180results about How to "Improve modeling accuracy" patented technology

The invention provides a distributed computing resource smart evolution method and system based on digital twinning, and relates to the technical field of resource evolution.The distributed computing resource smart evolution method comprises the steps that a smart sensing probe is deployed at a computing node to collect operation data, a double-layer attention mechanism is used for extracting features, and a digital twinning model is constructed based on a graph neural network; a resource allocation strategy and a scheduling decision are optimized in combination with a hierarchical reinforcement learning framework, a prediction sequence is generated through an attention-enhanced sequence prediction network, and finally an optimal configuration scheme is solved by adopting a particle swarm algorithm. According to the method, the utilization rate of distributed computing resources can be improved, the energy consumption of the system is reduced, and intelligent scheduling and optimal configuration of the computing resources are realized.

The invention discloses a digital core-based reef limestone voxel dynamic merging modeling method and system, and the method comprises the steps: carrying out the CT scanning of reef limestone, and obtaining a rock mass section gray image; carrying out image processing on the rock mass section grayscale image to obtain a binary image; establishing a three-dimensional digital core model of a rock microstructure according to the binarized image; calculating a representative volume unit size according to the three-dimensional digital core model; performing dynamic combination on the spatially continuous minimum homoplastid in the three-dimensional digital core model to obtain a voxel combination result; and modeling according to the representative body unit size and the voxel merging result to obtain a reef limestone three-dimensional pore and matrix numerical model. According to the embodiment of the invention, the number of units and nodes of the model can be reduced in the modeling process, the established finite element model not only can truly reflect the pore structure characteristics of the reef limestone, but also can remarkably improve the calculation efficiency and the modeling precision, and can be widely applied to the technical field of computers.

The embodiment of the invention provides a ship automatic berthing control method and system, electronic equipment and a storage medium, and belongs to the technical field of ship control. According to the method, motion state data of a current ship and a first relative distance between the current ship and a target berth are obtained, the motion state data and the first relative distance are input into a control strategy model for automatic berthing of the ship, and the ship control quantity at the next moment is obtained. The control strategy model is obtained through training based on a reinforcement learning algorithm, that is, environment interaction data is obtained, a target function is maximized, a value network is trained according to the environment interaction data, a strategy network is trained according to the value network and the environment interaction data, and the target function represents an accumulated reward value of an action output by the strategy network; the motion represents the ship control quantity, and then a control strategy model is determined according to the trained strategy network. According to the method, the workload of ship automatic berthing and leaving algorithm modeling can be reduced, the modeling precision is improved, and the safety of the ship automatic berthing process is improved.

The invention discloses a lithium battery state estimation method based on relaxation time scale modeling, and the method comprises the steps: 1, carrying out a sudden pulse charging test on a lithium battery, collecting voltage and current data, and calculating the open-circuit voltage, direct-current internal resistance and a time-domain impedance sequence of the lithium battery; and 2, converting the time domain impedance sequence of the lithium battery into a frequency domain impedance sequence after discrete Fourier transform, establishing a fitting equation set of a distribution function of the relaxation time scale DRT of the lithium battery and the frequency domain impedance sequence, and solving by adopting a regularized least square method. And 3, taking the solved DRT model distribution function as the input of a neural network, taking the state parameters of the lithium battery as the output of the neural network, and establishing a prediction model of the state parameters of the lithium battery. According to the method, EIS test required by traditional relaxation time scale modeling is avoided, the control complexity and design cost of test acquisition equipment are effectively reduced, and the method can be effectively applied to occasions such as battery life prediction, battery classification and screening, battery echelon utilization and the like.

The invention relates to the technical field of numerical control machine tools, in particular to a numerical control machine tool digital twin model updating method and system. The method comprises the following steps: acquiring actual processing technology data; performing cutting process simulation according to the actual machining process data and the digital twin model of the numerical control machine tool to obtain cutting process data; performing tool wear state feature analysis on the cutting process data to obtain tool wear state data; updating a tool model according to the tool wear state data to obtain an updated tool model; according to the updated cutter model, dynamic contact state solving is carried out, and a dynamic contact solving result is obtained; and performing contact key data analysis on a dynamic contact solving result to obtain cutter-workpiece dynamic contact information. According to the method, the modeling precision and the simulation reliability are greatly improved, so that the digital twin model can reflect complex processing conditions more truly, and a reliable decision basis is provided for process optimization.

The invention discloses an underground water pollution path micro-analysis method based on a graph neural network. The method comprises the following steps: S1, acquiring a historical data set and a real-time monitoring data set of underground water pollution; s2, using a fuzzy membership function to represent the language level of the fuzzy variable; s3, constructing a fuzzy logic rule base based on the historical data set; s4, using a fuzzy inference system to process fuzzy variables in the historical data set; s5, constructing an underground water pollution path diagram structure model based on the historical data set and the real-time monitoring data set; s6, constructing an incidence matrix between the nodes; s7, based on the trained graph neural network model, inputting water flow velocity, pollutant concentration and geologic structure parameters in the real-time monitoring data set; s8, generating real-time prediction of a pollution diffusion path; and S9, outputting an analysis result of the groundwater pollution path. The problems that in the prior art, a pollution diffusion path is difficult to accurately predict under a complex geological structure, and real-time dynamic response is insufficient are solved.

The invention provides a multi-task federated learning client contribution degree measurement method based on model layering, and relates to a federated learning and machine learning model layering technology. According to the method, a distributed architecture of a central server and a plurality of client nodes is included, firstly, a federation learning environment and data preparation are configured, then, the central server measures the contribution degree of each client under an existing federation task, and then, the central server layers received model parameters and calculates the gradient of each layer of a model; the model layering similarity relative to the initiator client is calculated to obtain a normalized contribution vector, a new model is obtained through calculation according to the contribution vector and the data size on the client, the client participating in training in the next round is selected, and the task queue is updated. According to the method, the contribution of each client of federal learning can be accurately identified, more accurate model aggregation under layered contribution measurement is realized, meanwhile, the privacy protection effect the same as that of general federal learning is kept, the federal learning time is optimized, and the model precision is improved.

The invention belongs to the field of lunar exploration and in-situ resource utilization, and particularly discloses a lunar lava pipe three-dimensional modeling method and system, and the method comprises the steps: carrying out the fusion of multi-modal data of a lunar lava pipe, and obtaining a basic three-dimensional model; the multi-modal data comprises point cloud data collected by a laser radar, point cloud data collected by a surrounding device penetrating radar, a three-dimensional image collected by a stereoscopic vision camera and a thermal image collected by an infrared thermal imager; respectively inputting a complete area in the basic three-dimensional model into a generation model based on the CGAN and the VAE, and correspondingly obtaining two three-dimensional completion models; and carrying out weighted fusion on the two three-dimensional complementation models to obtain a complete three-dimensional model of the lunar lava pipeline. According to the method, the integrity and precision of the three-dimensional model of the lunar lava pipeline can be improved, and technical support is provided for deep detection of the lunar lava pipeline.

The invention discloses an underground three-dimensional geologic modeling method and device under multi-modal data exploration, and relates to the technical field of geologic modeling, and the method comprises the steps: carrying out the drilling data collection of a target underground region, and obtaining a plurality of drilling data sets; performing partition construction on the initial three-dimensional geological model to obtain an initial three-dimensional geological partition model; performing multi-modal data acquisition according to the plurality of geological features and the plurality of geological division areas to obtain a plurality of multi-modal data sets; and performing data processing on the plurality of multi-modal data sets to obtain a plurality of corrected multi-modal data sets, performing space-time characteristic fusion loss analysis on the initial three-dimensional geological partition model to obtain a fusion model parameter set, and optimizing the initial three-dimensional geological partition model to obtain a target three-dimensional geological partition model. The technical problem that in the prior art, when a complex underground structure is modeled, precision is insufficient is solved, and the technical effect of improving the modeling precision and reliability of the underground geologic structure is achieved.

The invention provides an aircraft simulation model checking method. The aircraft simulation model checking method comprises the following steps: S1, determining a flight mode of an aircraft operated by a pilot and recording flight data; s2, after the flight data are obtained, an airplane simulation model is established in combination with existing appearance parameters of an airplane; s3, carrying out correction and compatibility detection on the flight data and the simulation data; s4, determining and identifying an aerodynamic derivative needing to be corrected according to a compatibility detection result, and correcting the aerodynamic derivative; and S5, when the corrected data accords with the specification, exporting a final corrected aerodynamic model parameter table, and generating a debugging report. According to the airplane simulation model checking method, airplane digitization can be faster and more efficient, and the method has extremely high replicability and can be applied to various aircrafts such as manned aerial vehicles and unmanned aerial vehicles. The flight simulation model created by the method can also be applied to national defense digital software such as war simulation, flight training machines and the like, and has very practical contributions to national safety and military strength.

The invention provides an SVG controller modeling analysis method based on field experiment data, and relates to the technical field of electric power grids. According to the method, the high-low penetration fault test is carried out on the SVG, the field experiment data is obtained, the calculation data of the transient model of the SVG under different model parameters are combined, the least square method is adopted to carry out parameter identification, and the optimal model parameters of the transient model of the SVG controller are obtained. The process avoids modeling of complex topology in the SVG and laboratory communication protocol debugging, is suitable for testing of SVGs of various models, and is high in field test result accuracy, simple in wiring and extremely low in risk. A field test result can truly reflect transient response characteristics of station-level current and reactive power, and a modeling path based on the field test is opened. The SVG control characteristic extraction efficiency is improved, the model precision and modeling efficiency of the complex topology SVG are improved, and therefore the analysis efficiency of the SVG analysis process is improved.

The invention discloses a self-adaptive sampling method for aerodynamic characteristic modeling, and belongs to the field of aerodynamics. The problem that in aerodynamic characteristic modeling, an existing traditional sampling method lacks the targeted sampling capacity for a complex function area, and consequently samples are wasted is solved. According to the method, modeling is carried out for aerodynamic characteristics, a parameter interval where a complex function is located is determined through comprehensive weighting of uncertainty of Gaussian process regression and a parameter sensitivity analysis result, non-uniform sampling is carried out according to the complexity condition of the parameter interval, and targeted sampling of a complex function area is achieved; sensitivity analysis adopts a joint data mining method, and comprises two methods of a Sobol algorithm and a decision tree; according to the method, the sample utilization efficiency of small sample aerodynamic characteristic modeling is effectively improved.

The invention provides a subway air-conditioning system load prediction method and device based on passenger flow dynamic characteristics, and the method comprises the steps: firstly obtaining in-out passenger flow parameters and the average passenger flow in a plurality of past preset time periods in real time, and then taking the average passenger flow in the plurality of past preset time periods as an original time sequence, the method comprises the steps that firstly, a single-parameter grey prediction model is established, the average passenger flow volume in a future preset time period is predicted through a single-parameter grey prediction model and an original time sequence, then load type classification is conducted on loads of the subway air conditioning system, and a simplified physical model containing various load parameters is established through a multiple linear regression method according to the average passenger flow volume in the future preset time period; and finally, initializing the simplified physical model, inputting the incoming and outgoing passenger flow parameters into the initialized simplified physical model, and predicting the load of the subway air conditioning system in a future preset time period. Compared with the prior art, the method has the advantages of being short in learning time, high in universality and high in prediction precision.

The invention relates to the technical field of engineering detection, in particular to an unmanned aerial vehicle photovoltaic station geological settlement dangerous case rapid detection method and system. An unmanned aerial vehicle is used for periodically collecting and processing image data of a photovoltaic station area along an air route to obtain digital elevation models at different times; and comparing the digital elevation models at different times to analyze the settlement condition of the photovoltaic station area. By adopting the unmanned aerial vehicle photography technology, the whole-area monitoring of the photovoltaic station can be realized, the real situation of the ground feature and landform of the subsidence area can be clearly and intuitively reflected, the comprehensiveness of ground subsidence monitoring can be ensured, and the aerial photography efficiency, the modeling speed and the modeling precision are greatly improved; the problems that a traditional subsidence monitoring method is high in cost, low in efficiency and low in precision are solved.

The invention discloses a quick and automatic layout method for a warehouse logistics conveying system based on Unity 3D and CAD. The method comprises the following steps: extracting detail data of warehouse logistics conveying equipment; exporting and optimizing warehouse logistics conveying equipment detail data, and adjusting data in exported equipment detail table grids and a list arrangement sequence; the optimized details of the warehouse logistics conveying equipment are imported into Unity; and querying and analyzing data in the equipment details on the basis of a linear traversal algorithm in combination with matrix transformation, and automatically substituting corresponding equipment position information, rotation parameters and scaling into matrix transformation to complete spatial layout and attribute assignment of the warehouse logistics conveying system. Compared with an existing traditional conveying system layout technology, the data conversion step can be reduced, and data interaction of Unity3D and CAD is improved; the modeling cost is reduced, and the project economic benefits are improved; errors of spatial layout and attributes are reduced, and the model precision is improved; compared with the prior art, the layout efficiency of the conveying system can be improved by 70%-85%.

The invention discloses a robot self-modeling method, system and device based on vision and a medium. The robot self-modeling method comprises the steps that initial pictures of various joint postures of a robot and corresponding joint angles are obtained; performing data preprocessing on the initial picture to obtain a first picture; acquiring camera information of the initial picture; robot self-modeling is carried out based on a three-dimensional Gaussian splash algorithm according to the first picture of the robot in the standard state and the camera information; constructing and training an initial deformation neural network to obtain a target deformation neural network; wherein the initial deformation neural network is used for changing ellipsoid parameters of the three-dimensional Gaussian splash model according to the joint angle and camera information corresponding to each first picture of the random attitude; and combining the three-dimensional Gaussian splashing model and the target deformation neural network into a robot model, and completing self-modeling of the robot. The method does not need a depth camera, can reduce the data collection difficulty, improves the self-modeling precision of the robot, and can be widely applied to the technical field of robots.

The invention belongs to the field of robot motion control, and discloses a dynamic sliding mode motion control method for a mobile manipulator based on dynamic online identification feedforward, which comprises the following steps of: 1, designing a physical consistency linearization coupling dynamic model of the mobile manipulator; 2, designing a self-adaptive Kalman filtering algorithm based on modeling error covariance dynamic updating, and realizing high-precision online identification of the physical consistency kinetic parameters of the mobile mechanical arm; 3, designing a recursive dynamics feedforward algorithm of the mobile mechanical arm; 4, a self-adaptive over-torque dynamic sliding mode control algorithm based on recursive dynamics feedforward is designed, the continuity of the control law is guaranteed, and high-precision finite time convergence of the motion error of the mobile mechanical arm is achieved; and 5, the stability of the controller is achieved through a Lyapunov design method, a paradigm framework of robot dynamics feedforward finite time motion control is formed, and the response speed and precision of robot motion control can be effectively improved.

The invention discloses a sequence immittance modeling method and device for a network-building converter, and belongs to the technical field of power system control, and the method comprises the steps: adding voltage disturbance to an AC port and a DC port in an equivalent dual-port network of the network-building converter to be analyzed and modeled; frequency coupling analysis is carried out on a nonlinear circuit under current response of voltage disturbance to model an initial transfer function of a sequence immittance model corresponding to each frequency coupling component, interaction between network-forming converters is fully considered, the frequency coupling rule of the converters is disclosed, and the accuracy of the sequence immittance model is improved; a zero-sequence component in a circuit equation of a nonlinear circuit is removed by using a control equation of a network-forming control loop model corresponding to control loop sequence immittance to obtain a corrected sequence immittance circuit equation, so that the modeling calculation complexity can be reduced; and correcting the initial transfer function of each sequence immittance model by using the corrected sequence immittance circuit equation, and accurately carrying out linear modeling on the sequence immittance of the grid-forming converter.

The invention discloses an aurora spectral image lossless compression method based on time-space spectrum combination of Transform. A neural network based on the Transform can improve the modeling precision and the prediction accuracy; time correlation is introduced, and meanwhile, reference pixels in time, space and spectrum directions are used for prediction, so that the prediction accuracy can be improved, and redundancy can be further eliminated; and by introducing exception processing, the code rate can be further reduced.

The invention discloses a pavement crack segmentation and quantification method based on pyramid region attention, and relates to the technical field of computer vision. The road maintenance mileage is increased year by year, the capital and human input required for maintaining the road network is quite huge, and the efficient, accurate and robust pavement crack segmentation and quantification method has important significance in monitoring the pavement damage condition and reducing the road maintenance expenditure. According to the method, the long-distance dependency relationship can be effectively captured while the low calculation cost is kept, the segmentation precision of the pavement crack is improved, the crack damage rate is calculated according to the segmentation result, a basis is provided for evaluation of the road damage condition, the pavement maintenance decision-making efficiency is improved, and the maintenance expenditure is reduced.

The invention provides a harmonic source modeling method based on time-frequency feature extraction. The method comprises the following steps: firstly, determining harmonic principal component frequency of a harmonic source; extracting harmonic voltage amplitude and phase angle corresponding to harmonic principal component frequency of the harmonic source to obtain a harmonic source frequency domain feature set; reconstructing the frequency domain feature set through IDFT to form a harmonic source frequency domain feature component matrix, and splicing the harmonic source frequency domain feature component matrix with an original voltage sequence acquired by a synchronous phasor measurement device to obtain a time-frequency feature component matrix; converting the component matrix into a grey-scale map by using a matrix normalization method, and converting the grey-scale map into a three-channel time-frequency characteristic component color map by using a pseudo-color coding technology; and finally, taking the acquired harmonic source voltage data and the time-frequency characteristic component color map as the input of the model, taking the acquired corresponding harmonic source current data as the output of the model, and continuously training the network model through the actually measured data until the accurate mapping of the relation between the harmonic voltage and the harmonic current of the harmonic source is realized. And obtaining a harmonic source data driving model.

The invention discloses a short-term traffic flow prediction method based on a dynamic multi-dimensional global perception graph convolutional network, and belongs to the field of traffic flow prediction. The method comprises the following steps: acquiring an input dynamic graph feature sequence, and generating space-time element parameters; carrying out feature enhancement on the dynamic graph feature sequence, fusing the dynamic graph feature sequence with the space-time element parameters, and then respectively carrying out space-time feature coding; fusing the spatio-temporal characteristics obtained by coding the spatio-temporal characteristics; and carrying out space-time trend alignment decoding on the fused space-time features. According to the method, the defects of limited modeling precision, insufficient dynamic adaptability, incomplete spatial-temporal feature capture and the like in short-term traffic flow prediction are overcome, and the accuracy and the applicability of short-term traffic flow prediction are improved.

The invention discloses a high-precision tunnel settlement measuring and modeling method based on laser ranging and an inclination angle. The method comprises the following steps: surveying and mapping to obtain coordinates of initial positions of laser range finders and targets in a plane T; determining a measuring laser range finder and a measured laser range finder; filtering the measurement data to obtain target measurement data of a target between the measurement laser range finder and the adjacent measured laser range finder and compensation amount measurement data of the measurement laser range finder and the measured laser range finder; and calculating the coordinates of the target in one measurement period, and comparing the difference between the coordinates of the target and the coordinates of the target at the initial position to obtain the settling volume of the target. According to the method, the high-precision tunnel section can be obtained, the more the sampling points are, the clearer the contour of the tunnel section is, and the higher the modeling precision is. A measuring instrument with higher precision is adopted, the precision of the outline of the tunnel is higher when a larger number of sampling points are arranged, and the method is suitable for various tasks such as subway tunnel construction, measurement, settlement monitoring and the like.

The invention relates to the field of artificial intelligence, in particular to a mineral resource recognition model training method based on data collected by an unmanned aerial vehicle. The training method comprises the steps of collecting real geological data, training a data generation model, generating simulated geological data by adopting the trained data generation model, and training a feature extraction model and a classification model by taking the simulated geological data and the real geological data as training samples together. An existing mineral resource identification model training method based on data acquired by an unmanned aerial vehicle has the problems of low model precision and low calculation speed of a mineral resource identification model. According to the mineral resource identification model training method based on the data acquired by the unmanned aerial vehicle provided by the invention, the model precision of the mineral resource identification model is relatively high, and the calculation speed is relatively high.

According to the high-resolution seismic wave imaging method and device, on the premise that the modeling precision is improved, migration travel time errors are reduced, a one-way wave pre-stack depth Q migration technology is adopted for the first time based on a grid chromatography Q body establishment technology of structural constraints, the seismic resolution of shale oil thin layers is effectively improved, and the seismic resolution of the shale oil thin layers is improved. On the basis of high-precision grid velocity tomography, common imaging point gather frequency characteristics are picked up, Q tomography inversion is performed by using a peak value frequency shift method, fine establishment of a Q body is realized, a guide seat is mounted on a seismic wave imager, a guide rod can be mounted in the guide seat, two ends of the guide rod can be respectively connected with a bracket and a linkage rod, the linkage rod is connected to a foot stool, and the seismic wave imager is mounted on the foot stool. When the foot stool is pushed by the conical head to be opened, the guide rod can be pushed upwards, the guide rod can drive the support to move upwards, the support can push the solar panel, opening is achieved, the seismic wave imager can be rapidly placed when used, and rapid use is achieved.

The invention discloses a Grasshopper-based complex keel high-precision modeling method, which comprises the steps of S1, constructing a three-dimensional curved surface model of a curved surface where a keel center line is located; step S2, constructing a keel center line three-dimensional distribution model on the three-dimensional curved surface model in the step S1; and S3, obtaining a three-dimensional distribution model of each edge of each keel according to the offset of the three-dimensional distribution model of the central line of the keel in the step S2, and obtaining a three-dimensional solid model of each keel according to the three-dimensional distribution model of each edge of each keel. According to the method, the edge line model of the keel is obtained through the curve parameter offset method, the three-dimensional solid model of the keel is further constructed through the edge line model of the keel, and compared with an existing modeling method of point taking, lofting and stretching, the method has the advantages that since all points of the center line of the whole keel serve as target points for offset, the point taking process does not exist; fitting errors are prevented from being introduced to a large part with the curvature of the keel, and the modeling precision of the complex keel is effectively improved.

The invention relates to the technical field of industrial big data, in particular to an Internet of Things sensing and data monitoring integrated system, which comprises an Internet of Things sensing module used for acquiring a sensing parameter set of a distributed simulation unit of an intelligent power plant and a historical performance evolution trend reflecting a dynamic evolution rule; the twin mapping module is used for realizing signal space-time synchronization by utilizing a time service protocol, calling a multi-physics field evolution model to calculate thermal stress offset so as to execute numerical compensation, and generating a high-fidelity physical feature vector; the collaborative decision-making module shares observation information by using a multi-agent distributed collaborative architecture, identifies an electromagnetic-dynamic coupling response mode through a joint reward function and outputs a collaborative optimization strategy; and the execution module is used for generating an evaluation result by calculating the numerical deviation between the physical feature vector and the design envelope, and adjusting the excitation control variable according to a strategy until the system converges to a target equilibrium value. According to the method, the steady state monitoring of the power system is realized through twin mapping and collaborative decision.

The invention discloses a river topography modeling method based on data interpolation and a related device, and relates to the technical field of river topography modeling, and the method comprises the following steps: firstly, obtaining river image data and actually measured cross section elevation data, drawing a plurality of river lines according to the data, and then aiming at any one river line, calculating the elevation of the cross section; interpolating the river channel lines according to the elevation data of the intersection points of the river channel lines and the two adjacent cross sections to obtain elevation data of each interpolation point, and joining the river channel lines of the main stream and the branch stream at the intersection of the main stream and the branch stream to obtain elevation data of the river channel of the drainage basin; and finally, based on the watershed river channel elevation data, generating a watershed river channel triangular mesh, and performing interpolation by using an inverse distance weighting method to obtain a high-precision watershed river channel triangular mesh model. According to the method, dense and uniformly distributed river terrain elevation data can be generated based on the river cross section data and the river image data, terrain data support is provided for modeling of the two-dimensional hydrodynamic model, and the modeling precision of the hydrodynamic model is improved.

The invention discloses a creep load characteristic modeling method in an aero-engine load spectrum, and relates to the technical field of aero-engine load spectrum modeling, and the method comprises the steps: extracting steady-state points of rotating speed and temperature in an actual measurement load spectrum of an aero-engine, and forming a rotating speed-temperature two-dimensional time distribution matrix; least square nonlinear regression is carried out on the steady state points of the rotating speed and the temperature, and a rotating speed-temperature regression relation is established; selecting logarithmic normal distribution as a basic function, selecting mixed distribution as a distribution type, adopting an EM algorithm to estimate parameters of creep load characteristics, determining the number of optimal basic functions through an AIC method, and establishing a rotating speed one-dimensional mixed distribution model; and combining the rotating speed-temperature regression relationship with the rotating speed one-dimensional mixed distribution model to construct a creep load characteristic model. According to the method, a high-precision mathematical model of creep load characteristics is finally obtained, and a load basis is provided for predicting the service life of a high-precision aero-engine.

The invention discloses a novel information system reliability determination method for a multi-input dependent starting scene, and belongs to the technical field of system reliability. Comprising the following steps: drawing a system structure chart containing a multi-input dependency starting module, and dividing a three-stage system structure of a core module-a support signal module-an auxiliary guarantee module; a GO graph is drawn, the multi-input dependent starting module is uniquely identified as a type 29 operator, and the number of input ports of the operator is in one-to-one correspondence with the number of support signals of the corresponding core module; and determining the signal effective probability, the correlation coefficient and the element reliability according to a standardized process, calculating the module reliability by combining a type 29 operator quantitative model, and finally determining the system reliability. According to the method, the problem that an existing GO method operator cannot adapt to a multi-input dependent starting scene is solved, the blank of a special tool for GO method modeling in the scene is filled up, and the application range of the GO method in a novel information system is expanded.