue damage interaction envelope line of the part is established; the creep-fatigue life of the dangerous position of the part is calculated based on the relationship between (1-R)*σ max and 2σ s . The relationship between (1-R)*σ max and 2σ s is used as the judgment criterion, the constraint relationship of temperature and load on the creep-fatigue interaction effect is comprehensively considered; the creep-fatigue interaction damage limit with reliability indexes is determined through the interaction damage envelope line with specific confidence and survival rate requirements; the creep-fatigue life calculation method considers the influence of stress relaxation on creep damage and fatigue damage in the cycle process, and the applicability of the analysis method under different stress states is ensured.

The application discloses a kind of baffle type stability discrimination method of one-word steel plate concrete composite wall component. The stability parameters of the component in plane and out of plane are obtained by calculating and processing the wall component, and the initial stability stress ratio of each is obtained by initializing calculation. The final stability stress ratio is obtained by iterative cycle processing according to the current stability stress ratio. The stability discrimination result of the wall component is obtained by judging and processing the final stability stress ratio obtained by the iteration of in-plane and out-of-plane. The stress ratio initial value formula considering the stability coefficient is introduced by the strength formula stress ratio analytical solution, which greatly improves the iteration efficiency, and the numerical differential form is used to gradually approach the stability stress ratio, which has faster convergence speed.

The invention belongs to the technical field of bridge engineering safety monitoring, and relates to a method for intelligently evaluating structural stability in a bridge demolition process. The method solves the problems of inaccurate structural stability evaluation and poor real-time performance in an existing demolition process. The scheme comprises the following steps: establishing an initial finite element model to simulate a demolition process, calculating stress and displacement of each stage, and determining a sensitive area; a sensor is installed for real-time monitoring, data are collected and compared with a model calculation value, a recursive least square method is adopted for adjusting the material elasticity modulus and the support rigidity parameter, and a correction model is obtained; and simulating the next dismantling operation based on the current progress, calculating a stress ratio and a displacement ratio, and triggering an alarm when the stress ratio is greater than 0.8 or the displacement ratio is greater than 1.0. The method is mainly used for real-time safety assessment and early warning of bridge demolition engineering, and construction safety is guaranteed.

A structural fatigue life prediction method considering strength degradation effect, wherein the method includes: obtaining strain-time data of the structure under at least one working condition; converting the strain-time data into a stress spectrum; processing the stress spectrum by using a nonlinear cumulative damage model considering strength degradation effect to obtain the residual damage of the structure; calculating the fatigue life of the structure according to the residual damage. The invention modifies the nonlinear cumulative damage model by introducing stress ratio and strength degradation coefficient. The function is mainly expressed in exponential form, which can better reflect the degradation performance of the material. The model form is simple and it can be well applied to practical engineering. This model can be applied to the prediction of fatigue life under multi-level load, which greatly improves the prediction accuracy of structural fatigue life.

The invention belongs to the technical field of offshore converter station construction design, and provides an offshore structural pipe node lightweight design method and system based on a response surface method.The method comprises the steps that a target function is established with the minimum total weight of structural pipe nodes as the target and the condition that the ultimate strength stress ratio is not larger than a preset allowable value as the constraint condition; adopting Latin hypercube sampling to generate a series of test sample points; extracting a structure response value corresponding to each sample point; according to the structure response value, a response surface method is adopted for fitting to obtain a polynomial function; obtaining a lightweight design scheme according to the polynomial function; according to the method, a stress ratio response surface in a high-dimensional design space can be effectively fitted based on a sampled high-precision response surface model, collaborative optimization is carried out on a plurality of key design parameters of a complex pipe node on the premise of meeting safety specifications, constraint conditions of different diagonal bracings are met, structural redundancy can be accurately released, and the design efficiency is improved. And obvious weight reduction is realized on the basis of not sacrificing safety.

The invention relates to an adjusting device for a large-section steel box girder. The device comprises a base, a jack system, a force sensor monitoring system, an early warning device and a control system. The base is connected with a bracket base through a bolt; the jack system is hydraulically driven, the maximum bearing capacity is not less than 10000 KN, and the adjustable height range is not less than 10 cm; the force sensor monitoring system monitors the stress state of the adjusting device in real time; the early warning device gives out a sound-light alarm when the stress exceeds a set threshold value; and the control system adopts a PLC (Programmable Logic Controller) to accurately control the lifting of the jack. According to the method, the condition of uneven stress of the bracket can be effectively improved, the maximum stress ratio is reduced to 1.01 from 1.68, and the construction safety is improved; the number of operators can be reduced by about 50%, the single operation time is shortened by about 2 hours, and the labor intensity of offshore night operation is remarkably reduced; and an accurate adjusting means is provided for bolt welding connection construction of the large-section steel box girder, and the construction quality is guaranteed.

The invention discloses an offshore wind power pile foundation surrounding soil damage state judgment method, which comprises the following steps: S1, carrying out a soil indoor cyclic load test to obtain a cyclic shear strain cumulative diagram; S2, obtaining complex wave force load data, and converting the data into a group of cyclic shear stress ratio data ranked from small to large; s2, finding a minimum cyclic shear stress ratio and a corresponding cyclic vibration frequency, and obtaining an equivalent cyclic vibration frequency corresponding to a next cyclic shear stress ratio based on the cyclic shear strain cumulative diagram obtained in S1; repeating the same operation until a final equivalent cycle vibration frequency corresponding to the maximum cycle shear stress ratio is obtained; s3, obtaining corresponding damage vibration times under different working conditions, and obtaining a damage vibration time contour map; s4, according to the average shear stress, finding a corresponding damage vibration frequency in the damage vibration frequency contour map obtained in S3; and comparing the final equivalent cycle vibration frequency with the damage vibration frequency, and judging whether the soil body is damaged or not. According to the method, the cost is reduced, the universality is high, and the precision can be ensured.

The invention discloses a direct shear test stress detection device based on an electronic universal testing machine in the technical field of geotechnical engineering test equipment, a stress conversion device, an upper shear box and a lower shear box are mounted in the electronic universal testing machine in an up-down overlapping manner, and the stress conversion device can adjust the stress angle; according to the device, the precise displacement control function of the electronic universal testing machine can be fully utilized to realize precise adjustment of the shearing rate, so that more accurate interface mechanical parameter test data can be obtained, and through vertical force application of the electronic universal testing machine, the mechanical performance of the interface can be improved. The force in the vertical direction is accurately decoupled, and the normal force and the shear force of the test soil body can be accurately obtained by combining the tandem type three-dimensional load sensor, so that the data relevance is stronger, the stress analysis of the soil body is facilitated, and the test accuracy is improved. Therefore, the device simulates the real working conditions of non-constant stress ratio in projects such as pile-soil interface lateral loading and retaining wall gradual sliding.

Disclosed is a 500 MPa-grade wind power steel having high strength, toughness and high crack arrest toughness, comprising the following alloy components in percentage by mass: 0.06-0.09% of C, 0.20-0.60% of Si, 1.48-1.80% of Mn, 0.15-0.30% of Ni, 0.02-0.04% of Al, 0.02-0.08R of Nb+V+Ti, 0.2-0.4% of Cr, 0.01-0.02% of Cu, 0.01-0.03% of Zr, P≤0.008%,,S≤0.003%, and the balance being Fe and other inevitable impurity elements. The present invention is based on a low-carbon equivalent composition design. The microstructure of the resulting steel plate is a heterogeneous structure composed of coarse quasi-polygonal ferrite and fine acicular ferrite. The steel plate has a thickness of 20-60 mm, a yield strength ≥ 500 MPa, a tensile strength ≥ 660MPa, a percentage elongation after fracture ≥ 20%, an impact energy at -40ºC ≥ 250 J, a CTOD value at -20ºC ≥ 0.8 mm, a fatigue strength > 640 MPa under the conditions of a stress ratio of 0.5 and 107 cycles, and a critical crack length > 25 mm when fatigue failure occurs. The present invention can meet the development requirements of wind power steel.

The application discloses a kind of high-throughput test methods for fatigue resistance of additive remanufacturing axle, comprising: establishing the finite element model of full-size axle-wheel assembly, taking the characteristic stress value of the target additive remanufacturing area on the surface of additive remanufacturing axle under the load condition required by full-size axle performance test specification;Establish the finite element model of test sample and prepare the test sample;The upper surface and the lower surface of the test sample are respectively symmetrically provided with two test sections, and unloading grooves are respectively formed on the two sides of each test section;Loading simulation is carried out on the test sample model, and the displacement value of the test sample model is determined when the determined characteristic stress value is reached;The determined displacement value is used as the core displacement control parameter, the actuator of the fatigue testing machine is used to apply alternating load with a stress ratio of-1 to the test sample to simulate the rotary bending stress state of the axle, and the test of the test sample is carried out.

The present application provides a kind of water pressure fracturing three-dimensional stress calculation method considering borehole inclination angle, it is related to rock mechanics and water pressure fracturing engineering technical field, the present application is by collecting geological feature data, and the elastic stiffness index of rock mass is generated in combination with these data, stress ratio index and inclination depth index, form a comprehensive feature vector, establish water pressure injection model, the feature vector is as input, predict the three-dimensional ground stress when fracture occurs, based on the three-dimensional ground stress of model output, in combination with borehole inclination angle, calculate the vertical stress and horizontal stress of rock mass, judge whether stress is overproof, if it does not exceed threshold value, adjust borehole inclination angle, until stress is overproof and record the real water pressure fracturing three-dimensional ground stress.The present application is by collecting geological feature data, generating rock mass feature vector, and based on water pressure injection model, predict three-dimensional ground stress, realize the accurate calculation of water pressure fracturing three-dimensional ground stress of inclined borehole.

The invention relates to a design method for steel plate crack damage additive manufacturing single-side repair, which comprises the following steps of: setting geometric and material parameters of a crack damage steel plate and a repair body, and determining a load state to calculate von Mises stress distribution of the steel plate under an undamaged condition; then, calculating the maximum reference semi-elliptical section of the restoration body in the direction perpendicular to the crack based on the thickness, the strength ratio and the crack width of the steel plate; determining the overall length of the restoration body along the crack direction according to the crack length; and finally, in combination with the maximum reference section and the stress distribution, calculating the variable cross-section size distribution of the restoration in the crack direction through a stress ratio function, and generating a semi-elliptical variable cross-section three-dimensional restoration model matched with the internal stress of the steel plate. Compared with the prior art, the method solves the problems that when the crack damage of the steel structure is repaired through metal additive manufacturing, a restoration body lacks a unified geometric description model, and calculation and design are not reliable.

The invention discloses a dynamic fracturing-grouting combined reinforcement construction method suitable for broken surrounding rock, which comprises the following steps: acquiring a brittleness index, rock mass integrity, a crack development index and a crustal stress ratio of the surrounding rock, and calculating a comprehensive fracturing index according to the brittleness index, the crack development index, the rock mass integrity and the crustal stress ratio; according to the comprehensive fracturing indexes, the strata are divided into four grades including the extremely-easy fracturing grade, the fracturing grade, the difficult fracturing grade and the extremely-difficult fracturing grade; drilling holes are arranged according to stratigraphic division grades; monitoring sensors are arranged in the drill holes, and a real-time fracturing-grouting dynamic regulation and control system is established; a mixed solution of fracturing fluid and a propping agent is pumped into the well, fracturing operation is conducted, high-pressure fluid forms a crack in rock and enables the crack to extend, the propping agent is embedded into the crack face to resist the ground stress closing effect, the wellhead pressure, the injection volume and the pumping rate are monitored in real time in the whole process, and it is ensured that the fracturing process is stable and controllable; and grouting parameters are adjusted and controlled in a self-adaptive mode.

The present application relates to the technical field of power transmission line disaster prevention and mitigation, and specifically provides a method and device for field measurement and evaluation of the stress state of a tower, comprising: determining dangerous members on the tower based on the stress ratios of the members of the tower; determining the average stress of the cross section of each preset measurement position at the maximum stress position of the dangerous member based on the strain values of the cross section of each preset measurement position at the maximum stress position of the dangerous member; and evaluating the safety of the stress state of the tower based on the average stress of the cross section of each preset measurement position at the maximum stress position of the dangerous member. The technical solution provided by the present application can measure the stress state of the tower in a more direct and accurate manner, thereby providing basic data support for tower safety early warning and avoiding the use of indirect load monitoring methods that introduce excessive errors and cause distortion in tower safety early warning.

This invention discloses a physical-data fusion-based method for rapid stress spectrum modeling and fatigue life prediction of bridge cranes, belonging to the field of crane structure safety assessment technology. Addressing the problems of low efficiency in traditional finite element stress calculation, the lack of consideration for the influence of variable stress ratios in conventional crack propagation models, and unreasonable handling of multiple alternating loads in a single working cycle, this invention establishes a stress sample library by building a finite element model of the crane's main beam and uses a gradient boosting decision tree model to achieve rapid stress prediction at critical points. Based on measured load spectra, the maximum and minimum stress values ​​of a single cycle are extracted to generate a stress spectrum. The Walker formula is used to correct the crack propagation rate, and the life prediction is completed by combining a periodic sample cycle method. This invention improves the efficiency of stress spectrum acquisition, ensuring that the stress spectrum compilation closely reflects actual service conditions, while correcting the life prediction deviation caused by variable stress ratios. It can be used for fatigue safety assessment and life prediction of in-service bridge crane metal structures, demonstrating high engineering practicality.