116 results about "Fast optimization" patented technology

The invention discloses an intelligent optimization method for a multi-type well seam joint control fine injection-production mode, and relates to the technical field of oil-gas field development. The method comprises the following steps: setting a well seam joint control fine injection-production mode, establishing an oil reservoir numerical simulation model in oil reservoir numerical simulation software, obtaining multiple groups of oil reservoir injection-production schemes based on a Latin hypercube sampling method, performing simulation according to each group of oil reservoir injection-production schemes by utilizing the oil reservoir numerical simulation model, generating multiple pieces of sample data, and establishing a sample database; a deep learning agent model is established, after the sample database is utilized to train and train the deep learning agent model, a particle swarm optimization algorithm is adopted to carry out single-target pre-search global optimization to obtain a preferred reference strategy, a reinforcement learning dynamic decision model is established, and a reinforcement learning agent is obtained through training based on a PPO near-end strategy optimization algorithm; and the optimal injection-production development scheme of the oil reservoir is obtained by utilizing the reinforcement learning agent, so that rapid optimization and decision support of the oil reservoir injection-production scheme in a new multi-type well seam joint control mode are realized.

The invention relates to the technical field of power system scheduling, and discloses an intra-day look-ahead scheduling rapid solving method considering large-scale new energy cluster power generation volatility. Comprising the following steps of S1, new energy cluster space-time fluctuation scene generation based on a neuron cellular automaton, S2, power grid dynamic security domain definition and simplification based on a physical information neural network, S3, scheduling rapid optimization solution based on model prediction path integration, and S4, scheduling scheme dynamic elasticity and stability evaluation based on a Kupman operator theory. The new energy cluster space-time fluctuation scene generation method based on the neuron cell automaton can effectively generate a space-time scene reflecting large-scale new energy cluster power generation volatility, supports uncertainty analysis, has the advantages of being high in calculation efficiency and scene authenticity, and is suitable for large-scale new energy cluster power generation. The problem that scene generation is inaccurate due to the fact that a traditional statistical model ignores space-time coupling is solved.

The invention discloses a fault co-seismic sliding surface inversion method and system based on Beidou and artificial intelligence. The method comprises the steps of collecting Beidou data and seismic waveform data of a target area in real time, and performing preprocessing to extract co-seismic displacement and waveform features; fusing the Beidou deformation features and the seismic wave features to form a multi-modal feature vector; a fault prediction model is constructed based on a graph neural network, forward modeling and historical earthquake example data training are utilized, and multi-modal features are input to obtain preliminary fault sliding distribution prediction; rapid optimization under physical constraint is carried out through the elastic dislocation model, and a final fault sliding model conforming to the geophysical law is obtained; finally, uncertainty quantification is carried out, and a visual product of the dynamic process including sliding distribution, seismic moments and fault deformation is generated. According to the system, full-process automatic processing is achieved through cooperation of all the units, the inversion speed, precision and physical credibility are improved, and reliable support is provided for earthquake emergency response and disaster assessment.

The invention discloses a data processing method and system for a precise automatic multi-axis numerical control electric spark forming machine, and the method comprises the steps: mapping preprocessed data into a digital twin model for fusion analysis, and extracting fusion features including instantaneous energy density, an effective machining angle, a thermal error compensation amount and a chip removal efficiency evaluation value; based on the fused feature data, performing real-time state evaluation and future discharge trend prediction by using a LightGBM neural network model, and outputting a processing prediction result; and a multi-target optimization function is established, an improved NSGA-II algorithm is utilized to carry out rapid optimization search by taking the current processing parameters as an initial population, a multi-axis cooperative motion instruction is generated, and the multi-axis cooperative motion instruction is transmitted to a multi-axis motion control module and a pulse power supply module to be executed. And the processing stability and reliability are improved.

The invention discloses a quick optimization design method and device for anti-flutter structural parameters of a wind turbine blade, and relates to the technical field of wind turbine blades, and the method comprises the following steps: constructing a blade aeroelastic characteristic equation to respectively determine the blade critical flutter speed of a plurality of to-be-optimized structural parameter combinations of a to-be-designed blade; carrying out standard orthogonal polynomial approximate expansion on the initial parameter-critical flutter velocity high-dimensional expansion model, converting coefficient solution into a 1-norm minimization problem, and carrying out solution based on each to-be-optimized structure parameter combination and each blade critical flutter velocity to determine a target parameter-critical flutter velocity high-dimensional expansion model; calculating the sensitivity index of each to-be-optimized structure parameter to determine a key to-be-optimized structure parameter; taking maximization of the critical flutter speed of the blade as a target, adjusting the parameter gradient of each key to-be-optimized structure to solve a target parameter-critical flutter speed high-dimensional expansion model, and determining a target optimization structure parameter combination. According to the scheme, the optimal anti-flutter structure parameter design can be quickly determined.

The invention discloses a hierarchical reinforcement learning-based multi-target reservoir gate optimal scheduling method, which comprises the following steps of: constructing a reservoir drainage facility gate optimal scheduling model, and determining a target function and a constraint condition; establishing a hierarchical reinforcement learning framework, determining options, an option network and an option internal strategy, determining a reservoir water level by the option network according to information such as reservoir inflow to minimize the maximum reservoir outflow of the reservoir, and determining a gate operation scheme by the option internal strategy according to the reservoir water level determined by the option network to minimize gate adjustment times; and solving the layered reinforcement learning framework by using a competitive double-depth Q network algorithm to obtain a reasonable gate operation scheme. According to the method, gate scheduling is decomposed into two levels of decisions, the problems that the number of gate optimization scheduling decision variables is too large and the solution dimension is too large are effectively solved, a reasonable gate operation scheme can be obtained through rapid optimization, and the maximum output flow of a reservoir and the gate adjustment frequency are effectively reduced.

The invention discloses an anti-swing predictive control method for an offshore crane, and belongs to the technical field of ocean engineering equipment control. The problem that in the prior art, due to control lag and an inaccurate model, the load swing restraining effect of an offshore crane is poor is solved. According to the scheme, the method is characterized in that the state of a crane and prediction information of future waves are obtained in real time through a state sensor set and a multi-source environment sensing system; mixing the prediction model to predict a crane system state sequence under different control instructions in a future time domain in a rolling manner; based on the prediction sequence, solving a reference control track aiming at suppressing swing and reducing structural fatigue in upper-layer optimization, and solving and outputting an instant control instruction meeting the constraint of an execution mechanism in lower-layer rapid optimization; meanwhile, system health management is independently executed, and a control mode is dynamically adjusted according to evaluation. The method is mainly used for precise anti-swing control of the offshore crane under the complex sea condition, load swing can be effectively inhibited in advance, and operation precision and equipment safety are improved.

The invention relates to the technical field of computational fluid mechanics and biological microfluidic design, in particular to a model order reduction method for rapid optimization of a circulating tumor cell (CTC) sorting structure, which comprises the following steps of: constructing a three-dimensional full-order computational fluid mechanics model by collecting channel geometric structure parameters and fluid working condition parameters, and generating a training data set; organizing a flow field snapshot into a matrix form, extracting a dominant mode, constructing a low-dimensional modal space by taking the dominant mode as a base vector, establishing a low-dimensional ordinary differential model through Galerkin projection, and training a parameter-modal coefficient mapping relation by adopting a deep neural network to form a complete reduced-order model; and finally, constructing a multi-objective optimization problem based on the reduced-order model, carrying out optimization iteration by adopting an evolutionary algorithm, and returning an optimization result to the full-order model for verification, so that rapid optimization design of the CTC sorting structure is realized, and an effective solution is provided for intelligent design of a biomedical microfluidic device.

The invention discloses a decoupling cell-hybrid equivalent model and a permanent magnet flat wire motor multi-physical field cooperation rapid optimization method, a rotor and a stator are modeled separately, and complete separation of a motor topological structure and an analysis grid is realized at the rotor part through decoupling cells, so that the motor topological structure can be completely separated from the analysis grid when facing various different rotor topological structures. And a new grid structure does not need to be repeatedly constructed, so that the modeling efficiency, the model universality and the modeling flexibility of a complex structure are greatly improved. And the stator adopts hybrid equivalent modeling, so that the solving complexity is remarkably reduced while the high calculation precision is kept. The rotor side adopts boundary encryption subdivision to ensure stress precision, and the stator side adopts a parameterized equivalent magnetocaloric network model to reduce analysis time consumption, and unification of high precision and high efficiency is realized. By means of an NSGA-II algorithm, a bidirectional coupling calculation framework among an electromagnetic field, a temperature field and a stress field is constructed, efficient coupling iteration among physical quantities of the three fields is achieved through coupling calculation, and coupling prediction precision and design reliability are effectively improved.

The invention provides a three-dimensional flow field acquisition method and system based on two-dimensional through-flow and a neural network, belongs to the field of fluid mechanics calculation, and can at least partially solve the problem that in the prior art, calculation efficiency is low, and two-dimensional through-flow cannot reflect three-dimensional features. Geometric parameters and working condition parameters of fluid machinery are input, and flow parameters on a two-dimensional flow surface are rapidly output; constructing and training a neural network model, wherein the neural network learns a mapping relation between a two-dimensional flow surface calculation result and a three-dimensional flow field; for the fluid machinery under the target working condition, a result is obtained through two-dimensional through-flow calculation, the result is preprocessed and then input into the trained neural network, the low-dimensional representation of the three-dimensional flow field is output, and complete three-dimensional flow field parameters are obtained through reconstruction. The calculation period is remarkably shortened, and rapid optimization of multiple schemes is supported.

The present invention relates to the technical field of artificial intelligence devices, and provides a system and method for compiling a convolutional neural network model for an embedded device. The system comprises a model computation graph representation unit, a convolutional neural network fixed optimization module, a convolutional neural network automatic optimization module, an automatic optimization process module, a model compilation optimization unit, and a model deployment and reasoning unit. A convolutional neural network operator having the highest computational load is optimized, and only the edge cropping size and the loop unrolling step size of the convolutional neural network operator are optimized, so that the optimization space is reduced and the optimization time is shortened while optimizing the operator to the greatest extent; in addition, the entire process from model training output to embedded device reasoning is established, and rapid optimization and deployment of convolutional neural network models are achieved. By means of the method, a high-performance convolutional neural network model can be rapidly deployed on an embedded device, so that the present invention has high practical value and innovative value.

The invention relates to the technical field of structure fatigue evaluation, in particular to a pipe truss structure fatigue analysis parameter optimization method and system based on deep learning, and the method comprises the following steps: constructing a deep learning proxy model fusing a multi-scale structure diagram encoder, a working condition parameter encoder and a damage dimension curve decoder; training the model by using a high-fidelity training data set; for the target truss structure and the load working condition, predicting a damage dimension relation curve through the model; determining the optimal dimension of a rain flow counting matrix by analyzing the convergence characteristic of the curve; and predicting a multi-working-condition damage value through a model, and screening out a dominant working condition based on a damage contribution percentage. According to the method, the deep learning agent model is used for replacing traditional iterative simulation, rapid optimization of key parameters in fatigue analysis is achieved, the efficiency and accuracy of fatigue evaluation of the large truss structure are remarkably improved, and the generalization ability of the model is improved by fusing the physical effect of a multi-scale structure chart encoder to capture key hotspots.

The invention provides a power system black-start partition decision method based on lightweight reinforcement learning, and the method comprises the steps: constructing a black-start model of a power system containing multiple physical constraints, and formalizing the black-start model into a Markov decision process, the Markov decision process comprises a state space, an action space, a reward function and a transfer process; decomposing the power system into a plurality of sub-regions by adopting a dynamic partition recovery strategy; based on the Markov decision process, a depth deterministic strategy gradient algorithm is adopted to design and train a lightweight strategy network of deep reinforcement learning; enabling the intelligent agent to interact with the environment in each sub-region through the lightweight strategy network of deep reinforcement learning, and learning an optimal decision strategy; and according to the optimal decision strategy, performing partition power supply capability recovery on the power system. According to the invention, black-start rapid optimization decision in a complex power grid environment is realized.

This invention discloses a deep learning-based method for improving energy efficiency in trailer production environments, comprising the following steps: S1, real-time collection of trailer production environment data; S2, preprocessing the data to generate a standardized dataset; S3, constructing and training an energy efficiency optimization control model; S4, inputting the real-time generated standardized dataset into the energy efficiency optimization control model to generate energy consumption, production efficiency, and environmental stability indicators; S5, using an improved RVEA optimization algorithm to optimize the generated energy consumption, production efficiency, and environmental stability indicators, generating optimal production strategy parameters; S6, deploying the optimal production strategy parameters to the actual production execution system. This invention combines deep learning with an improved RVEA optimization method to intelligently optimize trailer production energy efficiency, possessing advantages such as strong adaptability, fast optimization speed, and excellent overall performance.

A method, electronic device, and readable storage medium for rapid optimization of neutral bus arrester parameters are disclosed. Based on the main circuit topology of a symmetrical bipolar flexible DC system composed of a half-bridge submodule MMC converter, the method establishes equivalent circuits for different fault conditions, including DC pole-to-ground faults, single-phase-to-ground faults in the valve-side windings connected to the transformer delta connection, and neutral line open-circuit faults. It obtains the energy absorbed by the neutral bus arrester and, based on the relationship between the energy absorbed by the neutral bus arrester and its protection level, optimizes the energy absorption of the arrester under different fault conditions with the goal of balancing the energy absorbed. This allows for rapid optimization of the neutral bus arrester parameters, offering advantages of speed, economy, and efficiency.

The application relates to the technical field of power system dispatching, and discloses an intra-day forward-looking dispatching fast solving method considering large-scale new energy cluster power generation fluctuation, which comprises the following steps: S1: new energy cluster space-time fluctuation scene generation based on neuron cellular automata, S2: power grid dynamic security domain definition and simplification based on physical information neural network, S3: dispatching fast optimization solving based on model prediction path integral, and S4: dispatching scheme dynamic elasticity and stability evaluation based on the theory of Koopman operator. The new energy cluster space-time fluctuation scene generation method based on neuron cellular automata can effectively generate a space-time scene reflecting the large-scale new energy cluster power generation fluctuation, support uncertainty analysis, has the advantages of high calculation efficiency and scene authenticity, and solves the problem that the traditional statistical model ignores space-time coupling, thereby causing inaccurate scene generation.

The invention belongs to the technical field of ship intelligent digital optimization design, and particularly relates to a ship global deformation and optimization method, program and equipment considering drainage volume precision control and deformation rationality and a storage medium. The analytical expression of the drainage volume variation about the global deformation parameter is obtained based on the numerical integration and the recursion formula, the reasonable deformation parameter range of the ship body is determined based on the global deformation modification function and the regular design space, the ship body does not need to be actually deformed, the corresponding volume variation can be directly predicted according to the design parameter, and the calculation accuracy is improved. Accurate feedforward control of volume constraint and direct judgment of rationality of the deformed ship are realized. On the basis, rapid optimization of any ship type structure under the constraint of reasonable deformation and accurate volume control is realized in combination with an agent model. According to the method, a traditional'design-verification-adjustment 'experience iteration process is converted into deterministic one-step calculation, and subsequent optimization can be directly carried out in a pre-verified reasonable design space.

This application discloses an online optimization method and apparatus for hot forging process parameters, applicable to the field of hot forming technology. Based on a full-factor experimental design, this application performs multi-scale simulation of hot forgings to obtain grain size simulation results. Then, it obtains a pre-defined mesh corresponding to the final forging as the base mesh and constructs a rapid grain size prediction dataset based on the grain size simulation results. Next, it constructs a rapid grain size prediction model for hot forgings and a visualization model based on this dataset. The hot forging process parameters are then input into the rapid grain size prediction model to predict real-time grain size data. The real-time grain size data is visualized using the visualization model, thus achieving online visualization prediction of the global grain size of the hot forging. Finally, a biomimetic intelligent optimization algorithm is used to optimize the hot forging process parameters, enabling rapid optimization of process parameters.

The application relates to a robust optimization design method of an airborne high-temperature superconducting generator, which comprises the following steps: a baseline design scheme is obtained by establishing a two-dimensional electromagnetic finite element baseline model and a total loss accounting model of the generator containing electromagnetic characteristics of superconducting coils; a feasible technical scheme set is obtained by performing scheme screening on pre-engineering hard constraints; an optimal candidate scheme is determined by performing fast optimization on the feasible domain by using a Taguchi orthogonal test, and the optimal candidate scheme is determined by main effect and range analysis or signal-to-noise ratio calculation; and a final design scheme is determined by taking the minimum performance fluctuation or the maximum signal-to-noise ratio as a criterion by introducing cold end temperature fluctuation, air gap assembly deviation, tape critical current dispersion and load and speed disturbance as noise factors for robust verification. The application can efficiently obtain an optimal design with high performance, strong engineering feasibility and operation robustness under limited simulation resources, and is especially suitable for a megawatt airborne high-temperature superconducting power generation system.

The invention relates to an interpretable building reconstruction rapid optimization method considering parameter uncertainty. The method comprises the following steps: S1, collecting information and carrying out data processing on original data; s2, building a building simulation model and calibrating weather data; s3, uncertain parameter sensitivity is analyzed, and a simulation model is calibrated; s4, building reconstruction measures are set, and reconstruction multi-objective optimization is carried out; s5, training a rapid prediction model and explaining a black box model decision mechanism; the method is based on an optimization algorithm, a prediction algorithm and a simulation kernel, and aims to solve the technical problems of uncertainty, simulation speed and interpretability in building reconstruction multi-objective optimization.

The invention discloses a fuel gear pump unloading groove structure optimization method based on a lumped parameter framework. The method comprises the following steps: 1, establishing a fuel gear pump oil trapping mechanism model; 2, constructing a multi-cavity lumped parameter model of the fuel gear pump; 3, establishing an optimization sample library; and 4, constructing a BP neural network and optimizing a genetic algorithm. A multi-cavity performance model of the fuel gear pump is constructed by introducing a lumped parameter framework, so that the calculation complexity of the model is reduced, and a basis is provided for rapid optimization; a training sample is obtained based on a multi-cavity model, training of a neural network proxy model is carried out, a complex linear relation between unloading groove structure parameters and gear pump performance is mapped through the proxy model, and prediction precision and calculation efficiency are further improved; a genetic algorithm is adopted as an optimization engine, a neural network agent model is coupled, and multi-objective optimization of the structural parameters of the special-shaped unloading groove is carried out.

The application discloses a method for manufacturing a colorimetric sensing unit and array by using a multi-target Bayesian optimization algorithm. Different formulations of colorimetric sensing units are initially prepared on a hole plate; the hole plate is dried, and the dried hole plate is introduced into a gas test to obtain the values of response time, reversibility, responsivity and sensitivity of each formulation; the values of response time, reversibility, responsivity and sensitivity of each formulation are processed by a Sigmoid function to obtain score values, which are substituted into a multi-target Bayesian optimization algorithm to generate a next round of formulation; colorimetric sensing units are prepared on the hole plate according to the formulation; the steps are repeatedly cycled, and the number of cycles reaches a stop condition to obtain a global optimal formulation; and colorimetric sensing units are prepared according to the global optimal formulation. The method solves the problem that multiple indexes of a sensor are simultaneously optimized and some indexes are easily neglected, and can quickly optimize a CO2 colorimetric sensing array which simultaneously has wide range, high sensitivity, fast response and high reversibility.

The application discloses a lens antenna multi-target optimization method based on prior knowledge neural network, takes INN as the main body of the algorithm, adopts a reverse neural network to perform reverse design on the lens antenna, and the input of the reverse neural network is electromagnetic response, and the output is a structure parameter, so that the inversion of the antenna structure parameter of multiple performance indexes is realized. Meanwhile, multiple sub-FNNs are introduced to provide prior knowledge corresponding to multiple performance indexes, respectively, the input of the forward neural network is the structure parameter, and the output is the electromagnetic response. Compared with the existing lens antenna design method, the design method has the following advantages: 1) the antenna design efficiency is high, and the designed antenna can realize good multi-target characteristics; 2) the proposed KBANN model relieves the problem of large neural network data requirement and provides a new solution. The application can realize the rapid optimization of the multi-target lens antenna, and relieves the problem of large neural network data requirement.

The present application relates to the technical field of electromagnetic sounding, in particular to a multi-step variation AB-Hy encoding electromagnetic sounding one-dimensional inversion method and device, for the measured AB-Hy encoding electromagnetic sounding full area apparent resistivity observation value, the method presets the feasible solution space of one-dimensional horizontal layered model, randomly generates a population, forward calculation of the full area apparent resistivity of each individual in the population, calculates the fitness value of each individual in the population according to the full area apparent resistivity calculation value and observation value of each individual;Select the individual with the highest current fitness value as the optimal individual, and perform iterative calculation of multi-step differential evolution with the optimal individual participating in the population individual;The individual with the highest fitness value obtained is taken as the inversion result of the observation data. AB-Hy electromagnetic sounding one-dimensional inversion based on multi-step differential evolution algorithm is realized, the geoelectric model parameters corresponding to the observation data are obtained, and the basis for geological interpretation is provided. The method has fast optimization convergence speed and high accuracy of inversion result.

The invention discloses a case vibration analysis and test method, system, equipment and medium, and the method comprises the steps: obtaining three-dimensional geometric data of a to-be-detected case, constructing a three-dimensional geometric model, analyzing the three-dimensional geometric model, and extracting component information and geometric topology information; calling a preset material database to distribute corresponding material physical parameters for each component of the three-dimensional geometric model, generating test working condition setting data, calling a built-in solver according to the material physical parameters and geometric topological information of the components and the test working condition setting data, and performing structural dynamics simulation calculation to obtain a structural dynamics simulation result. The structural dynamics equation is solved to obtain simulation response data of the to-be-detected case, a vibration response map is generated according to the simulation response data, a model optimization suggestion is generated, full-process automatic testing of the vibration resistance of the case is achieved, and the method has the advantages of being high in testing precision, high in flexibility and rapid in optimization.

The invention relates to the technical field of petroleum and natural gas exploitation, in particular to a neural network fracturing process parameter optimization method and device driven by a physical model, and the method comprises the steps: carrying out the orthogonal experiment design through main fracturing process parameters which affect the fracturing transformation effect, and obtaining a fracturing construction scheme of different fracturing process parameter combinations; and inputting different fracturing process parameter combination construction schemes into the neural network productivity prediction model, and outputting corresponding productivity prediction results. According to the method, multiple fracturing construction parameters can be rapidly optimized at the same time, and time cost brought by simulation is greatly saved; secondly, the neural network is driven by a physical model, limitation caused by oil reservoir complexity is avoided, and the accuracy of a neural network productivity prediction model is improved; and 3, after the neural network productivity prediction model is established, the method can be suitable for different oil reservoirs and has wide applicability.

The application is suitable for the technical field of motion intention recognition, and provides an intelligent lower limb prosthesis human motion intention recognition method based on a stir-fried meat optimization algorithm. The application proposes a feature weight dynamic optimization framework based on the stir-fried meat optimization algorithm, realizes real-time adaptive distribution of motion feature weights through two links of offline weight vector training and real-time feature optimization execution. The algorithm achieves optimal results on 7 standard unimodal test functions and has good migration; through the above-knee amputation patient data set verification, the optimized weight matrix has the lowest number of recognition errors and the fastest optimization speed, significantly improves the classifier prediction accuracy and the environmental anti-interference ability of intention recognition, and meets the real-time requirement. The application solves the adaptability problem of intelligent lower limb prosthesis in complex life scenes, lays a foundation for high-reliability product development, has important practical application value in the motion scene recognition of lower limb prosthesis and walking aid robots, and has significant industrialization transformation potential.

The application discloses a kind of population pre-screening and space reduction proxy model aided optimization method, it is related to model optimization field, first, the extremely low computing cost advantage of proxy model is used to pre-screen population individual, then based on the individual characteristics after pre-screening, optimization space is reduced.Subsequently, subsequent operation is based on the individual selected in advance and reduced optimization space, to realize the goal of fast optimization convergence.On the other hand, in the optimization process, the method makes full use of the acceleration auxiliary role of proxy model in engine overall performance simulation, reduces the evaluation cost of objective function, further reduces optimization calculation amount.This not only improves optimization efficiency, but also guarantees the accuracy of original overall performance simulation model.

The application discloses a kind of circulator insertion loss quadratic response surface optimization methods.The method includes: obtaining the target performance of circulator, and determining the adjustable factor set of circulator according to target performance;Adopt experimental design method in adjustable factor set Significant factor is screened;According to significant factor, a quadratic response surface proxy model is constructed, and the minimum insertion loss is used as the optimization target to train the model;The trained model is used to execute multi-objective optimization with constraints, and the optimal parameter combination is obtained;After verifying the optimal parameter combination, the final design parameters are output.The application filters significant factors and constructs a quadratic response surface proxy model to minimize IL within the constraint space for fast optimization.The total amount of experiments is reduced by 70%, the verification error is less than 5%, the design cycle is significantly shortened, and the insertion loss is reduced, which is suitable for precise determination of low-loss process window for any-band self-biased circulator.

The invention relates to a method for predicting the instability characteristic of a planet row needle bearing retainer, belongs to the technical field of bearing characteristic analysis, and solves the problems that in the prior art, the research on the instability of a bearing retainer is mostly limited to a self-rotation working condition, and prediction is carried out only through a dynamic modeling or testing method; the prediction method comprises the following steps of: firstly, establishing a coordinate system of a planetary gear set, and constructing an index for describing the instability characteristic of the retainer on the basis of the coordinate system; using the kinetic model to form training data of the proxy model; furthermore, a construction and training method of the proxy model is provided, the instability characteristic of the planet row needle bearing retainer can be rapidly obtained, a large amount of dynamic calculation involved in the bearing optimization design process can be replaced, consumption of calculation resources and time can be reduced, and therefore rapid optimization design of the high-performance planet row needle bearing is supported.