1186 results about "Control equation" patented technology

A method and a system for constructing a soil water movement model based on the physical information neural networks are provided. The soil water movement model is constructed by fusing the physical information neural network and a control equation of the soil water movement model, and the model adopts automatic differentiation to replace difference operation of grid scale, so that the calculation error caused by equation discretization in the solving process of numerical differentiation is avoided, and the calculation accuracy is improved; and the automatic differentiation mode is mainly carried out aiming at the output of a neural network, so that the numerical value of gradient calculation is more accurate.

The invention discloses a data-mechanism dual-drive-based rock burst early warning method and system, and the method comprises the following steps: deploying a multi-modal sensor network to collect coal and rock stratum data, building a rock burst disaster precursor information sample database, providing a rock burst disaster multi-modal data precursor feature recognition algorithm, and carrying out the recognition of rock burst disaster multi-modal data precursor features. Mining the relevance between the multi-modal data and disaster-causing key risk indexes, and establishing a rock burst disaster multi-modal data prediction model; establishing a three-dimensional geological geometric model, fusing a multi-field coupling dynamics constitutive model and a catastrophe criterion, constructing a PINN physical information neural network prediction model of the rock burst disaster, and obtaining a time-space evolution rule of an energy field of a target area; providing a loss function coupling calculation method of a multi-modal data driving sample error and a physical driving control equation residual error, dynamic data and mechanism prediction result weight, comprehensively calculating a risk score, and accurately judging a top disaster danger level.

The present invention provides an inverter control method, device, computer equipment and storage medium, belonging to the field of power electronics. The method comprises: determining a frequency control equation of the inverter under a grid-connected condition when the inverter is in a VSG control mode; determining a relationship between a virtual electromotive force of a virtual synchronous generator in a reactive state and an output voltage of the inverter; constructing a voltage-current double closed-loop control structure of the inverter under the VSG control mode, and determining a current reference value and a voltage reference value of the virtual synchronous generator under dq axes through the frequency control equation and the relationship; constructing a fuzzy control rule of a virtual damping coefficient and a virtual inertia according to the current reference value and the voltage reference value; and controlling the virtual damping coefficient and the virtual inertia through the fuzzy control rule, thereby improving the stability and performance of the inverter during the grid-connected process, reducing the harmonic disturbance of the power system, and helping to improve the adaptability and reliability of the entire photovoltaic power generation system.

The invention relates to the technical field of tunnel engineering, and discloses a tunnel multi-field coupling nonlinear deformation analysis method and system.The method comprises the steps that geological environment information of a tunnel area is collected, a multi-source physical field boundary condition model is built based on collected data, and a heat-seepage-stress-time four-field coupling control model is built based on the collected data; specifying a nonlinear response model for the geological medium to truly reflect the stress-strain behavior of the geotechnical material; solving a coupling equation set, and optimizing the four-field coupling control model; introducing measured data to correct the model; the system comprises a geological data acquisition module, a boundary condition modeling module, a coupling model establishment module, a numerical solution module, a measured data correction module and a visual output and control interface module. According to the method, high-fidelity prediction and evolution analysis of the deformation behavior of the tunnel under the complex geological condition are realized based on comprehensive acquisition of the geological environment, multi-field boundary modeling, control equation construction and numerical calculation.

The invention discloses a deep covering layer panel rock-fill dam rheological numerical calculation method considering the seepage effect. The method comprises the steps that firstly, contact deformation between a panel and a dam body is simulated; then simulating the unstable seepage process of the rock-fill dam and the foundation, and solving the seepage problem with a free surface; carrying out seepage-stress coupling calculation on the dam body material, and establishing a seepage-stress coupling control equation of the dam body material; carrying out seepage-stress coupling calculation on the overburden foundation, establishing a seepage-stress coupling control equation of the foundation, and finally obtaining a relationship among stress, strain and pore pressure to realize the seepage-stress coupling calculation; numerical simulation is conducted, and a concrete faced rockfill dam rheological numerical simulation result considering the seepage effect is obtained. The problems that in the prior art, the stress deformation rule of the concrete faced rockfill dam under the seepage-rheology coupling effect is not clear yet, and meanwhile, a seepage-rheology coupling calculation method is not perfect enough are solved.

The invention provides a pump station flow channel flow field prediction and optimization method based on a transfer learning enhanced physical information neural network. The method comprises the following steps: constructing a training data set; constructing a loss function based on the control equation, the initial runner condition and the inlet and outlet boundary; a physical information neural network is constructed, hydraulic design parameters, space coordinates and time data are input into the physical information neural network, and pump station flow channel flow field data are output into the physical information neural network; intensively training the physical information neural network through time slice transfer learning by using the training data set based on the loss function to obtain a target physical information neural network model; determining a plurality of candidate hydraulic design parameters, and inputting each candidate hydraulic design parameter into the target physical information neural network model to obtain corresponding candidate pump station flow channel flow field data so as to obtain candidate performance parameters; and an objective function is constructed based on the performance parameters, the objective function is solved to obtain optimal performance parameters, and the candidate hydraulic design parameters corresponding to the optimal performance parameters are the optimal candidate hydraulic design parameters.

The invention discloses a physics-based method for discovering a control equation from scarce and noise data. According to the method, a physical information neural network and a sparse regression method are combined, and a partial differential control equation of a dynamic system is found from scarce and noisy data. Firstly, the size of a candidate function library is effectively reduced through a dimension verification method. And then modeling a physical system and calculating a candidate function by using the strong nonlinear fitting capability and automatic differential characteristic of the deep neural network. And finally, the form of a control equation and the coefficient of the equation can be obtained through sparse regression, and the coefficient is finely adjusted through DNN. The method not only can discover the control equation from the data, but also can obtain the network model to realize the response prediction of the dynamic system. The method is easy to implement, efficient, high in precision and high in universality. The method can be widely applied to physical knowledge mining, modeling and reasoning of a complex dynamic system.

The invention relates to the technical field of coast engineering, and discloses a multi-source data-based beach restoration decision-making method and system, and the method comprises the following steps: obtaining multi-source data of beach monitoring, carrying out the data fusion processing, and generating a feature tensor with a unified temporal-spatial resolution; performing symbol regression analysis based on the feature tensor, and automatically discovering a control equation of beach evolution; and inputting the evolution equation into a decision optimization framework to generate a beach restoration decision scheme. According to the method, through organic combination of multi-source data fusion, symbolic regression analysis and a decision optimization framework, accurate description of a beach evolution process and intelligent generation of a repair decision are realized; according to the scheme, information of various monitoring data can be fully utilized, a control equation of beach evolution and time-varying characteristics of the control equation can be automatically found, and a physical rule is directly converted into a specific engineering decision suggestion, so that prediction precision and decision efficiency of beach repair are improved.

The invention discloses a fan control method, an inverter and an energy storage system. The control method is used for the inverter, operation data of the inverter in different environments and when the inverter operates in multiple working modes are obtained, the operation data comprise temperature data, voltage data, power data and current data, and the temperature data are temperature data of multiple temperature detection points; respectively solving correlation coefficients of the temperature of the inverter and the external environment temperature, voltage and power of the inverter according to the operation data and a fitting algorithm; solving a target coefficient of the correlation coefficient and the rotating speed duty ratio of the fan according to the operation data; constructing a rotating speed duty ratio control equation about the fan according to the target coefficient; the target rotating speed of the fan is solved according to the rotating speed duty ratio control equation and the current operation data of the highest rotating speed inverter of the fan; controlling the fan to work according to the target rotating speed. Thus, intelligent control over the fan can be achieved under different working conditions, and energy waste is avoided while normal operation of the inverter is guaranteed.

The invention discloses a PINN-based high-precision hydrodynamic numerical simulation method and system, and the method comprises the steps: firstly building a computational domain, setting reasonable geometric parameters and boundary conditions, and constructing a dimensionless Navier-Stokes control equation set; then designing a deep neural network architecture with space-time coordinate input and flow field variable output, and adopting a loss function combining physical constraint and data driving; the core innovation lies in providing a timing sequence sensing RAR-D adaptive sampling strategy, dividing a time domain into a plurality of time frames, performing residual error evaluation in each frame, constructing a probability density function related to residual errors, and balancing priority sampling and overall coverage of a high residual error region; adam and L-BFGS optimizers are adopted to carry out network training, the weight of a loss function is dynamically adjusted, and a sampling point set is periodically updated; and finally, the solution precision is verified through multi-dimensional flow field visualization analysis. Therefore, the prediction precision of the complex flow field is effectively improved, and the calculation efficiency is remarkably improved.

The invention discloses an integrated simulation method for flood routing, and the method is characterized in that the method comprises the following steps: delineating the plane contour of a ground feature in a research region, and carrying out the recognition and classification of the ground feature; fine modeling of ground objects in the research area is carried out; performing space-time numerical discretization on a two-dimensional control equation describing water flow movement on a computational grid, and constructing a two-dimensional hydrodynamic solver; establishing a ground feature calculation module and a connection calculation module of the river channel and the urban / flood storage and detention area along the river; establishing a space-time connectivity control module of the river channel and the urban / detention and detention area along the river, and carrying out simulation of flood routing and regulation and control of the river channel and the urban / detention and detention area along the river step by step; results such as a water flow plane physical field, a section water level and a flow process calculated by the flood rehearsal cooperative work system are stored in a hard disk, and flood regulation and control analysis and evaluation are carried out. The method has the advantages of being good in stability, high in reliability, high in calculation efficiency, high in universality and the like.

The invention discloses a method for forecasting dynamic characteristic values of coarse particle solid-liquid two-phase flow in a vertical lifting pipeline, and belongs to the technical field of flow dynamic characteristic value forecasting. In order to solve the problem that the influence of particle motion on surrounding fluid is not considered in the theoretical calculation and numerical simulation of the solid-liquid two-phase flow in the pipe at present, the method comprises the following steps: firstly, carrying out modeling and grid division on a fluid domain; establishing a particle model based on particle material simulation software, and performing discrete control on particles; then based on computational fluid dynamics software, a coupling interface is established through a coupling interface control equation, the computational fluid dynamics software calculates and monitors the state of fluid, the state serves as an external environment of particles and is conveyed to particle material simulation software, and interference caused by movement of the particles is also transmitted to the computational fluid dynamics software through the coupling interface; and based on the initialized coupling interface, the pipeline model and the particle model, realizing coarse particle solid-liquid two-phase flow dynamic characteristic numerical prediction.

The invention relates to the technical field of multi-equipment cooperative control, and discloses a multi-equipment cooperative control method and device for drilling mud treatment.The method comprises the steps that stirring parameters of mixing tank equipment, precipitation time parameters of precipitation tank equipment and separation efficiency parameters of oil-water separation equipment are obtained; solving a steady state control equation and a dynamic adjustment equation simultaneously to obtain an initial cooperative control parameter set; performing branch control architecture division and parallel processing based on the initial cooperative control parameter set to obtain a branch parallel control parameter set; performing deep reinforcement learning training according to the branch parallel control parameter set, constructing a reinforcement learning model, and generating an optimal parameter adjustment strategy; monitoring and threshold triggering processing are carried out based on the optimal parameter adjustment strategy, a dynamic adjustment control instruction is output, the method solves the problem of coupling control among multiple devices, and dynamic adjustment and self-adaptive control of the multiple devices of the drilling mud are achieved.

A transient stability control method for an islanding system with parallel heterogeneous networking inverters comprises the following steps: when a symmetric short-circuit fault occurs in a common line, collecting a grid-connected point voltage effective value of a droop control inverter and a frequency output value of a droop control and virtual synchronous generator; calculating a fault degree based on the voltage effective value, and determining a relative frequency by combining droop control and a VSG frequency difference value; generating a transient stability improvement coefficient according to the fault degree; the lifting coefficient and the relative frequency are fused through an integrator, and adjusting power is generated; injecting the adjusting power into the droop control equation to obtain an improved droop control equation; and combining the improved droop control equation and the VSG control equation to obtain an equivalent synchronous motion equation of the heterogeneous network-building type inverter parallel system during the fault period. According to the method, the power distribution is dynamically adjusted, the power transmission limit of the system during the fault period is improved, the transient stability under the serious fault is ensured, and an effective control scheme is provided for the micro-grid containing the heterogeneous inverter.

The invention discloses an integral equation general solution method for horizontal bearing characteristics of a pile body composite foundation, which comprises the following steps of: S1, establishing a pile body composite foundation schematic diagram consisting of N (N = n1 * n2) foundation piles and a coordinate system {0, x, y, z} thereof, and dividing the pile body composite foundation schematic diagram into m subunits by taking a pile diameter d as a side length; determining the load resultant force V (y, 0) of the top of each subunit according to the horizontal load H0 of the upper structure borne by the foundation; s2, the pile-soil system is decomposed into semi-infinite space expansion soil and virtual pile units, and stress analysis schematic diagrams of the corresponding units are obtained; obtaining analytic expressions of pile body deflection # imgabs0 # and bending moment # imgabs1 # according to static equilibrium conditions and geometric conditions of the ith (i = 1,..., N) virtual pile unit; and S5, the lateral displacement # imgabs2 # of the extended soil unit at the corresponding position of the ith virtual pile is obtained based on the Mindlin solution, according to the lateral displacement coordination condition of the semi-infinite space extended soil and the virtual pile unit at the corresponding position, an integral control equation of the horizontal bearing characteristic of the pile body composite foundation is established, and then the pile body deflection and the internal force of the pile body composite foundation are obtained.

The invention discloses a nuclear reactor core channel analysis method based on two fluid models, which comprises the following steps of: 1, establishing a fluid domain computational grid according to the structure of a nuclear reactor core or an assembly; 2, respectively establishing a control equation set and a heat conduction model of the fuel rod for the continuous gas-liquid phase and the discrete liquid drop phase; 3, considering physical phenomena such as flow heat exchange, resistance pressure drop and turbulence mixing in a reactor core, and implanting a corresponding constitutive model; 4, discretizing the control equation based on a second-order discrete format to obtain a discrete equation set; 5, dividing parallel tasks and parallel regions through an MPI parallel strategy to form a large coefficient matrix of a pressure equation; and 6, solving a discrete equation set and a large coefficient matrix through a pressure coupling semi-implicit algorithm and a stable biconjugate gradient method. According to the method, the key physical parameter distribution of the pressurized water reactor can be more accurately and reasonably calculated, so that technical guidance is provided for safety analysis and engineering design of the reactor.

The invention discloses an oil-immersed transformer fault deduction characterization method and system based on multi-physics field simulation, and the method comprises the steps: firstly building a 110 kV oil-immersed transformer multi-physics field twin model through SOLIDWORKS and COMSOL, precisely setting boundary conditions and material attributes, and constructing a coupling multi-physics control equation set to solve a reference distribution field; thirdly, constructing a fault sensitive area monitoring mapping model, and screening monitoring point positions; meanwhile, a typical fault simulation database is built, and multiple disturbance types are covered. Simulation and actual measurement data are integrated through a multi-modal feature fusion model, and a future state is predicted by means of a state deduction model based on time sequence prediction. In addition, a self-adaptive degradation perception and model correction mechanism is introduced, so that the prediction credibility is improved. According to the method and the corresponding system, the fault can be deduced efficiently, powerful technical support is provided for fault diagnosis and maintenance of the oil-immersed transformer, and stable operation of a power grid is facilitated.

The invention discloses a simulation platform and a calculation method for computational fluid mechanics, and belongs to the technical field of computational fluid mechanics. In order to solve the problems that precision is insufficient, numerical dissipation is too large and calculation efficiency is low when a traditional method is used for processing the high Reynolds number turbulence or multi-physics coupling problem, a model and boundary conditions are rapidly generated, a grid generation module automatically optimizes a flowing important area grid through an adaptive algorithm, the solving process is accelerated, and the calculation efficiency is improved. Through parallel computing and efficient time integration methods, simulation efficiency of complex transient and steady problems is greatly improved, accurate calculation of critical areas such as a boundary layer and a separation area is ensured through grid encryption and optimization, consistency verification is combined with physical parameters and a control equation, numerical errors and parameter mismatching are avoided, and the method adapts to multi-physical-field complex scenes and is high in practicability. Meanwhile, optimization is carried out by automatically iteratively adjusting input parameters, and accurate and reliable design and research support is provided.

The invention relates to the field of lithium ion battery detection, in particular to a lithium ion battery internal temperature estimation method based on surface temperature. Firstly, a control equation and boundary conditions are constructed based on a one-dimensional heat conduction model; then, performing time discretization on the control equation by adopting a display Euler method, and performing spatial discretization on the control equation by adopting a central difference method; and finally, initializing the heat production rate, and substituting the initialized heat production rate into the control equation to obtain a battery surface temperature calculated value. If the difference between the calculated value and the measured value of the surface temperature of the battery is less than 0.001, increasing the heat production rate, otherwise, reducing the heat production rate; and continuously iterating the heat production rate until the absolute value of the difference between the calculated value and the measured value of the surface temperature of the battery is less than 0.001, and stopping iteration to obtain the heat production rate and the internal temperature of the battery in the current time step length. The heat production rate and the internal temperature of the battery are reversely deduced through numerical solution, the limitation of the prior art on the temperature equalization hypothesis is overcome, and the calculation precision under the large temperature difference working condition is improved.

The invention belongs to the related technical field of heat dissipation of electronic equipment, and discloses a liquid cooling device and a preparation method and application thereof, and the method comprises the steps: S1, enabling a control equation of the liquid cooling device to be equivalent to a continuity equation, an N-S equation and a heat transfer equation based on equivalent parameters; s2, taking the minimum average temperature and energy dissipation of the whole design domain of the liquid cooling device as a target function, taking the volume fraction of the fluid domain as a constraint condition, and constructing a topological optimization model based on a continuity equation, an N-S equation and a heat transfer equation; s3, an optimization solver is adopted to carry out iterative solution on the topological optimization model, whether a result meets a convergence condition or not is judged, if yes, a topological structure is output, and the step S4 is executed; otherwise, updating the design variable of the topological optimization model, and turning to the step S1; and S4, the three-dimensional model of the liquid cooling device is corrected based on the obtained topological structure, and then blowing forming is carried out based on the corrected three-dimensional model to obtain the liquid cooling device. According to the invention, the cost is reduced.

The invention discloses a roadbed pavement test and data acquisition system under the action of moving load, which comprises the following steps of: acquiring high-precision pavement unevenness data, decomposing features through a space-time convolution variational self-encoding network and inhibiting noise; based on the normal stiffness and the morphological gradient, the density of the sensor is adjusted by adopting dynamic grid division, and multi-modal data is fused by utilizing Bayesian weight. And adaptively extracting signal details by applying multi-scale transformation, and designing a filter to enhance the damage signal and optimize the structure entropy. And constructing a multi-field coupling grid control equation to realize dynamic topological optimization reconstruction. And establishing a damage evolution state space, and training the prediction model through a multi-stage reinforcement learning framework in combination with experience playback. And constructing a digital twin mapping model, integrating Bayesian optimization and reinforcement learning, and establishing a virtual-real feedback channel to realize dynamic decision optimization. According to the invention, innovative improvement on a traditional test method and a data acquisition system is provided, and meanwhile, complex nonlinear dynamic behaviors can be accurately simulated and analyzed.

The invention relates to a tunnel lining external load inversion method and system based on a physical information neural network. The method comprises the following steps: acquiring monitoring data of the inner surface of a to-be-inverted tunnel lining; according to the curved beam theory, a control equation of external load and lining neutral axis deformation is established, and boundary conditions are determined; according to the material mechanics theory, the corresponding relation between the strain and displacement of the inner side surface of the lining and the strain and displacement of the neutral axis position is established; a physical information neural network is constructed, lining space coordinates serve as input of the physical information neural network, neutral axis normal displacement, tangential displacement and lining external load at different coordinates serve as output, and neutral axis displacement is converted into lining inner surface strain and displacement; the physical information neural network is trained, so that the input and output relation meets the control equation, boundary conditions and monitoring data of the external load and lining deformation, and the normal displacement, tangential displacement and lining external load of the neutral axis at the corresponding coordinates are obtained, namely, the inversion result is obtained.

The invention discloses a reservoir-shaft integrated prediction method for geothermal exploitation, which belongs to the technical field of geothermal exploitation, and comprises the following steps: S1, constructing a cross-scale reservoir model, S2, establishing a reservoir-shaft coupling model, S3, establishing a heat-fluid-solid coupling control equation, S4, solving the coupling control equation, S5, simulating multiphase flow in a shaft, and S6, learning and optimizing a machine. S7, dynamically updating prediction; by constructing a cross-scale reservoir model and a wellbore-reservoir coupling model, accurate mapping from micro pores to macroscopic thermal storage and dynamic coupling of a reservoir and a wellbore are realized, and numerical solution and multiphase flow accurate simulation of a thermal-fluid-solid multi-field coupling control equation are combined. Rock heterogeneity, multi-physical field interaction and complex flow characteristics in the shaft are comprehensively considered, the prediction accuracy and comprehensiveness are greatly improved, and the defects that in a traditional method, reservoir and shaft analysis is split, and the model precision is limited are overcome.

The invention discloses an improved discrete velocity method for rotation unbalance calculation of diatomic molecules, and relates to the field of numerical simulation of rarefied gas dynamics. The method comprises the steps that a flow field is initialized according to actual working conditions, a Boltzmann equation based on a Rykov model is adopted as a control equation, a collision-free Boltzmann equation is solved to obtain a unit interface distribution function, a macroscopic equation flux corresponding to a local solution of the collision-free Boltzmann equation and a macroscopic equation flux corresponding to a Navier-Stokes equation considering the molecular rotation effect are calculated, and a unit interface distribution function is obtained; performing weighted calculation on the two types of fluxes according to the rarefaction degree of the gas to obtain a macroscopic flux, solving a macroscopic adjoint equation to obtain an estimated macroscopic quantity and an estimated equilibrium state distribution function, solving a microcosmic control equation to update the distribution function, and integrating the distribution function to update the macroscopic quantity and judge the convergence. On the basis of keeping the conciseness of the traditional semi-implicit discrete velocity method, the method can achieve the precise prediction of the full-basin unbalanced flow field of the diatomic molecular gas.

The invention is applicable to the technical field of coal bed gas development and geological sequestration, and provides a THMC multi-field coupling simulation method and system for a process of displacing CH4 by coal bed CO2, and the method comprises the following steps: collecting multi-source parameter information of a target coal bed; according to the multi-source parameter information, constructing a coal seam structure model comprising a matrix and a crack system; constructing a control equation system based on the coal seam structure model, and introducing a multi-field coupling mechanism to obtain a fully-coupled mathematical model; performing numerical solution on the fully-coupled mathematical model to obtain a spatio-temporal evolution result of the key field variables; and according to the spatio-temporal evolution result of the key field variable, evaluating the index of the target coal seam. According to the invention, a heat-force-gas-chemical multi-physical field full-coupling simulation system is constructed, so that the CH4 recovery rate and the CO2 storage stability can be accurately predicted. The method is suitable for gas injection-storage coupling optimization of a multi-coal-rank and low-permeability coal seam, and has high precision, high adaptability and remarkable engineering guidance value.

The invention discloses a dynamic efficiency optimization management and control method for a wind-light hydrogen storage system, which comprises the following steps of: acquiring operating parameters of an electrolytic bath based on a water electrolysis hydrogen production simulation framework of an alkali liquor medium, and analyzing joint probability distribution and correlation coefficients of historical wind-light data through a wind-light photovoltaic synergistic effect model; constructing a system load accommodating setting model; when the frequency or voltage fluctuation of the power grid is detected, starting a quasi-synchronous electric element regulation and control framework PSEERA, and adjusting the output power through a droop control equation; the comprehensive performance indexes are optimized by adopting a Ling-tuned chaos infinitesimal search (SACMESA) algorithm, and main control factors are extracted through a multi-element optimization evolution (BKEAMOEA) algorithm analyzed according to key elements to carry out multi-objective optimization; implementing a scattered point type cooperative control strategy including bottom-layer equipment control, middle-layer energy management and upper-layer system scheduling, and realizing cross-level dynamic optimization; the peak regulation and frequency modulation capability, the safety and the stability of the power grid are remarkably improved.

The invention discloses a fluid variable gradient calculation method and device, equipment and a storage medium, and relates to the technical field of fluid mechanics, and the method comprises the steps: obtaining a body center independent variable value of an unstructured grid unit in a current iteration round region when a fluid mechanics control equation of a fluid region is iteratively discretized; determining a surface center independent variable value of a boundary surface between the unstructured grid units based on the body center independent variable value, and determining an independent variable gradient of the units by using the volume of the units and the surface center independent variable value; determining a new face center independent variable value of the boundary surface by using the face center position vector of the boundary surface, the body center independent variable values of the unstructured grid units located on the left and right of the boundary surface, the independent variable gradient limiting coefficient and the independent variable gradient; a target grid argument gradient is determined based on the volume of the unstructured grid cell and the new face center argument value to determine a fluid region variable distribution using the target grid argument gradient. The compactness of gradient calculation is efficiently kept through an implicit expansion unit gradient calculation template.

The invention provides a hydraulic fracture evolution simulation method and device and electronic equipment.The hydraulic fracture evolution simulation method comprises the steps that a damaged rock mass is divided into a plurality of different calculation areas, and a seepage control equation of each calculation area is determined; in combination with seepage anisotropy, determining a seepage tensor of porous medium seepage-stress coupling in each calculation area; associating the seepage control equations of all the calculation areas with phase fields to obtain a target seepage control equation; and determining the displacement, fluid pressure and phase field of the damaged rock mass based on the target seepage control equation. Through the deduced seepage-stress coupling phase field model, the strain energy is decomposed through spectral decomposition, it is guaranteed that crack propagation occurs under the energy generated by tensile strain, and the problem that an existing hydraulic crack research method is limited is solved.

The invention discloses a soil hydraulic coupling simulation method and system based on a physical information neural network. The method comprises the following steps: firstly, constructing two improved full-connection neural networks for respectively predicting pore water pressure and deformation response in a soil body; according to a soil hydraulic coupling partial differential equation set, non-dimensionalization control equation loss items of a liquid phase and a solid phase are established based on a fixed stress splitting method, and a total loss function of the liquid phase and the solid phase is established in combination with an initial boundary value condition; and finally, alternately training loss functions of a liquid phase and a solid phase based on a sequential training strategy and a gradient normalization self-adaptive loss balance strategy. According to the method, a sequential training strategy, an improved full-connection neural network and a self-adaptive loss balance scheme are adopted to improve a traditional physical information neural network, and prediction precision and training stability are improved. The trained physical information neural network can be used as an agent model to predict pore water pressure and deformation, and has great application potential.

Provided is a method for predicting vibration response and stiffness degradation of a helical gear. The method includes: establishing a lumped parameter dynamic model of a gear system according to a meshing condition of a pair of gears, considering that the gear system is a multi-degree-of-freedom system under the action of a deterministic force and a random force, establishing a digital twin model of the system at multiple time scales of characteristic time and running time, calculating a translation-vibration coupling control equation, establishing a grey box model by combining unscented Kalman filter with machine learning, performing combined state parameter estimation upon collected data to construct a state prediction framework, and predicting stiffness degradation at a running time scale. Response of a nonlinear multi-degree-of-freedom system can be predicted, and the residual stiffness of the gear is predicted through the collected data.