39 results about "Energy method" patented technology

The application discloses a kind of wind turbine single blade installation process dynamic response analysis methods considering wind load action, comprising: according to the wind turbine blade installed and construction sea area, establish blade airfoil database and turbulent wind field database;When the position of lifting point and the position of tappet vertex are described, homogeneous transformation matrix is used to describe the motion of each mechanism of ship-mounted crane;When the position of lifting point is described, the position of tappet vertex is described, and the position of blade centroid in space is described by lifting point position, sling length and generalized coordinate;Wind load at each time point in the process of blade installation is obtained;The sling tension in the process of blade installation is obtained;The dynamics model of single blade installation system is established by using Lagrange method;The method can accurately analyze the coupling motion response between crane ship, ship-mounted crane, sling and blade in the installation process, and simultaneously by selecting generalized coordinate and modeling and analyzing the system based on energy method, the system modeling efficiency is effectively improved.

The invention relates to an engine component fatigue life evaluation method based on a structural simulation part, and belongs to the technical field of simulation data processing, and the method comprises the following steps: building a tensile strain energy life prediction model based on elastic strain energy and plastic strain energy, and predicting the fatigue life of a structural part based on the model; optimizing the design parameters of the simulation part of the engine component, manufacturing the simulation part based on the design parameters, performing a low-cycle fatigue test on the simulation part, and analyzing the fatigue life of the simulation part; comparing the fatigue life of the simulation part with the predicted fatigue life of the structural part, and if the requirements are not met, re-optimizing the design parameters of the simulation part; and if the requirement is met, outputting the fatigue life of the structural member. According to the method, the fatigue life of the simulation part is compared with the predicted fatigue life of the structural part, the model is further improved, a closed-loop research method is formed, the accuracy and efficiency of fatigue life prediction are improved, the limitation of a traditional hysteresis energy method is overcome, and the research cost and period are reduced.

The invention discloses a power system oscillation traceability analysis method and system based on multi-method probability fusion, which can effectively solve the problem of oscillation source positioning error caused by sparse measurement data and compressed sensing. Firstly, the oscillation source probability of each node is calculated through an oscillation energy method, a frequency spectrum characteristic method, a correlation analysis method, a voltage fluctuation method and a phase angle gradient method; secondly, calculating the adaptive weight of each method based on an information entropy theory, and completing multi-method probability fusion; the fusion probability is optimized in combination with a power grid topological structure, and an oscillation source candidate sequence is determined; and finally, a comprehensive probability distribution diagram and a detailed analysis report are output through a visual module, and reliable technical support is provided for safe and stable operation of a power system.

The invention discloses a high-overload gyroscope impact resistance design method based on a multi-section trial function energy method, and belongs to the technical field of micro electro mechanical system structure design. Comprising the following steps: constructing a physical model; establishing a trial function; calculating out-of-plane bending flexibility of the novel structural beam; introducing a torsion correction term and an outer frame equivalent flexibility; the flexibility is accumulated, and the reciprocal is taken to obtain the out-of-plane total rigidity; and the out-of-plane rigidity is applied to construction of an impact kinetic equation. A traditional Euler-Bernoulli beam theory cannot effectively consider the influence of rigidity coupling and torsional deformation of multiple sections of beams and the rigidity of an outer frame on the overall rigidity of a structure. According to the method, the out-of-plane equivalent stiffness of the novel structural beam and outer frame combined structure can be quickly estimated and obtained, the obtained stiffness parameter is applied to dynamic characteristic analysis of the gyroscope, and effective theoretical support is provided for design and engineering application of the novel structural beam structure of the high-overload gyroscope in the out-of-plane direction.

The application relates to the motor technical field and is a method for changing the slot torque of a permanent magnet synchronous motor. First, a slot torque expression based on an energy method is established, and a distribution function relationship expression before and after the change of the air gap length is derived; second, a motor model is established, the tooth crest height is changed, the air gap length is increased, and the slot torque is weakened; finally, the air gap length of the motor is further optimized through arc cutting of the tooth tip, and the slot torque is further weakened. Since the motor also affects other performances during optimization, the output torque and loss before and after optimization are compared and analyzed, the output torque is reduced, the loss is increased by less than 0.5%, and the efficiency and power of the motor are ensured.

The present invention discloses an energy management method for an electric flywheel hybrid vehicle based on multi-agent deep reinforcement learning, which belongs to the field of energy management for new energy commercial vehicles. The purpose of the present invention is to use a multi-agent deep reinforcement learning strategy to achieve efficient coordinated control between the main drive motor, the control motor and the flywheel, reduce battery energy consumption, and improve the economy and overall performance of the vehicle. The present invention mainly includes: constructing a model of an electric flywheel hybrid vehicle; defining six working modes; designing a multi-agent energy management method, and setting the state variables, action variables and reward functions required by the deep reinforcement learning SAC algorithm and PPO algorithm. Under standard working conditions, the multi-agent is trained to obtain the corresponding energy management method to achieve real-time energy management of the target vehicle. By applying the multi-agent deep reinforcement learning algorithm to the energy method of an electric flywheel hybrid vehicle, the battery energy consumption is reduced while ensuring the performance of the entire vehicle.

The present application relates to the field of tunnel engineering, and specifically discloses a method and system for fine prediction of rock burst grade in tunnel construction stage by drill and blast method, comprising the following steps: constructing a basic sample library; establishing a mapping relationship between drilling parameters and first principal stress, second principal stress, third principal stress, elastic modulus and Poisson's ratio and other surrounding rock mechanical parameters based on energy method; constructing an extended sample library based on the mapping relationship and the basic sample library; constructing an intelligent rock burst grade prediction model based on deep learning, and bringing the extended sample library into the intelligent rock burst grade prediction model for training; and fine prediction of rock burst grade in front of the tunnel face according to the constructed intelligent rock burst grade prediction model. The present application can effectively reduce the input of construction personnel and prevent the impact of rock burst on the safety of construction personnel, and guide the intelligent construction of tunnels.

This invention belongs to the field of dynamic modeling of vacuum manipulators, specifically a rigid-flexible coupling modeling and analysis method for vacuum manipulators. The method includes: using a rigid body model to describe the arm and a string model from the continuum domain to describe the steel strip. The rigid body is a finite-degree-of-freedom system, while the continuum is an infinite-degree-of-freedom system. A global space discretization method is used to discretize the infinite-degree-of-freedom system into a finite-degree-of-freedom system. Then, the two finite-degree-of-freedom systems are systematically integrated to obtain the rigid-flexible coupling dynamic equations of the vacuum manipulator. This invention establishes a system dynamic model based on the energy method, with a clear approach, and provides a good solution for dynamic modeling of rigid-flexible coupling systems. It solves the problem that vacuum manipulators lack end-point real-time sensing and cannot perceive the system state in real time to provide state feedback for control.

The application aims to provide an improved method for considering the lateral stiffness and the corner stiffness of the spline coupling with misalignment, comprising the following steps: establishing a schematic diagram of the load and deformation of the misaligned spline coupling, deducing the load and deformation balance equation of the misaligned spline engagement state according to the deformation geometry of the misaligned spline; deducing the single-tooth engagement stiffness according to the energy method, correcting the gear tooth engagement stiffness; bringing the single-tooth engagement stiffness of the spline obtained in step (2) into the engagement force balance equation obtained in step (1), and calculating the lateral stiffness and the corner stiffness of the misaligned spline coupling. Through comparison with the finite element results, the calculation results of the application are more efficient, and the vacancy of the calculation method of the lateral stiffness and the corner stiffness of the spline coupling under the misalignment condition at the present stage is made up.

The application provides a distributed line selection and positioning method, which synchronously and high-speed collects zero sequence voltage, zero sequence current and / or three-phase current on each power supply section, carries out zero sequence transient energy method and / or three-phase current transient correlation method analysis, determines a grounding line and positions a grounding fault section; each power supply section on the grounding line is differentially delayed and tripped by a power receiving end phase power supply end, when the fault section is tripped and the fault disappears, all power supply sections before the fault section stop timing, after the fault section isolation time reaches, the power supply of the fault section is restored through reclosing, if the fault is a transient fault, the power supply of the line on the fault section can be restored; if the fault is a permanent fault, the fault section is removed again through post-acceleration, and the permanent isolation of the fault is realized. The application realizes accurate positioning and reliable isolation of a single-phase grounding fault section, guarantees the reliability and safety of power supply, and improves the stability of power distribution network operation.

The invention provides a rapid prediction method for high-temperature yield strength of an orthotropic metal material. The method comprises the following steps: establishing an expression of material distortion energy density based on an equivalent energy method; deducing a specific expression of distortion energy density based on a stress-strain component by considering a uniaxial tensile stress state and orthoanisotropy of the material; calculating to obtain a key constant value under a uniaxial tensile stress state and a material melting temperature; and finally, deriving a high-temperature yield strength expression of the material in different directions. According to the method, a small number of parameters such as the elastic constant and the specific heat capacity which can be quickly obtained through table look-up are used as input, the yield strength values of the orthotropic material at different temperatures can be quickly predicted, and high cost caused by high-temperature tests of a large number of materials can be avoided; and a fast and efficient yield strength prediction mode is provided for material high-temperature performance prediction and structure high-temperature strength check in practical engineering.

The invention relates to the technical field of computational fluid mechanics and aeroelastic flutter calculation, and particularly discloses an aerofoil flutter calculation method based on an energy method.The aerofoil flutter calculation method comprises the steps that CFD grids and structural modal data of flow field calculation are prepared, and pretreatment such as modal interpolation is carried out; giving a generalized displacement motion law of a certain order mode, and setting other modes as coupling calculation; starting unsteady flow field calculation; for a mode with a given motion law, calculating generalized coordinates directly according to a motion law expression; for a coupling calculation mode, a generalized coordinate is obtained by solving a structural motion equation; according to the generalized coordinates, updating the grid through a dynamic grid method; solving the flow field and the structural deformation at the next moment in a loop iteration manner until the calculation is finished; according to the calculated generalized coordinates and the generalized aerodynamic force time history, work done by aerodynamic force in one period is calculated, and whether flutter occurs or not is judged according to whether the aerodynamic force does positive work or not. According to the airfoil flutter calculation method based on the energy method, the maximum vibration amplitude of the airfoil in fluid-structure interaction calculation can be manually controlled, the failure of a dynamic grid under large deformation can be avoided, and the calculation stability is improved; the aerodynamic force nonlinearity in flutter can be simulated; frequent fluid-solid data exchange is not needed, and the calculation efficiency is improved.

A phase control technology-based overvoltage suppression method, apparatus and device, and a storage medium, the method comprising: according to a preset iterative symplectic geometric mode decomposition-difference Hilbert transform model, obtaining transient characteristics from a collected voltage signal; determining a stable zero crossing point according to the transient characteristics; in a preset period of the stable zero crossing point, voltage values and current values at all moments before and after the stable zero crossing point are obtained; according to the voltage value and the current value at each moment before and after the stable zero crossing point, and a preset capacitance value and a preset inductance value, respectively calculating an energy sudden change value at each moment; and determining a minimum energy abrupt change value from the energy abrupt change values of the moments according to a minimum energy method, determining the moment corresponding to the minimum energy abrupt change value as a target moment, and controlling the switch to be switched on so as to suppress overvoltage, thereby solving the problems of large stable zero crossing point detection error, uncertain switch switching-on moment and poor stability in the prior art. And the overvoltage suppression effect is not good.

The application discloses a kind of approximate solving hamiltonian ground state energy method, system and electronic equipment, approximate solving hamiltonian ground state energy method includes: obtaining and preprocessing the hamiltonian to be solved, obtains the set of groups corresponding to hamiltonian;According to group set, generate Clifford operation sequence, and the new hamiltonian is obtained by the action of Clifford operation sequence to group set;According to new hamiltonian, generate energy expression containing variable parameter;Optimize variable parameter in energy expression, obtain the approximate value of the ground state energy of hamiltonian.The application is processed to group set by Clifford operation sequence, obtains new hamiltonian, and generates energy expression containing variable parameter, and then the approximate value of the ground state energy of hamiltonian is obtained by optimizing variable parameter, improve the calculation efficiency, shorten the calculation time, simultaneously, when multiple group dominants exist in hamiltonian, improve the approximate effect, so that the approximate value calculated and the precise value error can be negligible.

The present application relates to the technical field of acoustics, in particular to a method, system and device for predicting the dynamic performance of a composite rectangular plate. The method for predicting the dynamic performance of the composite rectangular plate comprises: setting parameters and elastic boundaries of a numerical model of the composite rectangular plate; establishing a dynamic model of the composite rectangular plate by using an energy method to obtain a Lagrange functional; dividing the composite rectangular plate into units to further obtain a vibration equation; applying forced excitation to the numerical model of the composite rectangular plate to obtain expressions of vibration displacement and vibration velocity of the composite rectangular plate structure; solving the vibration equation to obtain a Fourier coefficient matrix, and substituting the Fourier coefficient matrix into the expressions of the vibration displacement and the vibration velocity to obtain the vibration displacement and the vibration velocity of the composite rectangular plate, thereby realizing the prediction of the dynamic performance of the composite rectangular plate. The method improves the efficiency of predicting the dynamic performance of the composite rectangular plate.

The application relates to a solid-state electrolyte prediction screening method and system based on an improved bond valence site energy method, which comprises the following steps: obtaining the crystal structure of a solid-state electrolyte, constructing a three-dimensional calculation grid of a migration ion in a unit cell by using the crystal structure, calculating a global potential energy surface by using an improved BVSE model, and determining a migration energy barrier; the improved BVSE model is obtained by introducing a Coulomb repulsion term between migration ions in an original BVSE model; identifying migration ion sites based on the global potential energy surface, calculating the site energy of each migration ion site, obtaining characteristic Coulomb repulsion energy, and performing equivalent surface analysis and simple harmonic vibration analysis to obtain an equivalent surface surrounding volume and a site vibration frequency; and comparing the migration energy barrier, the characteristic Coulomb repulsion energy, the equivalent surface surrounding volume and the site vibration frequency with preset screening criteria to screen out potential solid-state electrolyte materials. The application can promote high-throughput screening of solid-state electrolyte materials.

The invention relates to an electromagnetic transient modeling and simulation method for a direct-current isolating switch based on variable capacitance. The method comprises the following steps: step 1, simplifying a three-dimensional geometric model of the direct-current isolating switch; 2, setting material attributes and excitation of a conductor part in the three-dimensional geometric model according to the type of the capacitor to be solved; 3, calculating the distribution of a three-dimensional electric field and a three-dimensional magnetic field of the direct-current isolating switch at different operation moments according to the setting in the step 2 by adopting a finite element method; 4, calculating capacitance values under different solving objects and an equivalent inductance value when the switch is completely closed in finite element software by adopting an electric field energy method and a magnetic field energy method; and 5, performing curve fitting on the capacitance values at the plurality of operation moments calculated in the step 4 to obtain a function relational expression between the capacitance values and the operation time. And 6, carrying out simulation analysis on the electromagnetic transient model of the isolating switch, and verifying the accuracy and effectiveness of the model.

The application provides a side channel energy method, device, storage medium and electronic equipment, and relates to the technical field of information security, and the method comprises the following steps: performing a preset encryption operation on a plurality of randomly selected plaintexts respectively; collecting encryption energy traces generated in the encryption operation process; and cyclically executing the following steps to obtain an overall key of the encryption operation: generating a plurality of key hypothesis values of a certain byte in the overall key; selecting a part of the energy traces corresponding to a certain sampling point of each encryption energy trace to obtain an energy trace set of the sampling point; calculating a Gini impurity index corresponding to each key hypothesis value based on the plurality of key hypothesis values and the energy trace set of the sampling point; and determining the key value of the certain byte in the overall key based on the Gini impurity index. The technical scheme provided by the application can reduce the dependence on attack equipment and energy models, and has high universality and small calculation cost.

The application discloses a method and system for determining seismic energy and ground motion amplification coefficient under complex terrain geological conditions based on energy method and artificial intelligence, and belongs to the technical field of earthquake engineering and geotechnical engineering. The method comprises the following steps: determining the energy of a seismic source; calculating the energy attenuation on the seismic wave propagation path; calculating the energy transformation of different geological interfaces; extracting terrain feature parameters and constructing a training database to train a deep neural network to determine the energy distribution coefficient of a complex combined terrain; predicting the energy distribution coefficient of each point of a target site; combining the incident energy of bedrock to calculate the ground motion amplification coefficient and perform energy conservation correction; and finally outputting an amplification coefficient distribution map. The application combines physical mechanisms with artificial intelligence, can efficiently and accurately predict the ground motion amplification effect of complex combined terrains (such as mountain groups and valleys), and the result conforms to energy conservation, so that the application can provide a scientific basis for seismic zoning and engineering seismic design.

This invention discloses a method for calculating the damage and deformation of a compartment structure under an internal explosion, relating to the field of ship damage and protection technology. The method includes: calculating the local damage area formed by the shock wave load on each compartment wall structure during the explosion; calculating the quasi-static pressure load on the exploded compartment; calculating the maximum overall deflection of each compartment wall structure under the coupled action of the two loads based on the energy method; determining the degree of damage to each compartment wall structure; if overall damage to the wall structure occurs, calculating the quasi-static pressure load on the adjacent damaged compartments, and calculating the maximum overall deflection of each compartment wall structure under the quasi-static pressure load; re-performing the determination of the degree of damage to each compartment wall structure until the deformation and damage status of all compartments is obtained. This method comprehensively considers the coupled loading effect of the two loads on the compartment structure under implosion, enabling rapid and accurate assessment of the damage and deformation status of the compartment structure under an internal explosion.

The invention belongs to the technical field of aircraft design, and particularly relates to an aircraft gliding distance calculation method and device based on an energy method. The method comprises the steps that S1, the height, the initial speed, the final state speed, the inclination angle and the lift-drag coefficient ratio of the hypersonic gliding aircraft are obtained; s2, determining initial state energy and final state energy of the hypersonic gliding aircraft according to the initial speed and the final state speed; and S3, determining the gliding range of the hypersonic gliding aircraft according to the initial state energy and the final state energy. The calculation precision of the gliding distance of the aircraft is improved, and a basis is provided for trajectory optimization of the aircraft.

A kind of harmonic modal detection and removal method based on blind source separation, rotating machinery generates harmonic excitation to structure in running state, based on the vibration response acceleration signal obtained by measurement, harmonic modal will appear in modal parameter identification, cause modal parameter identification error, low identification accuracy and other problems, harmonic modal should be detected and removed.In this method, based on the high similarity between modal expansion and blind separation principle, the vibration signal is analyzed under the condition of underdetermination sparse component, the energy peak scatter is clustered to estimate the mixing matrix by using the maximum energy method, and then the source signal is recovered based on the principle of minimum L1 norm;The probability density curve of each source signal is calculated, and the position of the harmonic modal is preliminarily determined;For the source signal containing harmonic, a spectral kurtosis curve diagram is drawn, so as to detect the frequency value corresponding to the harmonic modal;The corresponding harmonic source is removed, and the signal without harmonic interference is reconstructed.

The application provides a material radiation performance measuring device based on an energy method, which comprises a vacuum cover and a refrigerator, a copper screen is arranged in the vacuum cover, and a measuring assembly is arranged in the copper screen; the refrigerator is connected with the vacuum cover, and a refrigeration end of the refrigerator is connected with the measuring assembly; the measuring assembly comprises a black body, at least one sample table, a reflection mechanism and a measuring mechanism, the reflection mechanism is adapted to turn to the black body or the sample table, receive the radiation energy emitted by the black body or the sample table and transmit the radiation energy to the measuring mechanism. Through the above manner, the measuring assembly is arranged in the vacuum cover, the measuring assembly comprises at least one sample table and a black body, the reflection mechanism can turn to the black body or the sample table to transmit the radiation energy emitted by the black body and the sample table to the measuring mechanism, so that the measurement of the radiation energy of the material sample placed on the black body and the sample table is realized, then the radiation energy of the black body and the sample placed on the sample table is compared, and the measurement of the surface radiation performance of the sample at low temperature is realized.

The application discloses a state observer design method of a space tether system, a rigid body tether with a tensioning effect is used as the tether; firstly, a dynamics equation of the whole tether satellite system is established by using a Lagrange energy method; then, a criterion for the observability of the system is derived by using a linearization method when the velocity term state of the system is unobservable; and a nonlinear system state observer satisfying a linear observation convergence condition is further designed under the observability condition; the obtained observer can guarantee local asymptotic stability around a linearization point. The application can guarantee that the observation error converges in a dynamically changing neighborhood of an equilibrium point, and the application can be designed separately from a controller to realize the stability of the system.

The invention relates to a collision load intensity checking method and system based on an energy method, and belongs to the technical field of engineering mechanics and structural engineering.The collision load intensity checking method is used for checking the blocking column intensity under subsea pipeline collision through theoretical calculation and comprises the steps that known conditions are determined, comprise the length L of a hoisting steel wire rope, the simple pendulum angle theta of the subsea pipeline, the mass M of the subsea pipeline, the gravitational acceleration g and the rigidity k of a blocking column, and the blocking column and a deck are of a welding structure; according to an energy method in material mechanics, kinetic energy of the subsea pipeline and deformation energy of the blocking column are calculated; and judging whether the structural strength of the gear column meets the requirement or not through energy comparison. According to the method, the structural strength of the blocking column under the impact of the subsea pipeline can be checked through theoretical calculation, convenience is achieved, and the method can also be applied to structural component strength checking under the similar impact effect.

The invention provides a method for optimizing the dynamic reliability of a dangerous resonance component of a permanent magnet electric drive gear transmission system, and the method comprises the following steps: building an electromechanical coupling dynamic model of the system, and recognizing a dangerous resonance rotating speed and a component through a Campbell diagram and a modal energy method; applying a rain flow counting method and a modified P-S-N curve to analyze the strength degradation of the component, and establishing a dynamic reliability evolution model of the component; and a two-stage nesting strategy of firstly optimizing motor PI parameters and then optimizing mechanical parameters is adopted to carry out parameter optimization on the components which do not meet the life reliability requirement. According to the method, rapid prediction and collaborative optimization of the dynamic reliability of the dangerous resonance component can be realized in the design stage, and repeated design and expensive tests caused by resonance in the later stage are avoided, so that the research and development cycle is shortened, and high reliability and long service life of the system in the whole life cycle are guaranteed.

The invention discloses a bending, twisting and buckling bearing method for duplex stainless steel cold-bent edge-rolled angle steel, and relates to the technical field of metal structure materials. The method comprises the four steps of material mechanical property parameter acquisition, bending-torsion coupling calculation model establishment, bending-torsion combination test verification and engineering design method output. Accurate parameters are acquired by testing material microstructures and mechanical properties under different cold bending processes; deriving a bending-torsion coupling equation based on an energy method, and establishing a calculation model in combination with a finite element method; designing a standardized bending torsion loading test device, and verifying and correcting the model; load conditions are classified, a design formula is simplified, and an engineering design process is formulated. According to the method, the problems of large calculation error and poor practicability in the prior art are solved, the calculation error of the bending-torsion-buckling critical load is reduced to 5% or below, the blank of design specifications is filled up, the method can be applied to the fields of buildings, oceans, chemical engineering and the like, material waste is reduced by 10%-15%, and remarkable technical, economic and social benefits are achieved.

The invention discloses a complete analytic calculation method suitable for stepped multi-row piles, and relates to the technical field of geotechnical engineering.The complete analytic calculation method suitable for the stepped multi-row piles comprises the following steps that S1, geometric parameters of the stepped multi-row piles are determined and comprise the pile length, the pile diameter, the pile row distance, the inter-pile clear distance and the flexural rigidity of all the rows of piles; according to the equivalent stiffness principle, the row piles are simplified into an equivalent stiffness wall; s2, determining mechanical properties, including an elastic resistance coefficient, equivalent cohesive force and an internal friction angle, of the soil body, and determining a slip crack surface of the soil body according to a traditional soil pressure theory; s3, calculating the soil pressure of limited soil between the piles on each row of piles according to an energy method; according to the complete analytical calculation method suitable for the stepped multi-row piles, calculation reference can be provided for engineering application, the design work of the stepped multi-row piles is completed, and the blank in the field of structural form research is filled up.

The invention provides a transformer turn-to-turn short circuit current and loss calculation method and device, and the method comprises the steps: building a short circuit turn circuit model according to the short circuit turn information of a transformer when the transformer has a turn-to-turn short circuit; establishing a short-circuit turn electromagnetic field simulation model of the transformer, and calculating leakage inductance of transformer fault windings at different fault positions and different numbers of turns of short-circuit turn coils by adopting an energy method based on the short-circuit turn electromagnetic field simulation model; calculating the short-circuit turn short-circuit current of the transformer according to the short-circuit turn circuit model and the leakage inductance; and determining the short-circuit turn loss of the transformer according to the short-circuit turn short-circuit current and the short-circuit turn total resistance of the transformer. According to the invention, the accuracy of transformer turn-to-turn short-circuit current and loss calculation is improved.

The invention discloses a multi-direct-current power oscillation bearing capacity evaluation method based on an energy method and a physical information neural network, and the method comprises the steps: firstly, collecting the voltage and current of each node of a power system and the instantaneous values of related active power and reactive power at different oscillation frequencies, and forming time sequence data; secondly, the PINN model calculates energy flow conditions among nodes in the system through a physical constraint formula of an embedded augmented energy function; and finally, by analyzing the energy flow direction under the dominant frequency and positioning the position of the oscillation source, the oscillation source in the power system is positioned, and the multi-direct-current power oscillation bearing capacity is evaluated. By embedding the physical law of the power system into a physical information neural network (PINN), it is ensured that the model outputs fitting data and conforms to the law of the power system, the accuracy of multi-direct-current power oscillation bearing capacity evaluation is remarkably improved, the problem that internal physical behaviors of the system cannot be explained is avoided, and meanwhile the generalization ability and the real-time performance of the model are improved.