49 results about "Critical energy" patented technology

The invention discloses an in-situ characterization method for fracture toughness of a high-temperature interface of a thermal barrier coating, which comprises the following steps: taking a metal test piece with the thermal barrier coating as a sample to be tested, spraying NiAl on the surface of a ceramic layer in the thermal barrier coating to serve as a buffer layer, then spraying a reinforcing layer, and forming a mixed reinforcing layer with the buffer layer; a three-point bending experiment is carried out on a to-be-tested sample at 1000-1400 DEG C by using a three-point bending device with a digital image correlation method in-situ observation function, and the three-point bending process is recorded in real time. A strain cloud picture of an observation area is obtained through a digital image correlation method, parameters are obtained from the strain cloud picture, and the interface critical energy release rate and the stress intensity factor of a three-point bending experiment are calculated and are both in direct proportion to the high-temperature interface fracture toughness of the thermal barrier coating. Therefore, in-situ characterization of the interface fracture toughness of the thermal barrier coating can be realized in a high-temperature environment of real service of the thermal barrier coating, test data can be accurately acquired in real time, and the test period is short.

The invention discloses a power grid operation risk assessment method and system considering time period coupling characteristics, and relates to the technical field of power grid operation risk assessment, and the method comprises the following steps: obtaining operation data of a target power grid in a plurality of continuous time periods, and constructing a time-space state tensor based on the operation data; introducing a time period memory kernel function to obtain a cross-time period evolution memory curve of a node state; constructing a risk diffusion path diagram based on the evolutionary memory curve and the power grid power flow equation; establishing a critical energy accumulation function based on the risk diffusion path diagram, and triggering a node risk source mark when accumulation exceeds a preset threshold value; and generating a space-time risk evolution spectrum based on the risk source mark, and outputting a risk trajectory and a threshold breakthrough time point of each node in a continuous time period. According to the method, the cross-time evolution memory curve and the dynamic risk diffusion path diagram are constructed, so that high-risk nodes of continuous-time-period tail events are recognized in advance, and the problem of lack of cross-time-period accumulation risk quantification is solved.

In one aspect, build materials for use with a three-dimensional (3D) printing system are described herein. In some embodiments, a build material described herein comprises an acrylate component, a photoinitiator component, a non-curable absorber component, and water. The photoinitiator component of the build material is operable to initiate curing of the acrylate component and / or other curable materials that may optionally be present when the photoinitiator is exposed to incident curing radiation having a Gaussian distribution of wavelengths and a peak wavelength λ. The build material has a penetration depth (Dp) and a critical energy (Ec) at the wavelength λ. In some embodiments, the Dp is greater than 200 μm and less than 300 μm, and the Ec is 3-12 mJ / cm2. In other embodiments, the Dp is greater than 10 μm and less than 50 μm, and the Ec is 5-40 mJ / cm2.

The invention provides a new energy transient stability optimization method based on new energy station energy distribution and storage control adjustment, and relates to the technical field of power systems.The new energy transient stability optimization method comprises the steps that new energy station access node positions, installed capacity and operation mode data of a target power grid system are collected, and a power grid simulation model comprising a new energy station, an energy storage system and load characteristics is constructed; calculating a shrinkage admittance matrix after the new energy station is accessed, simulating a fault scene through time domain simulation, and generating a stable and unstable balance point of the unit; then calculating transient critical energy of fault scenes in different operation modes based on an energy function method; and finally, generating a transient stability risk margin through a difference value between the transient energy and the critical energy at the fault clearing moment, thereby evaluating the transient stability risk of the power grid after the new energy is accessed. According to the method, through dynamic adjustment of the energy storage system, the transient stability of the power grid after new energy grid connection is effectively improved.

The invention provides a SiC / SiC pyrolytic carbon interface optimization method based on a neural network and a phase field fracture method. The SiC / SiC pyrolytic carbon interface optimization method comprises the following steps: firstly, constructing a representative volume element model of a SiC fiber reinforced composite material; performing transverse tensile simulation on the representative volume element model of the SiC fiber reinforced composite material by adopting a phase field fracture method to obtain transverse tensile strength; and finally, screening the optimal interface thickness by taking the transverse tensile strength as a criterion, and training a reverse neural network to realize prediction and optimization of the optimal interface thickness of the SiC fibers with different material parameters. According to the method, an accurate and efficient representative volume element model is used, a phase field fracture method is combined with a reverse design neural network, and the PyC interface parameters are systematically optimized by simulating crack behaviors and predicting the optimal interface thicknesses of fibers with different radiuses, elastic moduli, critical energy release rates and strengths, so that the performance of the PyC interface is improved. Therefore, the mechanical property and the reliability of the SiC / SiC composite material are improved.

In one aspect, inks for use with a three-dimensional (3D) printing system are described herein. In some embodiments, an ink described herein comprises up to 80 wt. % oligomeric curable material; up to 80 wt. % monomeric curable material; up to 10 wt. % photoinitiator; up to 1 wt. % non-curable absorber material; and up to 10 wt. % one or more additional components, based on the total weight of the ink, and wherein the total amount of the foregoing components is equal to 100 wt. %. Additionally, the photoinitiator is operable to initiate curing of the oligomeric curable material and / or the monomeric curable material when the photoinitiator is exposed to incident curing radiation having a peak wavelength λ. Moreover, the ink has a penetration depth (Dp), a critical energy (Ec), and a print through depth (DPT) at the wavelength λ of less than or equal to 2×Dp.

The application belongs to but is not limited to the technical field of electronic core industry, and discloses a polycrystalline NCM electrode particle cracking and pulverization prediction method and system, which comprises the following steps: constructing an anisotropic polycrystalline fracture phase field model, including a grain boundary phase field equation, a solid mechanics equation, a Li + diffusion equation and a fracture phase field equation; constructing a two-dimensional geometry of a polycrystalline NCM electrode particle, setting required parameters of physical fields, carrying out grid division and setting initial conditions and boundary conditions; using a finite element simulation software to perform numerical solution, and obtaining cracking and pulverization distribution of the polycrystalline NCM electrode particle. + The application considers bidirectional coupling of Li diffusion and mechanical stress, cracking and pulverization and mechanical stress, and uses grain boundary phase field calculation to correct the critical energy release rate, so that the application can accurately reflect the mechanism of cracking and pulverization of the polycrystalline NCM electrode particle, and improve the accuracy of cracking and pulverization prediction.

A network-constrained energy management system for electric vehicle (EV) site charging and scheduling. In one embodiment, a power schedule is received from an economic dispatch application of a charging site comprising an EV charging station and distributed energy resources. The power schedule may be simulated on a distribution network model of the charging site according to a load flow analysis to determine if any grid code violations have occurred. In response to detection of a violation, a constraint may be generated for each violating node, and the economic dispatch application may be re-run with the constraints to generate a new power schedule until no violations are detected. If all load demands cannot be met by the power schedule, the charging schedule may be adjusted to ensure that critical energy requirements are met. The final power and charging schedule may be used to schedule and control power generation and charging at the charging site.

The present invention discloses a transient stability assessment method, apparatus, terminal equipment and computer-readable storage medium for a grid-connected system of a new energy generator set and a grid-connected converter. The method comprises: obtaining system parameters after a fault occurs, and calculating the energy value of each time step after the fault occurs by using a dynamic equation and an approximate energy function; judging whether the energy value of each time step is less than a preset critical energy value, and if so, judging that the corresponding time step is in a stable state, and if not, judging that the corresponding time step is in an unstable state; taking the maximum time step corresponding to the stable state as the target maximum fault clearing time after the fault occurs, and performing transient stability assessment based on the target maximum fault clearing time; wherein the dynamic equation and the approximate energy function are determined in the following manner: constructing the dynamic equation and the energy function according to the structure of the grid-connected system of the new energy generator set and the grid-connected converter; and approximating the damping term in the energy function to obtain the approximate energy function.

Disclosed is a method for testing and evaluating a short-circuit withstand capability of a press-pack power component. The method includes: building a test platform; obtaining a voltage level, a pressure load, an environment temperature, and a maximum junction temperature fluctuation range of a to-be-tested component in an actual working condition; separately testing short-circuit withstand capabilities of the to-be-tested press-pack power component; monitoring, in real time, changes of a component short-circuit current, a collector-emitter voltage, and a grid-emitter voltage until the to-be-tested press-pack power component fails due to short circuit; correspondingly obtaining a relationship between a voltage and each of a short-circuit critical energy and a critical temperature, a relationship between a pressure and a short-circuit current, and a relationship between a temperature and a short-circuit current; obtaining a relationship between a short-circuit withstand capability of the to-be-tested press-pack power component and each of a voltage, a pressure, and a temperature.

The present application relates to a kind of short-circuit resistance test and evaluation method of crimping package power device, belong to the technical field of power electronics device.The method includes: S1: build test platform;S2: obtain the voltage grade, pressure loading, environmental temperature and maximum junction temperature fluctuation range under actual application condition of the device to be measured;S3: respectively carry out short-circuit resistance test of crimping package device under different voltage, pressure, temperature grade, real-time monitoring the change of device short-circuit current, collector voltage and gate voltage, until power device short-circuit failure, corresponding to obtain the relationship of voltage and short-circuit critical energy and critical temperature, the relationship of pressure and short-circuit current, the relationship of temperature and short-circuit current;S4: according to test result, obtain the relationship of short-circuit resistance of crimping package device to be measured and voltage, pressure, temperature.The present application considers the special application condition of crimping package power device, improves the accuracy of short-circuit resistance test and evaluation of crimping package power device.

The invention provides a method and a system for simulating and predicting tensile strength of aramid paper, relates to a composite material of the aramid paper and a use finite element method, and belongs to the technical field of electric digital data processing. By constructing the interface phase field model, the equivalent material field representing the three material phases can be generated, so that the phase field model can be used for analyzing the crack propagation problem of material attribute mutation. According to the method, a dynamic phase field model basic equation containing an interface phase field and a crack phase field is given, and the tensile strength of the aramid paper composite material can be obtained by combining finite element analysis. According to the method, when the tensile strength of the aramid paper is predicted, the real microstructure characteristics of the aramid paper, including the diameter and length of fibers, the random distribution of the fibers, the volume fraction of the fibers and the porosity, are fully considered; when the tensile strength is predicted, the volume fraction of a fiber reinforced material, the volume fraction of pores, the strength and critical energy release rate of an interface, the strength and critical energy release rate of a matrix and the like can be used as input characteristics.

The invention discloses a 2.5-dimensional automatic tape laying woven composite material microstructure optimization design method, and relates to the technical field of composite material optimization design. According to the method, whether a delamination layer is expanded or not can be judged according to a criterion established by fracture mechanics, and if the energy release rate of the crack tip is greater than or equal to the critical energy release rate, the delamination layer is expanded; the energy release rate of delamination in a novel woven composite material beam structure is solved through an energy method based on a beam theory, and the value of the energy release rate can be reduced for verifying the rigidity design of a laminated plate, so that delamination expansion is delayed or slowed down. The energy release rate of delamination in the three-point bending beam model can be affected by material combination and the number of parts divided under the same length, the interlayer energy release rate is reduced by changing the microstructure, delamination extension is delayed, and microstructure optimization design is carried out.

The invention provides a quasi-brittle material fracture simulation method considering a shear softening effect. The method comprises the following steps: step 10, constructing an extended bond-based near-field kinetic model of a quasi-brittle material; the extended bond-based near-field kinetic model combines a bond stretching softening effect and a shear softening effect; and step 20, solving the extended bond-based near-field kinetic model by adopting an arc length method. According to the quasi-brittle material fracture simulation method considering the shear softening effect, the shear softening effect is considered, the springback instability behavior of cracks of the quasi-brittle material can be accurately captured, the physical accuracy and numerical stability of crack simulation of the quasi-brittle material are improved, and the method is suitable for popularization and application. The invention discloses the influence of the type II critical energy release rate on a force-displacement curve and a material springback instability behavior.

The invention belongs to the field of new energy grid connection, relates to a port Hamiltonian energy-based multi-parallel grid-following converter system transient synchronization stability evaluation method and device, and solves the problem of multi-parallel grid-following converter system transient synchronization stability evaluation at the present stage, and the method comprises the steps of establishing a transient model of a multi-parallel grid-following converter system; constructing an energy function of the transient model of the multi-parallel network-following converter system, and further establishing a port Hamiltonian model; the critical energy threshold value of the multi-parallel grid-following converter system is determined by analyzing the maximum value of the total energy in the first swing process of the fault trajectory by using a dominant unstable equilibrium point method, and the critical clearing time is further determined based on the threshold value. According to the method, internal measurement data or model parameters are not needed, and the stability margin of the multi-parallel grid-following type converter system can be accurately and quantitatively evaluated.

The application discloses a kind of based on VSC-HVDC AC-DC system transient stability analysis method, first constructs the steady-state model and transient model of AC-DC system based on VSC-HVDC, determines stable equilibrium point before and after fault, then constructs the energy function of AC-DC system based on VSC-HVDC, and based on fault trajectory, determine the maximum value of system energy, as escape point, take escape point as initial value, based on stable boundary tracking determines the norm of reduced system integral process, find out the norm minimum point, take norm minimum point as initial value to determine leading unstable equilibrium point, finally determine the energy at leading unstable equilibrium point, and the energy of this point is as critical energy, determine system limit cut-off time, complete AC-DC system transient stability analysis.The scheme of the application can determine the minimum gradient point and leading unstable equilibrium point in the transient stability analysis of AC-DC system containing VSC-HVDC, improve the precision of direct method transient stability analysis, and is beneficial to the stability of flexible HVDC transmission system.

The present application relates to the field of deep coal mining disaster prevention and control, and relates to a deep coal seam outburst risk quantitative characterization method based on multi-field coupling effect, comprising: S1, establishing a codeable heat-flow-solid-coupling four-field coupling control equation set; S2, constructing a chemical damage evolution model; S3, based on the field variable distribution obtained by solving the control equation set, establishing an energy catastrophe instability criterion with the system total potential energy second-order variation as the core, and determining the critical energy threshold of outburst danger; S4, constructing and training a physical model driven neural network to realize rapid prediction of field variables; S5, using the trained physical model driven neural network for rapid prediction, and realizing quantitative grading and engineering early warning of deep coal seam outburst risk based on comparison of the prediction result with the critical energy threshold. The present application provides scientific, reliable and practical technical support for precise prevention and control of deep coal mining outburst disasters.

This application provides an ultrasonic-assisted forming method for capillary glass tubes used in optical inspection, applied to a forming apparatus including an ultrasonic base and a metal core needle. After preheating the forming apparatus to a first temperature, molten glass is poured in, causing it to coat the core needle and tend to form a transiently solidified layer. An acoustic model is established by collecting the effective working length of the core needle and the material's acoustic parameters. Based on the acoustic model and considering the critical energy density required to destroy the transiently solidified layer and the effective glass forming time, the acoustic energy output parameters of the core needle are determined. According to these parameters, high-frequency ultrasound is continuously applied through the ultrasonic base during the cooling process of the glass from the molten state to a second temperature, causing the core needle to vibrate to destroy and suppress the transiently solidified layer. The ultrasound is then turned off. This method can reduce interfacial stress concentration, suppress the formation of microcracks on the inner wall, and improve the smoothness of the inner wall of the capillary glass tube as well as its optical and mechanical properties.

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

The invention provides a fatigue crack propagation behavior evaluation method, and belongs to the technical field of material mechanics evaluation. According to the method, the microstructure characteristics, the critical energy release rate, the fatigue crack growth rate and the crack tip strain field distribution of a to-be-tested material are obtained through experimental characterization, a progressive fatigue damage model combining a viscoelastic-plastic constitutive region and a cyclic cohesion region is constructed, and the model is verified through a multi-scale verification method. By adopting the fatigue crack propagation behavior evaluation method, the whole-process and multi-scale correlation evaluation from microscopic damage to macroscopic failure is realized, a fatigue damage model with a more complete physical mechanism and higher prediction precision is provided, a key microscopic failure mechanism is disclosed, a clear direction is provided for guiding material improvement and performance optimization, and the method has a good application prospect. The engineering applicability and reliability of the evaluation result are enhanced, and a theoretical basis and a practical tool can be provided for the design of high-performance long-life engineering structures and parts.

The present invention relates to the field of adhesive films, and particularly to a low-dielectric and high-toughness adhesive film for heterogeneous interfaces and a preparation method thereof, which includes a matrix phase and a fiber felt. The fiber felt is impregnated in the matrix phase to form an adhesive film; the matrix phase includes a thermosetting resin system; the fiber felt is prepared by using short fibers as carriers to load nano-SiO2 to obtain nano-SiO2 grafted short fibers, and then making a fiber felt; the short fibers are organic synthetic fibers or inorganic fibers with a low dielectric constant. The adhesive film of the invention can exhibit strong adhesive strength at the heterogeneous interface, improve the overall critical energy release rate of the material, effectively inhibit the interlaminar delamination failure, through-thickness damage and non-through-thickness damage caused by out-of-plane impact to the composite material, and at the same time has high wave-transmitting performance. It can be applied to structures with high requirements for anti-impact and wave-transmitting performance, such as meteorological radomes, vehicle-mounted antenna covers, aircraft shells, etc.

This invention proposes a method and storage medium for evaluating the reliability and lifespan of thermal barrier coatings, comprising: S1, characterizing and analyzing the microstructure of the sample to obtain the microscopic morphology image of the ceramic layer and the property parameters of the sample, and establishing a geometric model; S2, conducting coupled thermal shock and CMAS corrosion experiments on the sample until its failure, recording load parameters and determining the main failure modes and CMAS melt penetration behavior through cross-sectional analysis; S3, forming a set of thermo-coupling failure control equations based on the main failure modes and penetration behavior; inputting the geometric model and the set of thermo-coupling failure control equations into finite element software for solving to obtain simulated crack morphology and stress distribution results; S4, establishing a limit state equation based on the set of thermo-coupling failure control equations with the actual critical energy release rate as the criterion; S5, calculating the failure probability based on the limit state equations; S6, constructing a lifespan prediction model based on the limit state equations to predict the lifespan of the thermal barrier coating under test.

The invention belongs to the technical field of micro-nano structure mechanical property testing, and aims to solve the problems that in the prior art, the dynamic expansion path of micro cracks in an integrated circuit multi-layer interconnection structure cannot be monitored in a three-dimensional mode in real time, and the nanoscale energy release rate cannot be quantitatively evaluated. The invention provides an in-situ monitoring method integrating a miniature double-cantilever beam mechanical testing device and a synchronous X-ray nanometer tomography system. According to the core scheme, three-dimensional shape data of crack propagation are obtained in real time by designing a sample clamp coupled by an asymmetric double-cantilever beam interface and combining a high-resolution X-ray imaging system, and a quantitative correlation model of a crack tip stress field and an energy release rate is established through a data reconstruction algorithm. Compared with a traditional electron microscope detection technology, the method has the advantages that the micro-crack monitoring resolution ratio can be increased to 100 nm or below, active guiding control over the crack path is achieved, and the critical energy release rate of the sub-hundred-nanometer area can be quantitatively measured on the premise that the sample stress state is kept.

The invention relates to the technical field of unmanned aerial vehicle design, in particular to an energy planning-based fixed-wing unmanned aerial vehicle airline guidance method, which comprises the following steps of: after an engine of an unmanned aerial vehicle has a parking fault, acquiring a current optimal airline return path; combining the energy consumption from the parking point to the FAF point and the glide critical energy of the FAF point to judge whether the current energy of the unmanned aerial vehicle meets the requirement of idle glide returning; if the energy is sufficient, according to the real-time flight state parameters of the unmanned aerial vehicle, dynamically determining the transverse course control mode of the unmanned aerial vehicle until the unmanned aerial vehicle enters air-slip glide guidance; controlling the longitudinal control mode at the final idle slip gliding section of the idle slip returning field until grounding; if the energy is insufficient, the target point is switched to be the forced landing point closest to the current position, and off-site forced landing is carried out; in the forced landing process, whether excess energy exists or not is judged, and circling height descending is needed. According to the method, the unmanned aerial vehicle can accurately track an air-sliding route and safely return to the field when energy is sufficient, and the unmanned aerial vehicle can be forced to land near a forced landing point when energy is insufficient.

The invention discloses a composite material fracture energy calculation method considering reinforcement-matrix interface dispersion. The method comprises the following steps: S1, establishing a matrix internal crack fracture energy model; s2, establishing a reinforcement-matrix interface fracture energy model; s3, establishing a composite material fracture control equation model; s4, correcting the critical energy release rate of the composite material; and S5, performing finite element discretization on an interface phase field, a displacement field and a crack phase field in the composite material fracture control equation, performing increment iteration, and calculating the crack propagation condition in the composite material considering interface dispersion. By adopting the phase field model and utilizing the advantage that the phase field model can realize microcosmic-macroscopic multi-scale simulation, the interface attribute in the composite material is associated with the matrix attribute, that is, the fracture attributes such as interface crack propagation in the composite material under the load action are dispersed into the surrounding matrix in the form of a continuous exponential function; and a mechanical model for more accurately predicting the mechanical behavior and fracture evolution of the composite material is established.

The invention discloses a power distribution network operation stability evaluation method considering an entropy space, and the method comprises the steps: constructing a distributed power supply dynamic model, and designing a distributed power supply energy function; based on a distributed power supply energy function, selecting an energy value of the dominant unstable equilibrium point as critical energy, and fitting a critical energy curved surface; constructing a system entropy index representing power flow balance and static voltage safety of the power distribution network, and dispersing the system entropy index to a distributed power supply level to obtain a distributed power supply entropy index; designing a distributed power supply entropy boundary condition, and constructing a distributed power supply entropy space representing safety and stability based on a boundary projection method; and rapidly solving a steady-state working point and an energy value under a given anticipated accident, rapidly positioning inside and outside an entropy space, and evaluating the operation stability of the power distribution network based on a positioning result and the entropy space of the distributed power supply. Compared with the prior art, the operation stability of the power distribution network is evaluated according to the entropy space of the distributed power supply, and a traditional safety and stability evaluation method is simplified.

This invention discloses a transient stability analysis method and system for a multi-machine grid-connected system. First, a transient model of the system is established, and the stable equilibrium point before the fault is determined based on the power balance equation and the eigenvalues ​​of the Jacobian matrix. Using the stable equilibrium point as initial values, the fault trajectory is calculated, and an interpolation correction algorithm is introduced to eliminate discrete simulation step size errors and accurately locate the point on the fault trajectory where the potential energy derivative changes from positive to negative. Using this point as an initial value, the system iteratively searches for the minimum point of power imbalance along the gradient descent path. Solving the power balance equation using the minimum point as an initial value yields the dominant unstable equilibrium point. Finally, the energy of the dominant unstable equilibrium point is used as the critical energy to determine whether the system is stable after the fault is cleared. The method provided by this invention reduces the conservatism of the traditional energy function method for stability assessment in multi-machine systems, effectively reduces the multi-saddle point interference problem in multi-machine systems, and accurately locates the dominant unstable equilibrium point related to the fault path.

The invention belongs to the technical field of power system stability discrimination, and discloses a power system transient stability assessment method and a related device. The power system transient stability evaluation method comprises the following steps: calculating to obtain transient energy of a power system; calculating to obtain critical energy based on the critical energy function of the two-machine equivalent model of the power system; correcting the critical energy by adopting the trained critical energy added value enhancement model to obtain corrected critical energy; and comparing the transient energy with the corrected critical energy, and obtaining a transient stability evaluation result of the power system based on a comparison result. According to the technical scheme, the advantages that a direct method has good interpretability and an artificial intelligence method has high precision are combined, and an accurate and mechanically interpretable stability judgment result can be quickly obtained according to the current state and possibly suffered faults of the power system.

The invention relates to the technical field of photovoltaic system safety, and provides a photovoltaic direct current arc fault fire risk assessment method. The method comprises the following steps: firstly, acquiring an arc fault basic sample set, wherein a sample comprises arcing time, arc average power and label information corresponding to whether combustible materials are ignited or not; generating a plurality of basic classifiers by adopting iterative training, and improving the recognition capability of boundary samples through dynamic adjustment of sample weights; carrying out weighted fusion on the plurality of basic classifiers to form an integrated classifier, and mapping an output result into ignition probability distribution; and finally, constructing a decision boundary function based on the ignition probability distribution to realize graded evaluation of the arc fault fire risk. According to the method, the limitation of traditional fixed threshold value judgment is broken through, the judgment precision can be improved in a critical energy interval, the stability of the model under different working conditions is ensured, and a risk grading and device performance evaluation basis which can be applied to a photovoltaic system is formed.

The present invention provides a SiC / SiC pyrolytic carbon interface optimization method based on a neural network and a phase field fracture method. The method comprises: first constructing a representative volume unit model of a SiC fiber-reinforced composite material; then using the phase field fracture method to simulate the transverse tensile strength of the representative volume unit model of the SiC fiber-reinforced composite material; finally, using the transverse tensile strength as a criterion for screening the optimal interface thickness and training an inverse neural network to predict and optimize the optimal interface thickness of SiC fibers with different material parameters. The present invention uses an accurate and efficient representative volume unit model and combines the phase field fracture method with an inverse design neural network. By simulating crack behavior and predicting the optimal interface thickness of fibers with different radii, elastic moduli, critical energy release rates, and strengths, the PyC interface parameters are systematically optimized, thereby improving the mechanical properties and reliability of the SiC / SiC composite material.